Fill-Mask
Transformers
Safetensors
English
Vietnamese
distilbert
finance
esg
text-classification
bert
Instructions to use nguyen599/MaskESG-DistilBERT-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nguyen599/MaskESG-DistilBERT-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="nguyen599/MaskESG-DistilBERT-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("nguyen599/MaskESG-DistilBERT-base") model = AutoModelForMaskedLM.from_pretrained("nguyen599/MaskESG-DistilBERT-base") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": 2600, | |
| "best_metric": 0.9406817969017098, | |
| "best_model_checkpoint": null, | |
| "epoch": 34.35204081632653, | |
| "eval_steps": 100, | |
| "global_step": 9000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03826530612244898, | |
| "grad_norm": 11.692060470581055, | |
| "learning_rate": 2.25e-06, | |
| "loss": 4.3177, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07653061224489796, | |
| "grad_norm": 7.558546543121338, | |
| "learning_rate": 4.75e-06, | |
| "loss": 3.933, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11479591836734694, | |
| "grad_norm": 5.750818729400635, | |
| "learning_rate": 7.25e-06, | |
| "loss": 3.5333, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15306122448979592, | |
| "grad_norm": 4.154467582702637, | |
| "learning_rate": 9.750000000000002e-06, | |
| "loss": 3.1531, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1913265306122449, | |
| "grad_norm": 3.642361640930176, | |
| "learning_rate": 1.225e-05, | |
| "loss": 2.984, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22959183673469388, | |
| "grad_norm": 3.478938102722168, | |
| "learning_rate": 1.475e-05, | |
| "loss": 2.8411, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 3.572298765182495, | |
| "learning_rate": 1.725e-05, | |
| "loss": 2.6656, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 3.913522481918335, | |
| "learning_rate": 1.9750000000000002e-05, | |
| "loss": 2.595, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34438775510204084, | |
| "grad_norm": 3.419506311416626, | |
| "learning_rate": 2.2250000000000002e-05, | |
| "loss": 2.4863, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3826530612244898, | |
| "grad_norm": 3.4079384803771973, | |
| "learning_rate": 2.4750000000000002e-05, | |
| "loss": 2.484, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3826530612244898, | |
| "eval_en_All_acc": 0.5176408076514346, | |
| "eval_en_Env_acc": 0.7681159420289855, | |
| "eval_en_Env_f1": 0.5824175824175825, | |
| "eval_en_Gov_acc": 0.640625, | |
| "eval_en_Gov_f1": 0.5578231292517006, | |
| "eval_en_Neu_acc": 0.21739130434782608, | |
| "eval_en_Neu_f1": 0.33707865168539325, | |
| "eval_en_Soc_acc": 0.37037037037037035, | |
| "eval_en_Soc_f1": 0.40816326530612246, | |
| "eval_en_cls_acc": 0.4911660777385159, | |
| "eval_en_cls_f1": 0.47137065716519966, | |
| "eval_en_loss": 3.0308988094329834, | |
| "eval_en_runtime": 5.6923, | |
| "eval_en_samples_per_second": 329.744, | |
| "eval_en_steps_per_second": 3.514, | |
| "eval_en_total_cls_tokens": 283, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3826530612244898, | |
| "eval_en_oof_All_acc": 0.5054863108554384, | |
| "eval_en_oof_Env_acc": 0.8701298701298701, | |
| "eval_en_oof_Env_f1": 0.6146788990825688, | |
| "eval_en_oof_Gov_acc": 0.5964912280701754, | |
| "eval_en_oof_Gov_f1": 0.5230769230769231, | |
| "eval_en_oof_Neu_acc": 0.24193548387096775, | |
| "eval_en_oof_Neu_f1": 0.3846153846153846, | |
| "eval_en_oof_Soc_acc": 0.3068181818181818, | |
| "eval_en_oof_Soc_f1": 0.38571428571428573, | |
| "eval_en_oof_cls_acc": 0.5035211267605634, | |
| "eval_en_oof_cls_f1": 0.47702137312229054, | |
| "eval_en_oof_loss": 3.131051540374756, | |
| "eval_en_oof_runtime": 5.5537, | |
| "eval_en_oof_samples_per_second": 337.975, | |
| "eval_en_oof_steps_per_second": 3.601, | |
| "eval_en_oof_total_cls_tokens": 284, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3826530612244898, | |
| "eval_vi_All_acc": 0.6196687265727889, | |
| "eval_vi_Env_acc": 0.35664335664335667, | |
| "eval_vi_Env_f1": 0.4454148471615721, | |
| "eval_vi_Gov_acc": 0.6346153846153846, | |
| "eval_vi_Gov_f1": 0.45308924485125857, | |
| "eval_vi_Neu_acc": 0.3924050632911392, | |
| "eval_vi_Neu_f1": 0.4290657439446367, | |
| "eval_vi_Soc_acc": 0.29375, | |
| "eval_vi_Soc_f1": 0.34306569343065696, | |
| "eval_vi_cls_acc": 0.419773095623987, | |
| "eval_vi_cls_f1": 0.4176588823470311, | |
| "eval_vi_loss": 1.9648041725158691, | |
| "eval_vi_runtime": 12.7123, | |
| "eval_vi_samples_per_second": 346.12, | |
| "eval_vi_steps_per_second": 3.619, | |
| "eval_vi_total_cls_tokens": 617, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3826530612244898, | |
| "eval_dan_All_acc": 0.5633970154928238, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.2857142857142857, | |
| "eval_dan_Gov_f1": 0.4210526315789473, | |
| "eval_dan_Neu_acc": 0.17647058823529413, | |
| "eval_dan_Neu_f1": 0.3, | |
| "eval_dan_Soc_acc": 0.47619047619047616, | |
| "eval_dan_Soc_f1": 0.6451612903225806, | |
| "eval_dan_cls_acc": 0.3269230769230769, | |
| "eval_dan_cls_f1": 0.341553480475382, | |
| "eval_dan_loss": 2.2690541744232178, | |
| "eval_dan_runtime": 8.7471, | |
| "eval_dan_samples_per_second": 342.969, | |
| "eval_dan_steps_per_second": 3.658, | |
| "eval_dan_total_cls_tokens": 52, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.42091836734693877, | |
| "grad_norm": 3.373872756958008, | |
| "learning_rate": 2.725e-05, | |
| "loss": 2.4461, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.45918367346938777, | |
| "grad_norm": 3.3780198097229004, | |
| "learning_rate": 2.975e-05, | |
| "loss": 2.3951, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.49744897959183676, | |
| "grad_norm": 3.1375372409820557, | |
| "learning_rate": 3.2250000000000005e-05, | |
| "loss": 2.3492, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 3.414963483810425, | |
| "learning_rate": 3.475e-05, | |
| "loss": 2.3454, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5739795918367347, | |
| "grad_norm": 3.433048963546753, | |
| "learning_rate": 3.7250000000000004e-05, | |
| "loss": 2.2903, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 3.484123468399048, | |
| "learning_rate": 3.9750000000000004e-05, | |
| "loss": 2.3064, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6505102040816326, | |
| "grad_norm": 3.401663064956665, | |
| "learning_rate": 4.2250000000000004e-05, | |
| "loss": 2.2553, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6887755102040817, | |
| "grad_norm": 3.347205638885498, | |
| "learning_rate": 4.4750000000000004e-05, | |
| "loss": 2.2418, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7270408163265306, | |
| "grad_norm": 3.300549030303955, | |
| "learning_rate": 4.7249999999999997e-05, | |
| "loss": 2.2547, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7653061224489796, | |
| "grad_norm": 3.227160692214966, | |
| "learning_rate": 4.975e-05, | |
| "loss": 2.2218, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7653061224489796, | |
| "eval_en_All_acc": 0.5353060570451875, | |
| "eval_en_Env_acc": 0.9852941176470589, | |
| "eval_en_Env_f1": 0.7444444444444446, | |
| "eval_en_Gov_acc": 0.5789473684210527, | |
| "eval_en_Gov_f1": 0.6470588235294117, | |
| "eval_en_Neu_acc": 0.581081081081081, | |
| "eval_en_Neu_f1": 0.6142857142857142, | |
| "eval_en_Soc_acc": 0.5833333333333334, | |
| "eval_en_Soc_f1": 0.6853146853146853, | |
| "eval_en_cls_acc": 0.6784452296819788, | |
| "eval_en_cls_f1": 0.672775916893564, | |
| "eval_en_loss": 2.877591371536255, | |
| "eval_en_runtime": 5.5464, | |
| "eval_en_samples_per_second": 338.415, | |
| "eval_en_steps_per_second": 3.606, | |
| "eval_en_total_cls_tokens": 283, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7653061224489796, | |
| "eval_en_oof_All_acc": 0.5409468969929623, | |
| "eval_en_oof_Env_acc": 0.9473684210526315, | |
| "eval_en_oof_Env_f1": 0.776978417266187, | |
| "eval_en_oof_Gov_acc": 0.6774193548387096, | |
| "eval_en_oof_Gov_f1": 0.7567567567567567, | |
| "eval_en_oof_Neu_acc": 0.6710526315789473, | |
| "eval_en_oof_Neu_f1": 0.6938775510204082, | |
| "eval_en_oof_Soc_acc": 0.7466666666666667, | |
| "eval_en_oof_Soc_f1": 0.7887323943661971, | |
| "eval_en_oof_cls_acc": 0.7518518518518519, | |
| "eval_en_oof_cls_f1": 0.7540862798523872, | |
| "eval_en_oof_loss": 2.8690555095672607, | |
| "eval_en_oof_runtime": 5.554, | |
| "eval_en_oof_samples_per_second": 337.957, | |
| "eval_en_oof_steps_per_second": 3.601, | |
| "eval_en_oof_total_cls_tokens": 270, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7653061224489796, | |
| "eval_vi_All_acc": 0.6706211812627291, | |
| "eval_vi_Env_acc": 0.8685714285714285, | |
| "eval_vi_Env_f1": 0.7524752475247525, | |
| "eval_vi_Gov_acc": 0.5730994152046783, | |
| "eval_vi_Gov_f1": 0.6621621621621621, | |
| "eval_vi_Neu_acc": 0.6178343949044586, | |
| "eval_vi_Neu_f1": 0.5418994413407822, | |
| "eval_vi_Soc_acc": 0.41975308641975306, | |
| "eval_vi_Soc_f1": 0.5037037037037038, | |
| "eval_vi_cls_acc": 0.6240601503759399, | |
| "eval_vi_cls_f1": 0.6150601386828501, | |
| "eval_vi_loss": 1.66096031665802, | |
| "eval_vi_runtime": 12.5792, | |
| "eval_vi_samples_per_second": 349.784, | |
| "eval_vi_steps_per_second": 3.657, | |
| "eval_vi_total_cls_tokens": 665, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7653061224489796, | |
| "eval_dan_All_acc": 0.5931197552042283, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.16666666666666666, | |
| "eval_dan_Gov_f1": 0.26666666666666666, | |
| "eval_dan_Neu_acc": 0.26666666666666666, | |
| "eval_dan_Neu_f1": 0.3809523809523809, | |
| "eval_dan_Soc_acc": 0.3125, | |
| "eval_dan_Soc_f1": 0.47619047619047616, | |
| "eval_dan_cls_acc": 0.25, | |
| "eval_dan_cls_f1": 0.28095238095238095, | |
| "eval_dan_loss": 2.170633316040039, | |
| "eval_dan_runtime": 8.8068, | |
| "eval_dan_samples_per_second": 340.645, | |
| "eval_dan_steps_per_second": 3.634, | |
| "eval_dan_total_cls_tokens": 44, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8035714285714286, | |
| "grad_norm": 3.386247158050537, | |
| "learning_rate": 4.9999870958602027e-05, | |
| "loss": 2.2123, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8418367346938775, | |
| "grad_norm": 3.076685905456543, | |
| "learning_rate": 4.999942489128224e-05, | |
| "loss": 2.1878, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8801020408163265, | |
| "grad_norm": 3.108447790145874, | |
| "learning_rate": 4.999866021062066e-05, | |
| "loss": 2.1225, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 3.365969657897949, | |
| "learning_rate": 4.9997576926363015e-05, | |
| "loss": 2.0872, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9566326530612245, | |
| "grad_norm": 3.221285581588745, | |
| "learning_rate": 4.999617505231557e-05, | |
| "loss": 2.1246, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9948979591836735, | |
| "grad_norm": 2.936293601989746, | |
| "learning_rate": 4.9994454606344976e-05, | |
| "loss": 2.1134, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.030612244897959, | |
| "grad_norm": 3.291677713394165, | |
| "learning_rate": 4.999241561037801e-05, | |
| "loss": 1.9138, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.068877551020408, | |
| "grad_norm": 3.103902816772461, | |
| "learning_rate": 4.9990058090401325e-05, | |
| "loss": 2.0589, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1071428571428572, | |
| "grad_norm": 3.178459405899048, | |
| "learning_rate": 4.99873820764611e-05, | |
| "loss": 2.1208, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1454081632653061, | |
| "grad_norm": 3.2897515296936035, | |
| "learning_rate": 4.9984387602662675e-05, | |
| "loss": 2.098, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1454081632653061, | |
| "eval_en_All_acc": 0.5541844289881086, | |
| "eval_en_Env_acc": 0.9558823529411765, | |
| "eval_en_Env_f1": 0.9285714285714286, | |
| "eval_en_Gov_acc": 0.6923076923076923, | |
| "eval_en_Gov_f1": 0.7999999999999999, | |
| "eval_en_Neu_acc": 0.8266666666666667, | |
| "eval_en_Neu_f1": 0.7898089171974522, | |
| "eval_en_Soc_acc": 0.7857142857142857, | |
| "eval_en_Soc_f1": 0.7692307692307693, | |
| "eval_en_cls_acc": 0.8226415094339623, | |
| "eval_en_cls_f1": 0.8219027787499125, | |
| "eval_en_loss": 2.7155141830444336, | |
| "eval_en_runtime": 5.6403, | |
| "eval_en_samples_per_second": 332.786, | |
| "eval_en_steps_per_second": 3.546, | |
| "eval_en_total_cls_tokens": 265, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1454081632653061, | |
| "eval_en_oof_All_acc": 0.5600981193785772, | |
| "eval_en_oof_Env_acc": 0.9594594594594594, | |
| "eval_en_oof_Env_f1": 0.9161290322580644, | |
| "eval_en_oof_Gov_acc": 0.8088235294117647, | |
| "eval_en_oof_Gov_f1": 0.88, | |
| "eval_en_oof_Neu_acc": 0.8048780487804879, | |
| "eval_en_oof_Neu_f1": 0.7951807228915663, | |
| "eval_en_oof_Soc_acc": 0.8, | |
| "eval_en_oof_Soc_f1": 0.7938931297709925, | |
| "eval_en_oof_cls_acc": 0.8442906574394463, | |
| "eval_en_oof_cls_f1": 0.8463007212301558, | |
| "eval_en_oof_loss": 2.697880268096924, | |
| "eval_en_oof_runtime": 5.5504, | |
| "eval_en_oof_samples_per_second": 338.173, | |
| "eval_en_oof_steps_per_second": 3.603, | |
| "eval_en_oof_total_cls_tokens": 289, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1454081632653061, | |
| "eval_vi_All_acc": 0.70428505369162, | |
| "eval_vi_Env_acc": 0.8852459016393442, | |
| "eval_vi_Env_f1": 0.8975069252077562, | |
| "eval_vi_Gov_acc": 0.6766467065868264, | |
| "eval_vi_Gov_f1": 0.7687074829931972, | |
| "eval_vi_Neu_acc": 0.7891891891891892, | |
| "eval_vi_Neu_f1": 0.7807486631016042, | |
| "eval_vi_Soc_acc": 0.8719512195121951, | |
| "eval_vi_Soc_f1": 0.7750677506775069, | |
| "eval_vi_cls_acc": 0.8068669527896996, | |
| "eval_vi_cls_f1": 0.8055077054950162, | |
| "eval_vi_loss": 1.4601171016693115, | |
| "eval_vi_runtime": 12.2278, | |
| "eval_vi_samples_per_second": 359.836, | |
| "eval_vi_steps_per_second": 3.762, | |
| "eval_vi_total_cls_tokens": 699, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1454081632653061, | |
| "eval_dan_All_acc": 0.6160471650315509, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2857142857142857, | |
| "eval_dan_Gov_f1": 0.4444444444444445, | |
| "eval_dan_Neu_acc": 0.375, | |
| "eval_dan_Neu_f1": 0.5454545454545454, | |
| "eval_dan_Soc_acc": 0.07142857142857142, | |
| "eval_dan_Soc_f1": 0.13333333333333333, | |
| "eval_dan_cls_acc": 0.2608695652173913, | |
| "eval_dan_cls_f1": 0.28080808080808084, | |
| "eval_dan_loss": 2.0174965858459473, | |
| "eval_dan_runtime": 9.3296, | |
| "eval_dan_samples_per_second": 321.559, | |
| "eval_dan_steps_per_second": 3.43, | |
| "eval_dan_total_cls_tokens": 46, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.183673469387755, | |
| "grad_norm": 3.2816624641418457, | |
| "learning_rate": 4.9981074707170105e-05, | |
| "loss": 2.0126, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.221938775510204, | |
| "grad_norm": 3.2059404850006104, | |
| "learning_rate": 4.997744343220566e-05, | |
| "loss": 2.0275, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.260204081632653, | |
| "grad_norm": 3.2183995246887207, | |
| "learning_rate": 4.997349382404932e-05, | |
| "loss": 2.0294, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.2984693877551021, | |
| "grad_norm": 2.919109582901001, | |
| "learning_rate": 4.996922593303814e-05, | |
| "loss": 1.9697, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.336734693877551, | |
| "grad_norm": 3.1916449069976807, | |
| "learning_rate": 4.996463981356567e-05, | |
| "loss": 2.0063, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.375, | |
| "grad_norm": 2.965237617492676, | |
| "learning_rate": 4.995973552408121e-05, | |
| "loss": 1.9826, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.413265306122449, | |
| "grad_norm": 3.005899429321289, | |
| "learning_rate": 4.995451312708907e-05, | |
| "loss": 2.0048, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.4515306122448979, | |
| "grad_norm": 3.0960004329681396, | |
| "learning_rate": 4.994897268914779e-05, | |
| "loss": 1.9609, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.489795918367347, | |
| "grad_norm": 3.0031135082244873, | |
| "learning_rate": 4.99431142808693e-05, | |
| "loss": 1.9593, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.5280612244897958, | |
| "grad_norm": 2.973250389099121, | |
| "learning_rate": 4.9936937976918003e-05, | |
| "loss": 1.9671, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5280612244897958, | |
| "eval_en_All_acc": 0.5549671679728871, | |
| "eval_en_Env_acc": 0.9726027397260274, | |
| "eval_en_Env_f1": 0.9594594594594594, | |
| "eval_en_Gov_acc": 0.8813559322033898, | |
| "eval_en_Gov_f1": 0.9043478260869564, | |
| "eval_en_Neu_acc": 0.7435897435897436, | |
| "eval_en_Neu_f1": 0.7891156462585034, | |
| "eval_en_Soc_acc": 0.9135802469135802, | |
| "eval_en_Soc_f1": 0.8604651162790699, | |
| "eval_en_cls_acc": 0.8762886597938144, | |
| "eval_en_cls_f1": 0.8783470120209973, | |
| "eval_en_loss": 2.721444606781006, | |
| "eval_en_runtime": 5.6125, | |
| "eval_en_samples_per_second": 334.43, | |
| "eval_en_steps_per_second": 3.563, | |
| "eval_en_total_cls_tokens": 291, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5280612244897958, | |
| "eval_en_oof_All_acc": 0.5584415584415584, | |
| "eval_en_oof_Env_acc": 0.9242424242424242, | |
| "eval_en_oof_Env_f1": 0.9312977099236641, | |
| "eval_en_oof_Gov_acc": 0.8305084745762712, | |
| "eval_en_oof_Gov_f1": 0.8828828828828829, | |
| "eval_en_oof_Neu_acc": 0.7857142857142857, | |
| "eval_en_oof_Neu_f1": 0.7746478873239437, | |
| "eval_en_oof_Soc_acc": 0.8769230769230769, | |
| "eval_en_oof_Soc_f1": 0.8382352941176471, | |
| "eval_en_oof_cls_acc": 0.8538461538461538, | |
| "eval_en_oof_cls_f1": 0.8567659435620345, | |
| "eval_en_oof_loss": 2.6919920444488525, | |
| "eval_en_oof_runtime": 5.563, | |
| "eval_en_oof_samples_per_second": 337.407, | |
| "eval_en_oof_steps_per_second": 3.595, | |
| "eval_en_oof_total_cls_tokens": 260, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5280612244897958, | |
| "eval_vi_All_acc": 0.7096399834949453, | |
| "eval_vi_Env_acc": 0.9032258064516129, | |
| "eval_vi_Env_f1": 0.9061488673139159, | |
| "eval_vi_Gov_acc": 0.7727272727272727, | |
| "eval_vi_Gov_f1": 0.7880794701986754, | |
| "eval_vi_Neu_acc": 0.75, | |
| "eval_vi_Neu_f1": 0.7859424920127795, | |
| "eval_vi_Soc_acc": 0.8539325842696629, | |
| "eval_vi_Soc_f1": 0.8042328042328041, | |
| "eval_vi_cls_acc": 0.8202764976958525, | |
| "eval_vi_cls_f1": 0.8211009084395438, | |
| "eval_vi_loss": 1.410032868385315, | |
| "eval_vi_runtime": 12.6603, | |
| "eval_vi_samples_per_second": 347.542, | |
| "eval_vi_steps_per_second": 3.633, | |
| "eval_vi_total_cls_tokens": 651, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5280612244897958, | |
| "eval_dan_All_acc": 0.6198026938150367, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3333333333333333, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.1111111111111111, | |
| "eval_dan_Neu_f1": 0.19999999999999998, | |
| "eval_dan_Soc_acc": 0.2857142857142857, | |
| "eval_dan_Soc_f1": 0.4444444444444445, | |
| "eval_dan_cls_acc": 0.19230769230769232, | |
| "eval_dan_cls_f1": 0.2861111111111111, | |
| "eval_dan_loss": 2.044161796569824, | |
| "eval_dan_runtime": 8.6659, | |
| "eval_dan_samples_per_second": 346.186, | |
| "eval_dan_steps_per_second": 3.693, | |
| "eval_dan_total_cls_tokens": 52, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.566326530612245, | |
| "grad_norm": 2.954650640487671, | |
| "learning_rate": 4.9930443856009826e-05, | |
| "loss": 1.9559, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.6045918367346939, | |
| "grad_norm": 3.046367645263672, | |
| "learning_rate": 4.9923632000911196e-05, | |
| "loss": 1.9798, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.6428571428571428, | |
| "grad_norm": 3.147254705429077, | |
| "learning_rate": 4.991650249843805e-05, | |
| "loss": 1.9619, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.681122448979592, | |
| "grad_norm": 2.9849867820739746, | |
| "learning_rate": 4.9909055439454655e-05, | |
| "loss": 1.8863, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.7193877551020407, | |
| "grad_norm": 2.9059383869171143, | |
| "learning_rate": 4.990129091887248e-05, | |
| "loss": 1.93, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.7576530612244898, | |
| "grad_norm": 2.964554786682129, | |
| "learning_rate": 4.9893209035649004e-05, | |
| "loss": 1.8758, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.7959183673469388, | |
| "grad_norm": 2.9072604179382324, | |
| "learning_rate": 4.9884809892786426e-05, | |
| "loss": 1.9152, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.8341836734693877, | |
| "grad_norm": 2.845878839492798, | |
| "learning_rate": 4.987609359733037e-05, | |
| "loss": 1.8356, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.8724489795918369, | |
| "grad_norm": 2.988858222961426, | |
| "learning_rate": 4.9867060260368515e-05, | |
| "loss": 1.8751, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.9107142857142856, | |
| "grad_norm": 2.9248316287994385, | |
| "learning_rate": 4.985770999702917e-05, | |
| "loss": 1.9019, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9107142857142856, | |
| "eval_en_All_acc": 0.5577339688041595, | |
| "eval_en_Env_acc": 0.9875, | |
| "eval_en_Env_f1": 0.9753086419753086, | |
| "eval_en_Gov_acc": 0.9591836734693877, | |
| "eval_en_Gov_f1": 0.912621359223301, | |
| "eval_en_Neu_acc": 0.8524590163934426, | |
| "eval_en_Neu_f1": 0.888888888888889, | |
| "eval_en_Soc_acc": 0.9253731343283582, | |
| "eval_en_Soc_f1": 0.9393939393939394, | |
| "eval_en_cls_acc": 0.933852140077821, | |
| "eval_en_cls_f1": 0.9290532073703595, | |
| "eval_en_loss": 2.7529537677764893, | |
| "eval_en_runtime": 5.6025, | |
| "eval_en_samples_per_second": 335.027, | |
| "eval_en_steps_per_second": 3.57, | |
| "eval_en_total_cls_tokens": 257, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9107142857142856, | |
| "eval_en_oof_All_acc": 0.5620826377295493, | |
| "eval_en_oof_Env_acc": 0.926829268292683, | |
| "eval_en_oof_Env_f1": 0.9500000000000001, | |
| "eval_en_oof_Gov_acc": 0.9701492537313433, | |
| "eval_en_oof_Gov_f1": 0.9420289855072463, | |
| "eval_en_oof_Neu_acc": 0.9047619047619048, | |
| "eval_en_oof_Neu_f1": 0.890625, | |
| "eval_en_oof_Soc_acc": 0.8870967741935484, | |
| "eval_en_oof_Soc_f1": 0.9016393442622951, | |
| "eval_en_oof_cls_acc": 0.9233576642335767, | |
| "eval_en_oof_cls_f1": 0.9210733324423854, | |
| "eval_en_oof_loss": 2.6755943298339844, | |
| "eval_en_oof_runtime": 5.572, | |
| "eval_en_oof_samples_per_second": 336.862, | |
| "eval_en_oof_steps_per_second": 3.589, | |
| "eval_en_oof_total_cls_tokens": 274, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9107142857142856, | |
| "eval_vi_All_acc": 0.7230820223859667, | |
| "eval_vi_Env_acc": 0.9347826086956522, | |
| "eval_vi_Env_f1": 0.9197860962566845, | |
| "eval_vi_Gov_acc": 0.772972972972973, | |
| "eval_vi_Gov_f1": 0.807909604519774, | |
| "eval_vi_Neu_acc": 0.76875, | |
| "eval_vi_Neu_f1": 0.7909967845659164, | |
| "eval_vi_Soc_acc": 0.8466257668711656, | |
| "eval_vi_Soc_f1": 0.7999999999999999, | |
| "eval_vi_cls_acc": 0.8323699421965318, | |
| "eval_vi_cls_f1": 0.8296731213355938, | |
| "eval_vi_loss": 1.3319677114486694, | |
| "eval_vi_runtime": 12.6366, | |
| "eval_vi_samples_per_second": 348.194, | |
| "eval_vi_steps_per_second": 3.64, | |
| "eval_vi_total_cls_tokens": 692, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9107142857142856, | |
| "eval_dan_All_acc": 0.6344721653323403, | |
| "eval_dan_Env_acc": 0.3333333333333333, | |
| "eval_dan_Env_f1": 0.5, | |
| "eval_dan_Gov_acc": 0.5, | |
| "eval_dan_Gov_f1": 0.6666666666666666, | |
| "eval_dan_Neu_acc": 0.25, | |
| "eval_dan_Neu_f1": 0.4, | |
| "eval_dan_Soc_acc": 0.38461538461538464, | |
| "eval_dan_Soc_f1": 0.5555555555555556, | |
| "eval_dan_cls_acc": 0.3333333333333333, | |
| "eval_dan_cls_f1": 0.5305555555555556, | |
| "eval_dan_loss": 1.9639889001846313, | |
| "eval_dan_runtime": 8.6577, | |
| "eval_dan_samples_per_second": 346.514, | |
| "eval_dan_steps_per_second": 3.696, | |
| "eval_dan_total_cls_tokens": 36, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9489795918367347, | |
| "grad_norm": 2.8369531631469727, | |
| "learning_rate": 4.984804292647982e-05, | |
| "loss": 1.9004, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.9872448979591837, | |
| "grad_norm": 2.884544849395752, | |
| "learning_rate": 4.983805917192561e-05, | |
| "loss": 1.8758, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.0229591836734695, | |
| "grad_norm": 2.6424052715301514, | |
| "learning_rate": 4.982775886060777e-05, | |
| "loss": 1.7272, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.061224489795918, | |
| "grad_norm": 2.782474994659424, | |
| "learning_rate": 4.981714212380197e-05, | |
| "loss": 1.8735, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.0994897959183674, | |
| "grad_norm": 2.8424980640411377, | |
| "learning_rate": 4.98062090968167e-05, | |
| "loss": 1.857, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.137755102040816, | |
| "grad_norm": 2.9368510246276855, | |
| "learning_rate": 4.979495991899148e-05, | |
| "loss": 1.8701, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.1760204081632653, | |
| "grad_norm": 2.669766426086426, | |
| "learning_rate": 4.978339473369515e-05, | |
| "loss": 1.8296, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.2142857142857144, | |
| "grad_norm": 2.8707900047302246, | |
| "learning_rate": 4.977151368832397e-05, | |
| "loss": 1.8117, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.252551020408163, | |
| "grad_norm": 2.733189821243286, | |
| "learning_rate": 4.9759316934299825e-05, | |
| "loss": 1.882, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.2908163265306123, | |
| "grad_norm": 2.6979124546051025, | |
| "learning_rate": 4.9746804627068236e-05, | |
| "loss": 1.8751, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.2908163265306123, | |
| "eval_en_All_acc": 0.5627158894645942, | |
| "eval_en_Env_acc": 0.9649122807017544, | |
| "eval_en_Env_f1": 0.9166666666666667, | |
| "eval_en_Gov_acc": 0.7727272727272727, | |
| "eval_en_Gov_f1": 0.864406779661017, | |
| "eval_en_Neu_acc": 0.8552631578947368, | |
| "eval_en_Neu_f1": 0.8024691358024691, | |
| "eval_en_Soc_acc": 0.8412698412698413, | |
| "eval_en_Soc_f1": 0.8548387096774194, | |
| "eval_en_cls_acc": 0.8549618320610687, | |
| "eval_en_cls_f1": 0.859595322951893, | |
| "eval_en_loss": 2.662379741668701, | |
| "eval_en_runtime": 5.603, | |
| "eval_en_samples_per_second": 335.001, | |
| "eval_en_steps_per_second": 3.57, | |
| "eval_en_total_cls_tokens": 262, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.2908163265306123, | |
| "eval_en_oof_All_acc": 0.557348451809856, | |
| "eval_en_oof_Env_acc": 0.9333333333333333, | |
| "eval_en_oof_Env_f1": 0.9256198347107439, | |
| "eval_en_oof_Gov_acc": 0.875, | |
| "eval_en_oof_Gov_f1": 0.9105691056910569, | |
| "eval_en_oof_Neu_acc": 0.8863636363636364, | |
| "eval_en_oof_Neu_f1": 0.8478260869565218, | |
| "eval_en_oof_Soc_acc": 0.8095238095238095, | |
| "eval_en_oof_Soc_f1": 0.8360655737704918, | |
| "eval_en_oof_cls_acc": 0.8763636363636363, | |
| "eval_en_oof_cls_f1": 0.8800201502822037, | |
| "eval_en_oof_loss": 2.691774845123291, | |
| "eval_en_oof_runtime": 5.5622, | |
| "eval_en_oof_samples_per_second": 337.459, | |
| "eval_en_oof_steps_per_second": 3.596, | |
| "eval_en_oof_total_cls_tokens": 275, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.2908163265306123, | |
| "eval_vi_All_acc": 0.7387760349704294, | |
| "eval_vi_Env_acc": 0.9482758620689655, | |
| "eval_vi_Env_f1": 0.9116022099447514, | |
| "eval_vi_Gov_acc": 0.7570621468926554, | |
| "eval_vi_Gov_f1": 0.8271604938271605, | |
| "eval_vi_Neu_acc": 0.8461538461538461, | |
| "eval_vi_Neu_f1": 0.8033707865168538, | |
| "eval_vi_Soc_acc": 0.834319526627219, | |
| "eval_vi_Soc_f1": 0.8392857142857143, | |
| "eval_vi_cls_acc": 0.8461538461538461, | |
| "eval_vi_cls_f1": 0.84535480114362, | |
| "eval_vi_loss": 1.2845317125320435, | |
| "eval_vi_runtime": 12.2382, | |
| "eval_vi_samples_per_second": 359.531, | |
| "eval_vi_steps_per_second": 3.759, | |
| "eval_vi_total_cls_tokens": 689, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.2908163265306123, | |
| "eval_dan_All_acc": 0.6347272223760732, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.125, | |
| "eval_dan_Gov_f1": 0.21052631578947367, | |
| "eval_dan_Neu_acc": 0.1875, | |
| "eval_dan_Neu_f1": 0.3157894736842105, | |
| "eval_dan_Soc_acc": 0.25, | |
| "eval_dan_Soc_f1": 0.4, | |
| "eval_dan_cls_acc": 0.17391304347826086, | |
| "eval_dan_cls_f1": 0.23157894736842105, | |
| "eval_dan_loss": 1.959936499595642, | |
| "eval_dan_runtime": 9.2293, | |
| "eval_dan_samples_per_second": 325.051, | |
| "eval_dan_steps_per_second": 3.467, | |
| "eval_dan_total_cls_tokens": 46, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.329081632653061, | |
| "grad_norm": 2.821786880493164, | |
| "learning_rate": 4.973397692609637e-05, | |
| "loss": 1.88, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.36734693877551, | |
| "grad_norm": 2.8813090324401855, | |
| "learning_rate": 4.972083399487108e-05, | |
| "loss": 1.8368, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.4056122448979593, | |
| "grad_norm": 2.75775408744812, | |
| "learning_rate": 4.9707376000896736e-05, | |
| "loss": 1.8114, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.443877551020408, | |
| "grad_norm": 2.801783323287964, | |
| "learning_rate": 4.969360311569314e-05, | |
| "loss": 1.8537, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.482142857142857, | |
| "grad_norm": 2.702641248703003, | |
| "learning_rate": 4.967951551479334e-05, | |
| "loss": 1.8156, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.520408163265306, | |
| "grad_norm": 2.892446279525757, | |
| "learning_rate": 4.966511337774136e-05, | |
| "loss": 1.8164, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.558673469387755, | |
| "grad_norm": 2.911881685256958, | |
| "learning_rate": 4.9650396888089946e-05, | |
| "loss": 1.8195, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.5969387755102042, | |
| "grad_norm": 2.8443522453308105, | |
| "learning_rate": 4.963536623339821e-05, | |
| "loss": 1.8233, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.635204081632653, | |
| "grad_norm": 2.764707088470459, | |
| "learning_rate": 4.962002160522925e-05, | |
| "loss": 1.8055, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.673469387755102, | |
| "grad_norm": 2.947256326675415, | |
| "learning_rate": 4.9604363199147686e-05, | |
| "loss": 1.8466, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.673469387755102, | |
| "eval_en_All_acc": 0.5729323308270676, | |
| "eval_en_Env_acc": 0.9367088607594937, | |
| "eval_en_Env_f1": 0.9548387096774194, | |
| "eval_en_Gov_acc": 0.9841269841269841, | |
| "eval_en_Gov_f1": 0.9465648854961831, | |
| "eval_en_Neu_acc": 0.8452380952380952, | |
| "eval_en_Neu_f1": 0.8819875776397517, | |
| "eval_en_Soc_acc": 0.9142857142857143, | |
| "eval_en_Soc_f1": 0.8827586206896552, | |
| "eval_en_cls_acc": 0.9155405405405406, | |
| "eval_en_cls_f1": 0.9165374483757524, | |
| "eval_en_loss": 2.585716962814331, | |
| "eval_en_runtime": 5.5857, | |
| "eval_en_samples_per_second": 336.038, | |
| "eval_en_steps_per_second": 3.581, | |
| "eval_en_total_cls_tokens": 296, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.673469387755102, | |
| "eval_en_oof_All_acc": 0.5745832431262178, | |
| "eval_en_oof_Env_acc": 0.8985507246376812, | |
| "eval_en_oof_Env_f1": 0.9323308270676692, | |
| "eval_en_oof_Gov_acc": 0.9841269841269841, | |
| "eval_en_oof_Gov_f1": 0.9465648854961831, | |
| "eval_en_oof_Neu_acc": 0.8023255813953488, | |
| "eval_en_oof_Neu_f1": 0.8571428571428572, | |
| "eval_en_oof_Soc_acc": 0.9272727272727272, | |
| "eval_en_oof_Soc_f1": 0.8429752066115703, | |
| "eval_en_oof_cls_acc": 0.8937728937728938, | |
| "eval_en_oof_cls_f1": 0.8947534440795699, | |
| "eval_en_oof_loss": 2.6026809215545654, | |
| "eval_en_oof_runtime": 5.5654, | |
| "eval_en_oof_samples_per_second": 337.263, | |
| "eval_en_oof_steps_per_second": 3.594, | |
| "eval_en_oof_total_cls_tokens": 273, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.673469387755102, | |
| "eval_vi_All_acc": 0.7397455833991894, | |
| "eval_vi_Env_acc": 0.8918918918918919, | |
| "eval_vi_Env_f1": 0.9263157894736843, | |
| "eval_vi_Gov_acc": 0.9386503067484663, | |
| "eval_vi_Gov_f1": 0.864406779661017, | |
| "eval_vi_Neu_acc": 0.8255813953488372, | |
| "eval_vi_Neu_f1": 0.8658536585365854, | |
| "eval_vi_Soc_acc": 0.8424242424242424, | |
| "eval_vi_Soc_f1": 0.8449848024316109, | |
| "eval_vi_cls_acc": 0.8734567901234568, | |
| "eval_vi_cls_f1": 0.8753902575257243, | |
| "eval_vi_loss": 1.2590796947479248, | |
| "eval_vi_runtime": 12.6432, | |
| "eval_vi_samples_per_second": 348.014, | |
| "eval_vi_steps_per_second": 3.638, | |
| "eval_vi_total_cls_tokens": 648, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.673469387755102, | |
| "eval_dan_All_acc": 0.6388643650387993, | |
| "eval_dan_Env_acc": 1.0, | |
| "eval_dan_Env_f1": 1.0, | |
| "eval_dan_Gov_acc": 0.3, | |
| "eval_dan_Gov_f1": 0.4285714285714285, | |
| "eval_dan_Neu_acc": 0.30434782608695654, | |
| "eval_dan_Neu_f1": 0.4666666666666667, | |
| "eval_dan_Soc_acc": 0.26666666666666666, | |
| "eval_dan_Soc_f1": 0.4210526315789474, | |
| "eval_dan_cls_acc": 0.30612244897959184, | |
| "eval_dan_cls_f1": 0.5790726817042606, | |
| "eval_dan_loss": 1.9637938737869263, | |
| "eval_dan_runtime": 8.6905, | |
| "eval_dan_samples_per_second": 345.203, | |
| "eval_dan_steps_per_second": 3.682, | |
| "eval_dan_total_cls_tokens": 49, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.711734693877551, | |
| "grad_norm": 2.80818510055542, | |
| "learning_rate": 4.958839121471719e-05, | |
| "loss": 1.7977, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 2.809807300567627, | |
| "learning_rate": 4.957210585549795e-05, | |
| "loss": 1.7574, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.788265306122449, | |
| "grad_norm": 2.615295886993408, | |
| "learning_rate": 4.9555507329044046e-05, | |
| "loss": 1.8136, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.826530612244898, | |
| "grad_norm": 2.728816032409668, | |
| "learning_rate": 4.953859584690082e-05, | |
| "loss": 1.7273, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.864795918367347, | |
| "grad_norm": 2.8085060119628906, | |
| "learning_rate": 4.9521371624602174e-05, | |
| "loss": 1.7956, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.9030612244897958, | |
| "grad_norm": 2.6751620769500732, | |
| "learning_rate": 4.9503834881667865e-05, | |
| "loss": 1.7978, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.941326530612245, | |
| "grad_norm": 2.8360347747802734, | |
| "learning_rate": 4.9485985841600626e-05, | |
| "loss": 1.7809, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.979591836734694, | |
| "grad_norm": 2.7588205337524414, | |
| "learning_rate": 4.9467824731883385e-05, | |
| "loss": 1.7721, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.0153061224489797, | |
| "grad_norm": 2.643064260482788, | |
| "learning_rate": 4.944935178397634e-05, | |
| "loss": 1.631, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.0535714285714284, | |
| "grad_norm": 2.5776360034942627, | |
| "learning_rate": 4.943056723331402e-05, | |
| "loss": 1.7577, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.0535714285714284, | |
| "eval_en_All_acc": 0.5727203399063079, | |
| "eval_en_Env_acc": 0.9857142857142858, | |
| "eval_en_Env_f1": 0.971830985915493, | |
| "eval_en_Gov_acc": 0.984375, | |
| "eval_en_Gov_f1": 0.9767441860465116, | |
| "eval_en_Neu_acc": 0.8888888888888888, | |
| "eval_en_Neu_f1": 0.9014084507042254, | |
| "eval_en_Soc_acc": 0.9142857142857143, | |
| "eval_en_Soc_f1": 0.920863309352518, | |
| "eval_en_cls_acc": 0.9420289855072463, | |
| "eval_en_cls_f1": 0.942711733004687, | |
| "eval_en_loss": 2.5750484466552734, | |
| "eval_en_runtime": 5.643, | |
| "eval_en_samples_per_second": 332.623, | |
| "eval_en_steps_per_second": 3.544, | |
| "eval_en_total_cls_tokens": 276, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.0535714285714284, | |
| "eval_en_oof_All_acc": 0.6061386563640266, | |
| "eval_en_oof_Env_acc": 0.96, | |
| "eval_en_oof_Env_f1": 0.96, | |
| "eval_en_oof_Gov_acc": 0.9859154929577465, | |
| "eval_en_oof_Gov_f1": 0.9655172413793103, | |
| "eval_en_oof_Neu_acc": 0.8513513513513513, | |
| "eval_en_oof_Neu_f1": 0.863013698630137, | |
| "eval_en_oof_Soc_acc": 0.9135802469135802, | |
| "eval_en_oof_Soc_f1": 0.9192546583850932, | |
| "eval_en_oof_cls_acc": 0.9269102990033222, | |
| "eval_en_oof_cls_f1": 0.926946399598635, | |
| "eval_en_oof_loss": 2.3532822132110596, | |
| "eval_en_oof_runtime": 5.5741, | |
| "eval_en_oof_samples_per_second": 336.735, | |
| "eval_en_oof_steps_per_second": 3.588, | |
| "eval_en_oof_total_cls_tokens": 301, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.0535714285714284, | |
| "eval_vi_All_acc": 0.7288831835686778, | |
| "eval_vi_Env_acc": 0.9322033898305084, | |
| "eval_vi_Env_f1": 0.9428571428571428, | |
| "eval_vi_Gov_acc": 0.8851351351351351, | |
| "eval_vi_Gov_f1": 0.8317460317460316, | |
| "eval_vi_Neu_acc": 0.70625, | |
| "eval_vi_Neu_f1": 0.795774647887324, | |
| "eval_vi_Soc_acc": 0.8685714285714285, | |
| "eval_vi_Soc_f1": 0.8194070080862533, | |
| "eval_vi_cls_acc": 0.85, | |
| "eval_vi_cls_f1": 0.8474462076441879, | |
| "eval_vi_loss": 1.3019784688949585, | |
| "eval_vi_runtime": 12.2678, | |
| "eval_vi_samples_per_second": 358.662, | |
| "eval_vi_steps_per_second": 3.75, | |
| "eval_vi_total_cls_tokens": 660, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.0535714285714284, | |
| "eval_dan_All_acc": 0.6491302303714152, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3076923076923077, | |
| "eval_dan_Gov_f1": 0.47058823529411764, | |
| "eval_dan_Neu_acc": 0.20833333333333334, | |
| "eval_dan_Neu_f1": 0.3448275862068966, | |
| "eval_dan_Soc_acc": 0.4117647058823529, | |
| "eval_dan_Soc_f1": 0.5833333333333334, | |
| "eval_dan_cls_acc": 0.2909090909090909, | |
| "eval_dan_cls_f1": 0.3496872887085869, | |
| "eval_dan_loss": 1.9071154594421387, | |
| "eval_dan_runtime": 9.2213, | |
| "eval_dan_samples_per_second": 325.332, | |
| "eval_dan_steps_per_second": 3.47, | |
| "eval_dan_total_cls_tokens": 55, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.0918367346938775, | |
| "grad_norm": 2.6600821018218994, | |
| "learning_rate": 4.941147131930227e-05, | |
| "loss": 1.7271, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.1301020408163267, | |
| "grad_norm": 2.5817995071411133, | |
| "learning_rate": 4.93920642853152e-05, | |
| "loss": 1.7869, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.1683673469387754, | |
| "grad_norm": 2.576220750808716, | |
| "learning_rate": 4.937234637869211e-05, | |
| "loss": 1.7399, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.2066326530612246, | |
| "grad_norm": 2.708327531814575, | |
| "learning_rate": 4.935231785073429e-05, | |
| "loss": 1.7358, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.2448979591836733, | |
| "grad_norm": 2.5467000007629395, | |
| "learning_rate": 4.9331978956701875e-05, | |
| "loss": 1.7619, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.2831632653061225, | |
| "grad_norm": 2.6811935901641846, | |
| "learning_rate": 4.931132995581055e-05, | |
| "loss": 1.7378, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.3214285714285716, | |
| "grad_norm": 2.5013163089752197, | |
| "learning_rate": 4.929037111122823e-05, | |
| "loss": 1.7197, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.3596938775510203, | |
| "grad_norm": 2.611159324645996, | |
| "learning_rate": 4.92691026900718e-05, | |
| "loss": 1.7463, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.3979591836734695, | |
| "grad_norm": 2.8072104454040527, | |
| "learning_rate": 4.924752496340357e-05, | |
| "loss": 1.7278, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.436224489795918, | |
| "grad_norm": 2.6788201332092285, | |
| "learning_rate": 4.9225638206227954e-05, | |
| "loss": 1.7657, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.436224489795918, | |
| "eval_en_All_acc": 0.5857066093498119, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9681528662420382, | |
| "eval_en_Gov_acc": 0.9661016949152542, | |
| "eval_en_Gov_f1": 0.9193548387096773, | |
| "eval_en_Neu_acc": 0.7777777777777778, | |
| "eval_en_Neu_f1": 0.8421052631578947, | |
| "eval_en_Soc_acc": 0.9428571428571428, | |
| "eval_en_Soc_f1": 0.9428571428571428, | |
| "eval_en_cls_acc": 0.9205776173285198, | |
| "eval_en_cls_f1": 0.9181175277416882, | |
| "eval_en_loss": 2.5098369121551514, | |
| "eval_en_runtime": 5.6145, | |
| "eval_en_samples_per_second": 334.31, | |
| "eval_en_steps_per_second": 3.562, | |
| "eval_en_total_cls_tokens": 277, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.436224489795918, | |
| "eval_en_oof_All_acc": 0.5824384080859129, | |
| "eval_en_oof_Env_acc": 0.9830508474576272, | |
| "eval_en_oof_Env_f1": 0.9354838709677421, | |
| "eval_en_oof_Gov_acc": 0.9814814814814815, | |
| "eval_en_oof_Gov_f1": 0.9380530973451328, | |
| "eval_en_oof_Neu_acc": 0.7560975609756098, | |
| "eval_en_oof_Neu_f1": 0.8378378378378378, | |
| "eval_en_oof_Soc_acc": 0.9358974358974359, | |
| "eval_en_oof_Soc_f1": 0.9068322981366459, | |
| "eval_en_oof_cls_acc": 0.9010989010989011, | |
| "eval_en_oof_cls_f1": 0.9045517760718397, | |
| "eval_en_oof_loss": 2.5283946990966797, | |
| "eval_en_oof_runtime": 5.544, | |
| "eval_en_oof_samples_per_second": 338.563, | |
| "eval_en_oof_steps_per_second": 3.607, | |
| "eval_en_oof_total_cls_tokens": 273, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.436224489795918, | |
| "eval_vi_All_acc": 0.7467078189300411, | |
| "eval_vi_Env_acc": 0.948051948051948, | |
| "eval_vi_Env_f1": 0.9329073482428114, | |
| "eval_vi_Gov_acc": 0.8764044943820225, | |
| "eval_vi_Gov_f1": 0.8739495798319328, | |
| "eval_vi_Neu_acc": 0.7802197802197802, | |
| "eval_vi_Neu_f1": 0.8304093567251462, | |
| "eval_vi_Soc_acc": 0.8827586206896552, | |
| "eval_vi_Soc_f1": 0.8366013071895424, | |
| "eval_vi_cls_acc": 0.8679817905918058, | |
| "eval_vi_cls_f1": 0.8684668979973582, | |
| "eval_vi_loss": 1.2167749404907227, | |
| "eval_vi_runtime": 12.7307, | |
| "eval_vi_samples_per_second": 345.621, | |
| "eval_vi_steps_per_second": 3.613, | |
| "eval_vi_total_cls_tokens": 659, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.436224489795918, | |
| "eval_dan_All_acc": 0.6491609264481532, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.25, | |
| "eval_dan_Gov_f1": 0.4, | |
| "eval_dan_Neu_acc": 0.3888888888888889, | |
| "eval_dan_Neu_f1": 0.56, | |
| "eval_dan_Soc_acc": 0.2, | |
| "eval_dan_Soc_f1": 0.33333333333333337, | |
| "eval_dan_cls_acc": 0.3023255813953488, | |
| "eval_dan_cls_f1": 0.49, | |
| "eval_dan_loss": 1.8971351385116577, | |
| "eval_dan_runtime": 8.7764, | |
| "eval_dan_samples_per_second": 341.824, | |
| "eval_dan_steps_per_second": 3.646, | |
| "eval_dan_total_cls_tokens": 43, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.4744897959183674, | |
| "grad_norm": 2.6341795921325684, | |
| "learning_rate": 4.920344269748787e-05, | |
| "loss": 1.7363, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.512755102040816, | |
| "grad_norm": 2.816460371017456, | |
| "learning_rate": 4.918093872006123e-05, | |
| "loss": 1.7107, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.5510204081632653, | |
| "grad_norm": 2.551896810531616, | |
| "learning_rate": 4.915812656075734e-05, | |
| "loss": 1.709, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.5892857142857144, | |
| "grad_norm": 2.6789584159851074, | |
| "learning_rate": 4.9135006510313233e-05, | |
| "loss": 1.7605, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.627551020408163, | |
| "grad_norm": 2.8077826499938965, | |
| "learning_rate": 4.911157886338992e-05, | |
| "loss": 1.7109, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.6658163265306123, | |
| "grad_norm": 2.646695613861084, | |
| "learning_rate": 4.908784391856872e-05, | |
| "loss": 1.7063, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.704081632653061, | |
| "grad_norm": 2.560657262802124, | |
| "learning_rate": 4.906380197834739e-05, | |
| "loss": 1.7147, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.74234693877551, | |
| "grad_norm": 2.6300690174102783, | |
| "learning_rate": 4.903945334913631e-05, | |
| "loss": 1.6869, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.7806122448979593, | |
| "grad_norm": 2.6879563331604004, | |
| "learning_rate": 4.901479834125453e-05, | |
| "loss": 1.75, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.818877551020408, | |
| "grad_norm": 2.554438352584839, | |
| "learning_rate": 4.898983726892585e-05, | |
| "loss": 1.6815, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.818877551020408, | |
| "eval_en_All_acc": 0.5934495509772847, | |
| "eval_en_Env_acc": 0.9705882352941176, | |
| "eval_en_Env_f1": 0.9565217391304348, | |
| "eval_en_Gov_acc": 0.9482758620689655, | |
| "eval_en_Gov_f1": 0.9649122807017544, | |
| "eval_en_Neu_acc": 0.8461538461538461, | |
| "eval_en_Neu_f1": 0.8661417322834646, | |
| "eval_en_Soc_acc": 0.9452054794520548, | |
| "eval_en_Soc_f1": 0.9261744966442953, | |
| "eval_en_cls_acc": 0.928030303030303, | |
| "eval_en_cls_f1": 0.9284375621899872, | |
| "eval_en_loss": 2.461064338684082, | |
| "eval_en_runtime": 5.539, | |
| "eval_en_samples_per_second": 338.869, | |
| "eval_en_steps_per_second": 3.611, | |
| "eval_en_total_cls_tokens": 264, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.818877551020408, | |
| "eval_en_oof_All_acc": 0.5720566159125027, | |
| "eval_en_oof_Env_acc": 0.958904109589041, | |
| "eval_en_oof_Env_f1": 0.9523809523809523, | |
| "eval_en_oof_Gov_acc": 0.9696969696969697, | |
| "eval_en_oof_Gov_f1": 0.9770992366412214, | |
| "eval_en_oof_Neu_acc": 0.8620689655172413, | |
| "eval_en_oof_Neu_f1": 0.8620689655172413, | |
| "eval_en_oof_Soc_acc": 0.8676470588235294, | |
| "eval_en_oof_Soc_f1": 0.8676470588235294, | |
| "eval_en_oof_cls_acc": 0.9115646258503401, | |
| "eval_en_oof_cls_f1": 0.9147990533407362, | |
| "eval_en_oof_loss": 2.5122690200805664, | |
| "eval_en_oof_runtime": 5.6432, | |
| "eval_en_oof_samples_per_second": 332.61, | |
| "eval_en_oof_steps_per_second": 3.544, | |
| "eval_en_oof_total_cls_tokens": 294, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.818877551020408, | |
| "eval_vi_All_acc": 0.7423837520042758, | |
| "eval_vi_Env_acc": 0.9554140127388535, | |
| "eval_vi_Env_f1": 0.9584664536741214, | |
| "eval_vi_Gov_acc": 0.8958333333333334, | |
| "eval_vi_Gov_f1": 0.8571428571428571, | |
| "eval_vi_Neu_acc": 0.7676056338028169, | |
| "eval_vi_Neu_f1": 0.7985347985347986, | |
| "eval_vi_Soc_acc": 0.8723404255319149, | |
| "eval_vi_Soc_f1": 0.8746666666666667, | |
| "eval_vi_cls_acc": 0.8748019017432647, | |
| "eval_vi_cls_f1": 0.872202694004611, | |
| "eval_vi_loss": 1.2391574382781982, | |
| "eval_vi_runtime": 12.3887, | |
| "eval_vi_samples_per_second": 355.161, | |
| "eval_vi_steps_per_second": 3.713, | |
| "eval_vi_total_cls_tokens": 631, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.818877551020408, | |
| "eval_dan_All_acc": 0.6563249124101052, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.3076923076923077, | |
| "eval_dan_Gov_f1": 0.47058823529411764, | |
| "eval_dan_Neu_acc": 0.25, | |
| "eval_dan_Neu_f1": 0.4, | |
| "eval_dan_Soc_acc": 0.2, | |
| "eval_dan_Soc_f1": 0.33333333333333337, | |
| "eval_dan_cls_acc": 0.2542372881355932, | |
| "eval_dan_cls_f1": 0.4676470588235294, | |
| "eval_dan_loss": 1.937129020690918, | |
| "eval_dan_runtime": 8.8939, | |
| "eval_dan_samples_per_second": 337.309, | |
| "eval_dan_steps_per_second": 3.598, | |
| "eval_dan_total_cls_tokens": 59, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.857142857142857, | |
| "grad_norm": 2.6249873638153076, | |
| "learning_rate": 4.896457045027484e-05, | |
| "loss": 1.7144, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.895408163265306, | |
| "grad_norm": 2.733449935913086, | |
| "learning_rate": 4.8938998207322706e-05, | |
| "loss": 1.7007, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.933673469387755, | |
| "grad_norm": 2.6901257038116455, | |
| "learning_rate": 4.891312086598326e-05, | |
| "loss": 1.7645, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.9719387755102042, | |
| "grad_norm": 2.8814775943756104, | |
| "learning_rate": 4.888693875605874e-05, | |
| "loss": 1.7128, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.00765306122449, | |
| "grad_norm": 2.609548330307007, | |
| "learning_rate": 4.886045221123561e-05, | |
| "loss": 1.5404, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.045918367346939, | |
| "grad_norm": 2.578418016433716, | |
| "learning_rate": 4.88336615690803e-05, | |
| "loss": 1.665, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 4.084183673469388, | |
| "grad_norm": 2.608092784881592, | |
| "learning_rate": 4.880656717103489e-05, | |
| "loss": 1.6756, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 4.122448979591836, | |
| "grad_norm": 2.64669132232666, | |
| "learning_rate": 4.87791693624128e-05, | |
| "loss": 1.7198, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.160714285714286, | |
| "grad_norm": 2.684515953063965, | |
| "learning_rate": 4.875146849239436e-05, | |
| "loss": 1.6825, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 4.198979591836735, | |
| "grad_norm": 2.5963499546051025, | |
| "learning_rate": 4.8723464914022354e-05, | |
| "loss": 1.7165, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.198979591836735, | |
| "eval_en_All_acc": 0.575412453432677, | |
| "eval_en_Env_acc": 0.9558823529411765, | |
| "eval_en_Env_f1": 0.9489051094890512, | |
| "eval_en_Gov_acc": 0.95, | |
| "eval_en_Gov_f1": 0.9421487603305784, | |
| "eval_en_Neu_acc": 0.84, | |
| "eval_en_Neu_f1": 0.8749999999999999, | |
| "eval_en_Soc_acc": 0.9444444444444444, | |
| "eval_en_Soc_f1": 0.918918918918919, | |
| "eval_en_cls_acc": 0.92, | |
| "eval_en_cls_f1": 0.9212431971846371, | |
| "eval_en_loss": 2.522178888320923, | |
| "eval_en_runtime": 5.6175, | |
| "eval_en_samples_per_second": 334.134, | |
| "eval_en_steps_per_second": 3.56, | |
| "eval_en_total_cls_tokens": 275, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.198979591836735, | |
| "eval_en_oof_All_acc": 0.5844748858447488, | |
| "eval_en_oof_Env_acc": 0.9861111111111112, | |
| "eval_en_oof_Env_f1": 0.9793103448275863, | |
| "eval_en_oof_Gov_acc": 0.9672131147540983, | |
| "eval_en_oof_Gov_f1": 0.944, | |
| "eval_en_oof_Neu_acc": 0.821917808219178, | |
| "eval_en_oof_Neu_f1": 0.8571428571428571, | |
| "eval_en_oof_Soc_acc": 0.863013698630137, | |
| "eval_en_oof_Soc_f1": 0.8513513513513513, | |
| "eval_en_oof_cls_acc": 0.9068100358422939, | |
| "eval_en_oof_cls_f1": 0.9079511383304487, | |
| "eval_en_oof_loss": 2.4619059562683105, | |
| "eval_en_oof_runtime": 5.5643, | |
| "eval_en_oof_samples_per_second": 337.327, | |
| "eval_en_oof_steps_per_second": 3.594, | |
| "eval_en_oof_total_cls_tokens": 279, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.198979591836735, | |
| "eval_vi_All_acc": 0.7456356567478972, | |
| "eval_vi_Env_acc": 0.91875, | |
| "eval_vi_Env_f1": 0.939297124600639, | |
| "eval_vi_Gov_acc": 0.8719512195121951, | |
| "eval_vi_Gov_f1": 0.8640483383685801, | |
| "eval_vi_Neu_acc": 0.7941176470588235, | |
| "eval_vi_Neu_f1": 0.8282208588957056, | |
| "eval_vi_Soc_acc": 0.8597560975609756, | |
| "eval_vi_Soc_f1": 0.815028901734104, | |
| "eval_vi_cls_acc": 0.8601823708206687, | |
| "eval_vi_cls_f1": 0.8616488058997572, | |
| "eval_vi_loss": 1.2197585105895996, | |
| "eval_vi_runtime": 12.2407, | |
| "eval_vi_samples_per_second": 359.456, | |
| "eval_vi_steps_per_second": 3.758, | |
| "eval_vi_total_cls_tokens": 658, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.198979591836735, | |
| "eval_dan_All_acc": 0.655165921393269, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3076923076923077, | |
| "eval_dan_Gov_f1": 0.47058823529411764, | |
| "eval_dan_Neu_acc": 0.23076923076923078, | |
| "eval_dan_Neu_f1": 0.375, | |
| "eval_dan_Soc_acc": 0.10526315789473684, | |
| "eval_dan_Soc_f1": 0.1904761904761905, | |
| "eval_dan_cls_acc": 0.1956521739130435, | |
| "eval_dan_cls_f1": 0.259016106442577, | |
| "eval_dan_loss": 1.9186526536941528, | |
| "eval_dan_runtime": 9.3011, | |
| "eval_dan_samples_per_second": 322.543, | |
| "eval_dan_steps_per_second": 3.44, | |
| "eval_dan_total_cls_tokens": 46, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.237244897959184, | |
| "grad_norm": 2.5716323852539062, | |
| "learning_rate": 4.869515898419755e-05, | |
| "loss": 1.6907, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 4.275510204081632, | |
| "grad_norm": 2.570605516433716, | |
| "learning_rate": 4.8666551063674115e-05, | |
| "loss": 1.648, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 4.313775510204081, | |
| "grad_norm": 2.718593120574951, | |
| "learning_rate": 4.8637641517055056e-05, | |
| "loss": 1.69, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 4.3520408163265305, | |
| "grad_norm": 2.588538885116577, | |
| "learning_rate": 4.8608430712787525e-05, | |
| "loss": 1.6841, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 4.39030612244898, | |
| "grad_norm": 2.6645848751068115, | |
| "learning_rate": 4.857891902315816e-05, | |
| "loss": 1.7093, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.428571428571429, | |
| "grad_norm": 2.6682679653167725, | |
| "learning_rate": 4.8549106824288346e-05, | |
| "loss": 1.6894, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 4.466836734693878, | |
| "grad_norm": 2.7469396591186523, | |
| "learning_rate": 4.851899449612941e-05, | |
| "loss": 1.6832, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 4.505102040816326, | |
| "grad_norm": 2.5457420349121094, | |
| "learning_rate": 4.848858242245773e-05, | |
| "loss": 1.6342, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 4.543367346938775, | |
| "grad_norm": 2.7167155742645264, | |
| "learning_rate": 4.8457870990869937e-05, | |
| "loss": 1.6601, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 4.581632653061225, | |
| "grad_norm": 2.510788917541504, | |
| "learning_rate": 4.8426860592777915e-05, | |
| "loss": 1.6492, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.581632653061225, | |
| "eval_en_All_acc": 0.58816, | |
| "eval_en_Env_acc": 0.9354838709677419, | |
| "eval_en_Env_f1": 0.9279999999999999, | |
| "eval_en_Gov_acc": 0.9166666666666666, | |
| "eval_en_Gov_f1": 0.9166666666666666, | |
| "eval_en_Neu_acc": 0.8831168831168831, | |
| "eval_en_Neu_f1": 0.8343558282208589, | |
| "eval_en_Soc_acc": 0.7878787878787878, | |
| "eval_en_Soc_f1": 0.8524590163934426, | |
| "eval_en_cls_acc": 0.8808664259927798, | |
| "eval_en_cls_f1": 0.882870377820242, | |
| "eval_en_loss": 2.4608476161956787, | |
| "eval_en_runtime": 5.5786, | |
| "eval_en_samples_per_second": 336.467, | |
| "eval_en_steps_per_second": 3.585, | |
| "eval_en_total_cls_tokens": 277, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.581632653061225, | |
| "eval_en_oof_All_acc": 0.5946415012474238, | |
| "eval_en_oof_Env_acc": 0.9523809523809523, | |
| "eval_en_oof_Env_f1": 0.9302325581395349, | |
| "eval_en_oof_Gov_acc": 0.9508196721311475, | |
| "eval_en_oof_Gov_f1": 0.9508196721311475, | |
| "eval_en_oof_Neu_acc": 0.8771929824561403, | |
| "eval_en_oof_Neu_f1": 0.8264462809917354, | |
| "eval_en_oof_Soc_acc": 0.8481012658227848, | |
| "eval_en_oof_Soc_f1": 0.9054054054054054, | |
| "eval_en_oof_cls_acc": 0.9038461538461539, | |
| "eval_en_oof_cls_f1": 0.9032259791669558, | |
| "eval_en_oof_loss": 2.4103167057037354, | |
| "eval_en_oof_runtime": 5.5566, | |
| "eval_en_oof_samples_per_second": 337.795, | |
| "eval_en_oof_steps_per_second": 3.599, | |
| "eval_en_oof_total_cls_tokens": 260, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.581632653061225, | |
| "eval_vi_All_acc": 0.7538929565845107, | |
| "eval_vi_Env_acc": 0.9166666666666666, | |
| "eval_vi_Env_f1": 0.9166666666666666, | |
| "eval_vi_Gov_acc": 0.861904761904762, | |
| "eval_vi_Gov_f1": 0.8850855745721272, | |
| "eval_vi_Neu_acc": 0.905, | |
| "eval_vi_Neu_f1": 0.851764705882353, | |
| "eval_vi_Soc_acc": 0.80625, | |
| "eval_vi_Soc_f1": 0.8459016393442622, | |
| "eval_vi_cls_acc": 0.8725490196078431, | |
| "eval_vi_cls_f1": 0.8748546466163523, | |
| "eval_vi_loss": 1.1619046926498413, | |
| "eval_vi_runtime": 12.5739, | |
| "eval_vi_samples_per_second": 349.932, | |
| "eval_vi_steps_per_second": 3.658, | |
| "eval_vi_total_cls_tokens": 714, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.581632653061225, | |
| "eval_dan_All_acc": 0.6548929591980138, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3333333333333333, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.4666666666666667, | |
| "eval_dan_Neu_f1": 0.6363636363636364, | |
| "eval_dan_Soc_acc": 0.2857142857142857, | |
| "eval_dan_Soc_f1": 0.4444444444444445, | |
| "eval_dan_cls_acc": 0.3611111111111111, | |
| "eval_dan_cls_f1": 0.3952020202020202, | |
| "eval_dan_loss": 1.9139089584350586, | |
| "eval_dan_runtime": 8.7876, | |
| "eval_dan_samples_per_second": 341.388, | |
| "eval_dan_steps_per_second": 3.641, | |
| "eval_dan_total_cls_tokens": 36, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.619897959183674, | |
| "grad_norm": 2.416146755218506, | |
| "learning_rate": 4.83955516234038e-05, | |
| "loss": 1.6413, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 4.658163265306122, | |
| "grad_norm": 2.4362900257110596, | |
| "learning_rate": 4.8363944481775e-05, | |
| "loss": 1.6746, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 4.696428571428571, | |
| "grad_norm": 2.7036330699920654, | |
| "learning_rate": 4.8332039570719054e-05, | |
| "loss": 1.666, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 4.73469387755102, | |
| "grad_norm": 2.737252712249756, | |
| "learning_rate": 4.829983729685854e-05, | |
| "loss": 1.6812, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 4.7729591836734695, | |
| "grad_norm": 2.699093818664551, | |
| "learning_rate": 4.826733807060585e-05, | |
| "loss": 1.6335, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 4.811224489795919, | |
| "grad_norm": 2.7211058139801025, | |
| "learning_rate": 4.8234542306158e-05, | |
| "loss": 1.6638, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 4.849489795918368, | |
| "grad_norm": 2.6445066928863525, | |
| "learning_rate": 4.8201450421491346e-05, | |
| "loss": 1.6955, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 4.887755102040816, | |
| "grad_norm": 2.5442757606506348, | |
| "learning_rate": 4.816806283835621e-05, | |
| "loss": 1.6795, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 4.926020408163265, | |
| "grad_norm": 2.5657365322113037, | |
| "learning_rate": 4.8134379982271556e-05, | |
| "loss": 1.6957, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 4.964285714285714, | |
| "grad_norm": 2.4745914936065674, | |
| "learning_rate": 4.810040228251956e-05, | |
| "loss": 1.6323, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.964285714285714, | |
| "eval_en_All_acc": 0.5802118597794037, | |
| "eval_en_Env_acc": 0.9850746268656716, | |
| "eval_en_Env_f1": 0.9705882352941176, | |
| "eval_en_Gov_acc": 0.9833333333333333, | |
| "eval_en_Gov_f1": 0.9593495934959351, | |
| "eval_en_Neu_acc": 0.8888888888888888, | |
| "eval_en_Neu_f1": 0.8959999999999999, | |
| "eval_en_Soc_acc": 0.896551724137931, | |
| "eval_en_Soc_f1": 0.9285714285714286, | |
| "eval_en_cls_acc": 0.9395161290322581, | |
| "eval_en_cls_f1": 0.9386273143403703, | |
| "eval_en_loss": 2.5013070106506348, | |
| "eval_en_runtime": 5.5985, | |
| "eval_en_samples_per_second": 335.27, | |
| "eval_en_steps_per_second": 3.572, | |
| "eval_en_total_cls_tokens": 248, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.964285714285714, | |
| "eval_en_oof_All_acc": 0.5918150975402884, | |
| "eval_en_oof_Env_acc": 0.9880952380952381, | |
| "eval_en_oof_Env_f1": 0.9822485207100591, | |
| "eval_en_oof_Gov_acc": 0.9482758620689655, | |
| "eval_en_oof_Gov_f1": 0.9322033898305084, | |
| "eval_en_oof_Neu_acc": 0.875, | |
| "eval_en_oof_Neu_f1": 0.8860759493670887, | |
| "eval_en_oof_Soc_acc": 0.9080459770114943, | |
| "eval_en_oof_Soc_f1": 0.9239766081871346, | |
| "eval_en_oof_cls_acc": 0.9288025889967637, | |
| "eval_en_oof_cls_f1": 0.9311261170236977, | |
| "eval_en_oof_loss": 2.466111660003662, | |
| "eval_en_oof_runtime": 5.5502, | |
| "eval_en_oof_samples_per_second": 338.187, | |
| "eval_en_oof_steps_per_second": 3.603, | |
| "eval_en_oof_total_cls_tokens": 309, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.964285714285714, | |
| "eval_vi_All_acc": 0.7582389089117639, | |
| "eval_vi_Env_acc": 0.9602649006622517, | |
| "eval_vi_Env_f1": 0.9385113268608414, | |
| "eval_vi_Gov_acc": 0.9300699300699301, | |
| "eval_vi_Gov_f1": 0.8956228956228957, | |
| "eval_vi_Neu_acc": 0.8323353293413174, | |
| "eval_vi_Neu_f1": 0.8687500000000001, | |
| "eval_vi_Soc_acc": 0.8516129032258064, | |
| "eval_vi_Soc_f1": 0.8655737704918034, | |
| "eval_vi_cls_acc": 0.8912337662337663, | |
| "eval_vi_cls_f1": 0.8921144982438851, | |
| "eval_vi_loss": 1.1528671979904175, | |
| "eval_vi_runtime": 12.5697, | |
| "eval_vi_samples_per_second": 350.049, | |
| "eval_vi_steps_per_second": 3.66, | |
| "eval_vi_total_cls_tokens": 616, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.964285714285714, | |
| "eval_dan_All_acc": 0.6538443451681166, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.36363636363636365, | |
| "eval_dan_Gov_f1": 0.5333333333333333, | |
| "eval_dan_Neu_acc": 0.2, | |
| "eval_dan_Neu_f1": 0.33333333333333337, | |
| "eval_dan_Soc_acc": 0.25, | |
| "eval_dan_Soc_f1": 0.4, | |
| "eval_dan_cls_acc": 0.25, | |
| "eval_dan_cls_f1": 0.31666666666666665, | |
| "eval_dan_loss": 1.9241294860839844, | |
| "eval_dan_runtime": 8.7987, | |
| "eval_dan_samples_per_second": 340.958, | |
| "eval_dan_steps_per_second": 3.637, | |
| "eval_dan_total_cls_tokens": 52, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.3080048561096191, | |
| "learning_rate": 4.806613017214012e-05, | |
| "loss": 1.5336, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 5.038265306122449, | |
| "grad_norm": 2.579637289047241, | |
| "learning_rate": 4.803156408792536e-05, | |
| "loss": 1.6504, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 5.076530612244898, | |
| "grad_norm": 2.507281541824341, | |
| "learning_rate": 4.799670447041402e-05, | |
| "loss": 1.605, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 5.114795918367347, | |
| "grad_norm": 2.6424460411071777, | |
| "learning_rate": 4.79615517638859e-05, | |
| "loss": 1.6174, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 5.153061224489796, | |
| "grad_norm": 2.5452277660369873, | |
| "learning_rate": 4.7926106416356163e-05, | |
| "loss": 1.62, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5.191326530612245, | |
| "grad_norm": 2.6596782207489014, | |
| "learning_rate": 4.7890368879569614e-05, | |
| "loss": 1.6345, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 5.229591836734694, | |
| "grad_norm": 2.658280849456787, | |
| "learning_rate": 4.785433960899498e-05, | |
| "loss": 1.6194, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 5.267857142857143, | |
| "grad_norm": 2.7173943519592285, | |
| "learning_rate": 4.7818019063819075e-05, | |
| "loss": 1.6237, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 5.3061224489795915, | |
| "grad_norm": 2.5845112800598145, | |
| "learning_rate": 4.778140770694096e-05, | |
| "loss": 1.6707, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 5.344387755102041, | |
| "grad_norm": 2.8999550342559814, | |
| "learning_rate": 4.7744506004966025e-05, | |
| "loss": 1.6342, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.344387755102041, | |
| "eval_en_All_acc": 0.5845921450151057, | |
| "eval_en_Env_acc": 0.9696969696969697, | |
| "eval_en_Env_f1": 0.9411764705882354, | |
| "eval_en_Gov_acc": 1.0, | |
| "eval_en_Gov_f1": 0.9624060150375939, | |
| "eval_en_Neu_acc": 0.8732394366197183, | |
| "eval_en_Neu_f1": 0.8985507246376812, | |
| "eval_en_Soc_acc": 0.896551724137931, | |
| "eval_en_Soc_f1": 0.9369369369369369, | |
| "eval_en_cls_acc": 0.9343629343629344, | |
| "eval_en_cls_f1": 0.9347675368001118, | |
| "eval_en_loss": 2.4863646030426025, | |
| "eval_en_runtime": 5.5961, | |
| "eval_en_samples_per_second": 335.411, | |
| "eval_en_steps_per_second": 3.574, | |
| "eval_en_total_cls_tokens": 259, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.344387755102041, | |
| "eval_en_oof_All_acc": 0.5910575515260728, | |
| "eval_en_oof_Env_acc": 0.9833333333333333, | |
| "eval_en_oof_Env_f1": 0.9593495934959351, | |
| "eval_en_oof_Gov_acc": 0.9516129032258065, | |
| "eval_en_oof_Gov_f1": 0.921875, | |
| "eval_en_oof_Neu_acc": 0.8135593220338984, | |
| "eval_en_oof_Neu_f1": 0.8421052631578948, | |
| "eval_en_oof_Soc_acc": 0.8620689655172413, | |
| "eval_en_oof_Soc_f1": 0.8849557522123893, | |
| "eval_en_oof_cls_acc": 0.9037656903765691, | |
| "eval_en_oof_cls_f1": 0.9020714022165548, | |
| "eval_en_oof_loss": 2.437871217727661, | |
| "eval_en_oof_runtime": 5.5452, | |
| "eval_en_oof_samples_per_second": 338.493, | |
| "eval_en_oof_steps_per_second": 3.607, | |
| "eval_en_oof_total_cls_tokens": 239, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.344387755102041, | |
| "eval_vi_All_acc": 0.7553043567823668, | |
| "eval_vi_Env_acc": 0.9548387096774194, | |
| "eval_vi_Env_f1": 0.9192546583850931, | |
| "eval_vi_Gov_acc": 0.9315068493150684, | |
| "eval_vi_Gov_f1": 0.8745980707395498, | |
| "eval_vi_Neu_acc": 0.8238993710691824, | |
| "eval_vi_Neu_f1": 0.859016393442623, | |
| "eval_vi_Soc_acc": 0.7709923664122137, | |
| "eval_vi_Soc_f1": 0.8278688524590163, | |
| "eval_vi_cls_acc": 0.8730964467005076, | |
| "eval_vi_cls_f1": 0.8701844937565706, | |
| "eval_vi_loss": 1.1543623208999634, | |
| "eval_vi_runtime": 12.2482, | |
| "eval_vi_samples_per_second": 359.235, | |
| "eval_vi_steps_per_second": 3.756, | |
| "eval_vi_total_cls_tokens": 591, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.344387755102041, | |
| "eval_dan_All_acc": 0.6495955605718585, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.5, | |
| "eval_dan_Gov_f1": 0.6666666666666666, | |
| "eval_dan_Neu_acc": 0.35294117647058826, | |
| "eval_dan_Neu_f1": 0.5217391304347826, | |
| "eval_dan_Soc_acc": 0.13333333333333333, | |
| "eval_dan_Soc_f1": 0.23529411764705882, | |
| "eval_dan_cls_acc": 0.275, | |
| "eval_dan_cls_f1": 0.355924978687127, | |
| "eval_dan_loss": 1.9863929748535156, | |
| "eval_dan_runtime": 9.0108, | |
| "eval_dan_samples_per_second": 332.935, | |
| "eval_dan_steps_per_second": 3.551, | |
| "eval_dan_total_cls_tokens": 40, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.38265306122449, | |
| "grad_norm": 2.2184009552001953, | |
| "learning_rate": 4.770731442820009e-05, | |
| "loss": 1.6272, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 5.420918367346939, | |
| "grad_norm": 2.641216278076172, | |
| "learning_rate": 4.766983345064337e-05, | |
| "loss": 1.6245, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 5.459183673469388, | |
| "grad_norm": 2.609149217605591, | |
| "learning_rate": 4.763206354998441e-05, | |
| "loss": 1.6192, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 5.497448979591836, | |
| "grad_norm": 2.7021641731262207, | |
| "learning_rate": 4.759400520759406e-05, | |
| "loss": 1.6247, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 5.535714285714286, | |
| "grad_norm": 2.771129608154297, | |
| "learning_rate": 4.7555658908519314e-05, | |
| "loss": 1.6357, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 5.573979591836735, | |
| "grad_norm": 2.617830514907837, | |
| "learning_rate": 4.751702514147711e-05, | |
| "loss": 1.6108, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 5.612244897959184, | |
| "grad_norm": 2.4795756340026855, | |
| "learning_rate": 4.747810439884811e-05, | |
| "loss": 1.5792, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 5.650510204081632, | |
| "grad_norm": 2.668059825897217, | |
| "learning_rate": 4.743889717667046e-05, | |
| "loss": 1.6382, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 5.688775510204081, | |
| "grad_norm": 2.4742913246154785, | |
| "learning_rate": 4.7399403974633406e-05, | |
| "loss": 1.6227, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 5.7270408163265305, | |
| "grad_norm": 2.5887014865875244, | |
| "learning_rate": 4.735962529607097e-05, | |
| "loss": 1.6434, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.7270408163265305, | |
| "eval_en_All_acc": 0.5982877839973658, | |
| "eval_en_Env_acc": 0.9863013698630136, | |
| "eval_en_Env_f1": 0.9600000000000001, | |
| "eval_en_Gov_acc": 0.9615384615384616, | |
| "eval_en_Gov_f1": 0.9554140127388535, | |
| "eval_en_Neu_acc": 0.8450704225352113, | |
| "eval_en_Neu_f1": 0.8695652173913043, | |
| "eval_en_Soc_acc": 0.92, | |
| "eval_en_Soc_f1": 0.9261744966442953, | |
| "eval_en_cls_acc": 0.9292929292929293, | |
| "eval_en_cls_f1": 0.9277884316936132, | |
| "eval_en_loss": 2.3783116340637207, | |
| "eval_en_runtime": 5.5888, | |
| "eval_en_samples_per_second": 335.848, | |
| "eval_en_steps_per_second": 3.579, | |
| "eval_en_total_cls_tokens": 297, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.7270408163265305, | |
| "eval_en_oof_All_acc": 0.5792696260660398, | |
| "eval_en_oof_Env_acc": 0.9833333333333333, | |
| "eval_en_oof_Env_f1": 0.9672131147540983, | |
| "eval_en_oof_Gov_acc": 0.9636363636363636, | |
| "eval_en_oof_Gov_f1": 0.9636363636363636, | |
| "eval_en_oof_Neu_acc": 0.8727272727272727, | |
| "eval_en_oof_Neu_f1": 0.8888888888888888, | |
| "eval_en_oof_Soc_acc": 0.9180327868852459, | |
| "eval_en_oof_Soc_f1": 0.9180327868852459, | |
| "eval_en_oof_cls_acc": 0.935064935064935, | |
| "eval_en_oof_cls_f1": 0.9344427885411491, | |
| "eval_en_oof_loss": 2.4880118370056152, | |
| "eval_en_oof_runtime": 5.5515, | |
| "eval_en_oof_samples_per_second": 338.105, | |
| "eval_en_oof_steps_per_second": 3.603, | |
| "eval_en_oof_total_cls_tokens": 231, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.7270408163265305, | |
| "eval_vi_All_acc": 0.7573225005174912, | |
| "eval_vi_Env_acc": 0.987012987012987, | |
| "eval_vi_Env_f1": 0.9589905362776026, | |
| "eval_vi_Gov_acc": 0.9097222222222222, | |
| "eval_vi_Gov_f1": 0.8851351351351351, | |
| "eval_vi_Neu_acc": 0.793939393939394, | |
| "eval_vi_Neu_f1": 0.8506493506493507, | |
| "eval_vi_Soc_acc": 0.8523489932885906, | |
| "eval_vi_Soc_f1": 0.8382838283828382, | |
| "eval_vi_cls_acc": 0.8839869281045751, | |
| "eval_vi_cls_f1": 0.8832647126112316, | |
| "eval_vi_loss": 1.1493161916732788, | |
| "eval_vi_runtime": 12.6483, | |
| "eval_vi_samples_per_second": 347.873, | |
| "eval_vi_steps_per_second": 3.637, | |
| "eval_vi_total_cls_tokens": 612, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.7270408163265305, | |
| "eval_dan_All_acc": 0.6577943185565553, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2222222222222222, | |
| "eval_dan_Gov_f1": 0.3636363636363636, | |
| "eval_dan_Neu_acc": 0.17391304347826086, | |
| "eval_dan_Neu_f1": 0.29629629629629634, | |
| "eval_dan_Soc_acc": 0.375, | |
| "eval_dan_Soc_f1": 0.5454545454545454, | |
| "eval_dan_cls_acc": 0.21428571428571427, | |
| "eval_dan_cls_f1": 0.3013468013468013, | |
| "eval_dan_loss": 1.902325987815857, | |
| "eval_dan_runtime": 8.6574, | |
| "eval_dan_samples_per_second": 346.524, | |
| "eval_dan_steps_per_second": 3.696, | |
| "eval_dan_total_cls_tokens": 42, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.76530612244898, | |
| "grad_norm": 2.48891019821167, | |
| "learning_rate": 4.7319561647955526e-05, | |
| "loss": 1.6278, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 5.803571428571429, | |
| "grad_norm": 2.447258949279785, | |
| "learning_rate": 4.727921354089133e-05, | |
| "loss": 1.661, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 5.841836734693878, | |
| "grad_norm": 2.5462565422058105, | |
| "learning_rate": 4.723858148910802e-05, | |
| "loss": 1.5872, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 5.880102040816326, | |
| "grad_norm": 2.5466713905334473, | |
| "learning_rate": 4.7197666010454064e-05, | |
| "loss": 1.5913, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 5.918367346938775, | |
| "grad_norm": 2.3348581790924072, | |
| "learning_rate": 4.715646762639015e-05, | |
| "loss": 1.5928, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 5.956632653061225, | |
| "grad_norm": 2.503695487976074, | |
| "learning_rate": 4.711498686198256e-05, | |
| "loss": 1.6087, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 5.994897959183674, | |
| "grad_norm": 2.40179443359375, | |
| "learning_rate": 4.707322424589643e-05, | |
| "loss": 1.5684, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 6.030612244897959, | |
| "grad_norm": 2.4875943660736084, | |
| "learning_rate": 4.70311803103891e-05, | |
| "loss": 1.5119, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 6.0688775510204085, | |
| "grad_norm": 2.5597469806671143, | |
| "learning_rate": 4.698885559130323e-05, | |
| "loss": 1.591, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 6.107142857142857, | |
| "grad_norm": 2.5664939880371094, | |
| "learning_rate": 4.694625062806004e-05, | |
| "loss": 1.5767, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.107142857142857, | |
| "eval_en_All_acc": 0.5880610117414682, | |
| "eval_en_Env_acc": 0.9859154929577465, | |
| "eval_en_Env_f1": 0.9589041095890412, | |
| "eval_en_Gov_acc": 0.9137931034482759, | |
| "eval_en_Gov_f1": 0.9298245614035087, | |
| "eval_en_Neu_acc": 0.8648648648648649, | |
| "eval_en_Neu_f1": 0.8590604026845637, | |
| "eval_en_Soc_acc": 0.84375, | |
| "eval_en_Soc_f1": 0.864, | |
| "eval_en_cls_acc": 0.9026217228464419, | |
| "eval_en_cls_f1": 0.9029472684192784, | |
| "eval_en_loss": 2.4334867000579834, | |
| "eval_en_runtime": 5.5789, | |
| "eval_en_samples_per_second": 336.444, | |
| "eval_en_steps_per_second": 3.585, | |
| "eval_en_total_cls_tokens": 267, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.107142857142857, | |
| "eval_en_oof_All_acc": 0.5707347318383796, | |
| "eval_en_oof_Env_acc": 0.967741935483871, | |
| "eval_en_oof_Env_f1": 0.96, | |
| "eval_en_oof_Gov_acc": 0.9324324324324325, | |
| "eval_en_oof_Gov_f1": 0.9324324324324325, | |
| "eval_en_oof_Neu_acc": 0.8918918918918919, | |
| "eval_en_oof_Neu_f1": 0.8918918918918919, | |
| "eval_en_oof_Soc_acc": 0.9382716049382716, | |
| "eval_en_oof_Soc_f1": 0.9440993788819876, | |
| "eval_en_oof_cls_acc": 0.9312714776632303, | |
| "eval_en_oof_cls_f1": 0.932105925801578, | |
| "eval_en_oof_loss": 2.5854978561401367, | |
| "eval_en_oof_runtime": 5.5891, | |
| "eval_en_oof_samples_per_second": 335.832, | |
| "eval_en_oof_steps_per_second": 3.578, | |
| "eval_en_oof_total_cls_tokens": 291, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.107142857142857, | |
| "eval_vi_All_acc": 0.7581668868682159, | |
| "eval_vi_Env_acc": 0.9054054054054054, | |
| "eval_vi_Env_f1": 0.9241379310344827, | |
| "eval_vi_Gov_acc": 0.9378531073446328, | |
| "eval_vi_Gov_f1": 0.9352112676056338, | |
| "eval_vi_Neu_acc": 0.8424242424242424, | |
| "eval_vi_Neu_f1": 0.8580246913580247, | |
| "eval_vi_Soc_acc": 0.9047619047619048, | |
| "eval_vi_Soc_f1": 0.8669201520912547, | |
| "eval_vi_cls_acc": 0.8977272727272727, | |
| "eval_vi_cls_f1": 0.896073510522349, | |
| "eval_vi_loss": 1.1488968133926392, | |
| "eval_vi_runtime": 12.2538, | |
| "eval_vi_samples_per_second": 359.071, | |
| "eval_vi_steps_per_second": 3.754, | |
| "eval_vi_total_cls_tokens": 616, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.107142857142857, | |
| "eval_dan_All_acc": 0.6577552538590292, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3, | |
| "eval_dan_Gov_f1": 0.4615384615384615, | |
| "eval_dan_Neu_acc": 0.17391304347826086, | |
| "eval_dan_Neu_f1": 0.2857142857142857, | |
| "eval_dan_Soc_acc": 0.23529411764705882, | |
| "eval_dan_Soc_f1": 0.38095238095238093, | |
| "eval_dan_cls_acc": 0.21153846153846154, | |
| "eval_dan_cls_f1": 0.28205128205128205, | |
| "eval_dan_loss": 1.9370394945144653, | |
| "eval_dan_runtime": 9.0997, | |
| "eval_dan_samples_per_second": 329.681, | |
| "eval_dan_steps_per_second": 3.517, | |
| "eval_dan_total_cls_tokens": 52, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.145408163265306, | |
| "grad_norm": 2.2917544841766357, | |
| "learning_rate": 4.690336596365241e-05, | |
| "loss": 1.5903, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 6.183673469387755, | |
| "grad_norm": 2.511667490005493, | |
| "learning_rate": 4.686020214463798e-05, | |
| "loss": 1.5589, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 6.221938775510204, | |
| "grad_norm": 2.533936023712158, | |
| "learning_rate": 4.681675972113212e-05, | |
| "loss": 1.5856, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 6.260204081632653, | |
| "grad_norm": 2.7195661067962646, | |
| "learning_rate": 4.677303924680101e-05, | |
| "loss": 1.6141, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 6.298469387755102, | |
| "grad_norm": 2.5510056018829346, | |
| "learning_rate": 4.672904127885453e-05, | |
| "loss": 1.6128, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6.336734693877551, | |
| "grad_norm": 2.4482080936431885, | |
| "learning_rate": 4.668476637803916e-05, | |
| "loss": 1.5969, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 6.375, | |
| "grad_norm": 2.5095040798187256, | |
| "learning_rate": 4.664021510863084e-05, | |
| "loss": 1.6343, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 6.413265306122449, | |
| "grad_norm": 2.495959758758545, | |
| "learning_rate": 4.659538803842779e-05, | |
| "loss": 1.5682, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 6.451530612244898, | |
| "grad_norm": 2.599862575531006, | |
| "learning_rate": 4.655028573874327e-05, | |
| "loss": 1.5812, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 6.489795918367347, | |
| "grad_norm": 2.52191162109375, | |
| "learning_rate": 4.650490878439825e-05, | |
| "loss": 1.5768, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.489795918367347, | |
| "eval_en_All_acc": 0.592226823829245, | |
| "eval_en_Env_acc": 0.9487179487179487, | |
| "eval_en_Env_f1": 0.9610389610389611, | |
| "eval_en_Gov_acc": 1.0, | |
| "eval_en_Gov_f1": 0.9640287769784173, | |
| "eval_en_Neu_acc": 0.8470588235294118, | |
| "eval_en_Neu_f1": 0.8944099378881987, | |
| "eval_en_Soc_acc": 0.9701492537313433, | |
| "eval_en_Soc_f1": 0.9285714285714287, | |
| "eval_en_cls_acc": 0.936026936026936, | |
| "eval_en_cls_f1": 0.9370122761192514, | |
| "eval_en_loss": 2.3523573875427246, | |
| "eval_en_runtime": 5.5957, | |
| "eval_en_samples_per_second": 335.437, | |
| "eval_en_steps_per_second": 3.574, | |
| "eval_en_total_cls_tokens": 297, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.489795918367347, | |
| "eval_en_oof_All_acc": 0.5940128919479952, | |
| "eval_en_oof_Env_acc": 0.9714285714285714, | |
| "eval_en_oof_Env_f1": 0.9444444444444445, | |
| "eval_en_oof_Gov_acc": 0.9811320754716981, | |
| "eval_en_oof_Gov_f1": 0.9454545454545454, | |
| "eval_en_oof_Neu_acc": 0.8115942028985508, | |
| "eval_en_oof_Neu_f1": 0.888888888888889, | |
| "eval_en_oof_Soc_acc": 0.9420289855072463, | |
| "eval_en_oof_Soc_f1": 0.9154929577464788, | |
| "eval_en_oof_cls_acc": 0.9233716475095786, | |
| "eval_en_oof_cls_f1": 0.9235702091335893, | |
| "eval_en_oof_loss": 2.3897814750671387, | |
| "eval_en_oof_runtime": 5.5672, | |
| "eval_en_oof_samples_per_second": 337.153, | |
| "eval_en_oof_steps_per_second": 3.592, | |
| "eval_en_oof_total_cls_tokens": 261, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.489795918367347, | |
| "eval_vi_All_acc": 0.7687618949642508, | |
| "eval_vi_Env_acc": 0.9565217391304348, | |
| "eval_vi_Env_f1": 0.9506172839506172, | |
| "eval_vi_Gov_acc": 0.9607843137254902, | |
| "eval_vi_Gov_f1": 0.8750000000000001, | |
| "eval_vi_Neu_acc": 0.7975460122699386, | |
| "eval_vi_Neu_f1": 0.8609271523178809, | |
| "eval_vi_Soc_acc": 0.8375, | |
| "eval_vi_Soc_f1": 0.8589743589743589, | |
| "eval_vi_cls_acc": 0.8869701726844584, | |
| "eval_vi_cls_f1": 0.8863796988107142, | |
| "eval_vi_loss": 1.0977121591567993, | |
| "eval_vi_runtime": 12.7138, | |
| "eval_vi_samples_per_second": 346.08, | |
| "eval_vi_steps_per_second": 3.618, | |
| "eval_vi_total_cls_tokens": 637, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.489795918367347, | |
| "eval_dan_All_acc": 0.6524508696634289, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.25, | |
| "eval_dan_Gov_f1": 0.4, | |
| "eval_dan_Neu_acc": 0.14285714285714285, | |
| "eval_dan_Neu_f1": 0.25, | |
| "eval_dan_Soc_acc": 0.35294117647058826, | |
| "eval_dan_Soc_f1": 0.5217391304347826, | |
| "eval_dan_cls_acc": 0.22916666666666666, | |
| "eval_dan_cls_f1": 0.29293478260869565, | |
| "eval_dan_loss": 1.9581139087677002, | |
| "eval_dan_runtime": 8.7159, | |
| "eval_dan_samples_per_second": 344.199, | |
| "eval_dan_steps_per_second": 3.671, | |
| "eval_dan_total_cls_tokens": 48, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.528061224489796, | |
| "grad_norm": 2.4551684856414795, | |
| "learning_rate": 4.645925775371418e-05, | |
| "loss": 1.6212, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 6.566326530612245, | |
| "grad_norm": 2.349735736846924, | |
| "learning_rate": 4.641333322850554e-05, | |
| "loss": 1.5801, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 6.604591836734694, | |
| "grad_norm": 2.703885555267334, | |
| "learning_rate": 4.636713579407245e-05, | |
| "loss": 1.6079, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 6.642857142857143, | |
| "grad_norm": 2.5508694648742676, | |
| "learning_rate": 4.63206660391932e-05, | |
| "loss": 1.5646, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 6.6811224489795915, | |
| "grad_norm": 2.3682239055633545, | |
| "learning_rate": 4.62739245561168e-05, | |
| "loss": 1.5833, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 6.719387755102041, | |
| "grad_norm": 2.5627987384796143, | |
| "learning_rate": 4.622691194055533e-05, | |
| "loss": 1.5514, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 6.75765306122449, | |
| "grad_norm": 2.5740673542022705, | |
| "learning_rate": 4.617962879167645e-05, | |
| "loss": 1.5803, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 6.795918367346939, | |
| "grad_norm": 2.5002400875091553, | |
| "learning_rate": 4.61320757120957e-05, | |
| "loss": 1.5651, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 6.834183673469388, | |
| "grad_norm": 2.5291388034820557, | |
| "learning_rate": 4.608425330786885e-05, | |
| "loss": 1.5404, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 6.872448979591836, | |
| "grad_norm": 2.568141460418701, | |
| "learning_rate": 4.603616218848416e-05, | |
| "loss": 1.5815, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.872448979591836, | |
| "eval_en_All_acc": 0.5843696397941681, | |
| "eval_en_Env_acc": 0.9733333333333334, | |
| "eval_en_Env_f1": 0.9864864864864865, | |
| "eval_en_Gov_acc": 0.9508196721311475, | |
| "eval_en_Gov_f1": 0.9354838709677418, | |
| "eval_en_Neu_acc": 0.9358974358974359, | |
| "eval_en_Neu_f1": 0.9068322981366459, | |
| "eval_en_Soc_acc": 0.8823529411764706, | |
| "eval_en_Soc_f1": 0.916030534351145, | |
| "eval_en_cls_acc": 0.9361702127659575, | |
| "eval_en_cls_f1": 0.9362082974855048, | |
| "eval_en_loss": 2.4846506118774414, | |
| "eval_en_runtime": 5.6197, | |
| "eval_en_samples_per_second": 334.003, | |
| "eval_en_steps_per_second": 3.559, | |
| "eval_en_total_cls_tokens": 282, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.872448979591836, | |
| "eval_en_oof_All_acc": 0.5787456074965392, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.971830985915493, | |
| "eval_en_oof_Gov_acc": 0.9622641509433962, | |
| "eval_en_oof_Gov_f1": 0.9714285714285713, | |
| "eval_en_oof_Neu_acc": 0.8666666666666667, | |
| "eval_en_oof_Neu_f1": 0.8888888888888888, | |
| "eval_en_oof_Soc_acc": 0.9298245614035088, | |
| "eval_en_oof_Soc_f1": 0.9298245614035088, | |
| "eval_en_oof_cls_acc": 0.9414225941422594, | |
| "eval_en_oof_cls_f1": 0.9404932519091155, | |
| "eval_en_oof_loss": 2.512021541595459, | |
| "eval_en_oof_runtime": 5.5703, | |
| "eval_en_oof_samples_per_second": 336.967, | |
| "eval_en_oof_steps_per_second": 3.59, | |
| "eval_en_oof_total_cls_tokens": 239, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.872448979591836, | |
| "eval_vi_All_acc": 0.7654610888486179, | |
| "eval_vi_Env_acc": 0.9754601226993865, | |
| "eval_vi_Env_f1": 0.9549549549549551, | |
| "eval_vi_Gov_acc": 0.9096774193548387, | |
| "eval_vi_Gov_f1": 0.8952380952380952, | |
| "eval_vi_Neu_acc": 0.8445945945945946, | |
| "eval_vi_Neu_f1": 0.8771929824561404, | |
| "eval_vi_Soc_acc": 0.8496732026143791, | |
| "eval_vi_Soc_f1": 0.8524590163934426, | |
| "eval_vi_cls_acc": 0.8966074313408724, | |
| "eval_vi_cls_f1": 0.8949612622606583, | |
| "eval_vi_loss": 1.1087512969970703, | |
| "eval_vi_runtime": 12.5699, | |
| "eval_vi_samples_per_second": 350.043, | |
| "eval_vi_steps_per_second": 3.66, | |
| "eval_vi_total_cls_tokens": 619, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.872448979591836, | |
| "eval_dan_All_acc": 0.6564337639486966, | |
| "eval_dan_Env_acc": 0.2, | |
| "eval_dan_Env_f1": 0.33333333333333337, | |
| "eval_dan_Gov_acc": 0.2727272727272727, | |
| "eval_dan_Gov_f1": 0.42857142857142855, | |
| "eval_dan_Neu_acc": 0.13636363636363635, | |
| "eval_dan_Neu_f1": 0.24000000000000002, | |
| "eval_dan_Soc_acc": 0.07142857142857142, | |
| "eval_dan_Soc_f1": 0.13333333333333333, | |
| "eval_dan_cls_acc": 0.15384615384615385, | |
| "eval_dan_cls_f1": 0.2838095238095238, | |
| "eval_dan_loss": 1.9571645259857178, | |
| "eval_dan_runtime": 8.7831, | |
| "eval_dan_samples_per_second": 341.565, | |
| "eval_dan_steps_per_second": 3.643, | |
| "eval_dan_total_cls_tokens": 52, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.910714285714286, | |
| "grad_norm": 2.681612491607666, | |
| "learning_rate": 4.5987802966854613e-05, | |
| "loss": 1.5584, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 6.948979591836735, | |
| "grad_norm": 2.540222406387329, | |
| "learning_rate": 4.593917625931012e-05, | |
| "loss": 1.5142, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 6.987244897959184, | |
| "grad_norm": 2.669194221496582, | |
| "learning_rate": 4.589028268558967e-05, | |
| "loss": 1.5933, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 7.0229591836734695, | |
| "grad_norm": 2.4838902950286865, | |
| "learning_rate": 4.5841122868833364e-05, | |
| "loss": 1.4637, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 7.061224489795919, | |
| "grad_norm": 2.551715612411499, | |
| "learning_rate": 4.5791697435574566e-05, | |
| "loss": 1.5885, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7.099489795918367, | |
| "grad_norm": 2.6968133449554443, | |
| "learning_rate": 4.574200701573187e-05, | |
| "loss": 1.5912, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 7.137755102040816, | |
| "grad_norm": 2.6120011806488037, | |
| "learning_rate": 4.569205224260107e-05, | |
| "loss": 1.551, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 7.176020408163265, | |
| "grad_norm": 2.4800548553466797, | |
| "learning_rate": 4.5641833752847096e-05, | |
| "loss": 1.5664, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 7.214285714285714, | |
| "grad_norm": 2.793236494064331, | |
| "learning_rate": 4.559135218649591e-05, | |
| "loss": 1.5559, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 7.252551020408164, | |
| "grad_norm": 2.422024965286255, | |
| "learning_rate": 4.554060818692634e-05, | |
| "loss": 1.5037, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.252551020408164, | |
| "eval_en_All_acc": 0.5978179484436839, | |
| "eval_en_Env_acc": 0.975609756097561, | |
| "eval_en_Env_f1": 0.9411764705882352, | |
| "eval_en_Gov_acc": 0.9464285714285714, | |
| "eval_en_Gov_f1": 0.9137931034482758, | |
| "eval_en_Neu_acc": 0.7831325301204819, | |
| "eval_en_Neu_f1": 0.8609271523178808, | |
| "eval_en_Soc_acc": 0.953125, | |
| "eval_en_Soc_f1": 0.9172932330827068, | |
| "eval_en_cls_acc": 0.9087719298245615, | |
| "eval_en_cls_f1": 0.9082974898592746, | |
| "eval_en_loss": 2.3768718242645264, | |
| "eval_en_runtime": 5.6241, | |
| "eval_en_samples_per_second": 333.744, | |
| "eval_en_steps_per_second": 3.556, | |
| "eval_en_total_cls_tokens": 285, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.252551020408164, | |
| "eval_en_oof_All_acc": 0.6092038753159225, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9746835443037974, | |
| "eval_en_oof_Gov_acc": 0.9375, | |
| "eval_en_oof_Gov_f1": 0.9302325581395349, | |
| "eval_en_oof_Neu_acc": 0.8076923076923077, | |
| "eval_en_oof_Neu_f1": 0.8689655172413794, | |
| "eval_en_oof_Soc_acc": 0.9594594594594594, | |
| "eval_en_oof_Soc_f1": 0.922077922077922, | |
| "eval_en_oof_cls_acc": 0.9249146757679181, | |
| "eval_en_oof_cls_f1": 0.9239898854406584, | |
| "eval_en_oof_loss": 2.3167083263397217, | |
| "eval_en_oof_runtime": 5.565, | |
| "eval_en_oof_samples_per_second": 337.288, | |
| "eval_en_oof_steps_per_second": 3.594, | |
| "eval_en_oof_total_cls_tokens": 293, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.252551020408164, | |
| "eval_vi_All_acc": 0.7690991727096312, | |
| "eval_vi_Env_acc": 0.9634146341463414, | |
| "eval_vi_Env_f1": 0.9634146341463414, | |
| "eval_vi_Gov_acc": 0.9349112426035503, | |
| "eval_vi_Gov_f1": 0.9054441260744986, | |
| "eval_vi_Neu_acc": 0.8662420382165605, | |
| "eval_vi_Neu_f1": 0.8774193548387097, | |
| "eval_vi_Soc_acc": 0.8512820512820513, | |
| "eval_vi_Soc_f1": 0.8668407310704961, | |
| "eval_vi_cls_acc": 0.9021897810218978, | |
| "eval_vi_cls_f1": 0.9032797115325114, | |
| "eval_vi_loss": 1.0928539037704468, | |
| "eval_vi_runtime": 12.279, | |
| "eval_vi_samples_per_second": 358.337, | |
| "eval_vi_steps_per_second": 3.746, | |
| "eval_vi_total_cls_tokens": 685, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.252551020408164, | |
| "eval_dan_All_acc": 0.6640314356551433, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.4, | |
| "eval_dan_Gov_f1": 0.5714285714285715, | |
| "eval_dan_Neu_acc": 0.22727272727272727, | |
| "eval_dan_Neu_f1": 0.35714285714285715, | |
| "eval_dan_Soc_acc": 0.1, | |
| "eval_dan_Soc_f1": 0.18181818181818182, | |
| "eval_dan_cls_acc": 0.19047619047619047, | |
| "eval_dan_cls_f1": 0.2775974025974026, | |
| "eval_dan_loss": 1.9352006912231445, | |
| "eval_dan_runtime": 9.2985, | |
| "eval_dan_samples_per_second": 322.632, | |
| "eval_dan_steps_per_second": 3.441, | |
| "eval_dan_total_cls_tokens": 42, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.290816326530612, | |
| "grad_norm": 2.454073667526245, | |
| "learning_rate": 4.548960240086186e-05, | |
| "loss": 1.5547, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 7.329081632653061, | |
| "grad_norm": 2.373873233795166, | |
| "learning_rate": 4.543833547836239e-05, | |
| "loss": 1.4933, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 7.36734693877551, | |
| "grad_norm": 2.6030843257904053, | |
| "learning_rate": 4.538680807281599e-05, | |
| "loss": 1.594, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 7.405612244897959, | |
| "grad_norm": 2.2914113998413086, | |
| "learning_rate": 4.533502084093051e-05, | |
| "loss": 1.5852, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 7.4438775510204085, | |
| "grad_norm": 2.5732812881469727, | |
| "learning_rate": 4.528297444272525e-05, | |
| "loss": 1.5553, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 7.482142857142857, | |
| "grad_norm": 2.5332298278808594, | |
| "learning_rate": 4.523066954152256e-05, | |
| "loss": 1.5597, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 7.520408163265306, | |
| "grad_norm": 2.638305425643921, | |
| "learning_rate": 4.5178106803939336e-05, | |
| "loss": 1.5102, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 7.558673469387755, | |
| "grad_norm": 2.569688320159912, | |
| "learning_rate": 4.512528689987857e-05, | |
| "loss": 1.5612, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 7.596938775510204, | |
| "grad_norm": 2.4558074474334717, | |
| "learning_rate": 4.507221050252081e-05, | |
| "loss": 1.5679, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 7.635204081632653, | |
| "grad_norm": 2.7440097332000732, | |
| "learning_rate": 4.5018878288315524e-05, | |
| "loss": 1.5308, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.635204081632653, | |
| "eval_en_All_acc": 0.5887305699481865, | |
| "eval_en_Env_acc": 0.9696969696969697, | |
| "eval_en_Env_f1": 0.9696969696969697, | |
| "eval_en_Gov_acc": 0.9710144927536232, | |
| "eval_en_Gov_f1": 0.9503546099290779, | |
| "eval_en_Neu_acc": 0.8615384615384616, | |
| "eval_en_Neu_f1": 0.8750000000000001, | |
| "eval_en_Soc_acc": 0.9146341463414634, | |
| "eval_en_Soc_f1": 0.9202453987730062, | |
| "eval_en_cls_acc": 0.9290780141843972, | |
| "eval_en_cls_f1": 0.9288242445997634, | |
| "eval_en_loss": 2.4251151084899902, | |
| "eval_en_runtime": 5.6203, | |
| "eval_en_samples_per_second": 333.97, | |
| "eval_en_steps_per_second": 3.559, | |
| "eval_en_total_cls_tokens": 282, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.635204081632653, | |
| "eval_en_oof_All_acc": 0.6077746232801922, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9645390070921985, | |
| "eval_en_oof_Gov_acc": 0.984375, | |
| "eval_en_oof_Gov_f1": 0.9692307692307692, | |
| "eval_en_oof_Neu_acc": 0.8169014084507042, | |
| "eval_en_oof_Neu_f1": 0.8854961832061069, | |
| "eval_en_oof_Soc_acc": 0.9629629629629629, | |
| "eval_en_oof_Soc_f1": 0.9369369369369369, | |
| "eval_en_oof_cls_acc": 0.9377431906614786, | |
| "eval_en_oof_cls_f1": 0.9390507241165029, | |
| "eval_en_oof_loss": 2.3028368949890137, | |
| "eval_en_oof_runtime": 5.5603, | |
| "eval_en_oof_samples_per_second": 337.572, | |
| "eval_en_oof_steps_per_second": 3.597, | |
| "eval_en_oof_total_cls_tokens": 257, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.635204081632653, | |
| "eval_vi_All_acc": 0.7574568888662472, | |
| "eval_vi_Env_acc": 0.9736842105263158, | |
| "eval_vi_Env_f1": 0.9396825396825397, | |
| "eval_vi_Gov_acc": 0.8863636363636364, | |
| "eval_vi_Gov_f1": 0.8939828080229225, | |
| "eval_vi_Neu_acc": 0.7976190476190477, | |
| "eval_vi_Neu_f1": 0.8401253918495298, | |
| "eval_vi_Soc_acc": 0.8742138364779874, | |
| "eval_vi_Soc_f1": 0.8501529051987767, | |
| "eval_vi_cls_acc": 0.8809160305343512, | |
| "eval_vi_cls_f1": 0.8809859111884422, | |
| "eval_vi_loss": 1.1471459865570068, | |
| "eval_vi_runtime": 12.7197, | |
| "eval_vi_samples_per_second": 345.92, | |
| "eval_vi_steps_per_second": 3.616, | |
| "eval_vi_total_cls_tokens": 655, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.635204081632653, | |
| "eval_dan_All_acc": 0.6647577919639505, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.4117647058823529, | |
| "eval_dan_Gov_f1": 0.5833333333333334, | |
| "eval_dan_Neu_acc": 0.1875, | |
| "eval_dan_Neu_f1": 0.3157894736842105, | |
| "eval_dan_Soc_acc": 0.38461538461538464, | |
| "eval_dan_Soc_f1": 0.5555555555555556, | |
| "eval_dan_cls_acc": 0.3191489361702128, | |
| "eval_dan_cls_f1": 0.36366959064327486, | |
| "eval_dan_loss": 1.938439965248108, | |
| "eval_dan_runtime": 8.6331, | |
| "eval_dan_samples_per_second": 347.499, | |
| "eval_dan_steps_per_second": 3.707, | |
| "eval_dan_total_cls_tokens": 47, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.673469387755102, | |
| "grad_norm": 2.649601697921753, | |
| "learning_rate": 4.496529093697256e-05, | |
| "loss": 1.588, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 7.711734693877551, | |
| "grad_norm": 2.402758836746216, | |
| "learning_rate": 4.491144913145344e-05, | |
| "loss": 1.5482, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "grad_norm": 2.548497438430786, | |
| "learning_rate": 4.4857353557962645e-05, | |
| "loss": 1.5667, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 7.788265306122449, | |
| "grad_norm": 2.5078744888305664, | |
| "learning_rate": 4.4803004905938893e-05, | |
| "loss": 1.5874, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 7.826530612244898, | |
| "grad_norm": 2.5391430854797363, | |
| "learning_rate": 4.474840386804634e-05, | |
| "loss": 1.5459, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 7.864795918367347, | |
| "grad_norm": 2.409688711166382, | |
| "learning_rate": 4.469355114016577e-05, | |
| "loss": 1.5779, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 7.903061224489796, | |
| "grad_norm": 2.4717087745666504, | |
| "learning_rate": 4.46384474213857e-05, | |
| "loss": 1.5608, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 7.941326530612245, | |
| "grad_norm": 2.465456247329712, | |
| "learning_rate": 4.458309341399348e-05, | |
| "loss": 1.5519, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 7.979591836734694, | |
| "grad_norm": 2.5235049724578857, | |
| "learning_rate": 4.452748982346636e-05, | |
| "loss": 1.5878, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 8.01530612244898, | |
| "grad_norm": 2.506821393966675, | |
| "learning_rate": 4.447163735846247e-05, | |
| "loss": 1.419, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.01530612244898, | |
| "eval_en_All_acc": 0.5944414751469802, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9586776859504132, | |
| "eval_en_Gov_acc": 0.9420289855072463, | |
| "eval_en_Gov_f1": 0.9219858156028369, | |
| "eval_en_Neu_acc": 0.7887323943661971, | |
| "eval_en_Neu_f1": 0.8421052631578947, | |
| "eval_en_Soc_acc": 0.9104477611940298, | |
| "eval_en_Soc_f1": 0.9037037037037037, | |
| "eval_en_cls_acc": 0.9056603773584906, | |
| "eval_en_cls_f1": 0.9066181171037122, | |
| "eval_en_loss": 2.3777682781219482, | |
| "eval_en_runtime": 5.6278, | |
| "eval_en_samples_per_second": 333.52, | |
| "eval_en_steps_per_second": 3.554, | |
| "eval_en_total_cls_tokens": 265, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.01530612244898, | |
| "eval_en_oof_All_acc": 0.5962491916361284, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9801324503311257, | |
| "eval_en_oof_Gov_acc": 0.9861111111111112, | |
| "eval_en_oof_Gov_f1": 0.9594594594594595, | |
| "eval_en_oof_Neu_acc": 0.868421052631579, | |
| "eval_en_oof_Neu_f1": 0.8918918918918918, | |
| "eval_en_oof_Soc_acc": 0.864406779661017, | |
| "eval_en_oof_Soc_f1": 0.8869565217391304, | |
| "eval_en_oof_cls_acc": 0.9323843416370107, | |
| "eval_en_oof_cls_f1": 0.9296100808554019, | |
| "eval_en_oof_loss": 2.413837194442749, | |
| "eval_en_oof_runtime": 5.5206, | |
| "eval_en_oof_samples_per_second": 340.002, | |
| "eval_en_oof_steps_per_second": 3.623, | |
| "eval_en_oof_total_cls_tokens": 281, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.01530612244898, | |
| "eval_vi_All_acc": 0.7669026686376721, | |
| "eval_vi_Env_acc": 0.9523809523809523, | |
| "eval_vi_Env_f1": 0.9427609427609427, | |
| "eval_vi_Gov_acc": 0.8805970149253731, | |
| "eval_vi_Gov_f1": 0.8489208633093526, | |
| "eval_vi_Neu_acc": 0.8465909090909091, | |
| "eval_vi_Neu_f1": 0.8922155688622755, | |
| "eval_vi_Soc_acc": 0.8536585365853658, | |
| "eval_vi_Soc_f1": 0.8408408408408409, | |
| "eval_vi_cls_acc": 0.8808373590982287, | |
| "eval_vi_cls_f1": 0.8811845539433529, | |
| "eval_vi_loss": 1.0732896327972412, | |
| "eval_vi_runtime": 12.4201, | |
| "eval_vi_samples_per_second": 354.265, | |
| "eval_vi_steps_per_second": 3.704, | |
| "eval_vi_total_cls_tokens": 621, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.01530612244898, | |
| "eval_dan_All_acc": 0.6709175452327241, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2857142857142857, | |
| "eval_dan_Gov_f1": 0.4444444444444445, | |
| "eval_dan_Neu_acc": 0.15, | |
| "eval_dan_Neu_f1": 0.2608695652173913, | |
| "eval_dan_Soc_acc": 0.23076923076923078, | |
| "eval_dan_Soc_f1": 0.375, | |
| "eval_dan_cls_acc": 0.1951219512195122, | |
| "eval_dan_cls_f1": 0.27007850241545894, | |
| "eval_dan_loss": 1.853433609008789, | |
| "eval_dan_runtime": 9.1642, | |
| "eval_dan_samples_per_second": 327.362, | |
| "eval_dan_steps_per_second": 3.492, | |
| "eval_dan_total_cls_tokens": 41, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.053571428571429, | |
| "grad_norm": 2.588351249694824, | |
| "learning_rate": 4.4415536730811794e-05, | |
| "loss": 1.5203, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 8.091836734693878, | |
| "grad_norm": 2.3677432537078857, | |
| "learning_rate": 4.435918865550713e-05, | |
| "loss": 1.5195, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 8.130102040816327, | |
| "grad_norm": 2.474693536758423, | |
| "learning_rate": 4.430259385069494e-05, | |
| "loss": 1.5149, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 8.168367346938776, | |
| "grad_norm": 2.446972608566284, | |
| "learning_rate": 4.4245753037666214e-05, | |
| "loss": 1.5075, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 8.206632653061224, | |
| "grad_norm": 2.5082125663757324, | |
| "learning_rate": 4.418866694084727e-05, | |
| "loss": 1.51, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 8.244897959183673, | |
| "grad_norm": 2.556925058364868, | |
| "learning_rate": 4.413133628779052e-05, | |
| "loss": 1.4836, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 8.283163265306122, | |
| "grad_norm": 2.424642562866211, | |
| "learning_rate": 4.407376180916522e-05, | |
| "loss": 1.56, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 8.321428571428571, | |
| "grad_norm": 2.359652280807495, | |
| "learning_rate": 4.4015944238748136e-05, | |
| "loss": 1.4578, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 8.35969387755102, | |
| "grad_norm": 2.6890335083007812, | |
| "learning_rate": 4.395788431341419e-05, | |
| "loss": 1.5582, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 8.39795918367347, | |
| "grad_norm": 2.415004014968872, | |
| "learning_rate": 4.3899582773127066e-05, | |
| "loss": 1.5014, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.39795918367347, | |
| "eval_en_All_acc": 0.6003732890916632, | |
| "eval_en_Env_acc": 0.9487179487179487, | |
| "eval_en_Env_f1": 0.9610389610389611, | |
| "eval_en_Gov_acc": 0.9428571428571428, | |
| "eval_en_Gov_f1": 0.9496402877697843, | |
| "eval_en_Neu_acc": 0.9459459459459459, | |
| "eval_en_Neu_f1": 0.8805031446540881, | |
| "eval_en_Soc_acc": 0.8513513513513513, | |
| "eval_en_Soc_f1": 0.9, | |
| "eval_en_cls_acc": 0.9222972972972973, | |
| "eval_en_cls_f1": 0.9227955983657083, | |
| "eval_en_loss": 2.3380000591278076, | |
| "eval_en_runtime": 5.5727, | |
| "eval_en_samples_per_second": 336.819, | |
| "eval_en_steps_per_second": 3.589, | |
| "eval_en_total_cls_tokens": 296, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.39795918367347, | |
| "eval_en_oof_All_acc": 0.6019879454372422, | |
| "eval_en_oof_Env_acc": 0.958904109589041, | |
| "eval_en_oof_Env_f1": 0.9722222222222222, | |
| "eval_en_oof_Gov_acc": 0.9594594594594594, | |
| "eval_en_oof_Gov_f1": 0.9594594594594594, | |
| "eval_en_oof_Neu_acc": 0.9230769230769231, | |
| "eval_en_oof_Neu_f1": 0.8695652173913043, | |
| "eval_en_oof_Soc_acc": 0.859375, | |
| "eval_en_oof_Soc_f1": 0.9016393442622951, | |
| "eval_en_oof_cls_acc": 0.927536231884058, | |
| "eval_en_oof_cls_f1": 0.9257215608338202, | |
| "eval_en_oof_loss": 2.388274669647217, | |
| "eval_en_oof_runtime": 5.5756, | |
| "eval_en_oof_samples_per_second": 336.648, | |
| "eval_en_oof_steps_per_second": 3.587, | |
| "eval_en_oof_total_cls_tokens": 276, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.39795918367347, | |
| "eval_vi_All_acc": 0.7748989532594052, | |
| "eval_vi_Env_acc": 0.9710982658959537, | |
| "eval_vi_Env_f1": 0.9491525423728814, | |
| "eval_vi_Gov_acc": 0.8141025641025641, | |
| "eval_vi_Gov_f1": 0.8610169491525423, | |
| "eval_vi_Neu_acc": 0.9032258064516129, | |
| "eval_vi_Neu_f1": 0.8484848484848486, | |
| "eval_vi_Soc_acc": 0.8411764705882353, | |
| "eval_vi_Soc_f1": 0.8693009118541033, | |
| "eval_vi_cls_acc": 0.8837920489296636, | |
| "eval_vi_cls_f1": 0.881988812966094, | |
| "eval_vi_loss": 1.0475819110870361, | |
| "eval_vi_runtime": 12.5396, | |
| "eval_vi_samples_per_second": 350.889, | |
| "eval_vi_steps_per_second": 3.668, | |
| "eval_vi_total_cls_tokens": 654, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.39795918367347, | |
| "eval_dan_All_acc": 0.6673520889802785, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.2, | |
| "eval_dan_Gov_f1": 0.33333333333333337, | |
| "eval_dan_Neu_acc": 0.13333333333333333, | |
| "eval_dan_Neu_f1": 0.23529411764705882, | |
| "eval_dan_Soc_acc": 0.21428571428571427, | |
| "eval_dan_Soc_f1": 0.35294117647058826, | |
| "eval_dan_cls_acc": 0.19444444444444445, | |
| "eval_dan_cls_f1": 0.3970588235294118, | |
| "eval_dan_loss": 1.9379643201828003, | |
| "eval_dan_runtime": 8.828, | |
| "eval_dan_samples_per_second": 339.828, | |
| "eval_dan_steps_per_second": 3.625, | |
| "eval_dan_total_cls_tokens": 36, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.436224489795919, | |
| "grad_norm": 2.54392147064209, | |
| "learning_rate": 4.384104036092981e-05, | |
| "loss": 1.4756, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 8.474489795918368, | |
| "grad_norm": 2.4726719856262207, | |
| "learning_rate": 4.378225782293533e-05, | |
| "loss": 1.5043, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 8.512755102040817, | |
| "grad_norm": 2.462343692779541, | |
| "learning_rate": 4.3723235908316897e-05, | |
| "loss": 1.5346, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 8.551020408163264, | |
| "grad_norm": 2.3272366523742676, | |
| "learning_rate": 4.3663975369298585e-05, | |
| "loss": 1.4828, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 8.589285714285714, | |
| "grad_norm": 2.7414770126342773, | |
| "learning_rate": 4.36044769611457e-05, | |
| "loss": 1.5149, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 8.627551020408163, | |
| "grad_norm": 2.5116066932678223, | |
| "learning_rate": 4.354474144215518e-05, | |
| "loss": 1.4917, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 8.665816326530612, | |
| "grad_norm": 2.465094804763794, | |
| "learning_rate": 4.3484769573645836e-05, | |
| "loss": 1.5209, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 8.704081632653061, | |
| "grad_norm": 2.586460590362549, | |
| "learning_rate": 4.3424562119948776e-05, | |
| "loss": 1.5252, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 8.74234693877551, | |
| "grad_norm": 2.444488763809204, | |
| "learning_rate": 4.336411984839755e-05, | |
| "loss": 1.4889, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 8.78061224489796, | |
| "grad_norm": 2.5610311031341553, | |
| "learning_rate": 4.330344352931846e-05, | |
| "loss": 1.5429, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.78061224489796, | |
| "eval_en_All_acc": 0.6061410964725882, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9923664122137404, | |
| "eval_en_Gov_acc": 0.9649122807017544, | |
| "eval_en_Gov_f1": 0.9322033898305084, | |
| "eval_en_Neu_acc": 0.8428571428571429, | |
| "eval_en_Neu_f1": 0.9076923076923077, | |
| "eval_en_Soc_acc": 0.9666666666666667, | |
| "eval_en_Soc_f1": 0.928, | |
| "eval_en_cls_acc": 0.9404761904761905, | |
| "eval_en_cls_f1": 0.9400655274341391, | |
| "eval_en_loss": 2.310546875, | |
| "eval_en_runtime": 5.5889, | |
| "eval_en_samples_per_second": 335.845, | |
| "eval_en_steps_per_second": 3.579, | |
| "eval_en_total_cls_tokens": 252, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.78061224489796, | |
| "eval_en_oof_All_acc": 0.6094312847942365, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9618320610687023, | |
| "eval_en_oof_Gov_acc": 0.9827586206896551, | |
| "eval_en_oof_Gov_f1": 0.9579831932773109, | |
| "eval_en_oof_Neu_acc": 0.8026315789473685, | |
| "eval_en_oof_Neu_f1": 0.8776978417266187, | |
| "eval_en_oof_Soc_acc": 0.9491525423728814, | |
| "eval_en_oof_Soc_f1": 0.9105691056910569, | |
| "eval_en_oof_cls_acc": 0.92578125, | |
| "eval_en_oof_cls_f1": 0.9270205504409221, | |
| "eval_en_oof_loss": 2.3137624263763428, | |
| "eval_en_oof_runtime": 5.5598, | |
| "eval_en_oof_samples_per_second": 337.604, | |
| "eval_en_oof_steps_per_second": 3.597, | |
| "eval_en_oof_total_cls_tokens": 256, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.78061224489796, | |
| "eval_vi_All_acc": 0.7718304760427172, | |
| "eval_vi_Env_acc": 0.9673202614379085, | |
| "eval_vi_Env_f1": 0.9456869009584665, | |
| "eval_vi_Gov_acc": 0.926829268292683, | |
| "eval_vi_Gov_f1": 0.8941176470588236, | |
| "eval_vi_Neu_acc": 0.838150289017341, | |
| "eval_vi_Neu_f1": 0.8787878787878788, | |
| "eval_vi_Soc_acc": 0.8588957055214724, | |
| "eval_vi_Soc_f1": 0.8668730650154799, | |
| "eval_vi_cls_acc": 0.8958652373660031, | |
| "eval_vi_cls_f1": 0.8963663729551622, | |
| "eval_vi_loss": 1.0548739433288574, | |
| "eval_vi_runtime": 12.5263, | |
| "eval_vi_samples_per_second": 351.261, | |
| "eval_vi_steps_per_second": 3.672, | |
| "eval_vi_total_cls_tokens": 653, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.78061224489796, | |
| "eval_dan_All_acc": 0.66775996673904, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.4444444444444444, | |
| "eval_dan_Gov_f1": 0.6153846153846153, | |
| "eval_dan_Neu_acc": 0.25, | |
| "eval_dan_Neu_f1": 0.4, | |
| "eval_dan_Soc_acc": 0.0, | |
| "eval_dan_Soc_f1": 0.0, | |
| "eval_dan_cls_acc": 0.25, | |
| "eval_dan_cls_f1": 0.42051282051282046, | |
| "eval_dan_loss": 1.9144359827041626, | |
| "eval_dan_runtime": 8.8813, | |
| "eval_dan_samples_per_second": 337.787, | |
| "eval_dan_steps_per_second": 3.603, | |
| "eval_dan_total_cls_tokens": 44, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.818877551020408, | |
| "grad_norm": 2.3332748413085938, | |
| "learning_rate": 4.324253393602069e-05, | |
| "loss": 1.5074, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 8.857142857142858, | |
| "grad_norm": 2.655041217803955, | |
| "learning_rate": 4.318139184478645e-05, | |
| "loss": 1.5377, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 8.895408163265307, | |
| "grad_norm": 2.4485909938812256, | |
| "learning_rate": 4.31200180348611e-05, | |
| "loss": 1.4682, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 8.933673469387756, | |
| "grad_norm": 2.3908026218414307, | |
| "learning_rate": 4.3058413288443236e-05, | |
| "loss": 1.4728, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 8.971938775510203, | |
| "grad_norm": 2.668367624282837, | |
| "learning_rate": 4.299657839067468e-05, | |
| "loss": 1.5225, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 9.00765306122449, | |
| "grad_norm": 2.5744354724884033, | |
| "learning_rate": 4.2934514129630504e-05, | |
| "loss": 1.477, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 9.045918367346939, | |
| "grad_norm": 2.485384225845337, | |
| "learning_rate": 4.2872221296308954e-05, | |
| "loss": 1.5254, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 9.084183673469388, | |
| "grad_norm": 2.4510884284973145, | |
| "learning_rate": 4.280970068462142e-05, | |
| "loss": 1.4814, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 9.122448979591837, | |
| "grad_norm": 2.4104583263397217, | |
| "learning_rate": 4.274695309138226e-05, | |
| "loss": 1.5139, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 9.160714285714286, | |
| "grad_norm": 2.5406880378723145, | |
| "learning_rate": 4.268397931629869e-05, | |
| "loss": 1.4602, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.160714285714286, | |
| "eval_en_All_acc": 0.6023373003109252, | |
| "eval_en_Env_acc": 0.9871794871794872, | |
| "eval_en_Env_f1": 0.9871794871794872, | |
| "eval_en_Gov_acc": 0.96875, | |
| "eval_en_Gov_f1": 0.9465648854961832, | |
| "eval_en_Neu_acc": 0.8181818181818182, | |
| "eval_en_Neu_f1": 0.8513513513513514, | |
| "eval_en_Soc_acc": 0.9305555555555556, | |
| "eval_en_Soc_f1": 0.9115646258503401, | |
| "eval_en_cls_acc": 0.9243986254295533, | |
| "eval_en_cls_f1": 0.9241650874693405, | |
| "eval_en_loss": 2.331033229827881, | |
| "eval_en_runtime": 5.6231, | |
| "eval_en_samples_per_second": 333.801, | |
| "eval_en_steps_per_second": 3.557, | |
| "eval_en_total_cls_tokens": 291, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.160714285714286, | |
| "eval_en_oof_All_acc": 0.5969969311705392, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9722222222222222, | |
| "eval_en_oof_Gov_acc": 0.9622641509433962, | |
| "eval_en_oof_Gov_f1": 0.9532710280373832, | |
| "eval_en_oof_Neu_acc": 0.875, | |
| "eval_en_oof_Neu_f1": 0.9112426035502958, | |
| "eval_en_oof_Soc_acc": 0.9375, | |
| "eval_en_oof_Soc_f1": 0.923076923076923, | |
| "eval_en_oof_cls_acc": 0.9381818181818182, | |
| "eval_en_oof_cls_f1": 0.9399531942217061, | |
| "eval_en_oof_loss": 2.3871572017669678, | |
| "eval_en_oof_runtime": 5.5211, | |
| "eval_en_oof_samples_per_second": 339.969, | |
| "eval_en_oof_steps_per_second": 3.622, | |
| "eval_en_oof_total_cls_tokens": 275, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.160714285714286, | |
| "eval_vi_All_acc": 0.771213282247765, | |
| "eval_vi_Env_acc": 0.9617834394904459, | |
| "eval_vi_Env_f1": 0.9587301587301587, | |
| "eval_vi_Gov_acc": 0.9230769230769231, | |
| "eval_vi_Gov_f1": 0.908108108108108, | |
| "eval_vi_Neu_acc": 0.8497109826589595, | |
| "eval_vi_Neu_f1": 0.8802395209580838, | |
| "eval_vi_Soc_acc": 0.8719512195121951, | |
| "eval_vi_Soc_f1": 0.8588588588588588, | |
| "eval_vi_cls_acc": 0.900887573964497, | |
| "eval_vi_cls_f1": 0.9014841616638023, | |
| "eval_vi_loss": 1.0647811889648438, | |
| "eval_vi_runtime": 12.5593, | |
| "eval_vi_samples_per_second": 350.337, | |
| "eval_vi_steps_per_second": 3.663, | |
| "eval_vi_total_cls_tokens": 676, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.160714285714286, | |
| "eval_dan_All_acc": 0.6670105993809211, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.5454545454545454, | |
| "eval_dan_Gov_f1": 0.7058823529411764, | |
| "eval_dan_Neu_acc": 0.38461538461538464, | |
| "eval_dan_Neu_f1": 0.5555555555555556, | |
| "eval_dan_Soc_acc": 0.2857142857142857, | |
| "eval_dan_Soc_f1": 0.4444444444444445, | |
| "eval_dan_cls_acc": 0.4, | |
| "eval_dan_cls_f1": 0.5931372549019608, | |
| "eval_dan_loss": 1.96064293384552, | |
| "eval_dan_runtime": 8.7921, | |
| "eval_dan_samples_per_second": 341.216, | |
| "eval_dan_steps_per_second": 3.64, | |
| "eval_dan_total_cls_tokens": 40, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.198979591836734, | |
| "grad_norm": 2.5311741828918457, | |
| "learning_rate": 4.262078016196058e-05, | |
| "loss": 1.5023, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 9.237244897959183, | |
| "grad_norm": 2.5398976802825928, | |
| "learning_rate": 4.2557356433830204e-05, | |
| "loss": 1.5019, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 9.275510204081632, | |
| "grad_norm": 2.4927287101745605, | |
| "learning_rate": 4.2493708940231994e-05, | |
| "loss": 1.5078, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 9.313775510204081, | |
| "grad_norm": 2.5704030990600586, | |
| "learning_rate": 4.242983849234222e-05, | |
| "loss": 1.4984, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 9.35204081632653, | |
| "grad_norm": 2.5446693897247314, | |
| "learning_rate": 4.236574590417871e-05, | |
| "loss": 1.5059, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 9.39030612244898, | |
| "grad_norm": 2.5347185134887695, | |
| "learning_rate": 4.230143199259039e-05, | |
| "loss": 1.5226, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 9.428571428571429, | |
| "grad_norm": 2.358978748321533, | |
| "learning_rate": 4.223689757724692e-05, | |
| "loss": 1.4087, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 9.466836734693878, | |
| "grad_norm": 2.5118653774261475, | |
| "learning_rate": 4.2172143480628266e-05, | |
| "loss": 1.485, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 9.505102040816327, | |
| "grad_norm": 2.40613055229187, | |
| "learning_rate": 4.210717052801417e-05, | |
| "loss": 1.4935, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 9.543367346938776, | |
| "grad_norm": 2.4566972255706787, | |
| "learning_rate": 4.2041979547473665e-05, | |
| "loss": 1.5364, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.543367346938776, | |
| "eval_en_All_acc": 0.599870647838741, | |
| "eval_en_Env_acc": 0.9642857142857143, | |
| "eval_en_Env_f1": 0.972972972972973, | |
| "eval_en_Gov_acc": 0.9565217391304348, | |
| "eval_en_Gov_f1": 0.9462365591397849, | |
| "eval_en_Neu_acc": 0.9571428571428572, | |
| "eval_en_Neu_f1": 0.9305555555555555, | |
| "eval_en_Soc_acc": 0.9402985074626866, | |
| "eval_en_Soc_f1": 0.9692307692307692, | |
| "eval_en_cls_acc": 0.9539748953974896, | |
| "eval_en_cls_f1": 0.9547489642247706, | |
| "eval_en_loss": 2.389317512512207, | |
| "eval_en_runtime": 5.5321, | |
| "eval_en_samples_per_second": 339.295, | |
| "eval_en_steps_per_second": 3.615, | |
| "eval_en_total_cls_tokens": 239, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.543367346938776, | |
| "eval_en_oof_All_acc": 0.603538873994638, | |
| "eval_en_oof_Env_acc": 0.9871794871794872, | |
| "eval_en_oof_Env_f1": 0.9871794871794872, | |
| "eval_en_oof_Gov_acc": 0.9838709677419355, | |
| "eval_en_oof_Gov_f1": 0.9457364341085271, | |
| "eval_en_oof_Neu_acc": 0.9375, | |
| "eval_en_oof_Neu_f1": 0.8888888888888888, | |
| "eval_en_oof_Soc_acc": 0.8309859154929577, | |
| "eval_en_oof_Soc_f1": 0.9076923076923077, | |
| "eval_en_oof_cls_acc": 0.9345454545454546, | |
| "eval_en_oof_cls_f1": 0.9323742794673027, | |
| "eval_en_oof_loss": 2.3326351642608643, | |
| "eval_en_oof_runtime": 5.5855, | |
| "eval_en_oof_samples_per_second": 336.05, | |
| "eval_en_oof_steps_per_second": 3.581, | |
| "eval_en_oof_total_cls_tokens": 275, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.543367346938776, | |
| "eval_vi_All_acc": 0.77124790295522, | |
| "eval_vi_Env_acc": 0.9625, | |
| "eval_vi_Env_f1": 0.9535603715170279, | |
| "eval_vi_Gov_acc": 0.8986486486486487, | |
| "eval_vi_Gov_f1": 0.9016949152542374, | |
| "eval_vi_Neu_acc": 0.8690476190476191, | |
| "eval_vi_Neu_f1": 0.8538011695906432, | |
| "eval_vi_Soc_acc": 0.8658536585365854, | |
| "eval_vi_Soc_f1": 0.8875000000000001, | |
| "eval_vi_cls_acc": 0.8984375, | |
| "eval_vi_cls_f1": 0.8991391140904771, | |
| "eval_vi_loss": 1.0692591667175293, | |
| "eval_vi_runtime": 12.4122, | |
| "eval_vi_samples_per_second": 354.49, | |
| "eval_vi_steps_per_second": 3.706, | |
| "eval_vi_total_cls_tokens": 640, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.543367346938776, | |
| "eval_dan_All_acc": 0.6685501653803748, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.14814814814814814, | |
| "eval_dan_Neu_f1": 0.25806451612903225, | |
| "eval_dan_Soc_acc": 0.2857142857142857, | |
| "eval_dan_Soc_f1": 0.4444444444444445, | |
| "eval_dan_cls_acc": 0.19298245614035087, | |
| "eval_dan_cls_f1": 0.40479390681003585, | |
| "eval_dan_loss": 1.9309048652648926, | |
| "eval_dan_runtime": 8.9301, | |
| "eval_dan_samples_per_second": 335.942, | |
| "eval_dan_steps_per_second": 3.583, | |
| "eval_dan_total_cls_tokens": 57, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.581632653061224, | |
| "grad_norm": 2.40655517578125, | |
| "learning_rate": 4.19765713698545e-05, | |
| "loss": 1.4492, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 9.619897959183673, | |
| "grad_norm": 2.608046770095825, | |
| "learning_rate": 4.191094682877258e-05, | |
| "loss": 1.5036, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 9.658163265306122, | |
| "grad_norm": 2.5277328491210938, | |
| "learning_rate": 4.184510676060133e-05, | |
| "loss": 1.4931, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 9.696428571428571, | |
| "grad_norm": 2.523139476776123, | |
| "learning_rate": 4.1779052004461014e-05, | |
| "loss": 1.5199, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 9.73469387755102, | |
| "grad_norm": 2.4831342697143555, | |
| "learning_rate": 4.171278340220806e-05, | |
| "loss": 1.4874, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 9.77295918367347, | |
| "grad_norm": 2.3602335453033447, | |
| "learning_rate": 4.164630179842431e-05, | |
| "loss": 1.4963, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 9.811224489795919, | |
| "grad_norm": 2.379018783569336, | |
| "learning_rate": 4.1579608040406324e-05, | |
| "loss": 1.4832, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 9.849489795918368, | |
| "grad_norm": 2.3944358825683594, | |
| "learning_rate": 4.151270297815449e-05, | |
| "loss": 1.4919, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 9.887755102040817, | |
| "grad_norm": 2.3752331733703613, | |
| "learning_rate": 4.144558746436224e-05, | |
| "loss": 1.5038, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 9.926020408163264, | |
| "grad_norm": 2.4143567085266113, | |
| "learning_rate": 4.137826235440517e-05, | |
| "loss": 1.5175, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 9.926020408163264, | |
| "eval_en_All_acc": 0.6098942194678919, | |
| "eval_en_Env_acc": 0.9830508474576272, | |
| "eval_en_Env_f1": 0.9586776859504132, | |
| "eval_en_Gov_acc": 0.9324324324324325, | |
| "eval_en_Gov_f1": 0.9324324324324325, | |
| "eval_en_Neu_acc": 0.8266666666666667, | |
| "eval_en_Neu_f1": 0.8493150684931506, | |
| "eval_en_Soc_acc": 0.9166666666666666, | |
| "eval_en_Soc_f1": 0.9090909090909091, | |
| "eval_en_cls_acc": 0.9104477611940298, | |
| "eval_en_cls_f1": 0.9123790239917263, | |
| "eval_en_loss": 2.297198534011841, | |
| "eval_en_runtime": 5.598, | |
| "eval_en_samples_per_second": 335.298, | |
| "eval_en_steps_per_second": 3.573, | |
| "eval_en_total_cls_tokens": 268, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 9.926020408163264, | |
| "eval_en_oof_All_acc": 0.5982392097917114, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9913043478260869, | |
| "eval_en_oof_Gov_acc": 0.9558823529411765, | |
| "eval_en_oof_Gov_f1": 0.9558823529411765, | |
| "eval_en_oof_Neu_acc": 0.8518518518518519, | |
| "eval_en_oof_Neu_f1": 0.8961038961038961, | |
| "eval_en_oof_Soc_acc": 0.967741935483871, | |
| "eval_en_oof_Soc_f1": 0.9160305343511451, | |
| "eval_en_oof_cls_acc": 0.9365671641791045, | |
| "eval_en_oof_cls_f1": 0.9398302828055761, | |
| "eval_en_oof_loss": 2.3254308700561523, | |
| "eval_en_oof_runtime": 5.5668, | |
| "eval_en_oof_samples_per_second": 337.178, | |
| "eval_en_oof_steps_per_second": 3.593, | |
| "eval_en_oof_total_cls_tokens": 268, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 9.926020408163264, | |
| "eval_vi_All_acc": 0.7731492136555428, | |
| "eval_vi_Env_acc": 0.9607843137254902, | |
| "eval_vi_Env_f1": 0.9702970297029702, | |
| "eval_vi_Gov_acc": 0.9289940828402367, | |
| "eval_vi_Gov_f1": 0.9262536873156343, | |
| "eval_vi_Neu_acc": 0.9523809523809523, | |
| "eval_vi_Neu_f1": 0.9411764705882352, | |
| "eval_vi_Soc_acc": 0.9192546583850931, | |
| "eval_vi_Soc_f1": 0.925, | |
| "eval_vi_cls_acc": 0.9400921658986175, | |
| "eval_vi_cls_f1": 0.9406817969017098, | |
| "eval_vi_loss": 1.0580319166183472, | |
| "eval_vi_runtime": 12.5639, | |
| "eval_vi_samples_per_second": 350.211, | |
| "eval_vi_steps_per_second": 3.661, | |
| "eval_vi_total_cls_tokens": 651, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 9.926020408163264, | |
| "eval_dan_All_acc": 0.6667741044295055, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3076923076923077, | |
| "eval_dan_Gov_f1": 0.47058823529411764, | |
| "eval_dan_Neu_acc": 0.09523809523809523, | |
| "eval_dan_Neu_f1": 0.17391304347826084, | |
| "eval_dan_Soc_acc": 0.3333333333333333, | |
| "eval_dan_Soc_f1": 0.48275862068965514, | |
| "eval_dan_cls_acc": 0.22807017543859648, | |
| "eval_dan_cls_f1": 0.2818149748655084, | |
| "eval_dan_loss": 1.9838874340057373, | |
| "eval_dan_runtime": 8.8778, | |
| "eval_dan_samples_per_second": 337.923, | |
| "eval_dan_steps_per_second": 3.605, | |
| "eval_dan_total_cls_tokens": 57, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 9.964285714285714, | |
| "grad_norm": 2.599351167678833, | |
| "learning_rate": 4.1310728506330174e-05, | |
| "loss": 1.5135, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.426339030265808, | |
| "learning_rate": 4.1242986780844424e-05, | |
| "loss": 1.3985, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 10.03826530612245, | |
| "grad_norm": 2.4705862998962402, | |
| "learning_rate": 4.117503804130449e-05, | |
| "loss": 1.4722, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 10.076530612244898, | |
| "grad_norm": 2.599490165710449, | |
| "learning_rate": 4.1106883153705314e-05, | |
| "loss": 1.4813, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 10.114795918367347, | |
| "grad_norm": 2.6149954795837402, | |
| "learning_rate": 4.1038522986669104e-05, | |
| "loss": 1.4627, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 10.153061224489797, | |
| "grad_norm": 2.4201104640960693, | |
| "learning_rate": 4.0969958411434376e-05, | |
| "loss": 1.5068, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 10.191326530612244, | |
| "grad_norm": 2.4955694675445557, | |
| "learning_rate": 4.0901190301844765e-05, | |
| "loss": 1.4537, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 10.229591836734693, | |
| "grad_norm": 2.5328240394592285, | |
| "learning_rate": 4.0832219534337925e-05, | |
| "loss": 1.4531, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 10.267857142857142, | |
| "grad_norm": 2.5922133922576904, | |
| "learning_rate": 4.0763046987934325e-05, | |
| "loss": 1.5069, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 10.306122448979592, | |
| "grad_norm": 2.268569231033325, | |
| "learning_rate": 4.069367354422612e-05, | |
| "loss": 1.4286, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 10.306122448979592, | |
| "eval_en_All_acc": 0.6027411814704632, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9600000000000001, | |
| "eval_en_Gov_acc": 0.9215686274509803, | |
| "eval_en_Gov_f1": 0.9306930693069307, | |
| "eval_en_Neu_acc": 0.8412698412698413, | |
| "eval_en_Neu_f1": 0.8833333333333334, | |
| "eval_en_Soc_acc": 0.9538461538461539, | |
| "eval_en_Soc_f1": 0.9393939393939394, | |
| "eval_en_cls_acc": 0.9288702928870293, | |
| "eval_en_cls_f1": 0.9283550855085508, | |
| "eval_en_loss": 2.3355610370635986, | |
| "eval_en_runtime": 5.5908, | |
| "eval_en_samples_per_second": 335.729, | |
| "eval_en_steps_per_second": 3.577, | |
| "eval_en_total_cls_tokens": 239, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 10.306122448979592, | |
| "eval_en_oof_All_acc": 0.6055166374781086, | |
| "eval_en_oof_Env_acc": 0.9857142857142858, | |
| "eval_en_oof_Env_f1": 0.9650349650349651, | |
| "eval_en_oof_Gov_acc": 0.9322033898305084, | |
| "eval_en_oof_Gov_f1": 0.94017094017094, | |
| "eval_en_oof_Neu_acc": 0.8805970149253731, | |
| "eval_en_oof_Neu_f1": 0.8939393939393939, | |
| "eval_en_oof_Soc_acc": 0.927536231884058, | |
| "eval_en_oof_Soc_f1": 0.927536231884058, | |
| "eval_en_oof_cls_acc": 0.9320754716981132, | |
| "eval_en_oof_cls_f1": 0.9316703827573393, | |
| "eval_en_oof_loss": 2.3082077503204346, | |
| "eval_en_oof_runtime": 5.5075, | |
| "eval_en_oof_samples_per_second": 340.811, | |
| "eval_en_oof_steps_per_second": 3.631, | |
| "eval_en_oof_total_cls_tokens": 265, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 10.306122448979592, | |
| "eval_vi_All_acc": 0.7751341500455604, | |
| "eval_vi_Env_acc": 0.9828571428571429, | |
| "eval_vi_Env_f1": 0.9662921348314607, | |
| "eval_vi_Gov_acc": 0.9289940828402367, | |
| "eval_vi_Gov_f1": 0.9154518950437318, | |
| "eval_vi_Neu_acc": 0.8606060606060606, | |
| "eval_vi_Neu_f1": 0.9102564102564102, | |
| "eval_vi_Soc_acc": 0.9158415841584159, | |
| "eval_vi_Soc_f1": 0.9002433090024331, | |
| "eval_vi_cls_acc": 0.9226441631504922, | |
| "eval_vi_cls_f1": 0.9230609372835089, | |
| "eval_vi_loss": 1.0570933818817139, | |
| "eval_vi_runtime": 12.5587, | |
| "eval_vi_samples_per_second": 350.353, | |
| "eval_vi_steps_per_second": 3.663, | |
| "eval_vi_total_cls_tokens": 711, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 10.306122448979592, | |
| "eval_dan_All_acc": 0.6660553909813326, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.29411764705882354, | |
| "eval_dan_Gov_f1": 0.4347826086956522, | |
| "eval_dan_Neu_acc": 0.21052631578947367, | |
| "eval_dan_Neu_f1": 0.34782608695652173, | |
| "eval_dan_Soc_acc": 0.18181818181818182, | |
| "eval_dan_Soc_f1": 0.3076923076923077, | |
| "eval_dan_cls_acc": 0.22448979591836735, | |
| "eval_dan_cls_f1": 0.27257525083612044, | |
| "eval_dan_loss": 1.9794265031814575, | |
| "eval_dan_runtime": 8.6516, | |
| "eval_dan_samples_per_second": 346.757, | |
| "eval_dan_steps_per_second": 3.699, | |
| "eval_dan_total_cls_tokens": 49, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 10.34438775510204, | |
| "grad_norm": 2.3969454765319824, | |
| "learning_rate": 4.062410008736583e-05, | |
| "loss": 1.5197, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 10.38265306122449, | |
| "grad_norm": 2.4994394779205322, | |
| "learning_rate": 4.05543275040551e-05, | |
| "loss": 1.4423, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 10.420918367346939, | |
| "grad_norm": 2.609699249267578, | |
| "learning_rate": 4.048435668353345e-05, | |
| "loss": 1.4713, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 10.459183673469388, | |
| "grad_norm": 2.538325548171997, | |
| "learning_rate": 4.041418851756686e-05, | |
| "loss": 1.4799, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 10.497448979591837, | |
| "grad_norm": 2.364856481552124, | |
| "learning_rate": 4.034382390043645e-05, | |
| "loss": 1.4868, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 10.535714285714286, | |
| "grad_norm": 2.4188101291656494, | |
| "learning_rate": 4.027326372892709e-05, | |
| "loss": 1.4567, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 10.573979591836736, | |
| "grad_norm": 2.3802008628845215, | |
| "learning_rate": 4.020250890231595e-05, | |
| "loss": 1.498, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 10.612244897959183, | |
| "grad_norm": 2.415468215942383, | |
| "learning_rate": 4.013156032236104e-05, | |
| "loss": 1.4642, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 10.650510204081632, | |
| "grad_norm": 2.252380847930908, | |
| "learning_rate": 4.006041889328973e-05, | |
| "loss": 1.4972, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 10.688775510204081, | |
| "grad_norm": 2.6682181358337402, | |
| "learning_rate": 3.998908552178721e-05, | |
| "loss": 1.4716, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 10.688775510204081, | |
| "eval_en_All_acc": 0.6017249004865104, | |
| "eval_en_Env_acc": 0.9583333333333334, | |
| "eval_en_Env_f1": 0.9583333333333334, | |
| "eval_en_Gov_acc": 0.9375, | |
| "eval_en_Gov_f1": 0.9523809523809523, | |
| "eval_en_Neu_acc": 0.8873239436619719, | |
| "eval_en_Neu_f1": 0.881118881118881, | |
| "eval_en_Soc_acc": 0.9375, | |
| "eval_en_Soc_f1": 0.9302325581395349, | |
| "eval_en_cls_acc": 0.9298892988929889, | |
| "eval_en_cls_f1": 0.9305164312431753, | |
| "eval_en_loss": 2.3381669521331787, | |
| "eval_en_runtime": 5.6163, | |
| "eval_en_samples_per_second": 334.203, | |
| "eval_en_steps_per_second": 3.561, | |
| "eval_en_total_cls_tokens": 271, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 10.688775510204081, | |
| "eval_en_oof_All_acc": 0.602980883464737, | |
| "eval_en_oof_Env_acc": 0.9838709677419355, | |
| "eval_en_oof_Env_f1": 0.976, | |
| "eval_en_oof_Gov_acc": 0.967741935483871, | |
| "eval_en_oof_Gov_f1": 0.96, | |
| "eval_en_oof_Neu_acc": 0.9154929577464789, | |
| "eval_en_oof_Neu_f1": 0.896551724137931, | |
| "eval_en_oof_Soc_acc": 0.9, | |
| "eval_en_oof_Soc_f1": 0.9333333333333333, | |
| "eval_en_oof_cls_acc": 0.939622641509434, | |
| "eval_en_oof_cls_f1": 0.9414712643678161, | |
| "eval_en_oof_loss": 2.3173623085021973, | |
| "eval_en_oof_runtime": 5.5843, | |
| "eval_en_oof_samples_per_second": 336.124, | |
| "eval_en_oof_steps_per_second": 3.581, | |
| "eval_en_oof_total_cls_tokens": 265, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 10.688775510204081, | |
| "eval_vi_All_acc": 0.7788244353182752, | |
| "eval_vi_Env_acc": 0.9585798816568047, | |
| "eval_vi_Env_f1": 0.9501466275659824, | |
| "eval_vi_Gov_acc": 0.8830409356725146, | |
| "eval_vi_Gov_f1": 0.8934911242603552, | |
| "eval_vi_Neu_acc": 0.8759124087591241, | |
| "eval_vi_Neu_f1": 0.8633093525179856, | |
| "eval_vi_Soc_acc": 0.85625, | |
| "eval_vi_Soc_f1": 0.8643533123028391, | |
| "eval_vi_cls_acc": 0.8948194662480377, | |
| "eval_vi_cls_f1": 0.8928251041617905, | |
| "eval_vi_loss": 1.026656985282898, | |
| "eval_vi_runtime": 12.3993, | |
| "eval_vi_samples_per_second": 354.859, | |
| "eval_vi_steps_per_second": 3.71, | |
| "eval_vi_total_cls_tokens": 637, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 10.688775510204081, | |
| "eval_dan_All_acc": 0.6652546233032705, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.23076923076923078, | |
| "eval_dan_Gov_f1": 0.375, | |
| "eval_dan_Neu_acc": 0.14285714285714285, | |
| "eval_dan_Neu_f1": 0.25, | |
| "eval_dan_Soc_acc": 0.3333333333333333, | |
| "eval_dan_Soc_f1": 0.5, | |
| "eval_dan_cls_acc": 0.2, | |
| "eval_dan_cls_f1": 0.28125, | |
| "eval_dan_loss": 1.9970935583114624, | |
| "eval_dan_runtime": 8.9405, | |
| "eval_dan_samples_per_second": 335.553, | |
| "eval_dan_steps_per_second": 3.579, | |
| "eval_dan_total_cls_tokens": 45, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 10.72704081632653, | |
| "grad_norm": 2.3197813034057617, | |
| "learning_rate": 3.991756111698496e-05, | |
| "loss": 1.437, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 10.76530612244898, | |
| "grad_norm": 2.3464272022247314, | |
| "learning_rate": 3.984584659044913e-05, | |
| "loss": 1.5018, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 10.803571428571429, | |
| "grad_norm": 2.3882510662078857, | |
| "learning_rate": 3.977394285616893e-05, | |
| "loss": 1.4574, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 10.841836734693878, | |
| "grad_norm": 2.52211332321167, | |
| "learning_rate": 3.970185083054504e-05, | |
| "loss": 1.4583, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 10.880102040816327, | |
| "grad_norm": 2.395329713821411, | |
| "learning_rate": 3.9629571432377805e-05, | |
| "loss": 1.4496, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 10.918367346938776, | |
| "grad_norm": 2.447596549987793, | |
| "learning_rate": 3.955710558285566e-05, | |
| "loss": 1.4798, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 10.956632653061224, | |
| "grad_norm": 2.539644241333008, | |
| "learning_rate": 3.948445420554331e-05, | |
| "loss": 1.4476, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 10.994897959183673, | |
| "grad_norm": 2.2854537963867188, | |
| "learning_rate": 3.941161822636997e-05, | |
| "loss": 1.4815, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 11.03061224489796, | |
| "grad_norm": 2.466667413711548, | |
| "learning_rate": 3.93385985736176e-05, | |
| "loss": 1.3528, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 11.068877551020408, | |
| "grad_norm": 2.4220259189605713, | |
| "learning_rate": 3.926539617790902e-05, | |
| "loss": 1.4781, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.068877551020408, | |
| "eval_en_All_acc": 0.6229438607662103, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9871794871794872, | |
| "eval_en_Gov_acc": 0.9565217391304348, | |
| "eval_en_Gov_f1": 0.9635036496350365, | |
| "eval_en_Neu_acc": 0.8205128205128205, | |
| "eval_en_Neu_f1": 0.8827586206896552, | |
| "eval_en_Soc_acc": 0.9696969696969697, | |
| "eval_en_Soc_f1": 0.9014084507042254, | |
| "eval_en_cls_acc": 0.9344827586206896, | |
| "eval_en_cls_f1": 0.9337125520521011, | |
| "eval_en_loss": 2.1719837188720703, | |
| "eval_en_runtime": 5.5424, | |
| "eval_en_samples_per_second": 338.659, | |
| "eval_en_steps_per_second": 3.609, | |
| "eval_en_total_cls_tokens": 290, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.068877551020408, | |
| "eval_en_oof_All_acc": 0.6167400881057269, | |
| "eval_en_oof_Env_acc": 0.9655172413793104, | |
| "eval_en_oof_Env_f1": 0.9438202247191013, | |
| "eval_en_oof_Gov_acc": 0.9473684210526315, | |
| "eval_en_oof_Gov_f1": 0.9473684210526315, | |
| "eval_en_oof_Neu_acc": 0.8181818181818182, | |
| "eval_en_oof_Neu_f1": 0.881118881118881, | |
| "eval_en_oof_Soc_acc": 0.9571428571428572, | |
| "eval_en_oof_Soc_f1": 0.9115646258503401, | |
| "eval_en_oof_cls_acc": 0.9209621993127147, | |
| "eval_en_oof_cls_f1": 0.9209680381852385, | |
| "eval_en_oof_loss": 2.2190732955932617, | |
| "eval_en_oof_runtime": 5.5578, | |
| "eval_en_oof_samples_per_second": 337.725, | |
| "eval_en_oof_steps_per_second": 3.599, | |
| "eval_en_oof_total_cls_tokens": 291, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.068877551020408, | |
| "eval_vi_All_acc": 0.774164934867454, | |
| "eval_vi_Env_acc": 0.9659090909090909, | |
| "eval_vi_Env_f1": 0.9550561797752809, | |
| "eval_vi_Gov_acc": 0.8944444444444445, | |
| "eval_vi_Gov_f1": 0.9173789173789174, | |
| "eval_vi_Neu_acc": 0.8686131386861314, | |
| "eval_vi_Neu_f1": 0.89811320754717, | |
| "eval_vi_Soc_acc": 0.9079754601226994, | |
| "eval_vi_Soc_f1": 0.8705882352941177, | |
| "eval_vi_cls_acc": 0.9115853658536586, | |
| "eval_vi_cls_f1": 0.9102841349988715, | |
| "eval_vi_loss": 1.060866117477417, | |
| "eval_vi_runtime": 12.4166, | |
| "eval_vi_samples_per_second": 354.364, | |
| "eval_vi_steps_per_second": 3.705, | |
| "eval_vi_total_cls_tokens": 656, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.068877551020408, | |
| "eval_dan_All_acc": 0.6822878566203365, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.0, | |
| "eval_dan_Gov_f1": 0.0, | |
| "eval_dan_Neu_acc": 0.21052631578947367, | |
| "eval_dan_Neu_f1": 0.34782608695652173, | |
| "eval_dan_Soc_acc": 0.2222222222222222, | |
| "eval_dan_Soc_f1": 0.3636363636363636, | |
| "eval_dan_cls_acc": 0.17142857142857143, | |
| "eval_dan_cls_f1": 0.17786561264822132, | |
| "eval_dan_loss": 1.8786036968231201, | |
| "eval_dan_runtime": 8.8788, | |
| "eval_dan_samples_per_second": 337.884, | |
| "eval_dan_steps_per_second": 3.604, | |
| "eval_dan_total_cls_tokens": 35, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.107142857142858, | |
| "grad_norm": 2.4449799060821533, | |
| "learning_rate": 3.919201197219608e-05, | |
| "loss": 1.4727, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 11.145408163265307, | |
| "grad_norm": 2.4985783100128174, | |
| "learning_rate": 3.9118446891747804e-05, | |
| "loss": 1.4661, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 11.183673469387756, | |
| "grad_norm": 2.525754928588867, | |
| "learning_rate": 3.904470187413838e-05, | |
| "loss": 1.4101, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 11.221938775510203, | |
| "grad_norm": 2.5473992824554443, | |
| "learning_rate": 3.897077785923529e-05, | |
| "loss": 1.4774, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 11.260204081632653, | |
| "grad_norm": 2.2164602279663086, | |
| "learning_rate": 3.889667578918732e-05, | |
| "loss": 1.4419, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 11.298469387755102, | |
| "grad_norm": 2.5873472690582275, | |
| "learning_rate": 3.8822396608412516e-05, | |
| "loss": 1.4434, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 11.33673469387755, | |
| "grad_norm": 2.4988577365875244, | |
| "learning_rate": 3.874794126358617e-05, | |
| "loss": 1.4972, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 11.375, | |
| "grad_norm": 2.3808345794677734, | |
| "learning_rate": 3.867331070362876e-05, | |
| "loss": 1.4863, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 11.41326530612245, | |
| "grad_norm": 2.4077110290527344, | |
| "learning_rate": 3.859850587969387e-05, | |
| "loss": 1.4963, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 11.451530612244898, | |
| "grad_norm": 2.487607002258301, | |
| "learning_rate": 3.852352774515601e-05, | |
| "loss": 1.4351, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.451530612244898, | |
| "eval_en_All_acc": 0.6191306242510077, | |
| "eval_en_Env_acc": 0.9594594594594594, | |
| "eval_en_Env_f1": 0.9726027397260274, | |
| "eval_en_Gov_acc": 0.9655172413793104, | |
| "eval_en_Gov_f1": 0.9491525423728815, | |
| "eval_en_Neu_acc": 0.8918918918918919, | |
| "eval_en_Neu_f1": 0.8918918918918919, | |
| "eval_en_Soc_acc": 0.922077922077922, | |
| "eval_en_Soc_f1": 0.922077922077922, | |
| "eval_en_cls_acc": 0.9328621908127208, | |
| "eval_en_cls_f1": 0.9339312740171808, | |
| "eval_en_loss": 2.2227301597595215, | |
| "eval_en_runtime": 5.5879, | |
| "eval_en_samples_per_second": 335.905, | |
| "eval_en_steps_per_second": 3.579, | |
| "eval_en_total_cls_tokens": 283, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.451530612244898, | |
| "eval_en_oof_All_acc": 0.6148949713558243, | |
| "eval_en_oof_Env_acc": 0.9305555555555556, | |
| "eval_en_oof_Env_f1": 0.9503546099290779, | |
| "eval_en_oof_Gov_acc": 0.9565217391304348, | |
| "eval_en_oof_Gov_f1": 0.9496402877697843, | |
| "eval_en_oof_Neu_acc": 0.8846153846153846, | |
| "eval_en_oof_Neu_f1": 0.8961038961038961, | |
| "eval_en_oof_Soc_acc": 0.9558823529411765, | |
| "eval_en_oof_Soc_f1": 0.9285714285714286, | |
| "eval_en_oof_cls_acc": 0.9303135888501742, | |
| "eval_en_oof_cls_f1": 0.9311675555935468, | |
| "eval_en_oof_loss": 2.2407608032226562, | |
| "eval_en_oof_runtime": 5.5321, | |
| "eval_en_oof_samples_per_second": 339.293, | |
| "eval_en_oof_steps_per_second": 3.615, | |
| "eval_en_oof_total_cls_tokens": 287, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.451530612244898, | |
| "eval_vi_All_acc": 0.7749549085287297, | |
| "eval_vi_Env_acc": 0.9731543624161074, | |
| "eval_vi_Env_f1": 0.9570957095709572, | |
| "eval_vi_Gov_acc": 0.869281045751634, | |
| "eval_vi_Gov_f1": 0.8750000000000001, | |
| "eval_vi_Neu_acc": 0.900523560209424, | |
| "eval_vi_Neu_f1": 0.9076517150395778, | |
| "eval_vi_Soc_acc": 0.8802395209580839, | |
| "eval_vi_Soc_f1": 0.8802395209580839, | |
| "eval_vi_cls_acc": 0.9045454545454545, | |
| "eval_vi_cls_f1": 0.9049967363921547, | |
| "eval_vi_loss": 1.0486485958099365, | |
| "eval_vi_runtime": 12.7271, | |
| "eval_vi_samples_per_second": 345.72, | |
| "eval_vi_steps_per_second": 3.614, | |
| "eval_vi_total_cls_tokens": 660, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.451530612244898, | |
| "eval_dan_All_acc": 0.6732014140764887, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.3, | |
| "eval_dan_Gov_f1": 0.4615384615384615, | |
| "eval_dan_Neu_acc": 0.13043478260869565, | |
| "eval_dan_Neu_f1": 0.23076923076923078, | |
| "eval_dan_Soc_acc": 0.3181818181818182, | |
| "eval_dan_Soc_f1": 0.4827586206896552, | |
| "eval_dan_cls_acc": 0.23636363636363636, | |
| "eval_dan_cls_f1": 0.2937665782493369, | |
| "eval_dan_loss": 1.943729043006897, | |
| "eval_dan_runtime": 8.6286, | |
| "eval_dan_samples_per_second": 347.679, | |
| "eval_dan_steps_per_second": 3.709, | |
| "eval_dan_total_cls_tokens": 55, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.489795918367347, | |
| "grad_norm": 2.4125232696533203, | |
| "learning_rate": 3.8448377255598514e-05, | |
| "loss": 1.4519, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 11.528061224489797, | |
| "grad_norm": 2.622631788253784, | |
| "learning_rate": 3.837305536880139e-05, | |
| "loss": 1.4632, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 11.566326530612244, | |
| "grad_norm": 2.3326470851898193, | |
| "learning_rate": 3.8297563044729014e-05, | |
| "loss": 1.4486, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 11.604591836734693, | |
| "grad_norm": 2.483226776123047, | |
| "learning_rate": 3.822190124551801e-05, | |
| "loss": 1.4299, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 11.642857142857142, | |
| "grad_norm": 2.5282413959503174, | |
| "learning_rate": 3.814607093546489e-05, | |
| "loss": 1.4697, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 11.681122448979592, | |
| "grad_norm": 2.498478651046753, | |
| "learning_rate": 3.8070073081013835e-05, | |
| "loss": 1.4434, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 11.71938775510204, | |
| "grad_norm": 2.402667284011841, | |
| "learning_rate": 3.799390865074434e-05, | |
| "loss": 1.4174, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 11.75765306122449, | |
| "grad_norm": 2.2516682147979736, | |
| "learning_rate": 3.791757861535889e-05, | |
| "loss": 1.4767, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 11.795918367346939, | |
| "grad_norm": 2.71427059173584, | |
| "learning_rate": 3.784108394767055e-05, | |
| "loss": 1.4808, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 11.834183673469388, | |
| "grad_norm": 2.533104419708252, | |
| "learning_rate": 3.776442562259064e-05, | |
| "loss": 1.4811, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 11.834183673469388, | |
| "eval_en_All_acc": 0.6100549218419941, | |
| "eval_en_Env_acc": 0.95, | |
| "eval_en_Env_f1": 0.957983193277311, | |
| "eval_en_Gov_acc": 1.0, | |
| "eval_en_Gov_f1": 0.9473684210526316, | |
| "eval_en_Neu_acc": 0.8591549295774648, | |
| "eval_en_Neu_f1": 0.9037037037037037, | |
| "eval_en_Soc_acc": 0.9285714285714286, | |
| "eval_en_Soc_f1": 0.923076923076923, | |
| "eval_en_cls_acc": 0.9316546762589928, | |
| "eval_en_cls_f1": 0.9330330602776422, | |
| "eval_en_loss": 2.268557548522949, | |
| "eval_en_runtime": 5.6122, | |
| "eval_en_samples_per_second": 334.45, | |
| "eval_en_steps_per_second": 3.564, | |
| "eval_en_total_cls_tokens": 278, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 11.834183673469388, | |
| "eval_en_oof_All_acc": 0.604526568991909, | |
| "eval_en_oof_Env_acc": 0.9090909090909091, | |
| "eval_en_oof_Env_f1": 0.9374999999999999, | |
| "eval_en_oof_Gov_acc": 1.0, | |
| "eval_en_oof_Gov_f1": 0.9846153846153847, | |
| "eval_en_oof_Neu_acc": 0.8488372093023255, | |
| "eval_en_oof_Neu_f1": 0.8848484848484849, | |
| "eval_en_oof_Soc_acc": 0.9722222222222222, | |
| "eval_en_oof_Soc_f1": 0.9150326797385621, | |
| "eval_en_oof_cls_acc": 0.9270833333333334, | |
| "eval_en_oof_cls_f1": 0.9304991373006078, | |
| "eval_en_oof_loss": 2.306154489517212, | |
| "eval_en_oof_runtime": 5.5754, | |
| "eval_en_oof_samples_per_second": 336.658, | |
| "eval_en_oof_steps_per_second": 3.587, | |
| "eval_en_oof_total_cls_tokens": 288, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 11.834183673469388, | |
| "eval_vi_All_acc": 0.7824712865181531, | |
| "eval_vi_Env_acc": 0.9529411764705882, | |
| "eval_vi_Env_f1": 0.9557522123893805, | |
| "eval_vi_Gov_acc": 0.9038461538461539, | |
| "eval_vi_Gov_f1": 0.8980891719745223, | |
| "eval_vi_Neu_acc": 0.8405797101449275, | |
| "eval_vi_Neu_f1": 0.8754716981132076, | |
| "eval_vi_Soc_acc": 0.90625, | |
| "eval_vi_Soc_f1": 0.8787878787878787, | |
| "eval_vi_cls_acc": 0.9038461538461539, | |
| "eval_vi_cls_f1": 0.9020252403162472, | |
| "eval_vi_loss": 1.0164951086044312, | |
| "eval_vi_runtime": 12.6561, | |
| "eval_vi_samples_per_second": 347.658, | |
| "eval_vi_steps_per_second": 3.635, | |
| "eval_vi_total_cls_tokens": 624, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 11.834183673469388, | |
| "eval_dan_All_acc": 0.6639127407751219, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.4, | |
| "eval_dan_Gov_f1": 0.5714285714285715, | |
| "eval_dan_Neu_acc": 0.17391304347826086, | |
| "eval_dan_Neu_f1": 0.29629629629629634, | |
| "eval_dan_Soc_acc": 0.2727272727272727, | |
| "eval_dan_Soc_f1": 0.42857142857142855, | |
| "eval_dan_cls_acc": 0.24444444444444444, | |
| "eval_dan_cls_f1": 0.32407407407407407, | |
| "eval_dan_loss": 1.9950141906738281, | |
| "eval_dan_runtime": 8.5549, | |
| "eval_dan_samples_per_second": 350.677, | |
| "eval_dan_steps_per_second": 3.741, | |
| "eval_dan_total_cls_tokens": 45, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 11.872448979591837, | |
| "grad_norm": 2.3424129486083984, | |
| "learning_rate": 3.768760461711622e-05, | |
| "loss": 1.4143, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 11.910714285714286, | |
| "grad_norm": 2.542257308959961, | |
| "learning_rate": 3.76106219103177e-05, | |
| "loss": 1.4876, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.948979591836736, | |
| "grad_norm": 2.3927953243255615, | |
| "learning_rate": 3.753347848332638e-05, | |
| "loss": 1.435, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 11.987244897959183, | |
| "grad_norm": 2.355803966522217, | |
| "learning_rate": 3.7456175319321854e-05, | |
| "loss": 1.4315, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 12.02295918367347, | |
| "grad_norm": 2.4041826725006104, | |
| "learning_rate": 3.737871340351957e-05, | |
| "loss": 1.3748, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 12.061224489795919, | |
| "grad_norm": 2.5043528079986572, | |
| "learning_rate": 3.730109372315822e-05, | |
| "loss": 1.459, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 12.099489795918368, | |
| "grad_norm": 2.2725017070770264, | |
| "learning_rate": 3.7223317267487224e-05, | |
| "loss": 1.4252, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 12.137755102040817, | |
| "grad_norm": 2.411857843399048, | |
| "learning_rate": 3.7145385027754014e-05, | |
| "loss": 1.4654, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 12.176020408163266, | |
| "grad_norm": 2.5134103298187256, | |
| "learning_rate": 3.7067297997191494e-05, | |
| "loss": 1.438, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 12.214285714285714, | |
| "grad_norm": 2.5114264488220215, | |
| "learning_rate": 3.698905717100536e-05, | |
| "loss": 1.4475, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 12.214285714285714, | |
| "eval_en_All_acc": 0.6050456253354805, | |
| "eval_en_Env_acc": 0.9726027397260274, | |
| "eval_en_Env_f1": 0.9861111111111112, | |
| "eval_en_Gov_acc": 0.9552238805970149, | |
| "eval_en_Gov_f1": 0.9411764705882353, | |
| "eval_en_Neu_acc": 0.9090909090909091, | |
| "eval_en_Neu_f1": 0.8988764044943819, | |
| "eval_en_Soc_acc": 0.8933333333333333, | |
| "eval_en_Soc_f1": 0.9054054054054055, | |
| "eval_en_cls_acc": 0.9306930693069307, | |
| "eval_en_cls_f1": 0.9328923478997835, | |
| "eval_en_loss": 2.289191484451294, | |
| "eval_en_runtime": 5.6563, | |
| "eval_en_samples_per_second": 331.84, | |
| "eval_en_steps_per_second": 3.536, | |
| "eval_en_total_cls_tokens": 303, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 12.214285714285714, | |
| "eval_en_oof_All_acc": 0.618796992481203, | |
| "eval_en_oof_Env_acc": 0.971830985915493, | |
| "eval_en_oof_Env_f1": 0.9583333333333334, | |
| "eval_en_oof_Gov_acc": 0.9375, | |
| "eval_en_oof_Gov_f1": 0.9375, | |
| "eval_en_oof_Neu_acc": 0.9178082191780822, | |
| "eval_en_oof_Neu_f1": 0.8933333333333333, | |
| "eval_en_oof_Soc_acc": 0.9090909090909091, | |
| "eval_en_oof_Soc_f1": 0.9523809523809523, | |
| "eval_en_oof_cls_acc": 0.9343065693430657, | |
| "eval_en_oof_cls_f1": 0.9353869047619048, | |
| "eval_en_oof_loss": 2.2200918197631836, | |
| "eval_en_oof_runtime": 5.5325, | |
| "eval_en_oof_samples_per_second": 339.27, | |
| "eval_en_oof_steps_per_second": 3.615, | |
| "eval_en_oof_total_cls_tokens": 274, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 12.214285714285714, | |
| "eval_vi_All_acc": 0.7781892051736995, | |
| "eval_vi_Env_acc": 0.95, | |
| "eval_vi_Env_f1": 0.9470404984423676, | |
| "eval_vi_Gov_acc": 0.8789808917197452, | |
| "eval_vi_Gov_f1": 0.8903225806451612, | |
| "eval_vi_Neu_acc": 0.879746835443038, | |
| "eval_vi_Neu_f1": 0.8553846153846154, | |
| "eval_vi_Soc_acc": 0.8571428571428571, | |
| "eval_vi_Soc_f1": 0.872093023255814, | |
| "eval_vi_cls_acc": 0.8907692307692308, | |
| "eval_vi_cls_f1": 0.8912101794319895, | |
| "eval_vi_loss": 1.0409399271011353, | |
| "eval_vi_runtime": 12.6029, | |
| "eval_vi_samples_per_second": 349.127, | |
| "eval_vi_steps_per_second": 3.65, | |
| "eval_vi_total_cls_tokens": 650, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 12.214285714285714, | |
| "eval_dan_All_acc": 0.6705528394133132, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.25, | |
| "eval_dan_Gov_f1": 0.375, | |
| "eval_dan_Neu_acc": 0.23529411764705882, | |
| "eval_dan_Neu_f1": 0.38095238095238093, | |
| "eval_dan_Soc_acc": 0.125, | |
| "eval_dan_Soc_f1": 0.2222222222222222, | |
| "eval_dan_cls_acc": 0.1836734693877551, | |
| "eval_dan_cls_f1": 0.24454365079365079, | |
| "eval_dan_loss": 1.9355813264846802, | |
| "eval_dan_runtime": 8.7771, | |
| "eval_dan_samples_per_second": 341.8, | |
| "eval_dan_steps_per_second": 3.646, | |
| "eval_dan_total_cls_tokens": 49, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 12.252551020408163, | |
| "grad_norm": 2.309133529663086, | |
| "learning_rate": 3.6910663546361395e-05, | |
| "loss": 1.411, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 12.290816326530612, | |
| "grad_norm": 2.5108816623687744, | |
| "learning_rate": 3.6832118122372766e-05, | |
| "loss": 1.4056, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 12.329081632653061, | |
| "grad_norm": 2.3962154388427734, | |
| "learning_rate": 3.67534219000873e-05, | |
| "loss": 1.3743, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 12.36734693877551, | |
| "grad_norm": 2.345639705657959, | |
| "learning_rate": 3.6674575882474725e-05, | |
| "loss": 1.4254, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 12.40561224489796, | |
| "grad_norm": 2.4741663932800293, | |
| "learning_rate": 3.659558107441389e-05, | |
| "loss": 1.4286, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 12.443877551020408, | |
| "grad_norm": 2.484936237335205, | |
| "learning_rate": 3.651643848267994e-05, | |
| "loss": 1.4491, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 12.482142857142858, | |
| "grad_norm": 2.623774766921997, | |
| "learning_rate": 3.6437149115931514e-05, | |
| "loss": 1.4337, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 12.520408163265307, | |
| "grad_norm": 2.4078221321105957, | |
| "learning_rate": 3.635771398469785e-05, | |
| "loss": 1.4404, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 12.558673469387756, | |
| "grad_norm": 2.395644187927246, | |
| "learning_rate": 3.6278134101365944e-05, | |
| "loss": 1.4538, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 12.596938775510203, | |
| "grad_norm": 2.4204623699188232, | |
| "learning_rate": 3.6198410480167646e-05, | |
| "loss": 1.4447, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 12.596938775510203, | |
| "eval_en_All_acc": 0.6090754154239455, | |
| "eval_en_Env_acc": 0.9508196721311475, | |
| "eval_en_Env_f1": 0.9354838709677418, | |
| "eval_en_Gov_acc": 0.9705882352941176, | |
| "eval_en_Gov_f1": 0.9565217391304348, | |
| "eval_en_Neu_acc": 0.7816091954022989, | |
| "eval_en_Neu_f1": 0.84472049689441, | |
| "eval_en_Soc_acc": 0.9516129032258065, | |
| "eval_en_Soc_f1": 0.887218045112782, | |
| "eval_en_cls_acc": 0.9028776978417267, | |
| "eval_en_cls_f1": 0.905986038026342, | |
| "eval_en_loss": 2.2940428256988525, | |
| "eval_en_runtime": 5.5647, | |
| "eval_en_samples_per_second": 337.306, | |
| "eval_en_steps_per_second": 3.594, | |
| "eval_en_total_cls_tokens": 278, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 12.596938775510203, | |
| "eval_en_oof_All_acc": 0.6066298342541436, | |
| "eval_en_oof_Env_acc": 0.984375, | |
| "eval_en_oof_Env_f1": 0.984375, | |
| "eval_en_oof_Gov_acc": 0.9365079365079365, | |
| "eval_en_oof_Gov_f1": 0.944, | |
| "eval_en_oof_Neu_acc": 0.8513513513513513, | |
| "eval_en_oof_Neu_f1": 0.8936170212765957, | |
| "eval_en_oof_Soc_acc": 0.9710144927536232, | |
| "eval_en_oof_Soc_f1": 0.9178082191780821, | |
| "eval_en_oof_cls_acc": 0.9333333333333333, | |
| "eval_en_oof_cls_f1": 0.9349500601136693, | |
| "eval_en_oof_loss": 2.281923532485962, | |
| "eval_en_oof_runtime": 5.6151, | |
| "eval_en_oof_samples_per_second": 334.279, | |
| "eval_en_oof_steps_per_second": 3.562, | |
| "eval_en_oof_total_cls_tokens": 270, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 12.596938775510203, | |
| "eval_vi_All_acc": 0.7759637421780444, | |
| "eval_vi_Env_acc": 0.9767441860465116, | |
| "eval_vi_Env_f1": 0.9464788732394366, | |
| "eval_vi_Gov_acc": 0.875, | |
| "eval_vi_Gov_f1": 0.8832807570977919, | |
| "eval_vi_Neu_acc": 0.8353658536585366, | |
| "eval_vi_Neu_f1": 0.8810289389067524, | |
| "eval_vi_Soc_acc": 0.8666666666666667, | |
| "eval_vi_Soc_f1": 0.8414239482200647, | |
| "eval_vi_cls_acc": 0.8900928792569659, | |
| "eval_vi_cls_f1": 0.8880531293660113, | |
| "eval_vi_loss": 1.042203426361084, | |
| "eval_vi_runtime": 12.7253, | |
| "eval_vi_samples_per_second": 345.768, | |
| "eval_vi_steps_per_second": 3.615, | |
| "eval_vi_total_cls_tokens": 646, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 12.596938775510203, | |
| "eval_dan_All_acc": 0.6718742713239751, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2857142857142857, | |
| "eval_dan_Gov_f1": 0.4444444444444445, | |
| "eval_dan_Neu_acc": 0.3157894736842105, | |
| "eval_dan_Neu_f1": 0.4799999999999999, | |
| "eval_dan_Soc_acc": 0.1111111111111111, | |
| "eval_dan_Soc_f1": 0.19999999999999998, | |
| "eval_dan_cls_acc": 0.23076923076923078, | |
| "eval_dan_cls_f1": 0.2811111111111111, | |
| "eval_dan_loss": 2.0078485012054443, | |
| "eval_dan_runtime": 8.6611, | |
| "eval_dan_samples_per_second": 346.376, | |
| "eval_dan_steps_per_second": 3.695, | |
| "eval_dan_total_cls_tokens": 52, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 12.635204081632653, | |
| "grad_norm": 2.3494927883148193, | |
| "learning_rate": 3.611854413716669e-05, | |
| "loss": 1.4675, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 12.673469387755102, | |
| "grad_norm": 2.627265453338623, | |
| "learning_rate": 3.6038536090245786e-05, | |
| "loss": 1.4502, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 12.71173469387755, | |
| "grad_norm": 2.4417901039123535, | |
| "learning_rate": 3.595838735909364e-05, | |
| "loss": 1.4433, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "grad_norm": 2.4412739276885986, | |
| "learning_rate": 3.587809896519197e-05, | |
| "loss": 1.4299, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 12.78826530612245, | |
| "grad_norm": 2.4363300800323486, | |
| "learning_rate": 3.579767193180244e-05, | |
| "loss": 1.4496, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 12.826530612244898, | |
| "grad_norm": 2.3639259338378906, | |
| "learning_rate": 3.5717107283953663e-05, | |
| "loss": 1.4313, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 12.864795918367347, | |
| "grad_norm": 2.370990514755249, | |
| "learning_rate": 3.563640604842814e-05, | |
| "loss": 1.3992, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 12.903061224489797, | |
| "grad_norm": 2.3328969478607178, | |
| "learning_rate": 3.555556925374914e-05, | |
| "loss": 1.4056, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 12.941326530612244, | |
| "grad_norm": 2.4815256595611572, | |
| "learning_rate": 3.547459793016761e-05, | |
| "loss": 1.4082, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 12.979591836734693, | |
| "grad_norm": 2.5033936500549316, | |
| "learning_rate": 3.5393493109649045e-05, | |
| "loss": 1.4574, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 12.979591836734693, | |
| "eval_en_All_acc": 0.6223203705698589, | |
| "eval_en_Env_acc": 0.9850746268656716, | |
| "eval_en_Env_f1": 0.949640287769784, | |
| "eval_en_Gov_acc": 0.9701492537313433, | |
| "eval_en_Gov_f1": 0.9558823529411764, | |
| "eval_en_Neu_acc": 0.8307692307692308, | |
| "eval_en_Neu_f1": 0.8780487804878049, | |
| "eval_en_Soc_acc": 0.961038961038961, | |
| "eval_en_Soc_f1": 0.961038961038961, | |
| "eval_en_cls_acc": 0.9384057971014492, | |
| "eval_en_cls_f1": 0.9361525955594316, | |
| "eval_en_loss": 2.215664863586426, | |
| "eval_en_runtime": 5.5904, | |
| "eval_en_samples_per_second": 335.751, | |
| "eval_en_steps_per_second": 3.578, | |
| "eval_en_total_cls_tokens": 276, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 12.979591836734693, | |
| "eval_en_oof_All_acc": 0.6089337485235692, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9827586206896551, | |
| "eval_en_oof_Gov_acc": 0.9855072463768116, | |
| "eval_en_oof_Gov_f1": 0.951048951048951, | |
| "eval_en_oof_Neu_acc": 0.8333333333333334, | |
| "eval_en_oof_Neu_f1": 0.8943089430894309, | |
| "eval_en_oof_Soc_acc": 0.9852941176470589, | |
| "eval_en_oof_Soc_f1": 0.9710144927536232, | |
| "eval_en_oof_cls_acc": 0.95, | |
| "eval_en_oof_cls_f1": 0.9497827518954152, | |
| "eval_en_oof_loss": 2.3029184341430664, | |
| "eval_en_oof_runtime": 5.5842, | |
| "eval_en_oof_samples_per_second": 336.129, | |
| "eval_en_oof_steps_per_second": 3.582, | |
| "eval_en_oof_total_cls_tokens": 260, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 12.979591836734693, | |
| "eval_vi_All_acc": 0.7809259306443804, | |
| "eval_vi_Env_acc": 1.0, | |
| "eval_vi_Env_f1": 0.9480122324159022, | |
| "eval_vi_Gov_acc": 0.8895348837209303, | |
| "eval_vi_Gov_f1": 0.8999999999999999, | |
| "eval_vi_Neu_acc": 0.8674698795180723, | |
| "eval_vi_Neu_f1": 0.9142857142857144, | |
| "eval_vi_Soc_acc": 0.910828025477707, | |
| "eval_vi_Soc_f1": 0.8993710691823898, | |
| "eval_vi_cls_acc": 0.9153846153846154, | |
| "eval_vi_cls_f1": 0.9154172539710015, | |
| "eval_vi_loss": 1.0044718980789185, | |
| "eval_vi_runtime": 12.7452, | |
| "eval_vi_samples_per_second": 345.229, | |
| "eval_vi_steps_per_second": 3.609, | |
| "eval_vi_total_cls_tokens": 650, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 12.979591836734693, | |
| "eval_dan_All_acc": 0.6659278755136907, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.15384615384615385, | |
| "eval_dan_Gov_f1": 0.2666666666666667, | |
| "eval_dan_Neu_acc": 0.3333333333333333, | |
| "eval_dan_Neu_f1": 0.48, | |
| "eval_dan_Soc_acc": 0.23529411764705882, | |
| "eval_dan_Soc_f1": 0.38095238095238093, | |
| "eval_dan_cls_acc": 0.23076923076923078, | |
| "eval_dan_cls_f1": 0.2819047619047619, | |
| "eval_dan_loss": 1.9854305982589722, | |
| "eval_dan_runtime": 8.6916, | |
| "eval_dan_samples_per_second": 345.162, | |
| "eval_dan_steps_per_second": 3.682, | |
| "eval_dan_total_cls_tokens": 52, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 13.01530612244898, | |
| "grad_norm": 2.6840760707855225, | |
| "learning_rate": 3.531225582586035e-05, | |
| "loss": 1.3618, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 13.053571428571429, | |
| "grad_norm": 2.3670849800109863, | |
| "learning_rate": 3.523088711415665e-05, | |
| "loss": 1.4243, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 13.091836734693878, | |
| "grad_norm": 2.5354480743408203, | |
| "learning_rate": 3.5149388011568064e-05, | |
| "loss": 1.4077, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 13.130102040816327, | |
| "grad_norm": 2.486201286315918, | |
| "learning_rate": 3.506775955678656e-05, | |
| "loss": 1.4487, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 13.168367346938776, | |
| "grad_norm": 2.28735089302063, | |
| "learning_rate": 3.498600279015266e-05, | |
| "loss": 1.4582, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 13.206632653061224, | |
| "grad_norm": 2.408360481262207, | |
| "learning_rate": 3.4904118753642184e-05, | |
| "loss": 1.4102, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 13.244897959183673, | |
| "grad_norm": 2.4393131732940674, | |
| "learning_rate": 3.482210849085302e-05, | |
| "loss": 1.3934, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 13.283163265306122, | |
| "grad_norm": 2.3820347785949707, | |
| "learning_rate": 3.473997304699175e-05, | |
| "loss": 1.373, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 13.321428571428571, | |
| "grad_norm": 2.408625602722168, | |
| "learning_rate": 3.4657713468860405e-05, | |
| "loss": 1.3831, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 13.35969387755102, | |
| "grad_norm": 2.4793286323547363, | |
| "learning_rate": 3.4575330804843045e-05, | |
| "loss": 1.3763, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.35969387755102, | |
| "eval_en_All_acc": 0.6234469576298184, | |
| "eval_en_Env_acc": 0.9577464788732394, | |
| "eval_en_Env_f1": 0.9577464788732394, | |
| "eval_en_Gov_acc": 0.9655172413793104, | |
| "eval_en_Gov_f1": 0.9655172413793104, | |
| "eval_en_Neu_acc": 0.918918918918919, | |
| "eval_en_Neu_f1": 0.912751677852349, | |
| "eval_en_Soc_acc": 0.9538461538461539, | |
| "eval_en_Soc_f1": 0.9612403100775193, | |
| "eval_en_cls_acc": 0.9477611940298507, | |
| "eval_en_cls_f1": 0.9493139270456046, | |
| "eval_en_loss": 2.193057060241699, | |
| "eval_en_runtime": 5.5847, | |
| "eval_en_samples_per_second": 336.095, | |
| "eval_en_steps_per_second": 3.581, | |
| "eval_en_total_cls_tokens": 268, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.35969387755102, | |
| "eval_en_oof_All_acc": 0.6018124249372202, | |
| "eval_en_oof_Env_acc": 0.9452054794520548, | |
| "eval_en_oof_Env_f1": 0.9583333333333334, | |
| "eval_en_oof_Gov_acc": 0.9375, | |
| "eval_en_oof_Gov_f1": 0.9183673469387755, | |
| "eval_en_oof_Neu_acc": 0.9259259259259259, | |
| "eval_en_oof_Neu_f1": 0.9146341463414634, | |
| "eval_en_oof_Soc_acc": 0.9508196721311475, | |
| "eval_en_oof_Soc_f1": 0.9666666666666667, | |
| "eval_en_oof_cls_acc": 0.9391634980988594, | |
| "eval_en_oof_cls_f1": 0.9395003733200598, | |
| "eval_en_oof_loss": 2.332740545272827, | |
| "eval_en_oof_runtime": 5.5064, | |
| "eval_en_oof_samples_per_second": 340.878, | |
| "eval_en_oof_steps_per_second": 3.632, | |
| "eval_en_oof_total_cls_tokens": 263, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.35969387755102, | |
| "eval_vi_All_acc": 0.7865559995901219, | |
| "eval_vi_Env_acc": 0.9271523178807947, | |
| "eval_vi_Env_f1": 0.9395973154362416, | |
| "eval_vi_Gov_acc": 0.8657718120805369, | |
| "eval_vi_Gov_f1": 0.8865979381443297, | |
| "eval_vi_Neu_acc": 0.8486842105263158, | |
| "eval_vi_Neu_f1": 0.8543046357615894, | |
| "eval_vi_Soc_acc": 0.9102564102564102, | |
| "eval_vi_Soc_f1": 0.8738461538461538, | |
| "eval_vi_cls_acc": 0.8881578947368421, | |
| "eval_vi_cls_f1": 0.8885865107970787, | |
| "eval_vi_loss": 1.0093955993652344, | |
| "eval_vi_runtime": 12.4406, | |
| "eval_vi_samples_per_second": 353.68, | |
| "eval_vi_steps_per_second": 3.698, | |
| "eval_vi_total_cls_tokens": 608, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.35969387755102, | |
| "eval_dan_All_acc": 0.6721556886227545, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.18181818181818182, | |
| "eval_dan_Gov_f1": 0.3076923076923077, | |
| "eval_dan_Neu_acc": 0.42857142857142855, | |
| "eval_dan_Neu_f1": 0.5625, | |
| "eval_dan_Soc_acc": 0.21428571428571427, | |
| "eval_dan_Soc_f1": 0.35294117647058826, | |
| "eval_dan_cls_acc": 0.2978723404255319, | |
| "eval_dan_cls_f1": 0.305783371040724, | |
| "eval_dan_loss": 1.9672952890396118, | |
| "eval_dan_runtime": 8.9976, | |
| "eval_dan_samples_per_second": 333.422, | |
| "eval_dan_steps_per_second": 3.557, | |
| "eval_dan_total_cls_tokens": 47, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.39795918367347, | |
| "grad_norm": 2.5290422439575195, | |
| "learning_rate": 3.4492826104892475e-05, | |
| "loss": 1.4169, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 13.436224489795919, | |
| "grad_norm": 2.4342174530029297, | |
| "learning_rate": 3.441020042051681e-05, | |
| "loss": 1.4056, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 13.474489795918368, | |
| "grad_norm": 2.4106812477111816, | |
| "learning_rate": 3.432745480476607e-05, | |
| "loss": 1.4389, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 13.512755102040817, | |
| "grad_norm": 2.5299341678619385, | |
| "learning_rate": 3.4244590312218825e-05, | |
| "loss": 1.404, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 13.551020408163264, | |
| "grad_norm": 2.3914735317230225, | |
| "learning_rate": 3.4161607998968683e-05, | |
| "loss": 1.4288, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 13.589285714285714, | |
| "grad_norm": 2.3816561698913574, | |
| "learning_rate": 3.407850892261085e-05, | |
| "loss": 1.3935, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 13.627551020408163, | |
| "grad_norm": 2.543315887451172, | |
| "learning_rate": 3.399529414222866e-05, | |
| "loss": 1.4222, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 13.665816326530612, | |
| "grad_norm": 2.63822865486145, | |
| "learning_rate": 3.39119647183801e-05, | |
| "loss": 1.3942, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 13.704081632653061, | |
| "grad_norm": 2.4821722507476807, | |
| "learning_rate": 3.3828521713084235e-05, | |
| "loss": 1.4157, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 13.74234693877551, | |
| "grad_norm": 2.4227659702301025, | |
| "learning_rate": 3.374496618980772e-05, | |
| "loss": 1.3993, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 13.74234693877551, | |
| "eval_en_All_acc": 0.6091571279916753, | |
| "eval_en_Env_acc": 0.9411764705882353, | |
| "eval_en_Env_f1": 0.962406015037594, | |
| "eval_en_Gov_acc": 0.9705882352941176, | |
| "eval_en_Gov_f1": 0.9565217391304348, | |
| "eval_en_Neu_acc": 0.7796610169491526, | |
| "eval_en_Neu_f1": 0.8141592920353983, | |
| "eval_en_Soc_acc": 0.9620253164556962, | |
| "eval_en_Soc_f1": 0.926829268292683, | |
| "eval_en_cls_acc": 0.9197080291970803, | |
| "eval_en_cls_f1": 0.9149790786240275, | |
| "eval_en_loss": 2.2553272247314453, | |
| "eval_en_runtime": 5.5781, | |
| "eval_en_samples_per_second": 336.493, | |
| "eval_en_steps_per_second": 3.585, | |
| "eval_en_total_cls_tokens": 274, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 13.74234693877551, | |
| "eval_en_oof_All_acc": 0.6112254848846029, | |
| "eval_en_oof_Env_acc": 0.9655172413793104, | |
| "eval_en_oof_Env_f1": 0.9710982658959537, | |
| "eval_en_oof_Gov_acc": 1.0, | |
| "eval_en_oof_Gov_f1": 0.923076923076923, | |
| "eval_en_oof_Neu_acc": 0.8333333333333334, | |
| "eval_en_oof_Neu_f1": 0.8695652173913043, | |
| "eval_en_oof_Soc_acc": 0.9142857142857143, | |
| "eval_en_oof_Soc_f1": 0.9343065693430657, | |
| "eval_en_oof_cls_acc": 0.9298892988929889, | |
| "eval_en_oof_cls_f1": 0.9245117439268117, | |
| "eval_en_oof_loss": 2.2628135681152344, | |
| "eval_en_oof_runtime": 5.6147, | |
| "eval_en_oof_samples_per_second": 334.298, | |
| "eval_en_oof_steps_per_second": 3.562, | |
| "eval_en_oof_total_cls_tokens": 271, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 13.74234693877551, | |
| "eval_vi_All_acc": 0.7816521271969096, | |
| "eval_vi_Env_acc": 0.9343065693430657, | |
| "eval_vi_Env_f1": 0.9377289377289377, | |
| "eval_vi_Gov_acc": 0.9473684210526315, | |
| "eval_vi_Gov_f1": 0.9257142857142858, | |
| "eval_vi_Neu_acc": 0.8323353293413174, | |
| "eval_vi_Neu_f1": 0.8769716088328076, | |
| "eval_vi_Soc_acc": 0.8947368421052632, | |
| "eval_vi_Soc_f1": 0.8662420382165605, | |
| "eval_vi_cls_acc": 0.9011164274322169, | |
| "eval_vi_cls_f1": 0.9016642176231479, | |
| "eval_vi_loss": 1.030401587486267, | |
| "eval_vi_runtime": 12.2825, | |
| "eval_vi_samples_per_second": 358.232, | |
| "eval_vi_steps_per_second": 3.745, | |
| "eval_vi_total_cls_tokens": 627, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 13.74234693877551, | |
| "eval_dan_All_acc": 0.6747295603324203, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3333333333333333, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.24, | |
| "eval_dan_Neu_f1": 0.3870967741935484, | |
| "eval_dan_Soc_acc": 0.46153846153846156, | |
| "eval_dan_Soc_f1": 0.631578947368421, | |
| "eval_dan_cls_acc": 0.2962962962962963, | |
| "eval_dan_cls_f1": 0.3796689303904923, | |
| "eval_dan_loss": 1.961978554725647, | |
| "eval_dan_runtime": 9.0847, | |
| "eval_dan_samples_per_second": 330.226, | |
| "eval_dan_steps_per_second": 3.522, | |
| "eval_dan_total_cls_tokens": 54, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 13.78061224489796, | |
| "grad_norm": 2.6046035289764404, | |
| "learning_rate": 3.366129921345124e-05, | |
| "loss": 1.4115, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 13.818877551020408, | |
| "grad_norm": 2.4044082164764404, | |
| "learning_rate": 3.357752185033592e-05, | |
| "loss": 1.4624, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 13.857142857142858, | |
| "grad_norm": 2.198232889175415, | |
| "learning_rate": 3.349363516818975e-05, | |
| "loss": 1.4001, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 13.895408163265307, | |
| "grad_norm": 2.537644863128662, | |
| "learning_rate": 3.340964023613396e-05, | |
| "loss": 1.4654, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 13.933673469387756, | |
| "grad_norm": 2.4458909034729004, | |
| "learning_rate": 3.332553812466943e-05, | |
| "loss": 1.4417, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 13.971938775510203, | |
| "grad_norm": 2.502185106277466, | |
| "learning_rate": 3.3241329905662985e-05, | |
| "loss": 1.3898, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 14.00765306122449, | |
| "grad_norm": 2.3415753841400146, | |
| "learning_rate": 3.315701665233382e-05, | |
| "loss": 1.3333, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 14.045918367346939, | |
| "grad_norm": 2.5160932540893555, | |
| "learning_rate": 3.3072599439239746e-05, | |
| "loss": 1.4225, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 14.084183673469388, | |
| "grad_norm": 2.6143288612365723, | |
| "learning_rate": 3.298807934226352e-05, | |
| "loss": 1.4214, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 14.122448979591837, | |
| "grad_norm": 2.398244857788086, | |
| "learning_rate": 3.290345743859915e-05, | |
| "loss": 1.4228, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 14.122448979591837, | |
| "eval_en_All_acc": 0.6157985363753766, | |
| "eval_en_Env_acc": 0.9436619718309859, | |
| "eval_en_Env_f1": 0.9571428571428571, | |
| "eval_en_Gov_acc": 0.96, | |
| "eval_en_Gov_f1": 0.9473684210526316, | |
| "eval_en_Neu_acc": 0.881578947368421, | |
| "eval_en_Neu_f1": 0.8933333333333332, | |
| "eval_en_Soc_acc": 0.9305555555555556, | |
| "eval_en_Soc_f1": 0.9178082191780821, | |
| "eval_en_cls_acc": 0.9285714285714286, | |
| "eval_en_cls_f1": 0.928913207676726, | |
| "eval_en_loss": 2.2351953983306885, | |
| "eval_en_runtime": 5.5986, | |
| "eval_en_samples_per_second": 335.262, | |
| "eval_en_steps_per_second": 3.572, | |
| "eval_en_total_cls_tokens": 294, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 14.122448979591837, | |
| "eval_en_oof_All_acc": 0.612094709897611, | |
| "eval_en_oof_Env_acc": 0.9850746268656716, | |
| "eval_en_oof_Env_f1": 0.9777777777777777, | |
| "eval_en_oof_Gov_acc": 0.9841269841269841, | |
| "eval_en_oof_Gov_f1": 0.9393939393939393, | |
| "eval_en_oof_Neu_acc": 0.8266666666666667, | |
| "eval_en_oof_Neu_f1": 0.8732394366197183, | |
| "eval_en_oof_Soc_acc": 0.9130434782608695, | |
| "eval_en_oof_Soc_f1": 0.9064748201438848, | |
| "eval_en_oof_cls_acc": 0.9233576642335767, | |
| "eval_en_oof_cls_f1": 0.92422149348383, | |
| "eval_en_oof_loss": 2.2446963787078857, | |
| "eval_en_oof_runtime": 5.5366, | |
| "eval_en_oof_samples_per_second": 339.017, | |
| "eval_en_oof_steps_per_second": 3.612, | |
| "eval_en_oof_total_cls_tokens": 274, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 14.122448979591837, | |
| "eval_vi_All_acc": 0.7894573723494925, | |
| "eval_vi_Env_acc": 0.901840490797546, | |
| "eval_vi_Env_f1": 0.9274447949526813, | |
| "eval_vi_Gov_acc": 0.9490445859872612, | |
| "eval_vi_Gov_f1": 0.91131498470948, | |
| "eval_vi_Neu_acc": 0.874251497005988, | |
| "eval_vi_Neu_f1": 0.8848484848484848, | |
| "eval_vi_Soc_acc": 0.8675496688741722, | |
| "eval_vi_Soc_f1": 0.8675496688741722, | |
| "eval_vi_cls_acc": 0.8981191222570533, | |
| "eval_vi_cls_f1": 0.8977894833462046, | |
| "eval_vi_loss": 0.9798475503921509, | |
| "eval_vi_runtime": 12.7093, | |
| "eval_vi_samples_per_second": 346.204, | |
| "eval_vi_steps_per_second": 3.619, | |
| "eval_vi_total_cls_tokens": 638, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 14.122448979591837, | |
| "eval_dan_All_acc": 0.6739242887373619, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.16666666666666666, | |
| "eval_dan_Gov_f1": 0.2857142857142857, | |
| "eval_dan_Neu_acc": 0.3333333333333333, | |
| "eval_dan_Neu_f1": 0.5, | |
| "eval_dan_Soc_acc": 0.4, | |
| "eval_dan_Soc_f1": 0.5714285714285715, | |
| "eval_dan_cls_acc": 0.3333333333333333, | |
| "eval_dan_cls_f1": 0.5059523809523809, | |
| "eval_dan_loss": 1.959991455078125, | |
| "eval_dan_runtime": 8.5379, | |
| "eval_dan_samples_per_second": 351.375, | |
| "eval_dan_steps_per_second": 3.748, | |
| "eval_dan_total_cls_tokens": 39, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 14.160714285714286, | |
| "grad_norm": 2.5617339611053467, | |
| "learning_rate": 3.281873480673815e-05, | |
| "loss": 1.3894, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 14.198979591836734, | |
| "grad_norm": 2.284759759902954, | |
| "learning_rate": 3.2733912526455786e-05, | |
| "loss": 1.3893, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 14.237244897959183, | |
| "grad_norm": 2.2918496131896973, | |
| "learning_rate": 3.264899167879734e-05, | |
| "loss": 1.3461, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 14.275510204081632, | |
| "grad_norm": 2.3468589782714844, | |
| "learning_rate": 3.25639733460643e-05, | |
| "loss": 1.4239, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 14.313775510204081, | |
| "grad_norm": 2.6296956539154053, | |
| "learning_rate": 3.2478858611800605e-05, | |
| "loss": 1.3948, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 14.35204081632653, | |
| "grad_norm": 2.4912006855010986, | |
| "learning_rate": 3.239364856077882e-05, | |
| "loss": 1.4223, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 14.39030612244898, | |
| "grad_norm": 2.337029457092285, | |
| "learning_rate": 3.230834427898627e-05, | |
| "loss": 1.4526, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 14.428571428571429, | |
| "grad_norm": 2.3849709033966064, | |
| "learning_rate": 3.222294685361126e-05, | |
| "loss": 1.3753, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 14.466836734693878, | |
| "grad_norm": 2.328383207321167, | |
| "learning_rate": 3.21374573730292e-05, | |
| "loss": 1.4105, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 14.505102040816327, | |
| "grad_norm": 2.3454034328460693, | |
| "learning_rate": 3.205187692678872e-05, | |
| "loss": 1.3866, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 14.505102040816327, | |
| "eval_en_All_acc": 0.6097055616139586, | |
| "eval_en_Env_acc": 0.9714285714285714, | |
| "eval_en_Env_f1": 0.9784172661870504, | |
| "eval_en_Gov_acc": 0.971830985915493, | |
| "eval_en_Gov_f1": 0.971830985915493, | |
| "eval_en_Neu_acc": 0.967741935483871, | |
| "eval_en_Neu_f1": 0.8888888888888888, | |
| "eval_en_Soc_acc": 0.8405797101449275, | |
| "eval_en_Soc_f1": 0.9062499999999999, | |
| "eval_en_cls_acc": 0.9375, | |
| "eval_en_cls_f1": 0.9363467852478581, | |
| "eval_en_loss": 2.2652902603149414, | |
| "eval_en_runtime": 5.5934, | |
| "eval_en_samples_per_second": 335.576, | |
| "eval_en_steps_per_second": 3.576, | |
| "eval_en_total_cls_tokens": 272, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 14.505102040816327, | |
| "eval_en_oof_All_acc": 0.6099775664993057, | |
| "eval_en_oof_Env_acc": 0.958904109589041, | |
| "eval_en_oof_Env_f1": 0.9722222222222222, | |
| "eval_en_oof_Gov_acc": 0.94, | |
| "eval_en_oof_Gov_f1": 0.94, | |
| "eval_en_oof_Neu_acc": 0.9193548387096774, | |
| "eval_en_oof_Neu_f1": 0.890625, | |
| "eval_en_oof_Soc_acc": 0.9166666666666666, | |
| "eval_en_oof_Soc_f1": 0.9295774647887323, | |
| "eval_en_oof_cls_acc": 0.933852140077821, | |
| "eval_en_oof_cls_f1": 0.9331061717527386, | |
| "eval_en_oof_loss": 2.2664647102355957, | |
| "eval_en_oof_runtime": 5.574, | |
| "eval_en_oof_samples_per_second": 336.74, | |
| "eval_en_oof_steps_per_second": 3.588, | |
| "eval_en_oof_total_cls_tokens": 257, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 14.505102040816327, | |
| "eval_vi_All_acc": 0.7793844726260439, | |
| "eval_vi_Env_acc": 0.9705882352941176, | |
| "eval_vi_Env_f1": 0.9593023255813955, | |
| "eval_vi_Gov_acc": 0.9055555555555556, | |
| "eval_vi_Gov_f1": 0.9106145251396648, | |
| "eval_vi_Neu_acc": 0.9036144578313253, | |
| "eval_vi_Neu_f1": 0.9146341463414634, | |
| "eval_vi_Soc_acc": 0.8982035928143712, | |
| "eval_vi_Soc_f1": 0.8928571428571429, | |
| "eval_vi_cls_acc": 0.9194729136163983, | |
| "eval_vi_cls_f1": 0.9193520349799167, | |
| "eval_vi_loss": 1.0355857610702515, | |
| "eval_vi_runtime": 12.749, | |
| "eval_vi_samples_per_second": 345.124, | |
| "eval_vi_steps_per_second": 3.608, | |
| "eval_vi_total_cls_tokens": 683, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 14.505102040816327, | |
| "eval_dan_All_acc": 0.6667898383371824, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2857142857142857, | |
| "eval_dan_Gov_f1": 0.4444444444444445, | |
| "eval_dan_Neu_acc": 0.17647058823529413, | |
| "eval_dan_Neu_f1": 0.3, | |
| "eval_dan_Soc_acc": 0.15384615384615385, | |
| "eval_dan_Soc_f1": 0.25, | |
| "eval_dan_cls_acc": 0.1956521739130435, | |
| "eval_dan_cls_f1": 0.24861111111111112, | |
| "eval_dan_loss": 2.01391863822937, | |
| "eval_dan_runtime": 8.6818, | |
| "eval_dan_samples_per_second": 345.55, | |
| "eval_dan_steps_per_second": 3.686, | |
| "eval_dan_total_cls_tokens": 46, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 14.543367346938776, | |
| "grad_norm": 2.4125187397003174, | |
| "learning_rate": 3.1966206605597775e-05, | |
| "loss": 1.4295, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 14.581632653061224, | |
| "grad_norm": 2.4281513690948486, | |
| "learning_rate": 3.188044750130979e-05, | |
| "loss": 1.3908, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 14.619897959183673, | |
| "grad_norm": 2.478541612625122, | |
| "learning_rate": 3.179460070690969e-05, | |
| "loss": 1.387, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 14.658163265306122, | |
| "grad_norm": 2.482215642929077, | |
| "learning_rate": 3.170866731650002e-05, | |
| "loss": 1.4175, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 14.696428571428571, | |
| "grad_norm": 2.597892999649048, | |
| "learning_rate": 3.1622648425286944e-05, | |
| "loss": 1.4082, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 14.73469387755102, | |
| "grad_norm": 2.3432674407958984, | |
| "learning_rate": 3.1536545129566356e-05, | |
| "loss": 1.3965, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 14.77295918367347, | |
| "grad_norm": 2.601710081100464, | |
| "learning_rate": 3.1450358526709825e-05, | |
| "loss": 1.3615, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 14.811224489795919, | |
| "grad_norm": 2.6126604080200195, | |
| "learning_rate": 3.136408971515071e-05, | |
| "loss": 1.413, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 14.849489795918368, | |
| "grad_norm": 2.3269197940826416, | |
| "learning_rate": 3.127773979437006e-05, | |
| "loss": 1.3993, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 14.887755102040817, | |
| "grad_norm": 2.3482260704040527, | |
| "learning_rate": 3.119130986488268e-05, | |
| "loss": 1.4288, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 14.887755102040817, | |
| "eval_en_All_acc": 0.6116515348032858, | |
| "eval_en_Env_acc": 0.9545454545454546, | |
| "eval_en_Env_f1": 0.9618320610687022, | |
| "eval_en_Gov_acc": 0.9714285714285714, | |
| "eval_en_Gov_f1": 0.9784172661870504, | |
| "eval_en_Neu_acc": 0.9142857142857143, | |
| "eval_en_Neu_f1": 0.8767123287671234, | |
| "eval_en_Soc_acc": 0.9, | |
| "eval_en_Soc_f1": 0.9230769230769231, | |
| "eval_en_cls_acc": 0.9335664335664335, | |
| "eval_en_cls_f1": 0.9350096447749497, | |
| "eval_en_loss": 2.252328634262085, | |
| "eval_en_runtime": 5.6214, | |
| "eval_en_samples_per_second": 333.904, | |
| "eval_en_steps_per_second": 3.558, | |
| "eval_en_total_cls_tokens": 286, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 14.887755102040817, | |
| "eval_en_oof_All_acc": 0.5978990686593025, | |
| "eval_en_oof_Env_acc": 0.9838709677419355, | |
| "eval_en_oof_Env_f1": 0.9838709677419355, | |
| "eval_en_oof_Gov_acc": 0.896551724137931, | |
| "eval_en_oof_Gov_f1": 0.896551724137931, | |
| "eval_en_oof_Neu_acc": 0.9552238805970149, | |
| "eval_en_oof_Neu_f1": 0.9208633093525178, | |
| "eval_en_oof_Soc_acc": 0.8955223880597015, | |
| "eval_en_oof_Soc_f1": 0.930232558139535, | |
| "eval_en_oof_cls_acc": 0.9330708661417323, | |
| "eval_en_oof_cls_f1": 0.9328796398429797, | |
| "eval_en_oof_loss": 2.3406786918640137, | |
| "eval_en_oof_runtime": 5.5764, | |
| "eval_en_oof_samples_per_second": 336.594, | |
| "eval_en_oof_steps_per_second": 3.587, | |
| "eval_en_oof_total_cls_tokens": 254, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 14.887755102040817, | |
| "eval_vi_All_acc": 0.7873651771956857, | |
| "eval_vi_Env_acc": 0.9808917197452229, | |
| "eval_vi_Env_f1": 0.9565217391304348, | |
| "eval_vi_Gov_acc": 0.9183673469387755, | |
| "eval_vi_Gov_f1": 0.903010033444816, | |
| "eval_vi_Neu_acc": 0.8791946308724832, | |
| "eval_vi_Neu_f1": 0.8972602739726028, | |
| "eval_vi_Soc_acc": 0.8742857142857143, | |
| "eval_vi_Soc_f1": 0.892128279883382, | |
| "eval_vi_cls_acc": 0.9124203821656051, | |
| "eval_vi_cls_f1": 0.9122300816078088, | |
| "eval_vi_loss": 0.9974566698074341, | |
| "eval_vi_runtime": 12.5597, | |
| "eval_vi_samples_per_second": 350.328, | |
| "eval_vi_steps_per_second": 3.663, | |
| "eval_vi_total_cls_tokens": 628, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 14.887755102040817, | |
| "eval_dan_All_acc": 0.6693548387096774, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.5, | |
| "eval_dan_Gov_f1": 0.6666666666666666, | |
| "eval_dan_Neu_acc": 0.16666666666666666, | |
| "eval_dan_Neu_f1": 0.2857142857142857, | |
| "eval_dan_Soc_acc": 0.09090909090909091, | |
| "eval_dan_Soc_f1": 0.15384615384615385, | |
| "eval_dan_cls_acc": 0.225, | |
| "eval_dan_cls_f1": 0.2765567765567766, | |
| "eval_dan_loss": 2.008380889892578, | |
| "eval_dan_runtime": 8.7357, | |
| "eval_dan_samples_per_second": 343.417, | |
| "eval_dan_steps_per_second": 3.663, | |
| "eval_dan_total_cls_tokens": 40, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 14.926020408163264, | |
| "grad_norm": 2.6033029556274414, | |
| "learning_rate": 3.110480102822304e-05, | |
| "loss": 1.3995, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 14.964285714285714, | |
| "grad_norm": 2.356266736984253, | |
| "learning_rate": 3.10182143869313e-05, | |
| "loss": 1.4061, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 1.4249842166900635, | |
| "learning_rate": 3.0931551044539194e-05, | |
| "loss": 1.2979, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 15.03826530612245, | |
| "grad_norm": 2.384026050567627, | |
| "learning_rate": 3.084481210555603e-05, | |
| "loss": 1.3823, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 15.076530612244898, | |
| "grad_norm": 2.404273748397827, | |
| "learning_rate": 3.0757998675454566e-05, | |
| "loss": 1.4349, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 15.114795918367347, | |
| "grad_norm": 2.35463547706604, | |
| "learning_rate": 3.067111186065693e-05, | |
| "loss": 1.4227, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 15.153061224489797, | |
| "grad_norm": 2.492060422897339, | |
| "learning_rate": 3.058415276852054e-05, | |
| "loss": 1.4085, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 15.191326530612244, | |
| "grad_norm": 2.551771879196167, | |
| "learning_rate": 3.049712250732396e-05, | |
| "loss": 1.3937, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 15.229591836734693, | |
| "grad_norm": 2.313629150390625, | |
| "learning_rate": 3.0410022186252816e-05, | |
| "loss": 1.4242, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 15.267857142857142, | |
| "grad_norm": 2.526322364807129, | |
| "learning_rate": 3.032285291538561e-05, | |
| "loss": 1.382, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.267857142857142, | |
| "eval_en_All_acc": 0.6168194070080862, | |
| "eval_en_Env_acc": 0.9240506329113924, | |
| "eval_en_Env_f1": 0.9419354838709677, | |
| "eval_en_Gov_acc": 0.9518072289156626, | |
| "eval_en_Gov_f1": 0.9634146341463414, | |
| "eval_en_Neu_acc": 0.9042553191489362, | |
| "eval_en_Neu_f1": 0.8994708994708994, | |
| "eval_en_Soc_acc": 0.9358974358974359, | |
| "eval_en_Soc_f1": 0.9125, | |
| "eval_en_cls_acc": 0.9281437125748503, | |
| "eval_en_cls_f1": 0.9293302543720522, | |
| "eval_en_loss": 2.1972010135650635, | |
| "eval_en_runtime": 5.5969, | |
| "eval_en_samples_per_second": 335.365, | |
| "eval_en_steps_per_second": 3.573, | |
| "eval_en_total_cls_tokens": 334, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.267857142857142, | |
| "eval_en_oof_All_acc": 0.6177115300306883, | |
| "eval_en_oof_Env_acc": 0.9818181818181818, | |
| "eval_en_oof_Env_f1": 0.9642857142857142, | |
| "eval_en_oof_Gov_acc": 0.9142857142857143, | |
| "eval_en_oof_Gov_f1": 0.9481481481481482, | |
| "eval_en_oof_Neu_acc": 0.9452054794520548, | |
| "eval_en_oof_Neu_f1": 0.9019607843137256, | |
| "eval_en_oof_Soc_acc": 0.8970588235294118, | |
| "eval_en_oof_Soc_f1": 0.9242424242424244, | |
| "eval_en_oof_cls_acc": 0.9323308270676691, | |
| "eval_en_oof_cls_f1": 0.9346592677475032, | |
| "eval_en_oof_loss": 2.225543975830078, | |
| "eval_en_oof_runtime": 5.5609, | |
| "eval_en_oof_samples_per_second": 337.538, | |
| "eval_en_oof_steps_per_second": 3.597, | |
| "eval_en_oof_total_cls_tokens": 266, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.267857142857142, | |
| "eval_vi_All_acc": 0.7836412288375444, | |
| "eval_vi_Env_acc": 0.9235294117647059, | |
| "eval_vi_Env_f1": 0.9486404833836858, | |
| "eval_vi_Gov_acc": 0.8774193548387097, | |
| "eval_vi_Gov_f1": 0.8859934853420195, | |
| "eval_vi_Neu_acc": 0.9166666666666666, | |
| "eval_vi_Neu_f1": 0.8825214899713467, | |
| "eval_vi_Soc_acc": 0.8837209302325582, | |
| "eval_vi_Soc_f1": 0.8862973760932944, | |
| "eval_vi_cls_acc": 0.9007518796992481, | |
| "eval_vi_cls_f1": 0.9008632086975866, | |
| "eval_vi_loss": 1.0053502321243286, | |
| "eval_vi_runtime": 12.5854, | |
| "eval_vi_samples_per_second": 349.611, | |
| "eval_vi_steps_per_second": 3.655, | |
| "eval_vi_total_cls_tokens": 665, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.267857142857142, | |
| "eval_dan_All_acc": 0.6645502155072531, | |
| "eval_dan_Env_acc": 0.4, | |
| "eval_dan_Env_f1": 0.5714285714285715, | |
| "eval_dan_Gov_acc": 0.0, | |
| "eval_dan_Gov_f1": 0.0, | |
| "eval_dan_Neu_acc": 0.1111111111111111, | |
| "eval_dan_Neu_f1": 0.19999999999999998, | |
| "eval_dan_Soc_acc": 0.4666666666666667, | |
| "eval_dan_Soc_f1": 0.6363636363636364, | |
| "eval_dan_cls_acc": 0.2391304347826087, | |
| "eval_dan_cls_f1": 0.35194805194805195, | |
| "eval_dan_loss": 2.090144395828247, | |
| "eval_dan_runtime": 8.8091, | |
| "eval_dan_samples_per_second": 340.555, | |
| "eval_dan_steps_per_second": 3.633, | |
| "eval_dan_total_cls_tokens": 46, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.306122448979592, | |
| "grad_norm": 2.6183903217315674, | |
| "learning_rate": 3.0235615805679596e-05, | |
| "loss": 1.3909, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 15.34438775510204, | |
| "grad_norm": 2.367849826812744, | |
| "learning_rate": 3.014831196895665e-05, | |
| "loss": 1.3888, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 15.38265306122449, | |
| "grad_norm": 2.337021589279175, | |
| "learning_rate": 3.0060942517889046e-05, | |
| "loss": 1.3802, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 15.420918367346939, | |
| "grad_norm": 2.423004388809204, | |
| "learning_rate": 2.9973508565985313e-05, | |
| "loss": 1.3579, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 15.459183673469388, | |
| "grad_norm": 2.353525161743164, | |
| "learning_rate": 2.9886011227576033e-05, | |
| "loss": 1.4126, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 15.497448979591837, | |
| "grad_norm": 2.5038511753082275, | |
| "learning_rate": 2.9798451617799627e-05, | |
| "loss": 1.3747, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 15.535714285714286, | |
| "grad_norm": 2.3598599433898926, | |
| "learning_rate": 2.9710830852588174e-05, | |
| "loss": 1.3874, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 15.573979591836736, | |
| "grad_norm": 2.201620101928711, | |
| "learning_rate": 2.9623150048653137e-05, | |
| "loss": 1.3332, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 15.612244897959183, | |
| "grad_norm": 2.4558441638946533, | |
| "learning_rate": 2.9535410323471192e-05, | |
| "loss": 1.3704, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 15.650510204081632, | |
| "grad_norm": 2.5303151607513428, | |
| "learning_rate": 2.9447612795269953e-05, | |
| "loss": 1.3894, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 15.650510204081632, | |
| "eval_en_All_acc": 0.6180570681768678, | |
| "eval_en_Env_acc": 0.9859154929577465, | |
| "eval_en_Env_f1": 0.979020979020979, | |
| "eval_en_Gov_acc": 0.9512195121951219, | |
| "eval_en_Gov_f1": 0.9570552147239264, | |
| "eval_en_Neu_acc": 0.890625, | |
| "eval_en_Neu_f1": 0.8769230769230768, | |
| "eval_en_Soc_acc": 0.9178082191780822, | |
| "eval_en_Soc_f1": 0.9305555555555556, | |
| "eval_en_cls_acc": 0.9379310344827586, | |
| "eval_en_cls_f1": 0.9358887065558844, | |
| "eval_en_loss": 2.230309247970581, | |
| "eval_en_runtime": 5.5603, | |
| "eval_en_samples_per_second": 337.572, | |
| "eval_en_steps_per_second": 3.597, | |
| "eval_en_total_cls_tokens": 290, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 15.650510204081632, | |
| "eval_en_oof_All_acc": 0.6107240869748786, | |
| "eval_en_oof_Env_acc": 0.984375, | |
| "eval_en_oof_Env_f1": 0.9692307692307692, | |
| "eval_en_oof_Gov_acc": 0.9863013698630136, | |
| "eval_en_oof_Gov_f1": 0.9863013698630136, | |
| "eval_en_oof_Neu_acc": 0.898876404494382, | |
| "eval_en_oof_Neu_f1": 0.9195402298850575, | |
| "eval_en_oof_Soc_acc": 0.9384615384615385, | |
| "eval_en_oof_Soc_f1": 0.9242424242424243, | |
| "eval_en_oof_cls_acc": 0.9484536082474226, | |
| "eval_en_oof_cls_f1": 0.9498286983053161, | |
| "eval_en_oof_loss": 2.266608238220215, | |
| "eval_en_oof_runtime": 5.6147, | |
| "eval_en_oof_samples_per_second": 334.303, | |
| "eval_en_oof_steps_per_second": 3.562, | |
| "eval_en_oof_total_cls_tokens": 291, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 15.650510204081632, | |
| "eval_vi_All_acc": 0.7812941872123814, | |
| "eval_vi_Env_acc": 0.9695121951219512, | |
| "eval_vi_Env_f1": 0.9665653495440729, | |
| "eval_vi_Gov_acc": 0.9117647058823529, | |
| "eval_vi_Gov_f1": 0.9117647058823528, | |
| "eval_vi_Neu_acc": 0.863905325443787, | |
| "eval_vi_Neu_f1": 0.9153605015673981, | |
| "eval_vi_Soc_acc": 0.9235668789808917, | |
| "eval_vi_Soc_f1": 0.8734939759036146, | |
| "eval_vi_cls_acc": 0.9166666666666666, | |
| "eval_vi_cls_f1": 0.9167961332243596, | |
| "eval_vi_loss": 1.0185942649841309, | |
| "eval_vi_runtime": 12.7412, | |
| "eval_vi_samples_per_second": 345.338, | |
| "eval_vi_steps_per_second": 3.61, | |
| "eval_vi_total_cls_tokens": 660, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 15.650510204081632, | |
| "eval_dan_All_acc": 0.6601619855065599, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2, | |
| "eval_dan_Gov_f1": 0.33333333333333337, | |
| "eval_dan_Neu_acc": 0.13333333333333333, | |
| "eval_dan_Neu_f1": 0.23529411764705882, | |
| "eval_dan_Soc_acc": 0.07142857142857142, | |
| "eval_dan_Soc_f1": 0.13333333333333333, | |
| "eval_dan_cls_acc": 0.11627906976744186, | |
| "eval_dan_cls_f1": 0.17549019607843136, | |
| "eval_dan_loss": 2.0869133472442627, | |
| "eval_dan_runtime": 8.712, | |
| "eval_dan_samples_per_second": 344.352, | |
| "eval_dan_steps_per_second": 3.673, | |
| "eval_dan_total_cls_tokens": 43, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 15.688775510204081, | |
| "grad_norm": 2.5090577602386475, | |
| "learning_rate": 2.9359758583013697e-05, | |
| "loss": 1.3597, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 15.72704081632653, | |
| "grad_norm": 2.5291616916656494, | |
| "learning_rate": 2.9271848806389163e-05, | |
| "loss": 1.4075, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 15.76530612244898, | |
| "grad_norm": 2.469756603240967, | |
| "learning_rate": 2.918388458579122e-05, | |
| "loss": 1.3292, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 15.803571428571429, | |
| "grad_norm": 2.5306360721588135, | |
| "learning_rate": 2.9095867042308645e-05, | |
| "loss": 1.3289, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 15.841836734693878, | |
| "grad_norm": 2.46146297454834, | |
| "learning_rate": 2.9007797297709782e-05, | |
| "loss": 1.3927, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 15.880102040816327, | |
| "grad_norm": 2.5624325275421143, | |
| "learning_rate": 2.8919676474428275e-05, | |
| "loss": 1.3474, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 15.918367346938776, | |
| "grad_norm": 2.3868062496185303, | |
| "learning_rate": 2.8831505695548762e-05, | |
| "loss": 1.3596, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 15.956632653061224, | |
| "grad_norm": 2.425652265548706, | |
| "learning_rate": 2.8743286084792553e-05, | |
| "loss": 1.3982, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 15.994897959183673, | |
| "grad_norm": 2.5391957759857178, | |
| "learning_rate": 2.865501876650331e-05, | |
| "loss": 1.3806, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 16.03061224489796, | |
| "grad_norm": 2.415642499923706, | |
| "learning_rate": 2.8566704865632733e-05, | |
| "loss": 1.2971, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 16.03061224489796, | |
| "eval_en_All_acc": 0.6298971328518276, | |
| "eval_en_Env_acc": 0.974025974025974, | |
| "eval_en_Env_f1": 0.9868421052631579, | |
| "eval_en_Gov_acc": 0.958904109589041, | |
| "eval_en_Gov_f1": 0.958904109589041, | |
| "eval_en_Neu_acc": 0.9305555555555556, | |
| "eval_en_Neu_f1": 0.9054054054054054, | |
| "eval_en_Soc_acc": 0.927536231884058, | |
| "eval_en_Soc_f1": 0.9411764705882353, | |
| "eval_en_cls_acc": 0.9484536082474226, | |
| "eval_en_cls_f1": 0.9480820227114598, | |
| "eval_en_loss": 2.1614060401916504, | |
| "eval_en_runtime": 5.6284, | |
| "eval_en_samples_per_second": 333.489, | |
| "eval_en_steps_per_second": 3.553, | |
| "eval_en_total_cls_tokens": 291, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 16.03061224489796, | |
| "eval_en_oof_All_acc": 0.62417200564665, | |
| "eval_en_oof_Env_acc": 0.9506172839506173, | |
| "eval_en_oof_Env_f1": 0.9746835443037974, | |
| "eval_en_oof_Gov_acc": 0.9523809523809523, | |
| "eval_en_oof_Gov_f1": 0.9375, | |
| "eval_en_oof_Neu_acc": 0.9393939393939394, | |
| "eval_en_oof_Neu_f1": 0.9185185185185185, | |
| "eval_en_oof_Soc_acc": 0.9122807017543859, | |
| "eval_en_oof_Soc_f1": 0.9203539823008849, | |
| "eval_en_oof_cls_acc": 0.9400749063670412, | |
| "eval_en_oof_cls_f1": 0.9377640112808002, | |
| "eval_en_oof_loss": 2.1825342178344727, | |
| "eval_en_oof_runtime": 5.5819, | |
| "eval_en_oof_samples_per_second": 336.268, | |
| "eval_en_oof_steps_per_second": 3.583, | |
| "eval_en_oof_total_cls_tokens": 267, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 16.03061224489796, | |
| "eval_vi_All_acc": 0.7860118896397541, | |
| "eval_vi_Env_acc": 0.9351351351351351, | |
| "eval_vi_Env_f1": 0.953168044077135, | |
| "eval_vi_Gov_acc": 0.9239130434782609, | |
| "eval_vi_Gov_f1": 0.9018567639257296, | |
| "eval_vi_Neu_acc": 0.8679245283018868, | |
| "eval_vi_Neu_f1": 0.8903225806451613, | |
| "eval_vi_Soc_acc": 0.9, | |
| "eval_vi_Soc_f1": 0.8852459016393444, | |
| "eval_vi_cls_acc": 0.9081920903954802, | |
| "eval_vi_cls_f1": 0.9076483225718426, | |
| "eval_vi_loss": 0.9966000914573669, | |
| "eval_vi_runtime": 12.6088, | |
| "eval_vi_samples_per_second": 348.964, | |
| "eval_vi_steps_per_second": 3.648, | |
| "eval_vi_total_cls_tokens": 708, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 16.03061224489796, | |
| "eval_dan_All_acc": 0.6664238892935178, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.38461538461538464, | |
| "eval_dan_Gov_f1": 0.5555555555555556, | |
| "eval_dan_Neu_acc": 0.13333333333333333, | |
| "eval_dan_Neu_f1": 0.23529411764705882, | |
| "eval_dan_Soc_acc": 0.3076923076923077, | |
| "eval_dan_Soc_f1": 0.47058823529411764, | |
| "eval_dan_cls_acc": 0.2558139534883721, | |
| "eval_dan_cls_f1": 0.315359477124183, | |
| "eval_dan_loss": 2.024994134902954, | |
| "eval_dan_runtime": 8.7943, | |
| "eval_dan_samples_per_second": 341.13, | |
| "eval_dan_steps_per_second": 3.639, | |
| "eval_dan_total_cls_tokens": 43, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 16.068877551020407, | |
| "grad_norm": 2.310542345046997, | |
| "learning_rate": 2.8478345507726183e-05, | |
| "loss": 1.3683, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 16.107142857142858, | |
| "grad_norm": 2.6199817657470703, | |
| "learning_rate": 2.8389941818908383e-05, | |
| "loss": 1.3746, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 16.145408163265305, | |
| "grad_norm": 2.5054383277893066, | |
| "learning_rate": 2.8301494925869055e-05, | |
| "loss": 1.3737, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 16.183673469387756, | |
| "grad_norm": 2.369536876678467, | |
| "learning_rate": 2.8213005955848508e-05, | |
| "loss": 1.3727, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 16.221938775510203, | |
| "grad_norm": 2.4244861602783203, | |
| "learning_rate": 2.812447603662337e-05, | |
| "loss": 1.3904, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 16.260204081632654, | |
| "grad_norm": 2.437948226928711, | |
| "learning_rate": 2.803590629649212e-05, | |
| "loss": 1.3389, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 16.2984693877551, | |
| "grad_norm": 2.3509361743927, | |
| "learning_rate": 2.794729786426076e-05, | |
| "loss": 1.347, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 16.336734693877553, | |
| "grad_norm": 2.4837801456451416, | |
| "learning_rate": 2.785865186922843e-05, | |
| "loss": 1.3703, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 16.375, | |
| "grad_norm": 2.402223587036133, | |
| "learning_rate": 2.7769969441172972e-05, | |
| "loss": 1.3687, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 16.413265306122447, | |
| "grad_norm": 2.421947956085205, | |
| "learning_rate": 2.768125171033658e-05, | |
| "loss": 1.3845, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 16.413265306122447, | |
| "eval_en_All_acc": 0.6074146553598608, | |
| "eval_en_Env_acc": 0.9466666666666667, | |
| "eval_en_Env_f1": 0.9466666666666667, | |
| "eval_en_Gov_acc": 1.0, | |
| "eval_en_Gov_f1": 0.9500000000000001, | |
| "eval_en_Neu_acc": 0.8433734939759037, | |
| "eval_en_Neu_f1": 0.8917197452229301, | |
| "eval_en_Soc_acc": 0.9545454545454546, | |
| "eval_en_Soc_f1": 0.9333333333333332, | |
| "eval_en_cls_acc": 0.9288256227758007, | |
| "eval_en_cls_f1": 0.9304299363057326, | |
| "eval_en_loss": 2.246497392654419, | |
| "eval_en_runtime": 5.6195, | |
| "eval_en_samples_per_second": 334.015, | |
| "eval_en_steps_per_second": 3.559, | |
| "eval_en_total_cls_tokens": 281, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 16.413265306122447, | |
| "eval_en_oof_All_acc": 0.621945945945946, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9770992366412213, | |
| "eval_en_oof_Gov_acc": 1.0, | |
| "eval_en_oof_Gov_f1": 0.9612403100775194, | |
| "eval_en_oof_Neu_acc": 0.8484848484848485, | |
| "eval_en_oof_Neu_f1": 0.9105691056910568, | |
| "eval_en_oof_Soc_acc": 0.95, | |
| "eval_en_oof_Soc_f1": 0.9421487603305784, | |
| "eval_en_oof_cls_acc": 0.9484126984126984, | |
| "eval_en_oof_cls_f1": 0.9477643531850939, | |
| "eval_en_oof_loss": 2.2377281188964844, | |
| "eval_en_oof_runtime": 5.5808, | |
| "eval_en_oof_samples_per_second": 336.33, | |
| "eval_en_oof_steps_per_second": 3.584, | |
| "eval_en_oof_total_cls_tokens": 252, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 16.413265306122447, | |
| "eval_vi_All_acc": 0.7923155176461382, | |
| "eval_vi_Env_acc": 0.9586206896551724, | |
| "eval_vi_Env_f1": 0.9652777777777778, | |
| "eval_vi_Gov_acc": 0.9329608938547486, | |
| "eval_vi_Gov_f1": 0.9226519337016574, | |
| "eval_vi_Neu_acc": 0.922077922077922, | |
| "eval_vi_Neu_f1": 0.9342105263157895, | |
| "eval_vi_Soc_acc": 0.9090909090909091, | |
| "eval_vi_Soc_f1": 0.9036144578313253, | |
| "eval_vi_cls_acc": 0.9300155520995335, | |
| "eval_vi_cls_f1": 0.9314386739066375, | |
| "eval_vi_loss": 0.9583326578140259, | |
| "eval_vi_runtime": 12.6929, | |
| "eval_vi_samples_per_second": 346.65, | |
| "eval_vi_steps_per_second": 3.624, | |
| "eval_vi_total_cls_tokens": 643, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 16.413265306122447, | |
| "eval_dan_All_acc": 0.6765270301895624, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2, | |
| "eval_dan_Gov_f1": 0.33333333333333337, | |
| "eval_dan_Neu_acc": 0.4782608695652174, | |
| "eval_dan_Neu_f1": 0.6470588235294118, | |
| "eval_dan_Soc_acc": 0.10526315789473684, | |
| "eval_dan_Soc_f1": 0.1904761904761905, | |
| "eval_dan_cls_acc": 0.2916666666666667, | |
| "eval_dan_cls_f1": 0.2927170868347339, | |
| "eval_dan_loss": 2.0184555053710938, | |
| "eval_dan_runtime": 8.6917, | |
| "eval_dan_samples_per_second": 345.156, | |
| "eval_dan_steps_per_second": 3.682, | |
| "eval_dan_total_cls_tokens": 48, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 16.4515306122449, | |
| "grad_norm": 2.508284091949463, | |
| "learning_rate": 2.7592499807411393e-05, | |
| "loss": 1.4241, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 16.489795918367346, | |
| "grad_norm": 2.3161635398864746, | |
| "learning_rate": 2.750371486352502e-05, | |
| "loss": 1.38, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 16.528061224489797, | |
| "grad_norm": 2.388101577758789, | |
| "learning_rate": 2.741489801022621e-05, | |
| "loss": 1.3398, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 16.566326530612244, | |
| "grad_norm": 2.613304853439331, | |
| "learning_rate": 2.7326050379470373e-05, | |
| "loss": 1.3649, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 16.604591836734695, | |
| "grad_norm": 2.4420080184936523, | |
| "learning_rate": 2.7237173103605194e-05, | |
| "loss": 1.4135, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 16.642857142857142, | |
| "grad_norm": 2.456716537475586, | |
| "learning_rate": 2.7148267315356162e-05, | |
| "loss": 1.3682, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 16.681122448979593, | |
| "grad_norm": 2.506779432296753, | |
| "learning_rate": 2.7059334147812142e-05, | |
| "loss": 1.3732, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 16.71938775510204, | |
| "grad_norm": 2.4386324882507324, | |
| "learning_rate": 2.6970374734410976e-05, | |
| "loss": 1.3634, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 16.757653061224488, | |
| "grad_norm": 2.3646740913391113, | |
| "learning_rate": 2.688139020892496e-05, | |
| "loss": 1.3316, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 16.79591836734694, | |
| "grad_norm": 2.5421674251556396, | |
| "learning_rate": 2.679238170544649e-05, | |
| "loss": 1.3644, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 16.79591836734694, | |
| "eval_en_All_acc": 0.6101482564209647, | |
| "eval_en_Env_acc": 0.9259259259259259, | |
| "eval_en_Env_f1": 0.9433962264150944, | |
| "eval_en_Gov_acc": 0.974025974025974, | |
| "eval_en_Gov_f1": 0.967741935483871, | |
| "eval_en_Neu_acc": 0.8804347826086957, | |
| "eval_en_Neu_f1": 0.8901098901098902, | |
| "eval_en_Soc_acc": 0.9384615384615385, | |
| "eval_en_Soc_f1": 0.9104477611940298, | |
| "eval_en_cls_acc": 0.926984126984127, | |
| "eval_en_cls_f1": 0.9279239533007213, | |
| "eval_en_loss": 2.2553231716156006, | |
| "eval_en_runtime": 5.6211, | |
| "eval_en_samples_per_second": 333.921, | |
| "eval_en_steps_per_second": 3.558, | |
| "eval_en_total_cls_tokens": 315, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 16.79591836734694, | |
| "eval_en_oof_All_acc": 0.6214561855670103, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.991869918699187, | |
| "eval_en_oof_Gov_acc": 1.0, | |
| "eval_en_oof_Gov_f1": 0.976, | |
| "eval_en_oof_Neu_acc": 0.9137931034482759, | |
| "eval_en_oof_Neu_f1": 0.9298245614035087, | |
| "eval_en_oof_Soc_acc": 0.9402985074626866, | |
| "eval_en_oof_Soc_f1": 0.9545454545454547, | |
| "eval_en_oof_cls_acc": 0.9635627530364372, | |
| "eval_en_oof_cls_f1": 0.9630599836620375, | |
| "eval_en_oof_loss": 2.1954355239868164, | |
| "eval_en_oof_runtime": 5.5719, | |
| "eval_en_oof_samples_per_second": 336.871, | |
| "eval_en_oof_steps_per_second": 3.589, | |
| "eval_en_oof_total_cls_tokens": 247, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 16.79591836734694, | |
| "eval_vi_All_acc": 0.7797483704714264, | |
| "eval_vi_Env_acc": 0.9649122807017544, | |
| "eval_vi_Env_f1": 0.9705882352941176, | |
| "eval_vi_Gov_acc": 0.9361702127659575, | |
| "eval_vi_Gov_f1": 0.9263157894736843, | |
| "eval_vi_Neu_acc": 0.9041916167664671, | |
| "eval_vi_Neu_f1": 0.9096385542168675, | |
| "eval_vi_Soc_acc": 0.9141104294478528, | |
| "eval_vi_Soc_f1": 0.9141104294478528, | |
| "eval_vi_cls_acc": 0.93033381712627, | |
| "eval_vi_cls_f1": 0.9301632521081307, | |
| "eval_vi_loss": 1.0255835056304932, | |
| "eval_vi_runtime": 12.4324, | |
| "eval_vi_samples_per_second": 353.913, | |
| "eval_vi_steps_per_second": 3.7, | |
| "eval_vi_total_cls_tokens": 689, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 16.79591836734694, | |
| "eval_dan_All_acc": 0.6743782004389174, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.0, | |
| "eval_dan_Gov_f1": 0.0, | |
| "eval_dan_Neu_acc": 0.1111111111111111, | |
| "eval_dan_Neu_f1": 0.19999999999999998, | |
| "eval_dan_Soc_acc": 0.45454545454545453, | |
| "eval_dan_Soc_f1": 0.625, | |
| "eval_dan_cls_acc": 0.22857142857142856, | |
| "eval_dan_cls_f1": 0.3729166666666666, | |
| "eval_dan_loss": 2.0171778202056885, | |
| "eval_dan_runtime": 8.8554, | |
| "eval_dan_samples_per_second": 338.776, | |
| "eval_dan_steps_per_second": 3.614, | |
| "eval_dan_total_cls_tokens": 35, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 16.834183673469386, | |
| "grad_norm": 2.4400856494903564, | |
| "learning_rate": 2.6703350358373523e-05, | |
| "loss": 1.3685, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 16.872448979591837, | |
| "grad_norm": 2.2683985233306885, | |
| "learning_rate": 2.6614297302395152e-05, | |
| "loss": 1.3721, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 16.910714285714285, | |
| "grad_norm": 2.5611355304718018, | |
| "learning_rate": 2.652522367247716e-05, | |
| "loss": 1.4001, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 16.948979591836736, | |
| "grad_norm": 2.4479563236236572, | |
| "learning_rate": 2.643613060384756e-05, | |
| "loss": 1.3247, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 16.987244897959183, | |
| "grad_norm": 2.536884069442749, | |
| "learning_rate": 2.6347019231982055e-05, | |
| "loss": 1.3826, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 17.022959183673468, | |
| "grad_norm": 2.348360300064087, | |
| "learning_rate": 2.6257890692589667e-05, | |
| "loss": 1.3033, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 17.06122448979592, | |
| "grad_norm": 2.4022655487060547, | |
| "learning_rate": 2.616874612159819e-05, | |
| "loss": 1.3231, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 17.099489795918366, | |
| "grad_norm": 2.326883316040039, | |
| "learning_rate": 2.607958665513976e-05, | |
| "loss": 1.348, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 17.137755102040817, | |
| "grad_norm": 2.338292121887207, | |
| "learning_rate": 2.599041342953633e-05, | |
| "loss": 1.4219, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 17.176020408163264, | |
| "grad_norm": 2.489130973815918, | |
| "learning_rate": 2.590122758128522e-05, | |
| "loss": 1.3216, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.176020408163264, | |
| "eval_en_All_acc": 0.6225039619651347, | |
| "eval_en_Env_acc": 0.9714285714285714, | |
| "eval_en_Env_f1": 0.9784172661870504, | |
| "eval_en_Gov_acc": 0.9682539682539683, | |
| "eval_en_Gov_f1": 0.9457364341085271, | |
| "eval_en_Neu_acc": 0.8933333333333333, | |
| "eval_en_Neu_f1": 0.8874172185430463, | |
| "eval_en_Soc_acc": 0.8857142857142857, | |
| "eval_en_Soc_f1": 0.9051094890510949, | |
| "eval_en_cls_acc": 0.9280575539568345, | |
| "eval_en_cls_f1": 0.9291701019724297, | |
| "eval_en_loss": 2.1650185585021973, | |
| "eval_en_runtime": 5.6179, | |
| "eval_en_samples_per_second": 334.112, | |
| "eval_en_steps_per_second": 3.56, | |
| "eval_en_total_cls_tokens": 278, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.176020408163264, | |
| "eval_en_oof_All_acc": 0.6171671018276762, | |
| "eval_en_oof_Env_acc": 0.9259259259259259, | |
| "eval_en_oof_Env_f1": 0.9523809523809523, | |
| "eval_en_oof_Gov_acc": 0.9620253164556962, | |
| "eval_en_oof_Gov_f1": 0.9743589743589742, | |
| "eval_en_oof_Neu_acc": 0.918918918918919, | |
| "eval_en_oof_Neu_f1": 0.8662420382165605, | |
| "eval_en_oof_Soc_acc": 0.9012345679012346, | |
| "eval_en_oof_Soc_f1": 0.9240506329113924, | |
| "eval_en_oof_cls_acc": 0.9270833333333334, | |
| "eval_en_oof_cls_f1": 0.9292581494669698, | |
| "eval_en_oof_loss": 2.262599468231201, | |
| "eval_en_oof_runtime": 5.5697, | |
| "eval_en_oof_samples_per_second": 337.005, | |
| "eval_en_oof_steps_per_second": 3.591, | |
| "eval_en_oof_total_cls_tokens": 288, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.176020408163264, | |
| "eval_vi_All_acc": 0.7806413786071174, | |
| "eval_vi_Env_acc": 0.9428571428571428, | |
| "eval_vi_Env_f1": 0.9565217391304348, | |
| "eval_vi_Gov_acc": 0.891566265060241, | |
| "eval_vi_Gov_f1": 0.880952380952381, | |
| "eval_vi_Neu_acc": 0.8850574712643678, | |
| "eval_vi_Neu_f1": 0.8979591836734694, | |
| "eval_vi_Soc_acc": 0.8715083798882681, | |
| "eval_vi_Soc_f1": 0.8595041322314049, | |
| "eval_vi_cls_acc": 0.8952959028831563, | |
| "eval_vi_cls_f1": 0.8987343589969226, | |
| "eval_vi_loss": 1.0187090635299683, | |
| "eval_vi_runtime": 12.5596, | |
| "eval_vi_samples_per_second": 350.329, | |
| "eval_vi_steps_per_second": 3.663, | |
| "eval_vi_total_cls_tokens": 659, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.176020408163264, | |
| "eval_dan_All_acc": 0.6728116954762781, | |
| "eval_dan_Env_acc": 0.25, | |
| "eval_dan_Env_f1": 0.4, | |
| "eval_dan_Gov_acc": 0.3333333333333333, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.1, | |
| "eval_dan_Neu_f1": 0.18181818181818182, | |
| "eval_dan_Soc_acc": 0.3076923076923077, | |
| "eval_dan_Soc_f1": 0.47058823529411764, | |
| "eval_dan_cls_acc": 0.22448979591836735, | |
| "eval_dan_cls_f1": 0.3881016042780749, | |
| "eval_dan_loss": 2.0119221210479736, | |
| "eval_dan_runtime": 8.6938, | |
| "eval_dan_samples_per_second": 345.075, | |
| "eval_dan_steps_per_second": 3.681, | |
| "eval_dan_total_cls_tokens": 49, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.214285714285715, | |
| "grad_norm": 2.4613332748413086, | |
| "learning_rate": 2.5812030247044628e-05, | |
| "loss": 1.3695, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 17.252551020408163, | |
| "grad_norm": 2.414168357849121, | |
| "learning_rate": 2.5722822563619142e-05, | |
| "loss": 1.4079, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 17.290816326530614, | |
| "grad_norm": 2.4258556365966797, | |
| "learning_rate": 2.563360566794522e-05, | |
| "loss": 1.3608, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 17.32908163265306, | |
| "grad_norm": 2.445528745651245, | |
| "learning_rate": 2.5544380697076776e-05, | |
| "loss": 1.3818, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 17.367346938775512, | |
| "grad_norm": 2.406621217727661, | |
| "learning_rate": 2.5455148788170596e-05, | |
| "loss": 1.3402, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 17.40561224489796, | |
| "grad_norm": 2.229353666305542, | |
| "learning_rate": 2.5365911078471915e-05, | |
| "loss": 1.363, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 17.443877551020407, | |
| "grad_norm": 2.5730979442596436, | |
| "learning_rate": 2.5276668705299894e-05, | |
| "loss": 1.3265, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 17.482142857142858, | |
| "grad_norm": 2.593114137649536, | |
| "learning_rate": 2.518742280603313e-05, | |
| "loss": 1.3674, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 17.520408163265305, | |
| "grad_norm": 2.453253746032715, | |
| "learning_rate": 2.509817451809515e-05, | |
| "loss": 1.3637, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 17.558673469387756, | |
| "grad_norm": 2.425366163253784, | |
| "learning_rate": 2.500892497893994e-05, | |
| "loss": 1.3433, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 17.558673469387756, | |
| "eval_en_All_acc": 0.6086118251928021, | |
| "eval_en_Env_acc": 0.9701492537313433, | |
| "eval_en_Env_f1": 0.962962962962963, | |
| "eval_en_Gov_acc": 0.9838709677419355, | |
| "eval_en_Gov_f1": 0.9457364341085271, | |
| "eval_en_Neu_acc": 0.855072463768116, | |
| "eval_en_Neu_f1": 0.8613138686131386, | |
| "eval_en_Soc_acc": 0.875, | |
| "eval_en_Soc_f1": 0.9032258064516129, | |
| "eval_en_cls_acc": 0.9172661870503597, | |
| "eval_en_cls_f1": 0.9183097680340604, | |
| "eval_en_loss": 2.247319221496582, | |
| "eval_en_runtime": 5.5998, | |
| "eval_en_samples_per_second": 335.188, | |
| "eval_en_steps_per_second": 3.572, | |
| "eval_en_total_cls_tokens": 278, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 17.558673469387756, | |
| "eval_en_oof_All_acc": 0.6364708404802745, | |
| "eval_en_oof_Env_acc": 0.9868421052631579, | |
| "eval_en_oof_Env_f1": 0.974025974025974, | |
| "eval_en_oof_Gov_acc": 0.9710144927536232, | |
| "eval_en_oof_Gov_f1": 0.9710144927536232, | |
| "eval_en_oof_Neu_acc": 0.8888888888888888, | |
| "eval_en_oof_Neu_f1": 0.9256198347107438, | |
| "eval_en_oof_Soc_acc": 0.9846153846153847, | |
| "eval_en_oof_Soc_f1": 0.962406015037594, | |
| "eval_en_oof_cls_acc": 0.9597069597069597, | |
| "eval_en_oof_cls_f1": 0.9582665791319838, | |
| "eval_en_oof_loss": 2.101902961730957, | |
| "eval_en_oof_runtime": 5.5636, | |
| "eval_en_oof_samples_per_second": 337.373, | |
| "eval_en_oof_steps_per_second": 3.595, | |
| "eval_en_oof_total_cls_tokens": 273, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 17.558673469387756, | |
| "eval_vi_All_acc": 0.7853968740422924, | |
| "eval_vi_Env_acc": 0.9612903225806452, | |
| "eval_vi_Env_f1": 0.964401294498382, | |
| "eval_vi_Gov_acc": 0.9075144508670521, | |
| "eval_vi_Gov_f1": 0.8746518105849582, | |
| "eval_vi_Neu_acc": 0.8424242424242424, | |
| "eval_vi_Neu_f1": 0.8938906752411576, | |
| "eval_vi_Soc_acc": 0.8959537572254336, | |
| "eval_vi_Soc_f1": 0.8781869688385271, | |
| "eval_vi_cls_acc": 0.9009009009009009, | |
| "eval_vi_cls_f1": 0.9027826872907562, | |
| "eval_vi_loss": 1.0016144514083862, | |
| "eval_vi_runtime": 12.6917, | |
| "eval_vi_samples_per_second": 346.682, | |
| "eval_vi_steps_per_second": 3.624, | |
| "eval_vi_total_cls_tokens": 666, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 17.558673469387756, | |
| "eval_dan_All_acc": 0.6774884717499651, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2857142857142857, | |
| "eval_dan_Gov_f1": 0.4444444444444445, | |
| "eval_dan_Neu_acc": 0.0, | |
| "eval_dan_Neu_f1": 0.0, | |
| "eval_dan_Soc_acc": 0.16666666666666666, | |
| "eval_dan_Soc_f1": 0.2857142857142857, | |
| "eval_dan_cls_acc": 0.10810810810810811, | |
| "eval_dan_cls_f1": 0.18253968253968256, | |
| "eval_dan_loss": 1.997637391090393, | |
| "eval_dan_runtime": 8.6641, | |
| "eval_dan_samples_per_second": 346.256, | |
| "eval_dan_steps_per_second": 3.693, | |
| "eval_dan_total_cls_tokens": 37, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 17.596938775510203, | |
| "grad_norm": 2.5557661056518555, | |
| "learning_rate": 2.491967532603742e-05, | |
| "loss": 1.3465, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 17.635204081632654, | |
| "grad_norm": 2.5336952209472656, | |
| "learning_rate": 2.4830426696858952e-05, | |
| "loss": 1.3397, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 17.6734693877551, | |
| "grad_norm": 2.3333818912506104, | |
| "learning_rate": 2.474118022886288e-05, | |
| "loss": 1.3431, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 17.711734693877553, | |
| "grad_norm": 2.434864044189453, | |
| "learning_rate": 2.465193705947998e-05, | |
| "loss": 1.3764, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "grad_norm": 2.50199556350708, | |
| "learning_rate": 2.4562698326098983e-05, | |
| "loss": 1.3579, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 17.788265306122447, | |
| "grad_norm": 2.5020456314086914, | |
| "learning_rate": 2.447346516605212e-05, | |
| "loss": 1.3316, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 17.8265306122449, | |
| "grad_norm": 2.412461757659912, | |
| "learning_rate": 2.438423871660054e-05, | |
| "loss": 1.3495, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 17.864795918367346, | |
| "grad_norm": 2.4075801372528076, | |
| "learning_rate": 2.4295020114919896e-05, | |
| "loss": 1.3903, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 17.903061224489797, | |
| "grad_norm": 2.5314748287200928, | |
| "learning_rate": 2.420581049808584e-05, | |
| "loss": 1.3918, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 17.941326530612244, | |
| "grad_norm": 2.4418952465057373, | |
| "learning_rate": 2.4116611003059472e-05, | |
| "loss": 1.3402, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 17.941326530612244, | |
| "eval_en_All_acc": 0.6148409893992933, | |
| "eval_en_Env_acc": 0.9701492537313433, | |
| "eval_en_Env_f1": 0.9774436090225564, | |
| "eval_en_Gov_acc": 0.9655172413793104, | |
| "eval_en_Gov_f1": 0.9655172413793104, | |
| "eval_en_Neu_acc": 0.9016393442622951, | |
| "eval_en_Neu_f1": 0.9016393442622952, | |
| "eval_en_Soc_acc": 0.9523809523809523, | |
| "eval_en_Soc_f1": 0.9448818897637795, | |
| "eval_en_cls_acc": 0.9477911646586346, | |
| "eval_en_cls_f1": 0.9473705211069854, | |
| "eval_en_loss": 2.2006311416625977, | |
| "eval_en_runtime": 5.6443, | |
| "eval_en_samples_per_second": 332.549, | |
| "eval_en_steps_per_second": 3.543, | |
| "eval_en_total_cls_tokens": 249, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 17.941326530612244, | |
| "eval_en_oof_All_acc": 0.6245169600686991, | |
| "eval_en_oof_Env_acc": 0.9629629629629629, | |
| "eval_en_oof_Env_f1": 0.9397590361445782, | |
| "eval_en_oof_Gov_acc": 0.9629629629629629, | |
| "eval_en_oof_Gov_f1": 0.9629629629629629, | |
| "eval_en_oof_Neu_acc": 0.8674698795180723, | |
| "eval_en_oof_Neu_f1": 0.8834355828220859, | |
| "eval_en_oof_Soc_acc": 0.9142857142857143, | |
| "eval_en_oof_Soc_f1": 0.920863309352518, | |
| "eval_en_oof_cls_acc": 0.9236111111111112, | |
| "eval_en_oof_cls_f1": 0.9267552228205362, | |
| "eval_en_oof_loss": 2.1492302417755127, | |
| "eval_en_oof_runtime": 5.5876, | |
| "eval_en_oof_samples_per_second": 335.921, | |
| "eval_en_oof_steps_per_second": 3.579, | |
| "eval_en_oof_total_cls_tokens": 288, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 17.941326530612244, | |
| "eval_vi_All_acc": 0.7927440063051382, | |
| "eval_vi_Env_acc": 0.9682539682539683, | |
| "eval_vi_Env_f1": 0.9581151832460734, | |
| "eval_vi_Gov_acc": 0.9270833333333334, | |
| "eval_vi_Gov_f1": 0.9343832020997376, | |
| "eval_vi_Neu_acc": 0.8930817610062893, | |
| "eval_vi_Neu_f1": 0.8847352024922117, | |
| "eval_vi_Soc_acc": 0.9085365853658537, | |
| "eval_vi_Soc_f1": 0.9197530864197531, | |
| "eval_vi_cls_acc": 0.9261363636363636, | |
| "eval_vi_cls_f1": 0.9242466685644439, | |
| "eval_vi_loss": 0.9583227038383484, | |
| "eval_vi_runtime": 12.7328, | |
| "eval_vi_samples_per_second": 345.563, | |
| "eval_vi_steps_per_second": 3.613, | |
| "eval_vi_total_cls_tokens": 704, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 17.941326530612244, | |
| "eval_dan_All_acc": 0.6766034747775863, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.125, | |
| "eval_dan_Gov_f1": 0.2222222222222222, | |
| "eval_dan_Neu_acc": 0.15789473684210525, | |
| "eval_dan_Neu_f1": 0.2727272727272727, | |
| "eval_dan_Soc_acc": 0.3, | |
| "eval_dan_Soc_f1": 0.4615384615384615, | |
| "eval_dan_cls_acc": 0.1891891891891892, | |
| "eval_dan_cls_f1": 0.23912198912198912, | |
| "eval_dan_loss": 2.0151352882385254, | |
| "eval_dan_runtime": 8.6539, | |
| "eval_dan_samples_per_second": 346.663, | |
| "eval_dan_steps_per_second": 3.698, | |
| "eval_dan_total_cls_tokens": 37, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 17.979591836734695, | |
| "grad_norm": 2.5318565368652344, | |
| "learning_rate": 2.4027422766672926e-05, | |
| "loss": 1.3646, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 18.01530612244898, | |
| "grad_norm": 2.4738309383392334, | |
| "learning_rate": 2.393824692561481e-05, | |
| "loss": 1.2922, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 18.053571428571427, | |
| "grad_norm": 2.424292802810669, | |
| "learning_rate": 2.3849084616415808e-05, | |
| "loss": 1.3885, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 18.091836734693878, | |
| "grad_norm": 2.4760782718658447, | |
| "learning_rate": 2.3759936975434087e-05, | |
| "loss": 1.3371, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 18.130102040816325, | |
| "grad_norm": 2.4807639122009277, | |
| "learning_rate": 2.3670805138840908e-05, | |
| "loss": 1.3671, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 18.168367346938776, | |
| "grad_norm": 2.555748701095581, | |
| "learning_rate": 2.3581690242606104e-05, | |
| "loss": 1.3362, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 18.206632653061224, | |
| "grad_norm": 2.454482078552246, | |
| "learning_rate": 2.349259342248358e-05, | |
| "loss": 1.3638, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 18.244897959183675, | |
| "grad_norm": 2.602994918823242, | |
| "learning_rate": 2.3403515813996892e-05, | |
| "loss": 1.3197, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 18.283163265306122, | |
| "grad_norm": 2.5649633407592773, | |
| "learning_rate": 2.331445855242474e-05, | |
| "loss": 1.3378, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 18.321428571428573, | |
| "grad_norm": 2.4638710021972656, | |
| "learning_rate": 2.3225422772786498e-05, | |
| "loss": 1.3987, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 18.321428571428573, | |
| "eval_en_All_acc": 0.6160801830264735, | |
| "eval_en_Env_acc": 0.9879518072289156, | |
| "eval_en_Env_f1": 0.9879518072289156, | |
| "eval_en_Gov_acc": 0.9117647058823529, | |
| "eval_en_Gov_f1": 0.9393939393939394, | |
| "eval_en_Neu_acc": 0.9104477611940298, | |
| "eval_en_Neu_f1": 0.9037037037037037, | |
| "eval_en_Soc_acc": 0.9852941176470589, | |
| "eval_en_Soc_f1": 0.9640287769784172, | |
| "eval_en_cls_acc": 0.951048951048951, | |
| "eval_en_cls_f1": 0.948769556826244, | |
| "eval_en_loss": 2.1800901889801025, | |
| "eval_en_runtime": 5.6479, | |
| "eval_en_samples_per_second": 332.336, | |
| "eval_en_steps_per_second": 3.541, | |
| "eval_en_total_cls_tokens": 286, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 18.321428571428573, | |
| "eval_en_oof_All_acc": 0.6198697405148351, | |
| "eval_en_oof_Env_acc": 0.9859154929577465, | |
| "eval_en_oof_Env_f1": 0.9722222222222222, | |
| "eval_en_oof_Gov_acc": 0.9433962264150944, | |
| "eval_en_oof_Gov_f1": 0.9259259259259259, | |
| "eval_en_oof_Neu_acc": 0.92, | |
| "eval_en_oof_Neu_f1": 0.9324324324324323, | |
| "eval_en_oof_Soc_acc": 0.9142857142857143, | |
| "eval_en_oof_Soc_f1": 0.9275362318840579, | |
| "eval_en_oof_cls_acc": 0.9405204460966543, | |
| "eval_en_oof_cls_f1": 0.9395292031161596, | |
| "eval_en_oof_loss": 2.2032523155212402, | |
| "eval_en_oof_runtime": 5.6094, | |
| "eval_en_oof_samples_per_second": 334.617, | |
| "eval_en_oof_steps_per_second": 3.565, | |
| "eval_en_oof_total_cls_tokens": 269, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 18.321428571428573, | |
| "eval_vi_All_acc": 0.7861200875638487, | |
| "eval_vi_Env_acc": 0.9515151515151515, | |
| "eval_vi_Env_f1": 0.9631901840490796, | |
| "eval_vi_Gov_acc": 0.8413793103448276, | |
| "eval_vi_Gov_f1": 0.8561403508771931, | |
| "eval_vi_Neu_acc": 0.89375, | |
| "eval_vi_Neu_f1": 0.8827160493827161, | |
| "eval_vi_Soc_acc": 0.8742138364779874, | |
| "eval_vi_Soc_f1": 0.8606811145510835, | |
| "eval_vi_cls_acc": 0.8918918918918919, | |
| "eval_vi_cls_f1": 0.8906819247150181, | |
| "eval_vi_loss": 0.9895921349525452, | |
| "eval_vi_runtime": 12.6435, | |
| "eval_vi_samples_per_second": 348.006, | |
| "eval_vi_steps_per_second": 3.638, | |
| "eval_vi_total_cls_tokens": 629, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 18.321428571428573, | |
| "eval_dan_All_acc": 0.675384686474747, | |
| "eval_dan_Env_acc": 1.0, | |
| "eval_dan_Env_f1": 1.0, | |
| "eval_dan_Gov_acc": 0.2, | |
| "eval_dan_Gov_f1": 0.28571428571428575, | |
| "eval_dan_Neu_acc": 0.3125, | |
| "eval_dan_Neu_f1": 0.47619047619047616, | |
| "eval_dan_Soc_acc": 0.2, | |
| "eval_dan_Soc_f1": 0.33333333333333337, | |
| "eval_dan_cls_acc": 0.2619047619047619, | |
| "eval_dan_cls_f1": 0.5238095238095238, | |
| "eval_dan_loss": 2.002314329147339, | |
| "eval_dan_runtime": 8.7953, | |
| "eval_dan_samples_per_second": 341.092, | |
| "eval_dan_steps_per_second": 3.638, | |
| "eval_dan_total_cls_tokens": 42, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 18.35969387755102, | |
| "grad_norm": 2.5380539894104004, | |
| "learning_rate": 2.313640960982776e-05, | |
| "loss": 1.3483, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 18.397959183673468, | |
| "grad_norm": 2.426342248916626, | |
| "learning_rate": 2.3047420198005885e-05, | |
| "loss": 1.2941, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 18.43622448979592, | |
| "grad_norm": 2.599245071411133, | |
| "learning_rate": 2.2958455671475514e-05, | |
| "loss": 1.3212, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 18.474489795918366, | |
| "grad_norm": 2.4708080291748047, | |
| "learning_rate": 2.286951716407413e-05, | |
| "loss": 1.3355, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 18.512755102040817, | |
| "grad_norm": 2.4804818630218506, | |
| "learning_rate": 2.2780605809307608e-05, | |
| "loss": 1.3834, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 18.551020408163264, | |
| "grad_norm": 2.576556921005249, | |
| "learning_rate": 2.2691722740335787e-05, | |
| "loss": 1.3733, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 18.589285714285715, | |
| "grad_norm": 2.4099221229553223, | |
| "learning_rate": 2.2602869089957974e-05, | |
| "loss": 1.3266, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 18.627551020408163, | |
| "grad_norm": 2.4236390590667725, | |
| "learning_rate": 2.2514045990598562e-05, | |
| "loss": 1.3541, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 18.665816326530614, | |
| "grad_norm": 2.5839293003082275, | |
| "learning_rate": 2.2425254574292588e-05, | |
| "loss": 1.3376, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 18.70408163265306, | |
| "grad_norm": 2.4446401596069336, | |
| "learning_rate": 2.233649597267126e-05, | |
| "loss": 1.3983, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 18.70408163265306, | |
| "eval_en_All_acc": 0.6345511369759672, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9818181818181818, | |
| "eval_en_Gov_acc": 0.9393939393939394, | |
| "eval_en_Gov_f1": 0.9538461538461539, | |
| "eval_en_Neu_acc": 0.8533333333333334, | |
| "eval_en_Neu_f1": 0.8767123287671234, | |
| "eval_en_Soc_acc": 0.9264705882352942, | |
| "eval_en_Soc_f1": 0.906474820143885, | |
| "eval_en_cls_acc": 0.9310344827586207, | |
| "eval_en_cls_f1": 0.929712871143836, | |
| "eval_en_loss": 2.0877373218536377, | |
| "eval_en_runtime": 5.6275, | |
| "eval_en_samples_per_second": 333.542, | |
| "eval_en_steps_per_second": 3.554, | |
| "eval_en_total_cls_tokens": 290, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 18.70408163265306, | |
| "eval_en_oof_All_acc": 0.6181894383906119, | |
| "eval_en_oof_Env_acc": 0.9583333333333334, | |
| "eval_en_oof_Env_f1": 0.9517241379310345, | |
| "eval_en_oof_Gov_acc": 0.9696969696969697, | |
| "eval_en_oof_Gov_f1": 0.955223880597015, | |
| "eval_en_oof_Neu_acc": 0.8518518518518519, | |
| "eval_en_oof_Neu_f1": 0.8734177215189873, | |
| "eval_en_oof_Soc_acc": 0.8928571428571429, | |
| "eval_en_oof_Soc_f1": 0.8849557522123894, | |
| "eval_en_oof_cls_acc": 0.9163636363636364, | |
| "eval_en_oof_cls_f1": 0.9163303730648567, | |
| "eval_en_oof_loss": 2.256789207458496, | |
| "eval_en_oof_runtime": 5.5958, | |
| "eval_en_oof_samples_per_second": 335.433, | |
| "eval_en_oof_steps_per_second": 3.574, | |
| "eval_en_oof_total_cls_tokens": 275, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 18.70408163265306, | |
| "eval_vi_All_acc": 0.7847435669469353, | |
| "eval_vi_Env_acc": 0.9625, | |
| "eval_vi_Env_f1": 0.9625000000000001, | |
| "eval_vi_Gov_acc": 0.8841463414634146, | |
| "eval_vi_Gov_f1": 0.9006211180124223, | |
| "eval_vi_Neu_acc": 0.9235668789808917, | |
| "eval_vi_Neu_f1": 0.9119496855345912, | |
| "eval_vi_Soc_acc": 0.8782051282051282, | |
| "eval_vi_Soc_f1": 0.8726114649681529, | |
| "eval_vi_cls_acc": 0.9120879120879121, | |
| "eval_vi_cls_f1": 0.9119205671287917, | |
| "eval_vi_loss": 0.9969497323036194, | |
| "eval_vi_runtime": 12.6933, | |
| "eval_vi_samples_per_second": 346.64, | |
| "eval_vi_steps_per_second": 3.624, | |
| "eval_vi_total_cls_tokens": 637, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 18.70408163265306, | |
| "eval_dan_All_acc": 0.6722669412205167, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.625, | |
| "eval_dan_Gov_f1": 0.7692307692307693, | |
| "eval_dan_Neu_acc": 0.3, | |
| "eval_dan_Neu_f1": 0.4615384615384615, | |
| "eval_dan_Soc_acc": 0.2, | |
| "eval_dan_Soc_f1": 0.33333333333333337, | |
| "eval_dan_cls_acc": 0.32558139534883723, | |
| "eval_dan_cls_f1": 0.391025641025641, | |
| "eval_dan_loss": 2.0452897548675537, | |
| "eval_dan_runtime": 8.6855, | |
| "eval_dan_samples_per_second": 345.405, | |
| "eval_dan_steps_per_second": 3.684, | |
| "eval_dan_total_cls_tokens": 43, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 18.742346938775512, | |
| "grad_norm": 2.57770037651062, | |
| "learning_rate": 2.224777131694759e-05, | |
| "loss": 1.3925, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 18.78061224489796, | |
| "grad_norm": 2.4741785526275635, | |
| "learning_rate": 2.2159081737901975e-05, | |
| "loss": 1.3552, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 18.818877551020407, | |
| "grad_norm": 2.4840309619903564, | |
| "learning_rate": 2.2070428365867724e-05, | |
| "loss": 1.3486, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "grad_norm": 2.4672648906707764, | |
| "learning_rate": 2.198181233071671e-05, | |
| "loss": 1.3592, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 18.895408163265305, | |
| "grad_norm": 2.4728000164031982, | |
| "learning_rate": 2.189323476184497e-05, | |
| "loss": 1.3207, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 18.933673469387756, | |
| "grad_norm": 2.39172625541687, | |
| "learning_rate": 2.1804696788158286e-05, | |
| "loss": 1.3446, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 18.971938775510203, | |
| "grad_norm": 2.3614144325256348, | |
| "learning_rate": 2.1716199538057782e-05, | |
| "loss": 1.3239, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 19.007653061224488, | |
| "grad_norm": 2.2942185401916504, | |
| "learning_rate": 2.162774413942561e-05, | |
| "loss": 1.2438, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 19.04591836734694, | |
| "grad_norm": 2.2886712551116943, | |
| "learning_rate": 2.1539331719610505e-05, | |
| "loss": 1.3054, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 19.084183673469386, | |
| "grad_norm": 2.6321005821228027, | |
| "learning_rate": 2.1450963405413452e-05, | |
| "loss": 1.3718, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.084183673469386, | |
| "eval_en_All_acc": 0.6258620689655172, | |
| "eval_en_Env_acc": 0.9841269841269841, | |
| "eval_en_Env_f1": 0.9763779527559054, | |
| "eval_en_Gov_acc": 0.96, | |
| "eval_en_Gov_f1": 0.9473684210526316, | |
| "eval_en_Neu_acc": 0.9107142857142857, | |
| "eval_en_Neu_f1": 0.918918918918919, | |
| "eval_en_Soc_acc": 0.9436619718309859, | |
| "eval_en_Soc_f1": 0.9571428571428571, | |
| "eval_en_cls_acc": 0.9509433962264151, | |
| "eval_en_cls_f1": 0.9499520374675782, | |
| "eval_en_loss": 2.14664626121521, | |
| "eval_en_runtime": 5.6252, | |
| "eval_en_samples_per_second": 333.68, | |
| "eval_en_steps_per_second": 3.555, | |
| "eval_en_total_cls_tokens": 265, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.084183673469386, | |
| "eval_en_oof_All_acc": 0.6295859257670028, | |
| "eval_en_oof_Env_acc": 0.9574468085106383, | |
| "eval_en_oof_Env_f1": 0.967741935483871, | |
| "eval_en_oof_Gov_acc": 0.9833333333333333, | |
| "eval_en_oof_Gov_f1": 0.9752066115702478, | |
| "eval_en_oof_Neu_acc": 0.8955223880597015, | |
| "eval_en_oof_Neu_f1": 0.9090909090909091, | |
| "eval_en_oof_Soc_acc": 0.9411764705882353, | |
| "eval_en_oof_Soc_f1": 0.9275362318840579, | |
| "eval_en_oof_cls_acc": 0.9421487603305785, | |
| "eval_en_oof_cls_f1": 0.9448939220072714, | |
| "eval_en_oof_loss": 2.153109073638916, | |
| "eval_en_oof_runtime": 5.652, | |
| "eval_en_oof_samples_per_second": 332.095, | |
| "eval_en_oof_steps_per_second": 3.539, | |
| "eval_en_oof_total_cls_tokens": 242, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.084183673469386, | |
| "eval_vi_All_acc": 0.7869072661378209, | |
| "eval_vi_Env_acc": 0.9625, | |
| "eval_vi_Env_f1": 0.9535603715170279, | |
| "eval_vi_Gov_acc": 0.9294871794871795, | |
| "eval_vi_Gov_f1": 0.9177215189873418, | |
| "eval_vi_Neu_acc": 0.8614457831325302, | |
| "eval_vi_Neu_f1": 0.8881987577639753, | |
| "eval_vi_Soc_acc": 0.9320987654320988, | |
| "eval_vi_Soc_f1": 0.9235474006116208, | |
| "eval_vi_cls_acc": 0.9208074534161491, | |
| "eval_vi_cls_f1": 0.9207570122199914, | |
| "eval_vi_loss": 0.9878730773925781, | |
| "eval_vi_runtime": 12.7668, | |
| "eval_vi_samples_per_second": 344.644, | |
| "eval_vi_steps_per_second": 3.603, | |
| "eval_vi_total_cls_tokens": 644, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.084183673469386, | |
| "eval_dan_All_acc": 0.6607276119402985, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2222222222222222, | |
| "eval_dan_Gov_f1": 0.3636363636363636, | |
| "eval_dan_Neu_acc": 0.2222222222222222, | |
| "eval_dan_Neu_f1": 0.3636363636363636, | |
| "eval_dan_Soc_acc": 0.2, | |
| "eval_dan_Soc_f1": 0.33333333333333337, | |
| "eval_dan_cls_acc": 0.20754716981132076, | |
| "eval_dan_cls_f1": 0.26515151515151514, | |
| "eval_dan_loss": 2.13490891456604, | |
| "eval_dan_runtime": 8.7156, | |
| "eval_dan_samples_per_second": 344.209, | |
| "eval_dan_steps_per_second": 3.672, | |
| "eval_dan_total_cls_tokens": 53, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.122448979591837, | |
| "grad_norm": 2.4047324657440186, | |
| "learning_rate": 2.1362640323073295e-05, | |
| "loss": 1.3496, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 19.160714285714285, | |
| "grad_norm": 2.364729881286621, | |
| "learning_rate": 2.1274363598252448e-05, | |
| "loss": 1.3361, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 19.198979591836736, | |
| "grad_norm": 2.4808499813079834, | |
| "learning_rate": 2.118613435602248e-05, | |
| "loss": 1.335, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 19.237244897959183, | |
| "grad_norm": 2.3506522178649902, | |
| "learning_rate": 2.1097953720849797e-05, | |
| "loss": 1.3102, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 19.275510204081634, | |
| "grad_norm": 2.6409342288970947, | |
| "learning_rate": 2.1009822816581337e-05, | |
| "loss": 1.3184, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 19.31377551020408, | |
| "grad_norm": 2.61771297454834, | |
| "learning_rate": 2.092174276643022e-05, | |
| "loss": 1.3685, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 19.352040816326532, | |
| "grad_norm": 2.3466103076934814, | |
| "learning_rate": 2.0833714692961413e-05, | |
| "loss": 1.3483, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 19.39030612244898, | |
| "grad_norm": 2.64559006690979, | |
| "learning_rate": 2.0745739718077494e-05, | |
| "loss": 1.3412, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 19.428571428571427, | |
| "grad_norm": 2.5324528217315674, | |
| "learning_rate": 2.0657818963004284e-05, | |
| "loss": 1.335, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 19.466836734693878, | |
| "grad_norm": 2.4550390243530273, | |
| "learning_rate": 2.0569953548276562e-05, | |
| "loss": 1.3533, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 19.466836734693878, | |
| "eval_en_All_acc": 0.6110003148945103, | |
| "eval_en_Env_acc": 0.95, | |
| "eval_en_Env_f1": 0.9500000000000001, | |
| "eval_en_Gov_acc": 0.9565217391304348, | |
| "eval_en_Gov_f1": 0.9705882352941176, | |
| "eval_en_Neu_acc": 0.8472222222222222, | |
| "eval_en_Neu_f1": 0.8714285714285713, | |
| "eval_en_Soc_acc": 0.9436619718309859, | |
| "eval_en_Soc_f1": 0.9054054054054054, | |
| "eval_en_cls_acc": 0.9246575342465754, | |
| "eval_en_cls_f1": 0.9243555530320237, | |
| "eval_en_loss": 2.274594783782959, | |
| "eval_en_runtime": 5.618, | |
| "eval_en_samples_per_second": 334.107, | |
| "eval_en_steps_per_second": 3.56, | |
| "eval_en_total_cls_tokens": 292, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 19.466836734693878, | |
| "eval_en_oof_All_acc": 0.6264654798089448, | |
| "eval_en_oof_Env_acc": 0.9857142857142858, | |
| "eval_en_oof_Env_f1": 0.971830985915493, | |
| "eval_en_oof_Gov_acc": 0.9846153846153847, | |
| "eval_en_oof_Gov_f1": 0.9696969696969696, | |
| "eval_en_oof_Neu_acc": 0.873015873015873, | |
| "eval_en_oof_Neu_f1": 0.9016393442622951, | |
| "eval_en_oof_Soc_acc": 0.9538461538461539, | |
| "eval_en_oof_Soc_f1": 0.9538461538461539, | |
| "eval_en_oof_cls_acc": 0.9505703422053232, | |
| "eval_en_oof_cls_f1": 0.9492533634302279, | |
| "eval_en_oof_loss": 2.1584627628326416, | |
| "eval_en_oof_runtime": 5.6238, | |
| "eval_en_oof_samples_per_second": 333.758, | |
| "eval_en_oof_steps_per_second": 3.556, | |
| "eval_en_oof_total_cls_tokens": 263, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 19.466836734693878, | |
| "eval_vi_All_acc": 0.7863279012859895, | |
| "eval_vi_Env_acc": 0.9863945578231292, | |
| "eval_vi_Env_f1": 0.9385113268608414, | |
| "eval_vi_Gov_acc": 0.8837209302325582, | |
| "eval_vi_Gov_f1": 0.9047619047619047, | |
| "eval_vi_Neu_acc": 0.906832298136646, | |
| "eval_vi_Neu_f1": 0.9329073482428115, | |
| "eval_vi_Soc_acc": 0.896969696969697, | |
| "eval_vi_Soc_f1": 0.891566265060241, | |
| "eval_vi_cls_acc": 0.9162790697674419, | |
| "eval_vi_cls_f1": 0.9169367112314497, | |
| "eval_vi_loss": 0.9970201253890991, | |
| "eval_vi_runtime": 12.7392, | |
| "eval_vi_samples_per_second": 345.39, | |
| "eval_vi_steps_per_second": 3.611, | |
| "eval_vi_total_cls_tokens": 645, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 19.466836734693878, | |
| "eval_dan_All_acc": 0.6656445993031359, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2727272727272727, | |
| "eval_dan_Gov_f1": 0.42857142857142855, | |
| "eval_dan_Neu_acc": 0.09523809523809523, | |
| "eval_dan_Neu_f1": 0.17391304347826084, | |
| "eval_dan_Soc_acc": 0.26666666666666666, | |
| "eval_dan_Soc_f1": 0.4210526315789474, | |
| "eval_dan_cls_acc": 0.1875, | |
| "eval_dan_cls_f1": 0.2558842759071592, | |
| "eval_dan_loss": 2.116994857788086, | |
| "eval_dan_runtime": 8.8841, | |
| "eval_dan_samples_per_second": 337.683, | |
| "eval_dan_steps_per_second": 3.602, | |
| "eval_dan_total_cls_tokens": 48, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 19.505102040816325, | |
| "grad_norm": 2.4608571529388428, | |
| "learning_rate": 2.0482144593723857e-05, | |
| "loss": 1.3289, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 19.543367346938776, | |
| "grad_norm": 2.4224390983581543, | |
| "learning_rate": 2.0394393218456065e-05, | |
| "loss": 1.2875, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 19.581632653061224, | |
| "grad_norm": 2.546992063522339, | |
| "learning_rate": 2.0306700540849287e-05, | |
| "loss": 1.3179, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 19.619897959183675, | |
| "grad_norm": 2.393714666366577, | |
| "learning_rate": 2.0219067678531494e-05, | |
| "loss": 1.3022, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 19.658163265306122, | |
| "grad_norm": 2.6133229732513428, | |
| "learning_rate": 2.0131495748368366e-05, | |
| "loss": 1.3343, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 19.696428571428573, | |
| "grad_norm": 2.3336665630340576, | |
| "learning_rate": 2.004398586644899e-05, | |
| "loss": 1.3418, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 19.73469387755102, | |
| "grad_norm": 2.3034348487854004, | |
| "learning_rate": 1.995653914807164e-05, | |
| "loss": 1.3341, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 19.772959183673468, | |
| "grad_norm": 2.499795436859131, | |
| "learning_rate": 1.986915670772962e-05, | |
| "loss": 1.3205, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 19.81122448979592, | |
| "grad_norm": 2.534120798110962, | |
| "learning_rate": 1.9781839659097e-05, | |
| "loss": 1.3247, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 19.849489795918366, | |
| "grad_norm": 2.439058542251587, | |
| "learning_rate": 1.9694589115014432e-05, | |
| "loss": 1.3483, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 19.849489795918366, | |
| "eval_en_All_acc": 0.6285652782262404, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.963855421686747, | |
| "eval_en_Gov_acc": 0.971830985915493, | |
| "eval_en_Gov_f1": 0.9517241379310345, | |
| "eval_en_Neu_acc": 0.8620689655172413, | |
| "eval_en_Neu_f1": 0.9009009009009009, | |
| "eval_en_Soc_acc": 0.9295774647887324, | |
| "eval_en_Soc_f1": 0.9565217391304348, | |
| "eval_en_cls_acc": 0.9464285714285714, | |
| "eval_en_cls_f1": 0.9432505499122793, | |
| "eval_en_loss": 2.131176233291626, | |
| "eval_en_runtime": 5.622, | |
| "eval_en_samples_per_second": 333.867, | |
| "eval_en_steps_per_second": 3.557, | |
| "eval_en_total_cls_tokens": 280, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 19.849489795918366, | |
| "eval_en_oof_All_acc": 0.6296911325141149, | |
| "eval_en_oof_Env_acc": 0.9866666666666667, | |
| "eval_en_oof_Env_f1": 0.9801324503311258, | |
| "eval_en_oof_Gov_acc": 0.9811320754716981, | |
| "eval_en_oof_Gov_f1": 0.9369369369369369, | |
| "eval_en_oof_Neu_acc": 0.9036144578313253, | |
| "eval_en_oof_Neu_f1": 0.9036144578313253, | |
| "eval_en_oof_Soc_acc": 0.8615384615384616, | |
| "eval_en_oof_Soc_f1": 0.903225806451613, | |
| "eval_en_oof_cls_acc": 0.9311594202898551, | |
| "eval_en_oof_cls_f1": 0.9309774128877503, | |
| "eval_en_oof_loss": 2.1567788124084473, | |
| "eval_en_oof_runtime": 5.5695, | |
| "eval_en_oof_samples_per_second": 337.014, | |
| "eval_en_oof_steps_per_second": 3.591, | |
| "eval_en_oof_total_cls_tokens": 276, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 19.849489795918366, | |
| "eval_vi_All_acc": 0.7883515473393933, | |
| "eval_vi_Env_acc": 0.9731543624161074, | |
| "eval_vi_Env_f1": 0.9602649006622517, | |
| "eval_vi_Gov_acc": 0.9150326797385621, | |
| "eval_vi_Gov_f1": 0.8974358974358974, | |
| "eval_vi_Neu_acc": 0.8950617283950617, | |
| "eval_vi_Neu_f1": 0.9006211180124224, | |
| "eval_vi_Soc_acc": 0.8544303797468354, | |
| "eval_vi_Soc_f1": 0.8766233766233766, | |
| "eval_vi_cls_acc": 0.9083601286173634, | |
| "eval_vi_cls_f1": 0.9087363231834871, | |
| "eval_vi_loss": 0.9945113658905029, | |
| "eval_vi_runtime": 12.711, | |
| "eval_vi_samples_per_second": 346.157, | |
| "eval_vi_steps_per_second": 3.619, | |
| "eval_vi_total_cls_tokens": 622, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 19.849489795918366, | |
| "eval_dan_All_acc": 0.6784700572332605, | |
| "eval_dan_Env_acc": 0.3333333333333333, | |
| "eval_dan_Env_f1": 0.5, | |
| "eval_dan_Gov_acc": 0.2, | |
| "eval_dan_Gov_f1": 0.33333333333333337, | |
| "eval_dan_Neu_acc": 0.4, | |
| "eval_dan_Neu_f1": 0.5714285714285715, | |
| "eval_dan_Soc_acc": 0.06666666666666667, | |
| "eval_dan_Soc_f1": 0.125, | |
| "eval_dan_cls_acc": 0.23684210526315788, | |
| "eval_dan_cls_f1": 0.3824404761904762, | |
| "eval_dan_loss": 2.0037529468536377, | |
| "eval_dan_runtime": 8.7719, | |
| "eval_dan_samples_per_second": 342.002, | |
| "eval_dan_steps_per_second": 3.648, | |
| "eval_dan_total_cls_tokens": 38, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 19.887755102040817, | |
| "grad_norm": 2.472348928451538, | |
| "learning_rate": 1.9607406187475016e-05, | |
| "loss": 1.3072, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 19.926020408163264, | |
| "grad_norm": 2.4986958503723145, | |
| "learning_rate": 1.952029198761005e-05, | |
| "loss": 1.3443, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 19.964285714285715, | |
| "grad_norm": 2.3642678260803223, | |
| "learning_rate": 1.9433247625674928e-05, | |
| "loss": 1.3544, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 1.5625319480895996, | |
| "learning_rate": 1.9346274211034993e-05, | |
| "loss": 1.222, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 20.038265306122447, | |
| "grad_norm": 2.4192848205566406, | |
| "learning_rate": 1.925937285215133e-05, | |
| "loss": 1.27, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 20.0765306122449, | |
| "grad_norm": 2.483203649520874, | |
| "learning_rate": 1.9172544656566734e-05, | |
| "loss": 1.3191, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 20.114795918367346, | |
| "grad_norm": 2.427279233932495, | |
| "learning_rate": 1.90857907308915e-05, | |
| "loss": 1.3111, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 20.153061224489797, | |
| "grad_norm": 2.3480257987976074, | |
| "learning_rate": 1.8999112180789413e-05, | |
| "loss": 1.3298, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 20.191326530612244, | |
| "grad_norm": 2.4819021224975586, | |
| "learning_rate": 1.8912510110963572e-05, | |
| "loss": 1.3459, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 20.229591836734695, | |
| "grad_norm": 2.3521764278411865, | |
| "learning_rate": 1.882598562514236e-05, | |
| "loss": 1.2847, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 20.229591836734695, | |
| "eval_en_All_acc": 0.6154586273252085, | |
| "eval_en_Env_acc": 0.9864864864864865, | |
| "eval_en_Env_f1": 0.9733333333333333, | |
| "eval_en_Gov_acc": 0.9833333333333333, | |
| "eval_en_Gov_f1": 0.9516129032258064, | |
| "eval_en_Neu_acc": 0.8529411764705882, | |
| "eval_en_Neu_f1": 0.8923076923076922, | |
| "eval_en_Soc_acc": 0.9382716049382716, | |
| "eval_en_Soc_f1": 0.9382716049382716, | |
| "eval_en_cls_acc": 0.9399293286219081, | |
| "eval_en_cls_f1": 0.9388813834512759, | |
| "eval_en_loss": 2.206486940383911, | |
| "eval_en_runtime": 5.61, | |
| "eval_en_samples_per_second": 334.584, | |
| "eval_en_steps_per_second": 3.565, | |
| "eval_en_total_cls_tokens": 283, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 20.229591836734695, | |
| "eval_en_oof_All_acc": 0.628696126568467, | |
| "eval_en_oof_Env_acc": 0.96, | |
| "eval_en_oof_Env_f1": 0.9504950495049505, | |
| "eval_en_oof_Gov_acc": 0.9846153846153847, | |
| "eval_en_oof_Gov_f1": 0.9481481481481482, | |
| "eval_en_oof_Neu_acc": 0.8831168831168831, | |
| "eval_en_oof_Neu_f1": 0.918918918918919, | |
| "eval_en_oof_Soc_acc": 0.9538461538461539, | |
| "eval_en_oof_Soc_f1": 0.9538461538461539, | |
| "eval_en_oof_cls_acc": 0.9416342412451362, | |
| "eval_en_oof_cls_f1": 0.9428520676045429, | |
| "eval_en_oof_loss": 2.1473746299743652, | |
| "eval_en_oof_runtime": 5.5995, | |
| "eval_en_oof_samples_per_second": 335.208, | |
| "eval_en_oof_steps_per_second": 3.572, | |
| "eval_en_oof_total_cls_tokens": 257, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 20.229591836734695, | |
| "eval_vi_All_acc": 0.7894284269094588, | |
| "eval_vi_Env_acc": 0.9702380952380952, | |
| "eval_vi_Env_f1": 0.9760479041916169, | |
| "eval_vi_Gov_acc": 0.9207317073170732, | |
| "eval_vi_Gov_f1": 0.893491124260355, | |
| "eval_vi_Neu_acc": 0.9096385542168675, | |
| "eval_vi_Neu_f1": 0.9263803680981595, | |
| "eval_vi_Soc_acc": 0.8741258741258742, | |
| "eval_vi_Soc_f1": 0.8802816901408451, | |
| "eval_vi_cls_acc": 0.9204368174726989, | |
| "eval_vi_cls_f1": 0.9190502716727441, | |
| "eval_vi_loss": 0.98747718334198, | |
| "eval_vi_runtime": 12.7202, | |
| "eval_vi_samples_per_second": 345.905, | |
| "eval_vi_steps_per_second": 3.616, | |
| "eval_vi_total_cls_tokens": 641, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 20.229591836734695, | |
| "eval_dan_All_acc": 0.677609310520703, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2, | |
| "eval_dan_Gov_f1": 0.33333333333333337, | |
| "eval_dan_Neu_acc": 0.13333333333333333, | |
| "eval_dan_Neu_f1": 0.23529411764705882, | |
| "eval_dan_Soc_acc": 0.1875, | |
| "eval_dan_Soc_f1": 0.3157894736842105, | |
| "eval_dan_cls_acc": 0.16279069767441862, | |
| "eval_dan_cls_f1": 0.2211042311661507, | |
| "eval_dan_loss": 2.030961036682129, | |
| "eval_dan_runtime": 8.9064, | |
| "eval_dan_samples_per_second": 336.837, | |
| "eval_dan_steps_per_second": 3.593, | |
| "eval_dan_total_cls_tokens": 43, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 20.267857142857142, | |
| "grad_norm": 2.6137948036193848, | |
| "learning_rate": 1.8739539826065388e-05, | |
| "loss": 1.3853, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 20.306122448979593, | |
| "grad_norm": 2.658452033996582, | |
| "learning_rate": 1.8653173815469378e-05, | |
| "loss": 1.3588, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 20.34438775510204, | |
| "grad_norm": 2.4993982315063477, | |
| "learning_rate": 1.8566888694074186e-05, | |
| "loss": 1.3909, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 20.382653061224488, | |
| "grad_norm": 2.4775662422180176, | |
| "learning_rate": 1.8480685561568753e-05, | |
| "loss": 1.2925, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 20.42091836734694, | |
| "grad_norm": 2.5399820804595947, | |
| "learning_rate": 1.839456551659707e-05, | |
| "loss": 1.3325, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 20.459183673469386, | |
| "grad_norm": 2.340092897415161, | |
| "learning_rate": 1.830852965674419e-05, | |
| "loss": 1.3272, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 20.497448979591837, | |
| "grad_norm": 2.6893601417541504, | |
| "learning_rate": 1.822257907852227e-05, | |
| "loss": 1.2918, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 20.535714285714285, | |
| "grad_norm": 2.5359303951263428, | |
| "learning_rate": 1.8136714877356544e-05, | |
| "loss": 1.3231, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 20.573979591836736, | |
| "grad_norm": 2.436483144760132, | |
| "learning_rate": 1.805093814757138e-05, | |
| "loss": 1.3074, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 20.612244897959183, | |
| "grad_norm": 2.3954195976257324, | |
| "learning_rate": 1.796524998237634e-05, | |
| "loss": 1.3093, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 20.612244897959183, | |
| "eval_en_All_acc": 0.6218145869947276, | |
| "eval_en_Env_acc": 0.971830985915493, | |
| "eval_en_Env_f1": 0.971830985915493, | |
| "eval_en_Gov_acc": 0.984375, | |
| "eval_en_Gov_f1": 0.9618320610687023, | |
| "eval_en_Neu_acc": 0.9078947368421053, | |
| "eval_en_Neu_f1": 0.9078947368421053, | |
| "eval_en_Soc_acc": 0.9032258064516129, | |
| "eval_en_Soc_f1": 0.9256198347107438, | |
| "eval_en_cls_acc": 0.9413919413919414, | |
| "eval_en_cls_f1": 0.9417944046342611, | |
| "eval_en_loss": 2.1507225036621094, | |
| "eval_en_runtime": 5.6119, | |
| "eval_en_samples_per_second": 334.468, | |
| "eval_en_steps_per_second": 3.564, | |
| "eval_en_total_cls_tokens": 273, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 20.612244897959183, | |
| "eval_en_oof_All_acc": 0.6235158138068719, | |
| "eval_en_oof_Env_acc": 0.9859154929577465, | |
| "eval_en_oof_Env_f1": 0.9722222222222222, | |
| "eval_en_oof_Gov_acc": 0.9605263157894737, | |
| "eval_en_oof_Gov_f1": 0.9668874172185431, | |
| "eval_en_oof_Neu_acc": 0.9027777777777778, | |
| "eval_en_oof_Neu_f1": 0.87248322147651, | |
| "eval_en_oof_Soc_acc": 0.8405797101449275, | |
| "eval_en_oof_Soc_f1": 0.8787878787878787, | |
| "eval_en_oof_cls_acc": 0.9236111111111112, | |
| "eval_en_oof_cls_f1": 0.9225951849262884, | |
| "eval_en_oof_loss": 2.1861770153045654, | |
| "eval_en_oof_runtime": 5.541, | |
| "eval_en_oof_samples_per_second": 338.748, | |
| "eval_en_oof_steps_per_second": 3.609, | |
| "eval_en_oof_total_cls_tokens": 288, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 20.612244897959183, | |
| "eval_vi_All_acc": 0.7886962269907455, | |
| "eval_vi_Env_acc": 0.9510869565217391, | |
| "eval_vi_Env_f1": 0.9459459459459459, | |
| "eval_vi_Gov_acc": 0.9585798816568047, | |
| "eval_vi_Gov_f1": 0.9391304347826087, | |
| "eval_vi_Neu_acc": 0.896969696969697, | |
| "eval_vi_Neu_f1": 0.9051987767584097, | |
| "eval_vi_Soc_acc": 0.8670886075949367, | |
| "eval_vi_Soc_f1": 0.8838709677419354, | |
| "eval_vi_cls_acc": 0.9201183431952663, | |
| "eval_vi_cls_f1": 0.9185365313072249, | |
| "eval_vi_loss": 0.9762837886810303, | |
| "eval_vi_runtime": 12.7093, | |
| "eval_vi_samples_per_second": 346.204, | |
| "eval_vi_steps_per_second": 3.619, | |
| "eval_vi_total_cls_tokens": 676, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 20.612244897959183, | |
| "eval_dan_All_acc": 0.678429140580535, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.5, | |
| "eval_dan_Gov_f1": 0.6666666666666666, | |
| "eval_dan_Neu_acc": 0.25, | |
| "eval_dan_Neu_f1": 0.4, | |
| "eval_dan_Soc_acc": 0.125, | |
| "eval_dan_Soc_f1": 0.2222222222222222, | |
| "eval_dan_cls_acc": 0.23404255319148937, | |
| "eval_dan_cls_f1": 0.3222222222222222, | |
| "eval_dan_loss": 2.0372114181518555, | |
| "eval_dan_runtime": 8.7027, | |
| "eval_dan_samples_per_second": 344.721, | |
| "eval_dan_steps_per_second": 3.677, | |
| "eval_dan_total_cls_tokens": 47, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 20.650510204081634, | |
| "grad_norm": 2.7092413902282715, | |
| "learning_rate": 1.7879651473852277e-05, | |
| "loss": 1.3073, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 20.68877551020408, | |
| "grad_norm": 2.421847343444824, | |
| "learning_rate": 1.7794143712937346e-05, | |
| "loss": 1.3527, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 20.727040816326532, | |
| "grad_norm": 2.602546453475952, | |
| "learning_rate": 1.7708727789413147e-05, | |
| "loss": 1.311, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 20.76530612244898, | |
| "grad_norm": 2.3734261989593506, | |
| "learning_rate": 1.762340479189086e-05, | |
| "loss": 1.3226, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 20.803571428571427, | |
| "grad_norm": 2.3179080486297607, | |
| "learning_rate": 1.7538175807797296e-05, | |
| "loss": 1.3012, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 20.841836734693878, | |
| "grad_norm": 2.30216646194458, | |
| "learning_rate": 1.74530419233611e-05, | |
| "loss": 1.3185, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 20.880102040816325, | |
| "grad_norm": 2.353257417678833, | |
| "learning_rate": 1.7368004223598912e-05, | |
| "loss": 1.2987, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 20.918367346938776, | |
| "grad_norm": 2.5512802600860596, | |
| "learning_rate": 1.7283063792301472e-05, | |
| "loss": 1.378, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 20.956632653061224, | |
| "grad_norm": 2.3176631927490234, | |
| "learning_rate": 1.7198221712019868e-05, | |
| "loss": 1.3153, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 20.994897959183675, | |
| "grad_norm": 2.616454601287842, | |
| "learning_rate": 1.711347906405173e-05, | |
| "loss": 1.3309, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 20.994897959183675, | |
| "eval_en_All_acc": 0.6183484212850519, | |
| "eval_en_Env_acc": 0.9583333333333334, | |
| "eval_en_Env_f1": 0.965034965034965, | |
| "eval_en_Gov_acc": 0.9682539682539683, | |
| "eval_en_Gov_f1": 0.953125, | |
| "eval_en_Neu_acc": 0.9, | |
| "eval_en_Neu_f1": 0.9130434782608695, | |
| "eval_en_Soc_acc": 0.9466666666666667, | |
| "eval_en_Soc_f1": 0.9403973509933775, | |
| "eval_en_cls_acc": 0.9428571428571428, | |
| "eval_en_cls_f1": 0.942900198572303, | |
| "eval_en_loss": 2.2630903720855713, | |
| "eval_en_runtime": 5.6535, | |
| "eval_en_samples_per_second": 332.008, | |
| "eval_en_steps_per_second": 3.538, | |
| "eval_en_total_cls_tokens": 280, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 20.994897959183675, | |
| "eval_en_oof_All_acc": 0.63000325414904, | |
| "eval_en_oof_Env_acc": 0.9852941176470589, | |
| "eval_en_oof_Env_f1": 0.9710144927536232, | |
| "eval_en_oof_Gov_acc": 0.9230769230769231, | |
| "eval_en_oof_Gov_f1": 0.9090909090909091, | |
| "eval_en_oof_Neu_acc": 0.9117647058823529, | |
| "eval_en_oof_Neu_f1": 0.9185185185185185, | |
| "eval_en_oof_Soc_acc": 0.9402985074626866, | |
| "eval_en_oof_Soc_f1": 0.9618320610687023, | |
| "eval_en_oof_cls_acc": 0.9402985074626866, | |
| "eval_en_oof_cls_f1": 0.9401139953579383, | |
| "eval_en_oof_loss": 2.1700963973999023, | |
| "eval_en_oof_runtime": 5.6175, | |
| "eval_en_oof_samples_per_second": 334.137, | |
| "eval_en_oof_steps_per_second": 3.56, | |
| "eval_en_oof_total_cls_tokens": 268, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 20.994897959183675, | |
| "eval_vi_All_acc": 0.7910528206970895, | |
| "eval_vi_Env_acc": 0.9607843137254902, | |
| "eval_vi_Env_f1": 0.9483870967741935, | |
| "eval_vi_Gov_acc": 0.9285714285714286, | |
| "eval_vi_Gov_f1": 0.9069767441860465, | |
| "eval_vi_Neu_acc": 0.8466257668711656, | |
| "eval_vi_Neu_f1": 0.8846153846153846, | |
| "eval_vi_Soc_acc": 0.8757396449704142, | |
| "eval_vi_Soc_f1": 0.8705882352941177, | |
| "eval_vi_cls_acc": 0.9019908116385911, | |
| "eval_vi_cls_f1": 0.9026418652174355, | |
| "eval_vi_loss": 0.9713738560676575, | |
| "eval_vi_runtime": 12.4294, | |
| "eval_vi_samples_per_second": 353.998, | |
| "eval_vi_steps_per_second": 3.701, | |
| "eval_vi_total_cls_tokens": 653, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 20.994897959183675, | |
| "eval_dan_All_acc": 0.6734921298230951, | |
| "eval_dan_Env_acc": 0.3333333333333333, | |
| "eval_dan_Env_f1": 0.5, | |
| "eval_dan_Gov_acc": 0.16666666666666666, | |
| "eval_dan_Gov_f1": 0.2857142857142857, | |
| "eval_dan_Neu_acc": 0.2777777777777778, | |
| "eval_dan_Neu_f1": 0.4166666666666667, | |
| "eval_dan_Soc_acc": 0.19047619047619047, | |
| "eval_dan_Soc_f1": 0.32, | |
| "eval_dan_cls_acc": 0.2222222222222222, | |
| "eval_dan_cls_f1": 0.38059523809523815, | |
| "eval_dan_loss": 2.0704948902130127, | |
| "eval_dan_runtime": 8.9653, | |
| "eval_dan_samples_per_second": 334.623, | |
| "eval_dan_steps_per_second": 3.569, | |
| "eval_dan_total_cls_tokens": 54, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 21.03061224489796, | |
| "grad_norm": 2.3630640506744385, | |
| "learning_rate": 1.7028836928427437e-05, | |
| "loss": 1.248, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 21.068877551020407, | |
| "grad_norm": 2.788430690765381, | |
| "learning_rate": 1.694429638389634e-05, | |
| "loss": 1.3217, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 21.107142857142858, | |
| "grad_norm": 2.44146466255188, | |
| "learning_rate": 1.6859858507913057e-05, | |
| "loss": 1.3272, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 21.145408163265305, | |
| "grad_norm": 2.4120965003967285, | |
| "learning_rate": 1.6775524376623698e-05, | |
| "loss": 1.3567, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 21.183673469387756, | |
| "grad_norm": 2.4673852920532227, | |
| "learning_rate": 1.6691295064852153e-05, | |
| "loss": 1.2903, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 21.221938775510203, | |
| "grad_norm": 2.606454849243164, | |
| "learning_rate": 1.660717164608641e-05, | |
| "loss": 1.2804, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 21.260204081632654, | |
| "grad_norm": 2.5645008087158203, | |
| "learning_rate": 1.6523155192464895e-05, | |
| "loss": 1.3601, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 21.2984693877551, | |
| "grad_norm": 2.4148519039154053, | |
| "learning_rate": 1.643924677476276e-05, | |
| "loss": 1.3226, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 21.336734693877553, | |
| "grad_norm": 2.5401194095611572, | |
| "learning_rate": 1.635544746237824e-05, | |
| "loss": 1.3199, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 21.375, | |
| "grad_norm": 2.3255534172058105, | |
| "learning_rate": 1.627175832331909e-05, | |
| "loss": 1.3569, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 21.375, | |
| "eval_en_All_acc": 0.6166510367823278, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9774436090225563, | |
| "eval_en_Gov_acc": 0.9833333333333333, | |
| "eval_en_Gov_f1": 0.944, | |
| "eval_en_Neu_acc": 0.8450704225352113, | |
| "eval_en_Neu_f1": 0.8888888888888888, | |
| "eval_en_Soc_acc": 0.9418604651162791, | |
| "eval_en_Soc_f1": 0.9473684210526314, | |
| "eval_en_cls_acc": 0.9397163120567376, | |
| "eval_en_cls_f1": 0.9394252297410192, | |
| "eval_en_loss": 2.242143154144287, | |
| "eval_en_runtime": 5.5972, | |
| "eval_en_samples_per_second": 335.346, | |
| "eval_en_steps_per_second": 3.573, | |
| "eval_en_total_cls_tokens": 282, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 21.375, | |
| "eval_en_oof_All_acc": 0.6111463620981388, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9763779527559054, | |
| "eval_en_oof_Gov_acc": 0.9482758620689655, | |
| "eval_en_oof_Gov_f1": 0.9565217391304347, | |
| "eval_en_oof_Neu_acc": 0.9135802469135802, | |
| "eval_en_oof_Neu_f1": 0.9192546583850932, | |
| "eval_en_oof_Soc_acc": 0.9230769230769231, | |
| "eval_en_oof_Soc_f1": 0.9290322580645162, | |
| "eval_en_oof_cls_acc": 0.942652329749104, | |
| "eval_en_oof_cls_f1": 0.9452966520839874, | |
| "eval_en_oof_loss": 2.2704451084136963, | |
| "eval_en_oof_runtime": 5.5816, | |
| "eval_en_oof_samples_per_second": 336.285, | |
| "eval_en_oof_steps_per_second": 3.583, | |
| "eval_en_oof_total_cls_tokens": 279, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 21.375, | |
| "eval_vi_All_acc": 0.7791357485814056, | |
| "eval_vi_Env_acc": 0.9444444444444444, | |
| "eval_vi_Env_f1": 0.9562499999999999, | |
| "eval_vi_Gov_acc": 0.9097222222222222, | |
| "eval_vi_Gov_f1": 0.9128919860627178, | |
| "eval_vi_Neu_acc": 0.8975903614457831, | |
| "eval_vi_Neu_f1": 0.8922155688622753, | |
| "eval_vi_Soc_acc": 0.8648648648648649, | |
| "eval_vi_Soc_f1": 0.8561872909698998, | |
| "eval_vi_cls_acc": 0.9048387096774193, | |
| "eval_vi_cls_f1": 0.9043862114737232, | |
| "eval_vi_loss": 1.0195897817611694, | |
| "eval_vi_runtime": 12.7127, | |
| "eval_vi_samples_per_second": 346.111, | |
| "eval_vi_steps_per_second": 3.618, | |
| "eval_vi_total_cls_tokens": 620, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 21.375, | |
| "eval_dan_All_acc": 0.6821167545563882, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.6, | |
| "eval_dan_Gov_f1": 0.7499999999999999, | |
| "eval_dan_Neu_acc": 0.1111111111111111, | |
| "eval_dan_Neu_f1": 0.19999999999999998, | |
| "eval_dan_Soc_acc": 0.125, | |
| "eval_dan_Soc_f1": 0.2222222222222222, | |
| "eval_dan_cls_acc": 0.20408163265306123, | |
| "eval_dan_cls_f1": 0.2930555555555555, | |
| "eval_dan_loss": 2.0280568599700928, | |
| "eval_dan_runtime": 8.8449, | |
| "eval_dan_samples_per_second": 339.178, | |
| "eval_dan_steps_per_second": 3.618, | |
| "eval_dan_total_cls_tokens": 49, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 21.413265306122447, | |
| "grad_norm": 2.4537513256073, | |
| "learning_rate": 1.6188180424188886e-05, | |
| "loss": 1.3142, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 21.4515306122449, | |
| "grad_norm": 2.554511308670044, | |
| "learning_rate": 1.6104714830173468e-05, | |
| "loss": 1.2873, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 21.489795918367346, | |
| "grad_norm": 2.6011545658111572, | |
| "learning_rate": 1.6021362605027403e-05, | |
| "loss": 1.2865, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 21.528061224489797, | |
| "grad_norm": 2.5153632164001465, | |
| "learning_rate": 1.5938124811060357e-05, | |
| "loss": 1.3032, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 21.566326530612244, | |
| "grad_norm": 2.353861093521118, | |
| "learning_rate": 1.5855002509123595e-05, | |
| "loss": 1.2757, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 21.604591836734695, | |
| "grad_norm": 2.400365114212036, | |
| "learning_rate": 1.5771996758596487e-05, | |
| "loss": 1.3061, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 21.642857142857142, | |
| "grad_norm": 2.4363622665405273, | |
| "learning_rate": 1.5689108617372924e-05, | |
| "loss": 1.3143, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 21.681122448979593, | |
| "grad_norm": 2.4674129486083984, | |
| "learning_rate": 1.5606339141847935e-05, | |
| "loss": 1.2709, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 21.71938775510204, | |
| "grad_norm": 2.4731342792510986, | |
| "learning_rate": 1.552368938690414e-05, | |
| "loss": 1.376, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 21.757653061224488, | |
| "grad_norm": 2.4795451164245605, | |
| "learning_rate": 1.5441160405898362e-05, | |
| "loss": 1.402, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 21.757653061224488, | |
| "eval_en_All_acc": 0.6269418794133623, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.99009900990099, | |
| "eval_en_Gov_acc": 0.967741935483871, | |
| "eval_en_Gov_f1": 0.975609756097561, | |
| "eval_en_Neu_acc": 0.9076923076923077, | |
| "eval_en_Neu_f1": 0.9076923076923076, | |
| "eval_en_Soc_acc": 0.9393939393939394, | |
| "eval_en_Soc_f1": 0.9393939393939394, | |
| "eval_en_cls_acc": 0.9506172839506173, | |
| "eval_en_cls_f1": 0.9531987532711995, | |
| "eval_en_loss": 2.1628870964050293, | |
| "eval_en_runtime": 5.6484, | |
| "eval_en_samples_per_second": 332.306, | |
| "eval_en_steps_per_second": 3.541, | |
| "eval_en_total_cls_tokens": 243, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 21.757653061224488, | |
| "eval_en_oof_All_acc": 0.6319831667543399, | |
| "eval_en_oof_Env_acc": 0.9850746268656716, | |
| "eval_en_oof_Env_f1": 0.9705882352941176, | |
| "eval_en_oof_Gov_acc": 0.9833333333333333, | |
| "eval_en_oof_Gov_f1": 0.9593495934959351, | |
| "eval_en_oof_Neu_acc": 0.9178082191780822, | |
| "eval_en_oof_Neu_f1": 0.9370629370629371, | |
| "eval_en_oof_Soc_acc": 0.9428571428571428, | |
| "eval_en_oof_Soc_f1": 0.9565217391304348, | |
| "eval_en_oof_cls_acc": 0.9555555555555556, | |
| "eval_en_oof_cls_f1": 0.9558806262458561, | |
| "eval_en_oof_loss": 2.1182117462158203, | |
| "eval_en_oof_runtime": 5.5361, | |
| "eval_en_oof_samples_per_second": 339.045, | |
| "eval_en_oof_steps_per_second": 3.613, | |
| "eval_en_oof_total_cls_tokens": 270, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 21.757653061224488, | |
| "eval_vi_All_acc": 0.7946309755348552, | |
| "eval_vi_Env_acc": 0.9806451612903225, | |
| "eval_vi_Env_f1": 0.9712460063897763, | |
| "eval_vi_Gov_acc": 0.9230769230769231, | |
| "eval_vi_Gov_f1": 0.9142857142857143, | |
| "eval_vi_Neu_acc": 0.9015151515151515, | |
| "eval_vi_Neu_f1": 0.9153846153846155, | |
| "eval_vi_Soc_acc": 0.8932584269662921, | |
| "eval_vi_Soc_f1": 0.8983050847457628, | |
| "eval_vi_cls_acc": 0.9243156199677939, | |
| "eval_vi_cls_f1": 0.9248053552014672, | |
| "eval_vi_loss": 0.9391768574714661, | |
| "eval_vi_runtime": 12.4387, | |
| "eval_vi_samples_per_second": 353.734, | |
| "eval_vi_steps_per_second": 3.698, | |
| "eval_vi_total_cls_tokens": 621, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 21.757653061224488, | |
| "eval_dan_All_acc": 0.6718360825226749, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.25, | |
| "eval_dan_Gov_f1": 0.36363636363636365, | |
| "eval_dan_Neu_acc": 0.2, | |
| "eval_dan_Neu_f1": 0.33333333333333337, | |
| "eval_dan_Soc_acc": 0.06666666666666667, | |
| "eval_dan_Soc_f1": 0.125, | |
| "eval_dan_cls_acc": 0.15217391304347827, | |
| "eval_dan_cls_f1": 0.20549242424242425, | |
| "eval_dan_loss": 2.0830695629119873, | |
| "eval_dan_runtime": 9.0249, | |
| "eval_dan_samples_per_second": 332.413, | |
| "eval_dan_steps_per_second": 3.546, | |
| "eval_dan_total_cls_tokens": 46, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 21.79591836734694, | |
| "grad_norm": 2.401956558227539, | |
| "learning_rate": 1.535875325064818e-05, | |
| "loss": 1.3103, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 21.834183673469386, | |
| "grad_norm": 2.4306986331939697, | |
| "learning_rate": 1.5276468971418507e-05, | |
| "loss": 1.3175, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 21.872448979591837, | |
| "grad_norm": 2.5168862342834473, | |
| "learning_rate": 1.5194308616908246e-05, | |
| "loss": 1.3259, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 21.910714285714285, | |
| "grad_norm": 2.51094651222229, | |
| "learning_rate": 1.511227323423689e-05, | |
| "loss": 1.3186, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 21.948979591836736, | |
| "grad_norm": 2.456575870513916, | |
| "learning_rate": 1.5030363868931175e-05, | |
| "loss": 1.3366, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 21.987244897959183, | |
| "grad_norm": 2.392465829849243, | |
| "learning_rate": 1.4948581564911798e-05, | |
| "loss": 1.2775, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 22.022959183673468, | |
| "grad_norm": 2.3026108741760254, | |
| "learning_rate": 1.486692736448005e-05, | |
| "loss": 1.2236, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 22.06122448979592, | |
| "grad_norm": 2.3944742679595947, | |
| "learning_rate": 1.4785402308304575e-05, | |
| "loss": 1.2984, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 22.099489795918366, | |
| "grad_norm": 2.4375264644622803, | |
| "learning_rate": 1.4704007435408118e-05, | |
| "loss": 1.3734, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 22.137755102040817, | |
| "grad_norm": 2.4551303386688232, | |
| "learning_rate": 1.4622743783154223e-05, | |
| "loss": 1.3306, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 22.137755102040817, | |
| "eval_en_All_acc": 0.6243082162622392, | |
| "eval_en_Env_acc": 0.9382716049382716, | |
| "eval_en_Env_f1": 0.95, | |
| "eval_en_Gov_acc": 0.967741935483871, | |
| "eval_en_Gov_f1": 0.967741935483871, | |
| "eval_en_Neu_acc": 0.9459459459459459, | |
| "eval_en_Neu_f1": 0.9333333333333332, | |
| "eval_en_Soc_acc": 0.9692307692307692, | |
| "eval_en_Soc_f1": 0.9692307692307692, | |
| "eval_en_cls_acc": 0.9539007092198581, | |
| "eval_en_cls_f1": 0.9550765095119933, | |
| "eval_en_loss": 2.199098587036133, | |
| "eval_en_runtime": 5.6163, | |
| "eval_en_samples_per_second": 334.206, | |
| "eval_en_steps_per_second": 3.561, | |
| "eval_en_total_cls_tokens": 282, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 22.137755102040817, | |
| "eval_en_oof_All_acc": 0.6163672240108007, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.993103448275862, | |
| "eval_en_oof_Gov_acc": 0.9838709677419355, | |
| "eval_en_oof_Gov_f1": 0.9384615384615386, | |
| "eval_en_oof_Neu_acc": 0.859375, | |
| "eval_en_oof_Neu_f1": 0.88, | |
| "eval_en_oof_Soc_acc": 0.855072463768116, | |
| "eval_en_oof_Soc_f1": 0.8805970149253731, | |
| "eval_en_oof_cls_acc": 0.9250936329588015, | |
| "eval_en_oof_cls_f1": 0.9230405004156934, | |
| "eval_en_oof_loss": 2.1981453895568848, | |
| "eval_en_oof_runtime": 5.5817, | |
| "eval_en_oof_samples_per_second": 336.279, | |
| "eval_en_oof_steps_per_second": 3.583, | |
| "eval_en_oof_total_cls_tokens": 267, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 22.137755102040817, | |
| "eval_vi_All_acc": 0.7936375270979706, | |
| "eval_vi_Env_acc": 0.9573170731707317, | |
| "eval_vi_Env_f1": 0.9602446483180427, | |
| "eval_vi_Gov_acc": 0.9608938547486033, | |
| "eval_vi_Gov_f1": 0.9398907103825136, | |
| "eval_vi_Neu_acc": 0.9551282051282052, | |
| "eval_vi_Neu_f1": 0.9254658385093167, | |
| "eval_vi_Soc_acc": 0.845679012345679, | |
| "eval_vi_Soc_f1": 0.8925081433224755, | |
| "eval_vi_cls_acc": 0.9304084720121029, | |
| "eval_vi_cls_f1": 0.9295273351330872, | |
| "eval_vi_loss": 0.9567837119102478, | |
| "eval_vi_runtime": 12.7058, | |
| "eval_vi_samples_per_second": 346.3, | |
| "eval_vi_steps_per_second": 3.62, | |
| "eval_vi_total_cls_tokens": 661, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 22.137755102040817, | |
| "eval_dan_All_acc": 0.6668502202643172, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.09523809523809523, | |
| "eval_dan_Neu_f1": 0.17391304347826084, | |
| "eval_dan_Soc_acc": 0.10526315789473684, | |
| "eval_dan_Soc_f1": 0.1904761904761905, | |
| "eval_dan_cls_acc": 0.125, | |
| "eval_dan_cls_f1": 0.3202639751552795, | |
| "eval_dan_loss": 2.102728843688965, | |
| "eval_dan_runtime": 8.9375, | |
| "eval_dan_samples_per_second": 335.663, | |
| "eval_dan_steps_per_second": 3.58, | |
| "eval_dan_total_cls_tokens": 56, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 22.176020408163264, | |
| "grad_norm": 2.5087995529174805, | |
| "learning_rate": 1.454161238723407e-05, | |
| "loss": 1.3048, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 22.214285714285715, | |
| "grad_norm": 2.402632236480713, | |
| "learning_rate": 1.446061428165326e-05, | |
| "loss": 1.3343, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 22.252551020408163, | |
| "grad_norm": 2.5380680561065674, | |
| "learning_rate": 1.4379750498718619e-05, | |
| "loss": 1.3231, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 22.290816326530614, | |
| "grad_norm": 2.376584768295288, | |
| "learning_rate": 1.429902206902507e-05, | |
| "loss": 1.2743, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 22.32908163265306, | |
| "grad_norm": 2.6212494373321533, | |
| "learning_rate": 1.4218430021442447e-05, | |
| "loss": 1.3013, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 22.367346938775512, | |
| "grad_norm": 2.4580705165863037, | |
| "learning_rate": 1.4137975383102464e-05, | |
| "loss": 1.2905, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 22.40561224489796, | |
| "grad_norm": 2.5956878662109375, | |
| "learning_rate": 1.4057659179385566e-05, | |
| "loss": 1.3028, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 22.443877551020407, | |
| "grad_norm": 2.487039089202881, | |
| "learning_rate": 1.3977482433907827e-05, | |
| "loss": 1.3516, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 22.482142857142858, | |
| "grad_norm": 2.4328551292419434, | |
| "learning_rate": 1.3897446168508016e-05, | |
| "loss": 1.3261, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 22.520408163265305, | |
| "grad_norm": 2.2871997356414795, | |
| "learning_rate": 1.381755140323448e-05, | |
| "loss": 1.2444, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 22.520408163265305, | |
| "eval_en_All_acc": 0.6061422413793104, | |
| "eval_en_Env_acc": 0.9841269841269841, | |
| "eval_en_Env_f1": 0.96875, | |
| "eval_en_Gov_acc": 0.9577464788732394, | |
| "eval_en_Gov_f1": 0.9645390070921985, | |
| "eval_en_Neu_acc": 0.8970588235294118, | |
| "eval_en_Neu_f1": 0.9037037037037037, | |
| "eval_en_Soc_acc": 0.9523809523809523, | |
| "eval_en_Soc_f1": 0.9523809523809523, | |
| "eval_en_cls_acc": 0.9471698113207547, | |
| "eval_en_cls_f1": 0.9473434157942136, | |
| "eval_en_loss": 2.2259693145751953, | |
| "eval_en_runtime": 5.6051, | |
| "eval_en_samples_per_second": 334.875, | |
| "eval_en_steps_per_second": 3.568, | |
| "eval_en_total_cls_tokens": 265, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 22.520408163265305, | |
| "eval_en_oof_All_acc": 0.6316577540106952, | |
| "eval_en_oof_Env_acc": 0.9571428571428572, | |
| "eval_en_oof_Env_f1": 0.9640287769784173, | |
| "eval_en_oof_Gov_acc": 1.0, | |
| "eval_en_oof_Gov_f1": 0.967741935483871, | |
| "eval_en_oof_Neu_acc": 0.8837209302325582, | |
| "eval_en_oof_Neu_f1": 0.8994082840236686, | |
| "eval_en_oof_Soc_acc": 0.9066666666666666, | |
| "eval_en_oof_Soc_f1": 0.9066666666666666, | |
| "eval_en_oof_cls_acc": 0.9312714776632303, | |
| "eval_en_oof_cls_f1": 0.9344614157881559, | |
| "eval_en_oof_loss": 2.120981216430664, | |
| "eval_en_oof_runtime": 5.592, | |
| "eval_en_oof_samples_per_second": 335.659, | |
| "eval_en_oof_steps_per_second": 3.577, | |
| "eval_en_oof_total_cls_tokens": 291, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 22.520408163265305, | |
| "eval_vi_All_acc": 0.797610610509264, | |
| "eval_vi_Env_acc": 0.9515151515151515, | |
| "eval_vi_Env_f1": 0.9602446483180428, | |
| "eval_vi_Gov_acc": 0.9285714285714286, | |
| "eval_vi_Gov_f1": 0.9017341040462428, | |
| "eval_vi_Neu_acc": 0.8930817610062893, | |
| "eval_vi_Neu_f1": 0.8930817610062893, | |
| "eval_vi_Soc_acc": 0.8571428571428571, | |
| "eval_vi_Soc_f1": 0.8761904761904761, | |
| "eval_vi_cls_acc": 0.9081163859111792, | |
| "eval_vi_cls_f1": 0.9078127473902629, | |
| "eval_vi_loss": 0.933108389377594, | |
| "eval_vi_runtime": 12.7581, | |
| "eval_vi_samples_per_second": 344.878, | |
| "eval_vi_steps_per_second": 3.606, | |
| "eval_vi_total_cls_tokens": 653, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 22.520408163265305, | |
| "eval_dan_All_acc": 0.6787957749755712, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.16666666666666666, | |
| "eval_dan_Gov_f1": 0.2857142857142857, | |
| "eval_dan_Neu_acc": 0.22727272727272727, | |
| "eval_dan_Neu_f1": 0.37037037037037035, | |
| "eval_dan_Soc_acc": 0.1875, | |
| "eval_dan_Soc_f1": 0.3157894736842105, | |
| "eval_dan_cls_acc": 0.19607843137254902, | |
| "eval_dan_cls_f1": 0.24296853244221664, | |
| "eval_dan_loss": 2.04441499710083, | |
| "eval_dan_runtime": 8.7788, | |
| "eval_dan_samples_per_second": 341.732, | |
| "eval_dan_steps_per_second": 3.645, | |
| "eval_dan_total_cls_tokens": 51, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 22.558673469387756, | |
| "grad_norm": 2.3713488578796387, | |
| "learning_rate": 1.3737799156332143e-05, | |
| "loss": 1.3206, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 22.596938775510203, | |
| "grad_norm": 2.439526319503784, | |
| "learning_rate": 1.3658190444229604e-05, | |
| "loss": 1.3523, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 22.635204081632654, | |
| "grad_norm": 2.4420506954193115, | |
| "learning_rate": 1.3578726281526122e-05, | |
| "loss": 1.332, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 22.6734693877551, | |
| "grad_norm": 2.3967831134796143, | |
| "learning_rate": 1.3499407680978671e-05, | |
| "loss": 1.2873, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 22.711734693877553, | |
| "grad_norm": 2.510948657989502, | |
| "learning_rate": 1.3420235653489093e-05, | |
| "loss": 1.2932, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 22.75, | |
| "grad_norm": 2.575855255126953, | |
| "learning_rate": 1.3341211208091164e-05, | |
| "loss": 1.3036, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 22.788265306122447, | |
| "grad_norm": 2.754350185394287, | |
| "learning_rate": 1.3262335351937765e-05, | |
| "loss": 1.3577, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 22.8265306122449, | |
| "grad_norm": 2.4168365001678467, | |
| "learning_rate": 1.3183609090288023e-05, | |
| "loss": 1.3605, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 22.864795918367346, | |
| "grad_norm": 2.563758611679077, | |
| "learning_rate": 1.3105033426494517e-05, | |
| "loss": 1.2843, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 22.903061224489797, | |
| "grad_norm": 2.4595673084259033, | |
| "learning_rate": 1.3026609361990466e-05, | |
| "loss": 1.3559, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.903061224489797, | |
| "eval_en_All_acc": 0.6216157205240175, | |
| "eval_en_Env_acc": 0.9666666666666667, | |
| "eval_en_Env_f1": 0.9775280898876404, | |
| "eval_en_Gov_acc": 1.0, | |
| "eval_en_Gov_f1": 0.9508196721311475, | |
| "eval_en_Neu_acc": 0.8533333333333334, | |
| "eval_en_Neu_f1": 0.9014084507042254, | |
| "eval_en_Soc_acc": 0.9636363636363636, | |
| "eval_en_Soc_f1": 0.9298245614035089, | |
| "eval_en_cls_acc": 0.9424460431654677, | |
| "eval_en_cls_f1": 0.9398951935316305, | |
| "eval_en_loss": 2.2084569931030273, | |
| "eval_en_runtime": 5.6211, | |
| "eval_en_samples_per_second": 333.922, | |
| "eval_en_steps_per_second": 3.558, | |
| "eval_en_total_cls_tokens": 278, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.903061224489797, | |
| "eval_en_oof_All_acc": 0.6168039195246534, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9836065573770492, | |
| "eval_en_oof_Gov_acc": 1.0, | |
| "eval_en_oof_Gov_f1": 0.9777777777777777, | |
| "eval_en_oof_Neu_acc": 0.8571428571428571, | |
| "eval_en_oof_Neu_f1": 0.9166666666666667, | |
| "eval_en_oof_Soc_acc": 0.987012987012987, | |
| "eval_en_oof_Soc_f1": 0.9559748427672956, | |
| "eval_en_oof_cls_acc": 0.9571428571428572, | |
| "eval_en_oof_cls_f1": 0.9585064611471974, | |
| "eval_en_oof_loss": 2.2216591835021973, | |
| "eval_en_oof_runtime": 5.6047, | |
| "eval_en_oof_samples_per_second": 334.896, | |
| "eval_en_oof_steps_per_second": 3.568, | |
| "eval_en_oof_total_cls_tokens": 280, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.903061224489797, | |
| "eval_vi_All_acc": 0.7910633225978242, | |
| "eval_vi_Env_acc": 0.9574468085106383, | |
| "eval_vi_Env_f1": 0.96, | |
| "eval_vi_Gov_acc": 0.9583333333333334, | |
| "eval_vi_Gov_f1": 0.8961038961038961, | |
| "eval_vi_Neu_acc": 0.8387096774193549, | |
| "eval_vi_Neu_f1": 0.8873720136518771, | |
| "eval_vi_Soc_acc": 0.8802395209580839, | |
| "eval_vi_Soc_f1": 0.8855421686746987, | |
| "eval_vi_cls_acc": 0.9097859327217125, | |
| "eval_vi_cls_f1": 0.9072545196076179, | |
| "eval_vi_loss": 0.9607260227203369, | |
| "eval_vi_runtime": 12.7423, | |
| "eval_vi_samples_per_second": 345.306, | |
| "eval_vi_steps_per_second": 3.61, | |
| "eval_vi_total_cls_tokens": 654, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.903061224489797, | |
| "eval_dan_All_acc": 0.6761358247178223, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.1, | |
| "eval_dan_Gov_f1": 0.18181818181818182, | |
| "eval_dan_Neu_acc": 0.1, | |
| "eval_dan_Neu_f1": 0.18181818181818182, | |
| "eval_dan_Soc_acc": 0.04, | |
| "eval_dan_Soc_f1": 0.07692307692307693, | |
| "eval_dan_cls_acc": 0.07142857142857142, | |
| "eval_dan_cls_f1": 0.11013986013986014, | |
| "eval_dan_loss": 2.0693509578704834, | |
| "eval_dan_runtime": 8.8024, | |
| "eval_dan_samples_per_second": 340.816, | |
| "eval_dan_steps_per_second": 3.635, | |
| "eval_dan_total_cls_tokens": 56, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.941326530612244, | |
| "grad_norm": 2.4969124794006348, | |
| "learning_rate": 1.2948337896277004e-05, | |
| "loss": 1.3025, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 22.979591836734695, | |
| "grad_norm": 2.538426637649536, | |
| "learning_rate": 1.2870220026910407e-05, | |
| "loss": 1.3116, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 23.01530612244898, | |
| "grad_norm": 2.478489637374878, | |
| "learning_rate": 1.279225674948939e-05, | |
| "loss": 1.2708, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 23.053571428571427, | |
| "grad_norm": 2.365586042404175, | |
| "learning_rate": 1.271444905764243e-05, | |
| "loss": 1.3003, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 23.091836734693878, | |
| "grad_norm": 2.4379122257232666, | |
| "learning_rate": 1.2636797943015088e-05, | |
| "loss": 1.3451, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 23.130102040816325, | |
| "grad_norm": 2.600151777267456, | |
| "learning_rate": 1.255930439525737e-05, | |
| "loss": 1.2927, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 23.168367346938776, | |
| "grad_norm": 2.4998340606689453, | |
| "learning_rate": 1.2481969402011132e-05, | |
| "loss": 1.3401, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 23.206632653061224, | |
| "grad_norm": 2.3483169078826904, | |
| "learning_rate": 1.2404793948897466e-05, | |
| "loss": 1.2538, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 23.244897959183675, | |
| "grad_norm": 2.408175230026245, | |
| "learning_rate": 1.2327779019504162e-05, | |
| "loss": 1.2646, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 23.283163265306122, | |
| "grad_norm": 2.480390787124634, | |
| "learning_rate": 1.2250925595373175e-05, | |
| "loss": 1.3188, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 23.283163265306122, | |
| "eval_en_All_acc": 0.628828642384106, | |
| "eval_en_Env_acc": 0.9583333333333334, | |
| "eval_en_Env_f1": 0.9517241379310345, | |
| "eval_en_Gov_acc": 0.9875, | |
| "eval_en_Gov_f1": 0.9404761904761905, | |
| "eval_en_Neu_acc": 0.8602150537634409, | |
| "eval_en_Neu_f1": 0.903954802259887, | |
| "eval_en_Soc_acc": 0.9295774647887324, | |
| "eval_en_Soc_f1": 0.9295774647887324, | |
| "eval_en_cls_acc": 0.930379746835443, | |
| "eval_en_cls_f1": 0.9314331488639611, | |
| "eval_en_loss": 2.107430934906006, | |
| "eval_en_runtime": 5.6372, | |
| "eval_en_samples_per_second": 332.968, | |
| "eval_en_steps_per_second": 3.548, | |
| "eval_en_total_cls_tokens": 316, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 23.283163265306122, | |
| "eval_en_oof_All_acc": 0.6306616572740555, | |
| "eval_en_oof_Env_acc": 0.974025974025974, | |
| "eval_en_oof_Env_f1": 0.9615384615384615, | |
| "eval_en_oof_Gov_acc": 0.9591836734693877, | |
| "eval_en_oof_Gov_f1": 0.9494949494949495, | |
| "eval_en_oof_Neu_acc": 0.8857142857142857, | |
| "eval_en_oof_Neu_f1": 0.9117647058823529, | |
| "eval_en_oof_Soc_acc": 0.9436619718309859, | |
| "eval_en_oof_Soc_f1": 0.9370629370629372, | |
| "eval_en_oof_cls_acc": 0.9400749063670412, | |
| "eval_en_oof_cls_f1": 0.9399652634946752, | |
| "eval_en_oof_loss": 2.1617462635040283, | |
| "eval_en_oof_runtime": 5.6026, | |
| "eval_en_oof_samples_per_second": 335.022, | |
| "eval_en_oof_steps_per_second": 3.57, | |
| "eval_en_oof_total_cls_tokens": 267, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 23.283163265306122, | |
| "eval_vi_All_acc": 0.7940698723733403, | |
| "eval_vi_Env_acc": 0.9714285714285714, | |
| "eval_vi_Env_f1": 0.9714285714285714, | |
| "eval_vi_Gov_acc": 0.9192546583850931, | |
| "eval_vi_Gov_f1": 0.8996960486322189, | |
| "eval_vi_Neu_acc": 0.8561643835616438, | |
| "eval_vi_Neu_f1": 0.8833922261484098, | |
| "eval_vi_Soc_acc": 0.8869047619047619, | |
| "eval_vi_Soc_f1": 0.8816568047337278, | |
| "eval_vi_cls_acc": 0.9107692307692308, | |
| "eval_vi_cls_f1": 0.909043412735732, | |
| "eval_vi_loss": 0.9606111645698547, | |
| "eval_vi_runtime": 12.6943, | |
| "eval_vi_samples_per_second": 346.613, | |
| "eval_vi_steps_per_second": 3.624, | |
| "eval_vi_total_cls_tokens": 650, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 23.283163265306122, | |
| "eval_dan_All_acc": 0.6718975552968568, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2727272727272727, | |
| "eval_dan_Gov_f1": 0.42857142857142855, | |
| "eval_dan_Neu_acc": 0.25, | |
| "eval_dan_Neu_f1": 0.4, | |
| "eval_dan_Soc_acc": 0.058823529411764705, | |
| "eval_dan_Soc_f1": 0.1111111111111111, | |
| "eval_dan_cls_acc": 0.18867924528301888, | |
| "eval_dan_cls_f1": 0.23492063492063492, | |
| "eval_dan_loss": 2.105502128601074, | |
| "eval_dan_runtime": 8.9163, | |
| "eval_dan_samples_per_second": 336.464, | |
| "eval_dan_steps_per_second": 3.589, | |
| "eval_dan_total_cls_tokens": 53, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 23.321428571428573, | |
| "grad_norm": 2.4804580211639404, | |
| "learning_rate": 1.2174234655988053e-05, | |
| "loss": 1.2605, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 23.35969387755102, | |
| "grad_norm": 2.4707696437835693, | |
| "learning_rate": 1.2097707178761586e-05, | |
| "loss": 1.2825, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 23.397959183673468, | |
| "grad_norm": 2.4012439250946045, | |
| "learning_rate": 1.2021344139023186e-05, | |
| "loss": 1.2875, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 23.43622448979592, | |
| "grad_norm": 2.5559325218200684, | |
| "learning_rate": 1.1945146510006572e-05, | |
| "loss": 1.2924, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 23.474489795918366, | |
| "grad_norm": 2.3866677284240723, | |
| "learning_rate": 1.1869115262837368e-05, | |
| "loss": 1.2822, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 23.512755102040817, | |
| "grad_norm": 2.4277663230895996, | |
| "learning_rate": 1.1793251366520621e-05, | |
| "loss": 1.2728, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 23.551020408163264, | |
| "grad_norm": 2.4541287422180176, | |
| "learning_rate": 1.1717555787928558e-05, | |
| "loss": 1.3363, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 23.589285714285715, | |
| "grad_norm": 2.3311755657196045, | |
| "learning_rate": 1.1642029491788248e-05, | |
| "loss": 1.2745, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 23.627551020408163, | |
| "grad_norm": 2.509061813354492, | |
| "learning_rate": 1.156667344066923e-05, | |
| "loss": 1.2864, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 23.665816326530614, | |
| "grad_norm": 2.430168628692627, | |
| "learning_rate": 1.1491488594971328e-05, | |
| "loss": 1.3178, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 23.665816326530614, | |
| "eval_en_All_acc": 0.6064732376662826, | |
| "eval_en_Env_acc": 0.9692307692307692, | |
| "eval_en_Env_f1": 0.9618320610687022, | |
| "eval_en_Gov_acc": 0.9629629629629629, | |
| "eval_en_Gov_f1": 0.9629629629629629, | |
| "eval_en_Neu_acc": 0.859375, | |
| "eval_en_Neu_f1": 0.8943089430894309, | |
| "eval_en_Soc_acc": 0.9696969696969697, | |
| "eval_en_Soc_f1": 0.9411764705882354, | |
| "eval_en_cls_acc": 0.9397590361445783, | |
| "eval_en_cls_f1": 0.9400701094273329, | |
| "eval_en_loss": 2.2708165645599365, | |
| "eval_en_runtime": 5.6418, | |
| "eval_en_samples_per_second": 332.693, | |
| "eval_en_steps_per_second": 3.545, | |
| "eval_en_total_cls_tokens": 249, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 23.665816326530614, | |
| "eval_en_oof_All_acc": 0.6182393252503954, | |
| "eval_en_oof_Env_acc": 0.9857142857142858, | |
| "eval_en_oof_Env_f1": 0.9583333333333333, | |
| "eval_en_oof_Gov_acc": 0.9444444444444444, | |
| "eval_en_oof_Gov_f1": 0.9444444444444444, | |
| "eval_en_oof_Neu_acc": 0.8571428571428571, | |
| "eval_en_oof_Neu_f1": 0.8780487804878048, | |
| "eval_en_oof_Soc_acc": 0.9, | |
| "eval_en_oof_Soc_f1": 0.9, | |
| "eval_en_oof_cls_acc": 0.9195804195804196, | |
| "eval_en_oof_cls_f1": 0.9202066395663957, | |
| "eval_en_oof_loss": 2.1848878860473633, | |
| "eval_en_oof_runtime": 5.6026, | |
| "eval_en_oof_samples_per_second": 335.024, | |
| "eval_en_oof_steps_per_second": 3.57, | |
| "eval_en_oof_total_cls_tokens": 286, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 23.665816326530614, | |
| "eval_vi_All_acc": 0.7951720780052789, | |
| "eval_vi_Env_acc": 0.9770114942528736, | |
| "eval_vi_Env_f1": 0.9631728045325779, | |
| "eval_vi_Gov_acc": 0.906832298136646, | |
| "eval_vi_Gov_f1": 0.906832298136646, | |
| "eval_vi_Neu_acc": 0.9294871794871795, | |
| "eval_vi_Neu_f1": 0.926517571884984, | |
| "eval_vi_Soc_acc": 0.8896551724137931, | |
| "eval_vi_Soc_f1": 0.9084507042253521, | |
| "eval_vi_cls_acc": 0.9276729559748428, | |
| "eval_vi_cls_f1": 0.92624334469489, | |
| "eval_vi_loss": 0.9544464945793152, | |
| "eval_vi_runtime": 12.7748, | |
| "eval_vi_samples_per_second": 344.428, | |
| "eval_vi_steps_per_second": 3.601, | |
| "eval_vi_total_cls_tokens": 636, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 23.665816326530614, | |
| "eval_dan_All_acc": 0.6696037296037296, | |
| "eval_dan_Env_acc": 0.25, | |
| "eval_dan_Env_f1": 0.4, | |
| "eval_dan_Gov_acc": 0.5, | |
| "eval_dan_Gov_f1": 0.6666666666666666, | |
| "eval_dan_Neu_acc": 0.25, | |
| "eval_dan_Neu_f1": 0.4, | |
| "eval_dan_Soc_acc": 0.0, | |
| "eval_dan_Soc_f1": 0.0, | |
| "eval_dan_cls_acc": 0.21428571428571427, | |
| "eval_dan_cls_f1": 0.3666666666666667, | |
| "eval_dan_loss": 2.119600296020508, | |
| "eval_dan_runtime": 8.8333, | |
| "eval_dan_samples_per_second": 339.625, | |
| "eval_dan_steps_per_second": 3.623, | |
| "eval_dan_total_cls_tokens": 42, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 23.70408163265306, | |
| "grad_norm": 2.6157848834991455, | |
| "learning_rate": 1.1416475912912413e-05, | |
| "loss": 1.3299, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 23.742346938775512, | |
| "grad_norm": 2.6053552627563477, | |
| "learning_rate": 1.1341636350516103e-05, | |
| "loss": 1.3043, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 23.78061224489796, | |
| "grad_norm": 2.6155214309692383, | |
| "learning_rate": 1.1266970861599666e-05, | |
| "loss": 1.2893, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 23.818877551020407, | |
| "grad_norm": 2.432239055633545, | |
| "learning_rate": 1.1192480397761837e-05, | |
| "loss": 1.3023, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 23.857142857142858, | |
| "grad_norm": 2.3423879146575928, | |
| "learning_rate": 1.1118165908370678e-05, | |
| "loss": 1.2827, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 23.895408163265305, | |
| "grad_norm": 2.443567991256714, | |
| "learning_rate": 1.1044028340551488e-05, | |
| "loss": 1.3093, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 23.933673469387756, | |
| "grad_norm": 2.527402400970459, | |
| "learning_rate": 1.0970068639174736e-05, | |
| "loss": 1.3146, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 23.971938775510203, | |
| "grad_norm": 2.4607009887695312, | |
| "learning_rate": 1.0896287746844005e-05, | |
| "loss": 1.3244, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 24.007653061224488, | |
| "grad_norm": 2.437692642211914, | |
| "learning_rate": 1.0822686603884009e-05, | |
| "loss": 1.1969, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 24.04591836734694, | |
| "grad_norm": 2.5008132457733154, | |
| "learning_rate": 1.0749266148328538e-05, | |
| "loss": 1.2411, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 24.04591836734694, | |
| "eval_en_All_acc": 0.6387836814197597, | |
| "eval_en_Env_acc": 0.9846153846153847, | |
| "eval_en_Env_f1": 0.9770992366412214, | |
| "eval_en_Gov_acc": 0.9833333333333333, | |
| "eval_en_Gov_f1": 0.9833333333333333, | |
| "eval_en_Neu_acc": 0.9459459459459459, | |
| "eval_en_Neu_f1": 0.9395973154362416, | |
| "eval_en_Soc_acc": 0.9344262295081968, | |
| "eval_en_Soc_f1": 0.95, | |
| "eval_en_cls_acc": 0.9615384615384616, | |
| "eval_en_cls_f1": 0.9625074713526991, | |
| "eval_en_loss": 2.106539487838745, | |
| "eval_en_runtime": 5.6205, | |
| "eval_en_samples_per_second": 333.954, | |
| "eval_en_steps_per_second": 3.558, | |
| "eval_en_total_cls_tokens": 260, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 24.04591836734694, | |
| "eval_en_oof_All_acc": 0.6183823529411765, | |
| "eval_en_oof_Env_acc": 0.9863013698630136, | |
| "eval_en_oof_Env_f1": 0.993103448275862, | |
| "eval_en_oof_Gov_acc": 0.9482758620689655, | |
| "eval_en_oof_Gov_f1": 0.9565217391304347, | |
| "eval_en_oof_Neu_acc": 0.9538461538461539, | |
| "eval_en_oof_Neu_f1": 0.9253731343283582, | |
| "eval_en_oof_Soc_acc": 0.9436619718309859, | |
| "eval_en_oof_Soc_f1": 0.9571428571428571, | |
| "eval_en_oof_cls_acc": 0.9588014981273408, | |
| "eval_en_oof_cls_f1": 0.958035294719378, | |
| "eval_en_oof_loss": 2.2280666828155518, | |
| "eval_en_oof_runtime": 5.5941, | |
| "eval_en_oof_samples_per_second": 335.532, | |
| "eval_en_oof_steps_per_second": 3.575, | |
| "eval_en_oof_total_cls_tokens": 267, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 24.04591836734694, | |
| "eval_vi_All_acc": 0.7999487901677123, | |
| "eval_vi_Env_acc": 0.9693251533742331, | |
| "eval_vi_Env_f1": 0.9604863221884498, | |
| "eval_vi_Gov_acc": 0.9078947368421053, | |
| "eval_vi_Gov_f1": 0.913907284768212, | |
| "eval_vi_Neu_acc": 0.89171974522293, | |
| "eval_vi_Neu_f1": 0.9032258064516128, | |
| "eval_vi_Soc_acc": 0.9241379310344827, | |
| "eval_vi_Soc_f1": 0.9146757679180887, | |
| "eval_vi_cls_acc": 0.9238249594813615, | |
| "eval_vi_cls_f1": 0.9230737953315908, | |
| "eval_vi_loss": 0.9201207756996155, | |
| "eval_vi_runtime": 12.7335, | |
| "eval_vi_samples_per_second": 345.544, | |
| "eval_vi_steps_per_second": 3.613, | |
| "eval_vi_total_cls_tokens": 617, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 24.04591836734694, | |
| "eval_dan_All_acc": 0.6781614559029399, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.13043478260869565, | |
| "eval_dan_Neu_f1": 0.23076923076923078, | |
| "eval_dan_Soc_acc": 0.07142857142857142, | |
| "eval_dan_Soc_f1": 0.13333333333333333, | |
| "eval_dan_cls_acc": 0.10416666666666667, | |
| "eval_dan_cls_f1": 0.15352564102564104, | |
| "eval_dan_loss": 2.0422534942626953, | |
| "eval_dan_runtime": 8.8111, | |
| "eval_dan_samples_per_second": 340.48, | |
| "eval_dan_steps_per_second": 3.632, | |
| "eval_dan_total_cls_tokens": 48, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 24.084183673469386, | |
| "grad_norm": 2.5669384002685547, | |
| "learning_rate": 1.0676027315908618e-05, | |
| "loss": 1.2636, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 24.122448979591837, | |
| "grad_norm": 2.5607757568359375, | |
| "learning_rate": 1.0602971040040483e-05, | |
| "loss": 1.3019, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 24.160714285714285, | |
| "grad_norm": 2.3452446460723877, | |
| "learning_rate": 1.0530098251813697e-05, | |
| "loss": 1.2737, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 24.198979591836736, | |
| "grad_norm": 2.4445223808288574, | |
| "learning_rate": 1.0457409879979351e-05, | |
| "loss": 1.2816, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 24.237244897959183, | |
| "grad_norm": 2.450542688369751, | |
| "learning_rate": 1.0384906850938166e-05, | |
| "loss": 1.3066, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 24.275510204081634, | |
| "grad_norm": 2.4781429767608643, | |
| "learning_rate": 1.031259008872867e-05, | |
| "loss": 1.2728, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 24.31377551020408, | |
| "grad_norm": 2.531564235687256, | |
| "learning_rate": 1.0240460515015477e-05, | |
| "loss": 1.2779, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 24.352040816326532, | |
| "grad_norm": 2.4061906337738037, | |
| "learning_rate": 1.0168519049077541e-05, | |
| "loss": 1.2866, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 24.39030612244898, | |
| "grad_norm": 2.4513766765594482, | |
| "learning_rate": 1.0096766607796365e-05, | |
| "loss": 1.2489, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 24.428571428571427, | |
| "grad_norm": 2.5965521335601807, | |
| "learning_rate": 1.0025204105644398e-05, | |
| "loss": 1.3153, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 24.428571428571427, | |
| "eval_en_All_acc": 0.6172891313470416, | |
| "eval_en_Env_acc": 0.9863013698630136, | |
| "eval_en_Env_f1": 0.993103448275862, | |
| "eval_en_Gov_acc": 0.9696969696969697, | |
| "eval_en_Gov_f1": 0.9624060150375939, | |
| "eval_en_Neu_acc": 0.9375, | |
| "eval_en_Neu_f1": 0.9302325581395349, | |
| "eval_en_Soc_acc": 0.9375, | |
| "eval_en_Soc_f1": 0.9448818897637795, | |
| "eval_en_cls_acc": 0.9588014981273408, | |
| "eval_en_cls_f1": 0.9576559778041925, | |
| "eval_en_loss": 2.2371184825897217, | |
| "eval_en_runtime": 5.6501, | |
| "eval_en_samples_per_second": 332.207, | |
| "eval_en_steps_per_second": 3.54, | |
| "eval_en_total_cls_tokens": 267, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 24.428571428571427, | |
| "eval_en_oof_All_acc": 0.6257117827420061, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9801324503311257, | |
| "eval_en_oof_Gov_acc": 0.972972972972973, | |
| "eval_en_oof_Gov_f1": 0.979591836734694, | |
| "eval_en_oof_Neu_acc": 0.9402985074626866, | |
| "eval_en_oof_Neu_f1": 0.9473684210526316, | |
| "eval_en_oof_Soc_acc": 0.9682539682539683, | |
| "eval_en_oof_Soc_f1": 0.976, | |
| "eval_en_oof_cls_acc": 0.9712230215827338, | |
| "eval_en_oof_cls_f1": 0.9707731770296129, | |
| "eval_en_oof_loss": 2.196458578109741, | |
| "eval_en_oof_runtime": 5.59, | |
| "eval_en_oof_samples_per_second": 335.78, | |
| "eval_en_oof_steps_per_second": 3.578, | |
| "eval_en_oof_total_cls_tokens": 278, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 24.428571428571427, | |
| "eval_vi_All_acc": 0.7951550780458139, | |
| "eval_vi_Env_acc": 0.9751552795031055, | |
| "eval_vi_Env_f1": 0.9751552795031055, | |
| "eval_vi_Gov_acc": 0.9308176100628931, | |
| "eval_vi_Gov_f1": 0.9079754601226994, | |
| "eval_vi_Neu_acc": 0.8579881656804734, | |
| "eval_vi_Neu_f1": 0.8708708708708709, | |
| "eval_vi_Soc_acc": 0.8895027624309392, | |
| "eval_vi_Soc_f1": 0.8969359331476323, | |
| "eval_vi_cls_acc": 0.9119402985074627, | |
| "eval_vi_cls_f1": 0.912734385911077, | |
| "eval_vi_loss": 0.93353271484375, | |
| "eval_vi_runtime": 12.7545, | |
| "eval_vi_samples_per_second": 344.976, | |
| "eval_vi_steps_per_second": 3.607, | |
| "eval_vi_total_cls_tokens": 670, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 24.428571428571427, | |
| "eval_dan_All_acc": 0.680248387867208, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3333333333333333, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.1935483870967742, | |
| "eval_dan_Neu_f1": 0.3243243243243243, | |
| "eval_dan_Soc_acc": 0.42857142857142855, | |
| "eval_dan_Soc_f1": 0.6, | |
| "eval_dan_cls_acc": 0.2641509433962264, | |
| "eval_dan_cls_f1": 0.3560810810810811, | |
| "eval_dan_loss": 2.0569496154785156, | |
| "eval_dan_runtime": 8.7082, | |
| "eval_dan_samples_per_second": 344.501, | |
| "eval_dan_steps_per_second": 3.675, | |
| "eval_dan_total_cls_tokens": 53, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 24.466836734693878, | |
| "grad_norm": 2.4387292861938477, | |
| "learning_rate": 9.95383245467334e-06, | |
| "loss": 1.287, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 24.505102040816325, | |
| "grad_norm": 2.4185335636138916, | |
| "learning_rate": 9.882652564502522e-06, | |
| "loss": 1.3201, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 24.543367346938776, | |
| "grad_norm": 2.40505313873291, | |
| "learning_rate": 9.811665342307328e-06, | |
| "loss": 1.3076, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 24.581632653061224, | |
| "grad_norm": 2.5198564529418945, | |
| "learning_rate": 9.740871692807605e-06, | |
| "loss": 1.2868, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 24.619897959183675, | |
| "grad_norm": 2.44199800491333, | |
| "learning_rate": 9.670272518256163e-06, | |
| "loss": 1.2858, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 24.658163265306122, | |
| "grad_norm": 2.5254967212677, | |
| "learning_rate": 9.599868718427257e-06, | |
| "loss": 1.262, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 24.696428571428573, | |
| "grad_norm": 2.57082462310791, | |
| "learning_rate": 9.529661190605125e-06, | |
| "loss": 1.304, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 24.73469387755102, | |
| "grad_norm": 2.4790477752685547, | |
| "learning_rate": 9.459650829572556e-06, | |
| "loss": 1.3196, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 24.772959183673468, | |
| "grad_norm": 2.51210618019104, | |
| "learning_rate": 9.389838527599484e-06, | |
| "loss": 1.3256, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 24.81122448979592, | |
| "grad_norm": 2.382573366165161, | |
| "learning_rate": 9.320225174431588e-06, | |
| "loss": 1.2661, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.81122448979592, | |
| "eval_en_All_acc": 0.6284652150823155, | |
| "eval_en_Env_acc": 0.9682539682539683, | |
| "eval_en_Env_f1": 0.9606299212598425, | |
| "eval_en_Gov_acc": 0.971830985915493, | |
| "eval_en_Gov_f1": 0.965034965034965, | |
| "eval_en_Neu_acc": 0.8153846153846154, | |
| "eval_en_Neu_f1": 0.848, | |
| "eval_en_Soc_acc": 0.9444444444444444, | |
| "eval_en_Soc_f1": 0.918918918918919, | |
| "eval_en_cls_acc": 0.924901185770751, | |
| "eval_en_cls_f1": 0.9231459513034316, | |
| "eval_en_loss": 2.1538894176483154, | |
| "eval_en_runtime": 5.5874, | |
| "eval_en_samples_per_second": 335.937, | |
| "eval_en_steps_per_second": 3.58, | |
| "eval_en_total_cls_tokens": 253, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.81122448979592, | |
| "eval_en_oof_All_acc": 0.6276652169300944, | |
| "eval_en_oof_Env_acc": 0.9647058823529412, | |
| "eval_en_oof_Env_f1": 0.9647058823529412, | |
| "eval_en_oof_Gov_acc": 0.9848484848484849, | |
| "eval_en_oof_Gov_f1": 0.9774436090225564, | |
| "eval_en_oof_Neu_acc": 0.9066666666666666, | |
| "eval_en_oof_Neu_f1": 0.9315068493150686, | |
| "eval_en_oof_Soc_acc": 0.9722222222222222, | |
| "eval_en_oof_Soc_f1": 0.9523809523809524, | |
| "eval_en_oof_cls_acc": 0.9563758389261745, | |
| "eval_en_oof_cls_f1": 0.9565093232678796, | |
| "eval_en_oof_loss": 2.1532833576202393, | |
| "eval_en_oof_runtime": 5.617, | |
| "eval_en_oof_samples_per_second": 334.165, | |
| "eval_en_oof_steps_per_second": 3.561, | |
| "eval_en_oof_total_cls_tokens": 298, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.81122448979592, | |
| "eval_vi_All_acc": 0.7944067884306928, | |
| "eval_vi_Env_acc": 0.9709302325581395, | |
| "eval_vi_Env_f1": 0.9597701149425287, | |
| "eval_vi_Gov_acc": 0.8782051282051282, | |
| "eval_vi_Gov_f1": 0.8867313915857605, | |
| "eval_vi_Neu_acc": 0.8978102189781022, | |
| "eval_vi_Neu_f1": 0.924812030075188, | |
| "eval_vi_Soc_acc": 0.9289940828402367, | |
| "eval_vi_Soc_f1": 0.9101449275362319, | |
| "eval_vi_cls_acc": 0.9211356466876972, | |
| "eval_vi_cls_f1": 0.9203646160349273, | |
| "eval_vi_loss": 0.9486858248710632, | |
| "eval_vi_runtime": 12.7428, | |
| "eval_vi_samples_per_second": 345.294, | |
| "eval_vi_steps_per_second": 3.61, | |
| "eval_vi_total_cls_tokens": 634, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.81122448979592, | |
| "eval_dan_All_acc": 0.675863667980524, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.4, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.20833333333333334, | |
| "eval_dan_Neu_f1": 0.3448275862068966, | |
| "eval_dan_Soc_acc": 0.38461538461538464, | |
| "eval_dan_Soc_f1": 0.5555555555555556, | |
| "eval_dan_cls_acc": 0.2857142857142857, | |
| "eval_dan_cls_f1": 0.35009578544061304, | |
| "eval_dan_loss": 2.089972496032715, | |
| "eval_dan_runtime": 8.673, | |
| "eval_dan_samples_per_second": 345.9, | |
| "eval_dan_steps_per_second": 3.69, | |
| "eval_dan_total_cls_tokens": 42, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.849489795918366, | |
| "grad_norm": 2.561476469039917, | |
| "learning_rate": 9.250811657279027e-06, | |
| "loss": 1.2753, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 24.887755102040817, | |
| "grad_norm": 2.4686853885650635, | |
| "learning_rate": 9.181598860805057e-06, | |
| "loss": 1.2542, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 24.926020408163264, | |
| "grad_norm": 2.512068271636963, | |
| "learning_rate": 9.112587667114761e-06, | |
| "loss": 1.3327, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 24.964285714285715, | |
| "grad_norm": 2.4352872371673584, | |
| "learning_rate": 9.043778955743876e-06, | |
| "loss": 1.2841, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 1.2985997200012207, | |
| "learning_rate": 8.975173603647521e-06, | |
| "loss": 1.1889, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 25.038265306122447, | |
| "grad_norm": 2.3900318145751953, | |
| "learning_rate": 8.906772485189e-06, | |
| "loss": 1.2965, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 25.0765306122449, | |
| "grad_norm": 2.32544207572937, | |
| "learning_rate": 8.838576472128756e-06, | |
| "loss": 1.3004, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 25.114795918367346, | |
| "grad_norm": 2.492950916290283, | |
| "learning_rate": 8.77058643361315e-06, | |
| "loss": 1.2946, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 25.153061224489797, | |
| "grad_norm": 2.6994709968566895, | |
| "learning_rate": 8.702803236163449e-06, | |
| "loss": 1.3035, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 25.191326530612244, | |
| "grad_norm": 2.4942150115966797, | |
| "learning_rate": 8.635227743664787e-06, | |
| "loss": 1.2676, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 25.191326530612244, | |
| "eval_en_All_acc": 0.6239399869536856, | |
| "eval_en_Env_acc": 0.9705882352941176, | |
| "eval_en_Env_f1": 0.9496402877697842, | |
| "eval_en_Gov_acc": 0.9848484848484849, | |
| "eval_en_Gov_f1": 0.9701492537313432, | |
| "eval_en_Neu_acc": 0.8518518518518519, | |
| "eval_en_Neu_f1": 0.8679245283018868, | |
| "eval_en_Soc_acc": 0.8888888888888888, | |
| "eval_en_Soc_f1": 0.8999999999999999, | |
| "eval_en_cls_acc": 0.918918918918919, | |
| "eval_en_cls_f1": 0.9219285174507534, | |
| "eval_en_loss": 2.2110953330993652, | |
| "eval_en_runtime": 5.6375, | |
| "eval_en_samples_per_second": 332.952, | |
| "eval_en_steps_per_second": 3.548, | |
| "eval_en_total_cls_tokens": 296, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 25.191326530612244, | |
| "eval_en_oof_All_acc": 0.6383140101852856, | |
| "eval_en_oof_Env_acc": 0.9848484848484849, | |
| "eval_en_oof_Env_f1": 0.9848484848484849, | |
| "eval_en_oof_Gov_acc": 0.9821428571428571, | |
| "eval_en_oof_Gov_f1": 0.9734513274336283, | |
| "eval_en_oof_Neu_acc": 0.9180327868852459, | |
| "eval_en_oof_Neu_f1": 0.9032258064516128, | |
| "eval_en_oof_Soc_acc": 0.890625, | |
| "eval_en_oof_Soc_f1": 0.9120000000000001, | |
| "eval_en_oof_cls_acc": 0.9433198380566802, | |
| "eval_en_oof_cls_f1": 0.9433814046834315, | |
| "eval_en_oof_loss": 2.0972554683685303, | |
| "eval_en_oof_runtime": 5.5747, | |
| "eval_en_oof_samples_per_second": 336.701, | |
| "eval_en_oof_steps_per_second": 3.588, | |
| "eval_en_oof_total_cls_tokens": 247, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 25.191326530612244, | |
| "eval_vi_All_acc": 0.7888678051865907, | |
| "eval_vi_Env_acc": 0.9878048780487805, | |
| "eval_vi_Env_f1": 0.9700598802395209, | |
| "eval_vi_Gov_acc": 0.8743455497382199, | |
| "eval_vi_Gov_f1": 0.8978494623655914, | |
| "eval_vi_Neu_acc": 0.910958904109589, | |
| "eval_vi_Neu_f1": 0.9078498293515359, | |
| "eval_vi_Soc_acc": 0.8881118881118881, | |
| "eval_vi_Soc_f1": 0.878892733564014, | |
| "eval_vi_cls_acc": 0.9145962732919255, | |
| "eval_vi_cls_f1": 0.9136629763801656, | |
| "eval_vi_loss": 0.9907578229904175, | |
| "eval_vi_runtime": 12.7487, | |
| "eval_vi_samples_per_second": 345.134, | |
| "eval_vi_steps_per_second": 3.608, | |
| "eval_vi_total_cls_tokens": 644, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 25.191326530612244, | |
| "eval_dan_All_acc": 0.6734414249828728, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.25, | |
| "eval_dan_Gov_f1": 0.4, | |
| "eval_dan_Neu_acc": 0.1111111111111111, | |
| "eval_dan_Neu_f1": 0.19999999999999998, | |
| "eval_dan_Soc_acc": 0.15, | |
| "eval_dan_Soc_f1": 0.2608695652173913, | |
| "eval_dan_cls_acc": 0.14893617021276595, | |
| "eval_dan_cls_f1": 0.2152173913043478, | |
| "eval_dan_loss": 2.1164021492004395, | |
| "eval_dan_runtime": 8.745, | |
| "eval_dan_samples_per_second": 343.055, | |
| "eval_dan_steps_per_second": 3.659, | |
| "eval_dan_total_cls_tokens": 47, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 25.229591836734695, | |
| "grad_norm": 2.369295120239258, | |
| "learning_rate": 8.567860817355097e-06, | |
| "loss": 1.2736, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 25.267857142857142, | |
| "grad_norm": 2.4538395404815674, | |
| "learning_rate": 8.500703315814191e-06, | |
| "loss": 1.3131, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 25.306122448979593, | |
| "grad_norm": 2.488490104675293, | |
| "learning_rate": 8.433756094952819e-06, | |
| "loss": 1.3275, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 25.34438775510204, | |
| "grad_norm": 2.648719549179077, | |
| "learning_rate": 8.367020008001698e-06, | |
| "loss": 1.2872, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 25.382653061224488, | |
| "grad_norm": 2.3895843029022217, | |
| "learning_rate": 8.300495905500707e-06, | |
| "loss": 1.3012, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 25.42091836734694, | |
| "grad_norm": 2.5159616470336914, | |
| "learning_rate": 8.234184635288017e-06, | |
| "loss": 1.3058, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 25.459183673469386, | |
| "grad_norm": 2.566506862640381, | |
| "learning_rate": 8.168087042489283e-06, | |
| "loss": 1.2961, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 25.497448979591837, | |
| "grad_norm": 2.5162441730499268, | |
| "learning_rate": 8.102203969506886e-06, | |
| "loss": 1.2837, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 25.535714285714285, | |
| "grad_norm": 2.40036678314209, | |
| "learning_rate": 8.036536256009178e-06, | |
| "loss": 1.2544, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 25.573979591836736, | |
| "grad_norm": 2.488490581512451, | |
| "learning_rate": 7.971084738919798e-06, | |
| "loss": 1.2816, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 25.573979591836736, | |
| "eval_en_All_acc": 0.6127803639441388, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9549549549549551, | |
| "eval_en_Gov_acc": 0.9833333333333333, | |
| "eval_en_Gov_f1": 0.9672131147540983, | |
| "eval_en_Neu_acc": 0.8947368421052632, | |
| "eval_en_Neu_f1": 0.9340659340659342, | |
| "eval_en_Soc_acc": 0.9482758620689655, | |
| "eval_en_Soc_f1": 0.94017094017094, | |
| "eval_en_cls_acc": 0.9473684210526315, | |
| "eval_en_cls_f1": 0.9491012359864819, | |
| "eval_en_loss": 2.2661733627319336, | |
| "eval_en_runtime": 5.6341, | |
| "eval_en_samples_per_second": 333.147, | |
| "eval_en_steps_per_second": 3.55, | |
| "eval_en_total_cls_tokens": 266, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 25.573979591836736, | |
| "eval_en_oof_All_acc": 0.6223432101350644, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9793103448275862, | |
| "eval_en_oof_Gov_acc": 0.9354838709677419, | |
| "eval_en_oof_Gov_f1": 0.9586776859504132, | |
| "eval_en_oof_Neu_acc": 0.9333333333333333, | |
| "eval_en_oof_Neu_f1": 0.9545454545454545, | |
| "eval_en_oof_Soc_acc": 1.0, | |
| "eval_en_oof_Soc_f1": 0.9746835443037974, | |
| "eval_en_oof_cls_acc": 0.9666666666666667, | |
| "eval_en_oof_cls_f1": 0.9668042574068129, | |
| "eval_en_oof_loss": 2.2057576179504395, | |
| "eval_en_oof_runtime": 5.6149, | |
| "eval_en_oof_samples_per_second": 334.286, | |
| "eval_en_oof_steps_per_second": 3.562, | |
| "eval_en_oof_total_cls_tokens": 300, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 25.573979591836736, | |
| "eval_vi_All_acc": 0.7969717825189263, | |
| "eval_vi_Env_acc": 0.9887640449438202, | |
| "eval_vi_Env_f1": 0.9832402234636872, | |
| "eval_vi_Gov_acc": 0.9528795811518325, | |
| "eval_vi_Gov_f1": 0.9309462915601024, | |
| "eval_vi_Neu_acc": 0.9210526315789473, | |
| "eval_vi_Neu_f1": 0.9271523178807947, | |
| "eval_vi_Soc_acc": 0.8711656441717791, | |
| "eval_vi_Soc_f1": 0.8958990536277602, | |
| "eval_vi_cls_acc": 0.935672514619883, | |
| "eval_vi_cls_f1": 0.9343094716330861, | |
| "eval_vi_loss": 0.9301120638847351, | |
| "eval_vi_runtime": 12.6907, | |
| "eval_vi_samples_per_second": 346.71, | |
| "eval_vi_steps_per_second": 3.625, | |
| "eval_vi_total_cls_tokens": 684, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 25.573979591836736, | |
| "eval_dan_All_acc": 0.672090980537192, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3333333333333333, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.15789473684210525, | |
| "eval_dan_Neu_f1": 0.2727272727272727, | |
| "eval_dan_Soc_acc": 0.0, | |
| "eval_dan_Soc_f1": 0.0, | |
| "eval_dan_cls_acc": 0.19444444444444445, | |
| "eval_dan_cls_f1": 0.19318181818181818, | |
| "eval_dan_loss": 2.1295111179351807, | |
| "eval_dan_runtime": 8.9677, | |
| "eval_dan_samples_per_second": 334.534, | |
| "eval_dan_steps_per_second": 3.568, | |
| "eval_dan_total_cls_tokens": 36, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 25.612244897959183, | |
| "grad_norm": 2.4766621589660645, | |
| "learning_rate": 7.905850252407004e-06, | |
| "loss": 1.2626, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 25.650510204081634, | |
| "grad_norm": 2.585754871368408, | |
| "learning_rate": 7.840833627873028e-06, | |
| "loss": 1.2844, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 25.68877551020408, | |
| "grad_norm": 2.8109304904937744, | |
| "learning_rate": 7.776035693943496e-06, | |
| "loss": 1.28, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 25.727040816326532, | |
| "grad_norm": 2.6798696517944336, | |
| "learning_rate": 7.71145727645685e-06, | |
| "loss": 1.3266, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 25.76530612244898, | |
| "grad_norm": 2.5205228328704834, | |
| "learning_rate": 7.647099198453847e-06, | |
| "loss": 1.2604, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 25.803571428571427, | |
| "grad_norm": 2.611445665359497, | |
| "learning_rate": 7.582962280167044e-06, | |
| "loss": 1.2933, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 25.841836734693878, | |
| "grad_norm": 2.5490939617156982, | |
| "learning_rate": 7.519047339010368e-06, | |
| "loss": 1.3219, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 25.880102040816325, | |
| "grad_norm": 2.5222201347351074, | |
| "learning_rate": 7.4553551895686604e-06, | |
| "loss": 1.2998, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 25.918367346938776, | |
| "grad_norm": 2.442595958709717, | |
| "learning_rate": 7.391886643587342e-06, | |
| "loss": 1.289, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 25.956632653061224, | |
| "grad_norm": 2.410179376602173, | |
| "learning_rate": 7.328642509962066e-06, | |
| "loss": 1.2771, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 25.956632653061224, | |
| "eval_en_All_acc": 0.6434456928838951, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9714285714285714, | |
| "eval_en_Gov_acc": 0.9836065573770492, | |
| "eval_en_Gov_f1": 0.9677419354838709, | |
| "eval_en_Neu_acc": 0.8734177215189873, | |
| "eval_en_Neu_f1": 0.9078947368421053, | |
| "eval_en_Soc_acc": 0.9375, | |
| "eval_en_Soc_f1": 0.9375, | |
| "eval_en_cls_acc": 0.9448529411764706, | |
| "eval_en_cls_f1": 0.946141310938637, | |
| "eval_en_loss": 2.0509910583496094, | |
| "eval_en_runtime": 5.625, | |
| "eval_en_samples_per_second": 333.687, | |
| "eval_en_steps_per_second": 3.556, | |
| "eval_en_total_cls_tokens": 272, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 25.956632653061224, | |
| "eval_en_oof_All_acc": 0.628846357195728, | |
| "eval_en_oof_Env_acc": 0.9830508474576272, | |
| "eval_en_oof_Env_f1": 0.9508196721311476, | |
| "eval_en_oof_Gov_acc": 0.9354838709677419, | |
| "eval_en_oof_Gov_f1": 0.943089430894309, | |
| "eval_en_oof_Neu_acc": 0.8852459016393442, | |
| "eval_en_oof_Neu_f1": 0.9075630252100839, | |
| "eval_en_oof_Soc_acc": 0.974025974025974, | |
| "eval_en_oof_Soc_f1": 0.974025974025974, | |
| "eval_en_oof_cls_acc": 0.9459459459459459, | |
| "eval_en_oof_cls_f1": 0.9438745255653785, | |
| "eval_en_oof_loss": 2.1311235427856445, | |
| "eval_en_oof_runtime": 5.559, | |
| "eval_en_oof_samples_per_second": 337.651, | |
| "eval_en_oof_steps_per_second": 3.598, | |
| "eval_en_oof_total_cls_tokens": 259, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 25.956632653061224, | |
| "eval_vi_All_acc": 0.7890413754400286, | |
| "eval_vi_Env_acc": 0.9631578947368421, | |
| "eval_vi_Env_f1": 0.9606299212598425, | |
| "eval_vi_Gov_acc": 0.9425287356321839, | |
| "eval_vi_Gov_f1": 0.9187675070028011, | |
| "eval_vi_Neu_acc": 0.8888888888888888, | |
| "eval_vi_Neu_f1": 0.9158249158249158, | |
| "eval_vi_Soc_acc": 0.9101796407185628, | |
| "eval_vi_Soc_f1": 0.9129129129129129, | |
| "eval_vi_cls_acc": 0.9283625730994152, | |
| "eval_vi_cls_f1": 0.927033814250118, | |
| "eval_vi_loss": 0.9673053622245789, | |
| "eval_vi_runtime": 12.7519, | |
| "eval_vi_samples_per_second": 345.047, | |
| "eval_vi_steps_per_second": 3.607, | |
| "eval_vi_total_cls_tokens": 684, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 25.956632653061224, | |
| "eval_dan_All_acc": 0.6804879180000928, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.42857142857142855, | |
| "eval_dan_Gov_f1": 0.6, | |
| "eval_dan_Neu_acc": 0.3, | |
| "eval_dan_Neu_f1": 0.4615384615384615, | |
| "eval_dan_Soc_acc": 0.14285714285714285, | |
| "eval_dan_Soc_f1": 0.25, | |
| "eval_dan_cls_acc": 0.2619047619047619, | |
| "eval_dan_cls_f1": 0.3278846153846154, | |
| "eval_dan_loss": 2.0693531036376953, | |
| "eval_dan_runtime": 8.7874, | |
| "eval_dan_samples_per_second": 341.397, | |
| "eval_dan_steps_per_second": 3.642, | |
| "eval_dan_total_cls_tokens": 42, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 25.994897959183675, | |
| "grad_norm": 2.545499324798584, | |
| "learning_rate": 7.2656235947283376e-06, | |
| "loss": 1.2842, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 26.03061224489796, | |
| "grad_norm": 2.504988670349121, | |
| "learning_rate": 7.202830701051322e-06, | |
| "loss": 1.2142, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 26.068877551020407, | |
| "grad_norm": 2.3397915363311768, | |
| "learning_rate": 7.140264629215601e-06, | |
| "loss": 1.3321, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 26.107142857142858, | |
| "grad_norm": 2.410507917404175, | |
| "learning_rate": 7.0779261766149016e-06, | |
| "loss": 1.295, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 26.145408163265305, | |
| "grad_norm": 2.4722063541412354, | |
| "learning_rate": 7.015816137742023e-06, | |
| "loss": 1.3165, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 26.183673469387756, | |
| "grad_norm": 2.332484483718872, | |
| "learning_rate": 6.953935304178649e-06, | |
| "loss": 1.2788, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 26.221938775510203, | |
| "grad_norm": 2.335740089416504, | |
| "learning_rate": 6.892284464585294e-06, | |
| "loss": 1.2885, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 26.260204081632654, | |
| "grad_norm": 2.331174373626709, | |
| "learning_rate": 6.8308644046912316e-06, | |
| "loss": 1.2942, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 26.2984693877551, | |
| "grad_norm": 2.361612319946289, | |
| "learning_rate": 6.769675907284495e-06, | |
| "loss": 1.2546, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 26.336734693877553, | |
| "grad_norm": 2.414506673812866, | |
| "learning_rate": 6.708719752201884e-06, | |
| "loss": 1.3292, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 26.336734693877553, | |
| "eval_en_All_acc": 0.6187020526643168, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 1.0, | |
| "eval_en_Gov_acc": 0.9830508474576272, | |
| "eval_en_Gov_f1": 0.9830508474576272, | |
| "eval_en_Neu_acc": 0.9130434782608695, | |
| "eval_en_Neu_f1": 0.9473684210526315, | |
| "eval_en_Soc_acc": 1.0, | |
| "eval_en_Soc_f1": 0.965034965034965, | |
| "eval_en_cls_acc": 0.9735849056603774, | |
| "eval_en_cls_f1": 0.9738635583863059, | |
| "eval_en_loss": 2.2362046241760254, | |
| "eval_en_runtime": 5.6322, | |
| "eval_en_samples_per_second": 333.263, | |
| "eval_en_steps_per_second": 3.551, | |
| "eval_en_total_cls_tokens": 265, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 26.336734693877553, | |
| "eval_en_oof_All_acc": 0.6159180293935003, | |
| "eval_en_oof_Env_acc": 0.9577464788732394, | |
| "eval_en_oof_Env_f1": 0.951048951048951, | |
| "eval_en_oof_Gov_acc": 0.953125, | |
| "eval_en_oof_Gov_f1": 0.9242424242424244, | |
| "eval_en_oof_Neu_acc": 0.8, | |
| "eval_en_oof_Neu_f1": 0.8450704225352113, | |
| "eval_en_oof_Soc_acc": 0.9130434782608695, | |
| "eval_en_oof_Soc_f1": 0.8936170212765957, | |
| "eval_en_oof_cls_acc": 0.9032258064516129, | |
| "eval_en_oof_cls_f1": 0.9034947047757955, | |
| "eval_en_oof_loss": 2.2004921436309814, | |
| "eval_en_oof_runtime": 5.5971, | |
| "eval_en_oof_samples_per_second": 335.352, | |
| "eval_en_oof_steps_per_second": 3.573, | |
| "eval_en_oof_total_cls_tokens": 279, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 26.336734693877553, | |
| "eval_vi_All_acc": 0.7919226482100734, | |
| "eval_vi_Env_acc": 0.9727891156462585, | |
| "eval_vi_Env_f1": 0.962962962962963, | |
| "eval_vi_Gov_acc": 0.8888888888888888, | |
| "eval_vi_Gov_f1": 0.847682119205298, | |
| "eval_vi_Neu_acc": 0.8909090909090909, | |
| "eval_vi_Neu_f1": 0.901840490797546, | |
| "eval_vi_Soc_acc": 0.8361581920903954, | |
| "eval_vi_Soc_f1": 0.8680351906158358, | |
| "eval_vi_cls_acc": 0.8941548183254344, | |
| "eval_vi_cls_f1": 0.8951301908954107, | |
| "eval_vi_loss": 0.95640629529953, | |
| "eval_vi_runtime": 12.7569, | |
| "eval_vi_samples_per_second": 344.91, | |
| "eval_vi_steps_per_second": 3.606, | |
| "eval_vi_total_cls_tokens": 633, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 26.336734693877553, | |
| "eval_dan_All_acc": 0.6736550818441912, | |
| "eval_dan_Env_acc": 0.3333333333333333, | |
| "eval_dan_Env_f1": 0.5, | |
| "eval_dan_Gov_acc": 0.125, | |
| "eval_dan_Gov_f1": 0.2222222222222222, | |
| "eval_dan_Neu_acc": 0.25, | |
| "eval_dan_Neu_f1": 0.4, | |
| "eval_dan_Soc_acc": 0.13333333333333333, | |
| "eval_dan_Soc_f1": 0.23529411764705882, | |
| "eval_dan_cls_acc": 0.19047619047619047, | |
| "eval_dan_cls_f1": 0.3393790849673203, | |
| "eval_dan_loss": 2.0835816860198975, | |
| "eval_dan_runtime": 8.8236, | |
| "eval_dan_samples_per_second": 339.997, | |
| "eval_dan_steps_per_second": 3.627, | |
| "eval_dan_total_cls_tokens": 42, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 26.375, | |
| "grad_norm": 2.4954118728637695, | |
| "learning_rate": 6.6479967163190435e-06, | |
| "loss": 1.26, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 26.413265306122447, | |
| "grad_norm": 2.5237762928009033, | |
| "learning_rate": 6.587507573540552e-06, | |
| "loss": 1.275, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 26.4515306122449, | |
| "grad_norm": 2.41147780418396, | |
| "learning_rate": 6.527253094790062e-06, | |
| "loss": 1.2997, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 26.489795918367346, | |
| "grad_norm": 2.5627410411834717, | |
| "learning_rate": 6.467234048000478e-06, | |
| "loss": 1.2701, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 26.528061224489797, | |
| "grad_norm": 2.390385866165161, | |
| "learning_rate": 6.407451198104139e-06, | |
| "loss": 1.3119, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 26.566326530612244, | |
| "grad_norm": 2.2593681812286377, | |
| "learning_rate": 6.347905307023139e-06, | |
| "loss": 1.2797, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 26.604591836734695, | |
| "grad_norm": 2.6369011402130127, | |
| "learning_rate": 6.288597133659546e-06, | |
| "loss": 1.243, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 26.642857142857142, | |
| "grad_norm": 2.6097004413604736, | |
| "learning_rate": 6.2295274338857425e-06, | |
| "loss": 1.2763, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 26.681122448979593, | |
| "grad_norm": 2.393362522125244, | |
| "learning_rate": 6.170696960534847e-06, | |
| "loss": 1.266, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 26.71938775510204, | |
| "grad_norm": 2.3980636596679688, | |
| "learning_rate": 6.112106463391051e-06, | |
| "loss": 1.2952, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.71938775510204, | |
| "eval_en_All_acc": 0.6187287414965986, | |
| "eval_en_Env_acc": 0.9846153846153847, | |
| "eval_en_Env_f1": 0.962406015037594, | |
| "eval_en_Gov_acc": 0.9836065573770492, | |
| "eval_en_Gov_f1": 0.9836065573770492, | |
| "eval_en_Neu_acc": 0.9102564102564102, | |
| "eval_en_Neu_f1": 0.9403973509933774, | |
| "eval_en_Soc_acc": 0.9850746268656716, | |
| "eval_en_Soc_f1": 0.9705882352941176, | |
| "eval_en_cls_acc": 0.9630996309963099, | |
| "eval_en_cls_f1": 0.9642495396755346, | |
| "eval_en_loss": 2.203822374343872, | |
| "eval_en_runtime": 5.6339, | |
| "eval_en_samples_per_second": 333.16, | |
| "eval_en_steps_per_second": 3.55, | |
| "eval_en_total_cls_tokens": 271, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.71938775510204, | |
| "eval_en_oof_All_acc": 0.6313643491897543, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9732620320855615, | |
| "eval_en_oof_Gov_acc": 0.9571428571428572, | |
| "eval_en_oof_Gov_f1": 0.9710144927536232, | |
| "eval_en_oof_Neu_acc": 0.8846153846153846, | |
| "eval_en_oof_Neu_f1": 0.9261744966442953, | |
| "eval_en_oof_Soc_acc": 0.9868421052631579, | |
| "eval_en_oof_Soc_f1": 0.9615384615384615, | |
| "eval_en_oof_cls_acc": 0.9587301587301588, | |
| "eval_en_oof_cls_f1": 0.9579973707554854, | |
| "eval_en_oof_loss": 2.1271567344665527, | |
| "eval_en_oof_runtime": 5.5805, | |
| "eval_en_oof_samples_per_second": 336.348, | |
| "eval_en_oof_steps_per_second": 3.584, | |
| "eval_en_oof_total_cls_tokens": 315, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.71938775510204, | |
| "eval_vi_All_acc": 0.7964396882154708, | |
| "eval_vi_Env_acc": 0.9464285714285714, | |
| "eval_vi_Env_f1": 0.9380530973451328, | |
| "eval_vi_Gov_acc": 0.9066666666666666, | |
| "eval_vi_Gov_f1": 0.9096989966555183, | |
| "eval_vi_Neu_acc": 0.86875, | |
| "eval_vi_Neu_f1": 0.8996763754045307, | |
| "eval_vi_Soc_acc": 0.9066666666666666, | |
| "eval_vi_Soc_f1": 0.8802588996763754, | |
| "eval_vi_cls_acc": 0.9076433121019108, | |
| "eval_vi_cls_f1": 0.9069218422703893, | |
| "eval_vi_loss": 0.9379875063896179, | |
| "eval_vi_runtime": 12.5596, | |
| "eval_vi_samples_per_second": 350.331, | |
| "eval_vi_steps_per_second": 3.663, | |
| "eval_vi_total_cls_tokens": 628, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.71938775510204, | |
| "eval_dan_All_acc": 0.6739688359303392, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3, | |
| "eval_dan_Gov_f1": 0.4615384615384615, | |
| "eval_dan_Neu_acc": 0.05263157894736842, | |
| "eval_dan_Neu_f1": 0.1, | |
| "eval_dan_Soc_acc": 0.45454545454545453, | |
| "eval_dan_Soc_f1": 0.625, | |
| "eval_dan_cls_acc": 0.21951219512195122, | |
| "eval_dan_cls_f1": 0.2966346153846154, | |
| "eval_dan_loss": 2.0673747062683105, | |
| "eval_dan_runtime": 8.8071, | |
| "eval_dan_samples_per_second": 340.636, | |
| "eval_dan_steps_per_second": 3.633, | |
| "eval_dan_total_cls_tokens": 41, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.757653061224488, | |
| "grad_norm": 2.3423383235931396, | |
| "learning_rate": 6.053756689180082e-06, | |
| "loss": 1.2615, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 26.79591836734694, | |
| "grad_norm": 2.580850124359131, | |
| "learning_rate": 5.9956483815597235e-06, | |
| "loss": 1.2664, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 26.834183673469386, | |
| "grad_norm": 2.5235424041748047, | |
| "learning_rate": 5.937782281110302e-06, | |
| "loss": 1.2787, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 26.872448979591837, | |
| "grad_norm": 2.496351957321167, | |
| "learning_rate": 5.88015912532523e-06, | |
| "loss": 1.2936, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 26.910714285714285, | |
| "grad_norm": 2.5270462036132812, | |
| "learning_rate": 5.822779648601659e-06, | |
| "loss": 1.3032, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 26.948979591836736, | |
| "grad_norm": 2.435511589050293, | |
| "learning_rate": 5.765644582231086e-06, | |
| "loss": 1.275, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 26.987244897959183, | |
| "grad_norm": 2.5175130367279053, | |
| "learning_rate": 5.708754654390039e-06, | |
| "loss": 1.3223, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 27.022959183673468, | |
| "grad_norm": 2.663588762283325, | |
| "learning_rate": 5.652110590130799e-06, | |
| "loss": 1.2085, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 27.06122448979592, | |
| "grad_norm": 2.433781147003174, | |
| "learning_rate": 5.595713111372155e-06, | |
| "loss": 1.2956, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 27.099489795918366, | |
| "grad_norm": 2.504512310028076, | |
| "learning_rate": 5.5395629368902135e-06, | |
| "loss": 1.265, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 27.099489795918366, | |
| "eval_en_All_acc": 0.6245923026744945, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9921259842519685, | |
| "eval_en_Gov_acc": 0.9615384615384616, | |
| "eval_en_Gov_f1": 0.9433962264150944, | |
| "eval_en_Neu_acc": 0.8780487804878049, | |
| "eval_en_Neu_f1": 0.9056603773584906, | |
| "eval_en_Soc_acc": 0.921875, | |
| "eval_en_Soc_f1": 0.9076923076923077, | |
| "eval_en_cls_acc": 0.9348659003831418, | |
| "eval_en_cls_f1": 0.9372187239294651, | |
| "eval_en_loss": 2.178861141204834, | |
| "eval_en_runtime": 5.6386, | |
| "eval_en_samples_per_second": 332.883, | |
| "eval_en_steps_per_second": 3.547, | |
| "eval_en_total_cls_tokens": 261, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 27.099489795918366, | |
| "eval_en_oof_All_acc": 0.6213768115942029, | |
| "eval_en_oof_Env_acc": 0.9883720930232558, | |
| "eval_en_oof_Env_f1": 0.9826589595375722, | |
| "eval_en_oof_Gov_acc": 0.9838709677419355, | |
| "eval_en_oof_Gov_f1": 0.9531249999999999, | |
| "eval_en_oof_Neu_acc": 0.8571428571428571, | |
| "eval_en_oof_Neu_f1": 0.8648648648648648, | |
| "eval_en_oof_Soc_acc": 0.8823529411764706, | |
| "eval_en_oof_Soc_f1": 0.9090909090909091, | |
| "eval_en_oof_cls_acc": 0.9338235294117647, | |
| "eval_en_oof_cls_f1": 0.9274349333733365, | |
| "eval_en_oof_loss": 2.1597862243652344, | |
| "eval_en_oof_runtime": 5.6111, | |
| "eval_en_oof_samples_per_second": 334.513, | |
| "eval_en_oof_steps_per_second": 3.564, | |
| "eval_en_oof_total_cls_tokens": 272, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 27.099489795918366, | |
| "eval_vi_All_acc": 0.7954465052812453, | |
| "eval_vi_Env_acc": 0.9631901840490797, | |
| "eval_vi_Env_f1": 0.9602446483180427, | |
| "eval_vi_Gov_acc": 0.8994413407821229, | |
| "eval_vi_Gov_f1": 0.8969359331476323, | |
| "eval_vi_Neu_acc": 0.8571428571428571, | |
| "eval_vi_Neu_f1": 0.8873239436619718, | |
| "eval_vi_Soc_acc": 0.8835616438356164, | |
| "eval_vi_Soc_f1": 0.86, | |
| "eval_vi_cls_acc": 0.9023622047244094, | |
| "eval_vi_cls_f1": 0.9011261312819117, | |
| "eval_vi_loss": 0.9397348761558533, | |
| "eval_vi_runtime": 12.756, | |
| "eval_vi_samples_per_second": 344.936, | |
| "eval_vi_steps_per_second": 3.606, | |
| "eval_vi_total_cls_tokens": 635, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 27.099489795918366, | |
| "eval_dan_All_acc": 0.6756554657194934, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.17391304347826086, | |
| "eval_dan_Neu_f1": 0.29629629629629634, | |
| "eval_dan_Soc_acc": 0.16666666666666666, | |
| "eval_dan_Soc_f1": 0.2857142857142857, | |
| "eval_dan_cls_acc": 0.16, | |
| "eval_dan_cls_f1": 0.20800264550264552, | |
| "eval_dan_loss": 2.0897600650787354, | |
| "eval_dan_runtime": 8.8124, | |
| "eval_dan_samples_per_second": 340.429, | |
| "eval_dan_steps_per_second": 3.631, | |
| "eval_dan_total_cls_tokens": 50, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 27.137755102040817, | |
| "grad_norm": 2.569690704345703, | |
| "learning_rate": 5.483660782309222e-06, | |
| "loss": 1.3036, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 27.176020408163264, | |
| "grad_norm": 2.5049712657928467, | |
| "learning_rate": 5.428007360092463e-06, | |
| "loss": 1.2704, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 27.214285714285715, | |
| "grad_norm": 2.5624125003814697, | |
| "learning_rate": 5.3726033795331646e-06, | |
| "loss": 1.2977, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 27.252551020408163, | |
| "grad_norm": 2.422895908355713, | |
| "learning_rate": 5.31744954674547e-06, | |
| "loss": 1.2349, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 27.290816326530614, | |
| "grad_norm": 2.786591053009033, | |
| "learning_rate": 5.26254656465543e-06, | |
| "loss": 1.3528, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 27.32908163265306, | |
| "grad_norm": 2.541363000869751, | |
| "learning_rate": 5.2078951329920385e-06, | |
| "loss": 1.2566, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 27.367346938775512, | |
| "grad_norm": 2.4004898071289062, | |
| "learning_rate": 5.153495948278336e-06, | |
| "loss": 1.2782, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 27.40561224489796, | |
| "grad_norm": 2.392517566680908, | |
| "learning_rate": 5.099349703822509e-06, | |
| "loss": 1.3303, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 27.443877551020407, | |
| "grad_norm": 2.448375940322876, | |
| "learning_rate": 5.0454570897090715e-06, | |
| "loss": 1.3321, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 27.482142857142858, | |
| "grad_norm": 2.6198055744171143, | |
| "learning_rate": 4.991818792790062e-06, | |
| "loss": 1.2673, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 27.482142857142858, | |
| "eval_en_All_acc": 0.6185089420383538, | |
| "eval_en_Env_acc": 0.971830985915493, | |
| "eval_en_Env_f1": 0.9787234042553192, | |
| "eval_en_Gov_acc": 0.9538461538461539, | |
| "eval_en_Gov_f1": 0.96875, | |
| "eval_en_Neu_acc": 0.8870967741935484, | |
| "eval_en_Neu_f1": 0.9016393442622951, | |
| "eval_en_Soc_acc": 0.9857142857142858, | |
| "eval_en_Soc_f1": 0.9517241379310346, | |
| "eval_en_cls_acc": 0.9514925373134329, | |
| "eval_en_cls_f1": 0.9502092216121621, | |
| "eval_en_loss": 2.1912152767181396, | |
| "eval_en_runtime": 5.615, | |
| "eval_en_samples_per_second": 334.281, | |
| "eval_en_steps_per_second": 3.562, | |
| "eval_en_total_cls_tokens": 268, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 27.482142857142858, | |
| "eval_en_oof_All_acc": 0.6234757713922171, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9921259842519685, | |
| "eval_en_oof_Gov_acc": 0.9433962264150944, | |
| "eval_en_oof_Gov_f1": 0.9523809523809524, | |
| "eval_en_oof_Neu_acc": 0.9571428571428572, | |
| "eval_en_oof_Neu_f1": 0.943661971830986, | |
| "eval_en_oof_Soc_acc": 0.9444444444444444, | |
| "eval_en_oof_Soc_f1": 0.9577464788732395, | |
| "eval_en_oof_cls_acc": 0.9612403100775194, | |
| "eval_en_oof_cls_f1": 0.9614788468342866, | |
| "eval_en_oof_loss": 2.142436981201172, | |
| "eval_en_oof_runtime": 5.6226, | |
| "eval_en_oof_samples_per_second": 333.834, | |
| "eval_en_oof_steps_per_second": 3.557, | |
| "eval_en_oof_total_cls_tokens": 258, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 27.482142857142858, | |
| "eval_vi_All_acc": 0.7920051249199231, | |
| "eval_vi_Env_acc": 0.9629629629629629, | |
| "eval_vi_Env_f1": 0.9541284403669724, | |
| "eval_vi_Gov_acc": 0.9426751592356688, | |
| "eval_vi_Gov_f1": 0.9337539432176656, | |
| "eval_vi_Neu_acc": 0.86875, | |
| "eval_vi_Neu_f1": 0.9025974025974026, | |
| "eval_vi_Soc_acc": 0.952054794520548, | |
| "eval_vi_Soc_f1": 0.9328859060402684, | |
| "eval_vi_cls_acc": 0.9312, | |
| "eval_vi_cls_f1": 0.9308414230555773, | |
| "eval_vi_loss": 0.9665724039077759, | |
| "eval_vi_runtime": 12.7393, | |
| "eval_vi_samples_per_second": 345.389, | |
| "eval_vi_steps_per_second": 3.611, | |
| "eval_vi_total_cls_tokens": 625, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 27.482142857142858, | |
| "eval_dan_All_acc": 0.6713049846660869, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.38461538461538464, | |
| "eval_dan_Gov_f1": 0.5555555555555556, | |
| "eval_dan_Neu_acc": 0.058823529411764705, | |
| "eval_dan_Neu_f1": 0.1111111111111111, | |
| "eval_dan_Soc_acc": 0.0, | |
| "eval_dan_Soc_f1": 0.0, | |
| "eval_dan_cls_acc": 0.13043478260869565, | |
| "eval_dan_cls_f1": 0.16666666666666669, | |
| "eval_dan_loss": 2.101635456085205, | |
| "eval_dan_runtime": 8.8463, | |
| "eval_dan_samples_per_second": 339.123, | |
| "eval_dan_steps_per_second": 3.617, | |
| "eval_dan_total_cls_tokens": 46, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 27.520408163265305, | |
| "grad_norm": 2.4921021461486816, | |
| "learning_rate": 4.938435496676272e-06, | |
| "loss": 1.2973, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 27.558673469387756, | |
| "grad_norm": 2.47627329826355, | |
| "learning_rate": 4.88530788172859e-06, | |
| "loss": 1.2737, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 27.596938775510203, | |
| "grad_norm": 2.334864854812622, | |
| "learning_rate": 4.832436625049256e-06, | |
| "loss": 1.2741, | |
| "step": 7230 | |
| }, | |
| { | |
| "epoch": 27.635204081632654, | |
| "grad_norm": 2.462935209274292, | |
| "learning_rate": 4.779822400473274e-06, | |
| "loss": 1.2755, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 27.6734693877551, | |
| "grad_norm": 2.5375137329101562, | |
| "learning_rate": 4.72746587855985e-06, | |
| "loss": 1.3223, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 27.711734693877553, | |
| "grad_norm": 2.4291882514953613, | |
| "learning_rate": 4.675367726583774e-06, | |
| "loss": 1.3148, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "grad_norm": 2.6293418407440186, | |
| "learning_rate": 4.623528608526967e-06, | |
| "loss": 1.2583, | |
| "step": 7270 | |
| }, | |
| { | |
| "epoch": 27.788265306122447, | |
| "grad_norm": 2.648192882537842, | |
| "learning_rate": 4.571949185070037e-06, | |
| "loss": 1.2683, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 27.8265306122449, | |
| "grad_norm": 2.5220329761505127, | |
| "learning_rate": 4.520630113583785e-06, | |
| "loss": 1.2519, | |
| "step": 7290 | |
| }, | |
| { | |
| "epoch": 27.864795918367346, | |
| "grad_norm": 2.427839756011963, | |
| "learning_rate": 4.469572048120893e-06, | |
| "loss": 1.2679, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 27.864795918367346, | |
| "eval_en_All_acc": 0.6306516663128847, | |
| "eval_en_Env_acc": 0.9710144927536232, | |
| "eval_en_Env_f1": 0.937062937062937, | |
| "eval_en_Gov_acc": 0.9436619718309859, | |
| "eval_en_Gov_f1": 0.9571428571428571, | |
| "eval_en_Neu_acc": 0.8717948717948718, | |
| "eval_en_Neu_f1": 0.9127516778523489, | |
| "eval_en_Soc_acc": 0.9811320754716981, | |
| "eval_en_Soc_f1": 0.9454545454545454, | |
| "eval_en_cls_acc": 0.9372693726937269, | |
| "eval_en_cls_f1": 0.9381030043781721, | |
| "eval_en_loss": 2.154367446899414, | |
| "eval_en_runtime": 5.6146, | |
| "eval_en_samples_per_second": 334.309, | |
| "eval_en_steps_per_second": 3.562, | |
| "eval_en_total_cls_tokens": 271, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 27.864795918367346, | |
| "eval_en_oof_All_acc": 0.6340348639455783, | |
| "eval_en_oof_Env_acc": 0.9859154929577465, | |
| "eval_en_oof_Env_f1": 0.9722222222222222, | |
| "eval_en_oof_Gov_acc": 0.9411764705882353, | |
| "eval_en_oof_Gov_f1": 0.9411764705882353, | |
| "eval_en_oof_Neu_acc": 0.8472222222222222, | |
| "eval_en_oof_Neu_f1": 0.8776978417266188, | |
| "eval_en_oof_Soc_acc": 0.9571428571428572, | |
| "eval_en_oof_Soc_f1": 0.9370629370629371, | |
| "eval_en_oof_cls_acc": 0.9318181818181818, | |
| "eval_en_oof_cls_f1": 0.9320398679000033, | |
| "eval_en_oof_loss": 2.097123146057129, | |
| "eval_en_oof_runtime": 5.5911, | |
| "eval_en_oof_samples_per_second": 335.714, | |
| "eval_en_oof_steps_per_second": 3.577, | |
| "eval_en_oof_total_cls_tokens": 264, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 27.864795918367346, | |
| "eval_vi_All_acc": 0.7959125745103605, | |
| "eval_vi_Env_acc": 0.9877300613496932, | |
| "eval_vi_Env_f1": 0.9611940298507463, | |
| "eval_vi_Gov_acc": 0.9316770186335404, | |
| "eval_vi_Gov_f1": 0.911854103343465, | |
| "eval_vi_Neu_acc": 0.8582089552238806, | |
| "eval_vi_Neu_f1": 0.8949416342412452, | |
| "eval_vi_Soc_acc": 0.8780487804878049, | |
| "eval_vi_Soc_f1": 0.891640866873065, | |
| "eval_vi_cls_acc": 0.9163987138263665, | |
| "eval_vi_cls_f1": 0.9149076585771303, | |
| "eval_vi_loss": 0.9270099997520447, | |
| "eval_vi_runtime": 12.7237, | |
| "eval_vi_samples_per_second": 345.812, | |
| "eval_vi_steps_per_second": 3.615, | |
| "eval_vi_total_cls_tokens": 622, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 27.864795918367346, | |
| "eval_dan_All_acc": 0.6793286219081273, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.2, | |
| "eval_dan_Neu_f1": 0.33333333333333337, | |
| "eval_dan_Soc_acc": 0.4, | |
| "eval_dan_Soc_f1": 0.5714285714285715, | |
| "eval_dan_cls_acc": 0.22857142857142856, | |
| "eval_dan_cls_f1": 0.2886904761904762, | |
| "eval_dan_loss": 2.0731167793273926, | |
| "eval_dan_runtime": 8.8189, | |
| "eval_dan_samples_per_second": 340.179, | |
| "eval_dan_steps_per_second": 3.629, | |
| "eval_dan_total_cls_tokens": 35, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 27.903061224489797, | |
| "grad_norm": 2.6378579139709473, | |
| "learning_rate": 4.41877563940758e-06, | |
| "loss": 1.2559, | |
| "step": 7310 | |
| }, | |
| { | |
| "epoch": 27.941326530612244, | |
| "grad_norm": 2.510775089263916, | |
| "learning_rate": 4.368241534835263e-06, | |
| "loss": 1.2792, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 27.979591836734695, | |
| "grad_norm": 2.5333189964294434, | |
| "learning_rate": 4.317970378452363e-06, | |
| "loss": 1.2927, | |
| "step": 7330 | |
| }, | |
| { | |
| "epoch": 28.01530612244898, | |
| "grad_norm": 2.4932398796081543, | |
| "learning_rate": 4.267962810956061e-06, | |
| "loss": 1.2227, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 28.053571428571427, | |
| "grad_norm": 2.4231104850769043, | |
| "learning_rate": 4.218219469684151e-06, | |
| "loss": 1.291, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 28.091836734693878, | |
| "grad_norm": 2.6379287242889404, | |
| "learning_rate": 4.1687409886069e-06, | |
| "loss": 1.298, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 28.130102040816325, | |
| "grad_norm": 2.578568696975708, | |
| "learning_rate": 4.1195279983189835e-06, | |
| "loss": 1.2691, | |
| "step": 7370 | |
| }, | |
| { | |
| "epoch": 28.168367346938776, | |
| "grad_norm": 2.4994733333587646, | |
| "learning_rate": 4.070581126031444e-06, | |
| "loss": 1.2303, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 28.206632653061224, | |
| "grad_norm": 2.4998550415039062, | |
| "learning_rate": 4.021900995563702e-06, | |
| "loss": 1.2732, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 28.244897959183675, | |
| "grad_norm": 2.5645833015441895, | |
| "learning_rate": 3.97348822733557e-06, | |
| "loss": 1.2914, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 28.244897959183675, | |
| "eval_en_All_acc": 0.6257101481563997, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9767441860465117, | |
| "eval_en_Gov_acc": 0.9855072463768116, | |
| "eval_en_Gov_f1": 0.9645390070921985, | |
| "eval_en_Neu_acc": 0.8857142857142857, | |
| "eval_en_Neu_f1": 0.9323308270676691, | |
| "eval_en_Soc_acc": 0.9682539682539683, | |
| "eval_en_Soc_f1": 0.9606299212598425, | |
| "eval_en_cls_acc": 0.9584905660377359, | |
| "eval_en_cls_f1": 0.9585609853665555, | |
| "eval_en_loss": 2.171574831008911, | |
| "eval_en_runtime": 5.6196, | |
| "eval_en_samples_per_second": 334.009, | |
| "eval_en_steps_per_second": 3.559, | |
| "eval_en_total_cls_tokens": 265, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 28.244897959183675, | |
| "eval_en_oof_All_acc": 0.6310785706480166, | |
| "eval_en_oof_Env_acc": 0.9571428571428572, | |
| "eval_en_oof_Env_f1": 0.9571428571428572, | |
| "eval_en_oof_Gov_acc": 0.9714285714285714, | |
| "eval_en_oof_Gov_f1": 0.9444444444444445, | |
| "eval_en_oof_Neu_acc": 0.9130434782608695, | |
| "eval_en_oof_Neu_f1": 0.9333333333333332, | |
| "eval_en_oof_Soc_acc": 0.9295774647887324, | |
| "eval_en_oof_Soc_f1": 0.9361702127659575, | |
| "eval_en_oof_cls_acc": 0.9428571428571428, | |
| "eval_en_oof_cls_f1": 0.9427727119216481, | |
| "eval_en_oof_loss": 2.1144022941589355, | |
| "eval_en_oof_runtime": 5.5967, | |
| "eval_en_oof_samples_per_second": 335.375, | |
| "eval_en_oof_steps_per_second": 3.574, | |
| "eval_en_oof_total_cls_tokens": 280, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 28.244897959183675, | |
| "eval_vi_All_acc": 0.7912371793232217, | |
| "eval_vi_Env_acc": 0.9748427672955975, | |
| "eval_vi_Env_f1": 0.9657320872274143, | |
| "eval_vi_Gov_acc": 0.9230769230769231, | |
| "eval_vi_Gov_f1": 0.9017341040462428, | |
| "eval_vi_Neu_acc": 0.8703703703703703, | |
| "eval_vi_Neu_f1": 0.8924050632911392, | |
| "eval_vi_Soc_acc": 0.8609271523178808, | |
| "eval_vi_Soc_f1": 0.8695652173913043, | |
| "eval_vi_cls_acc": 0.9079563182527302, | |
| "eval_vi_cls_f1": 0.9073591179890251, | |
| "eval_vi_loss": 0.9618557691574097, | |
| "eval_vi_runtime": 12.7337, | |
| "eval_vi_samples_per_second": 345.539, | |
| "eval_vi_steps_per_second": 3.612, | |
| "eval_vi_total_cls_tokens": 641, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 28.244897959183675, | |
| "eval_dan_All_acc": 0.6592130033518527, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3, | |
| "eval_dan_Gov_f1": 0.4615384615384615, | |
| "eval_dan_Neu_acc": 0.05263157894736842, | |
| "eval_dan_Neu_f1": 0.1, | |
| "eval_dan_Soc_acc": 0.23076923076923078, | |
| "eval_dan_Soc_f1": 0.375, | |
| "eval_dan_cls_acc": 0.16279069767441862, | |
| "eval_dan_cls_f1": 0.23413461538461536, | |
| "eval_dan_loss": 2.1843409538269043, | |
| "eval_dan_runtime": 8.8719, | |
| "eval_dan_samples_per_second": 338.147, | |
| "eval_dan_steps_per_second": 3.607, | |
| "eval_dan_total_cls_tokens": 43, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 28.283163265306122, | |
| "grad_norm": 2.3411061763763428, | |
| "learning_rate": 3.925343438359414e-06, | |
| "loss": 1.3209, | |
| "step": 7410 | |
| }, | |
| { | |
| "epoch": 28.321428571428573, | |
| "grad_norm": 2.5727453231811523, | |
| "learning_rate": 3.877467242232235e-06, | |
| "loss": 1.2812, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 28.35969387755102, | |
| "grad_norm": 2.3149499893188477, | |
| "learning_rate": 3.829860249127845e-06, | |
| "loss": 1.2754, | |
| "step": 7430 | |
| }, | |
| { | |
| "epoch": 28.397959183673468, | |
| "grad_norm": 2.471343994140625, | |
| "learning_rate": 3.782523065789148e-06, | |
| "loss": 1.3038, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 28.43622448979592, | |
| "grad_norm": 2.3125405311584473, | |
| "learning_rate": 3.735456295520348e-06, | |
| "loss": 1.2391, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 28.474489795918366, | |
| "grad_norm": 2.6449663639068604, | |
| "learning_rate": 3.6886605381792726e-06, | |
| "loss": 1.3014, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 28.512755102040817, | |
| "grad_norm": 2.5746724605560303, | |
| "learning_rate": 3.6421363901697453e-06, | |
| "loss": 1.263, | |
| "step": 7470 | |
| }, | |
| { | |
| "epoch": 28.551020408163264, | |
| "grad_norm": 2.5000760555267334, | |
| "learning_rate": 3.5958844444339943e-06, | |
| "loss": 1.2208, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 28.589285714285715, | |
| "grad_norm": 2.4362869262695312, | |
| "learning_rate": 3.549905290445041e-06, | |
| "loss": 1.2672, | |
| "step": 7490 | |
| }, | |
| { | |
| "epoch": 28.627551020408163, | |
| "grad_norm": 2.5636978149414062, | |
| "learning_rate": 3.504199514199252e-06, | |
| "loss": 1.2824, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.627551020408163, | |
| "eval_en_All_acc": 0.6297167290219134, | |
| "eval_en_Env_acc": 0.9659090909090909, | |
| "eval_en_Env_f1": 0.9770114942528736, | |
| "eval_en_Gov_acc": 0.96875, | |
| "eval_en_Gov_f1": 0.9465648854961832, | |
| "eval_en_Neu_acc": 0.9210526315789473, | |
| "eval_en_Neu_f1": 0.9032258064516129, | |
| "eval_en_Soc_acc": 0.9, | |
| "eval_en_Soc_f1": 0.9264705882352942, | |
| "eval_en_cls_acc": 0.9395973154362416, | |
| "eval_en_cls_f1": 0.938318193608991, | |
| "eval_en_loss": 2.1404080390930176, | |
| "eval_en_runtime": 5.6304, | |
| "eval_en_samples_per_second": 333.366, | |
| "eval_en_steps_per_second": 3.552, | |
| "eval_en_total_cls_tokens": 298, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.627551020408163, | |
| "eval_en_oof_All_acc": 0.6192942699902881, | |
| "eval_en_oof_Env_acc": 0.9545454545454546, | |
| "eval_en_oof_Env_f1": 0.9545454545454546, | |
| "eval_en_oof_Gov_acc": 0.9655172413793104, | |
| "eval_en_oof_Gov_f1": 0.9572649572649573, | |
| "eval_en_oof_Neu_acc": 0.9066666666666666, | |
| "eval_en_oof_Neu_f1": 0.9006622516556291, | |
| "eval_en_oof_Soc_acc": 0.9090909090909091, | |
| "eval_en_oof_Soc_f1": 0.9259259259259259, | |
| "eval_en_oof_cls_acc": 0.9330708661417323, | |
| "eval_en_oof_cls_f1": 0.9345996473479918, | |
| "eval_en_oof_loss": 2.217505931854248, | |
| "eval_en_oof_runtime": 5.5508, | |
| "eval_en_oof_samples_per_second": 338.151, | |
| "eval_en_oof_steps_per_second": 3.603, | |
| "eval_en_oof_total_cls_tokens": 254, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.627551020408163, | |
| "eval_vi_All_acc": 0.7944938387147091, | |
| "eval_vi_Env_acc": 0.974025974025974, | |
| "eval_vi_Env_f1": 0.9554140127388535, | |
| "eval_vi_Gov_acc": 0.869281045751634, | |
| "eval_vi_Gov_f1": 0.8636363636363638, | |
| "eval_vi_Neu_acc": 0.872093023255814, | |
| "eval_vi_Neu_f1": 0.8955223880597015, | |
| "eval_vi_Soc_acc": 0.8834355828220859, | |
| "eval_vi_Soc_f1": 0.8807339449541284, | |
| "eval_vi_cls_acc": 0.8987538940809969, | |
| "eval_vi_cls_f1": 0.8988266773472617, | |
| "eval_vi_loss": 0.9457010626792908, | |
| "eval_vi_runtime": 12.6248, | |
| "eval_vi_samples_per_second": 348.519, | |
| "eval_vi_steps_per_second": 3.644, | |
| "eval_vi_total_cls_tokens": 642, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.627551020408163, | |
| "eval_dan_All_acc": 0.6704973881444469, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.375, | |
| "eval_dan_Gov_f1": 0.5454545454545454, | |
| "eval_dan_Neu_acc": 0.2222222222222222, | |
| "eval_dan_Neu_f1": 0.3636363636363636, | |
| "eval_dan_Soc_acc": 0.3333333333333333, | |
| "eval_dan_Soc_f1": 0.5, | |
| "eval_dan_cls_acc": 0.2857142857142857, | |
| "eval_dan_cls_f1": 0.35227272727272724, | |
| "eval_dan_loss": 2.1326823234558105, | |
| "eval_dan_runtime": 8.9224, | |
| "eval_dan_samples_per_second": 336.232, | |
| "eval_dan_steps_per_second": 3.586, | |
| "eval_dan_total_cls_tokens": 42, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.665816326530614, | |
| "grad_norm": 2.403343677520752, | |
| "learning_rate": 3.4587676982088315e-06, | |
| "loss": 1.3069, | |
| "step": 7510 | |
| }, | |
| { | |
| "epoch": 28.70408163265306, | |
| "grad_norm": 2.5111544132232666, | |
| "learning_rate": 3.4136104214944066e-06, | |
| "loss": 1.2505, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 28.742346938775512, | |
| "grad_norm": 2.450519323348999, | |
| "learning_rate": 3.368728259577647e-06, | |
| "loss": 1.2492, | |
| "step": 7530 | |
| }, | |
| { | |
| "epoch": 28.78061224489796, | |
| "grad_norm": 2.461505889892578, | |
| "learning_rate": 3.3241217844739407e-06, | |
| "loss": 1.2778, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 28.818877551020407, | |
| "grad_norm": 2.4424996376037598, | |
| "learning_rate": 3.279791564685089e-06, | |
| "loss": 1.2782, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 28.857142857142858, | |
| "grad_norm": 2.584388017654419, | |
| "learning_rate": 3.2357381651920648e-06, | |
| "loss": 1.2665, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 28.895408163265305, | |
| "grad_norm": 2.5529541969299316, | |
| "learning_rate": 3.191962147447819e-06, | |
| "loss": 1.3077, | |
| "step": 7570 | |
| }, | |
| { | |
| "epoch": 28.933673469387756, | |
| "grad_norm": 2.643890380859375, | |
| "learning_rate": 3.148464069370119e-06, | |
| "loss": 1.3093, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 28.971938775510203, | |
| "grad_norm": 2.511105537414551, | |
| "learning_rate": 3.105244485334441e-06, | |
| "loss": 1.3097, | |
| "step": 7590 | |
| }, | |
| { | |
| "epoch": 29.007653061224488, | |
| "grad_norm": 2.5213727951049805, | |
| "learning_rate": 3.062303946166889e-06, | |
| "loss": 1.1873, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 29.007653061224488, | |
| "eval_en_All_acc": 0.611782001470125, | |
| "eval_en_Env_acc": 0.9482758620689655, | |
| "eval_en_Env_f1": 0.9649122807017544, | |
| "eval_en_Gov_acc": 0.9508196721311475, | |
| "eval_en_Gov_f1": 0.9508196721311475, | |
| "eval_en_Neu_acc": 0.9102564102564102, | |
| "eval_en_Neu_f1": 0.9161290322580644, | |
| "eval_en_Soc_acc": 0.9583333333333334, | |
| "eval_en_Soc_f1": 0.9387755102040817, | |
| "eval_en_cls_acc": 0.9405204460966543, | |
| "eval_en_cls_f1": 0.942659123823762, | |
| "eval_en_loss": 2.242567539215088, | |
| "eval_en_runtime": 5.6647, | |
| "eval_en_samples_per_second": 331.353, | |
| "eval_en_steps_per_second": 3.531, | |
| "eval_en_total_cls_tokens": 269, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 29.007653061224488, | |
| "eval_en_oof_All_acc": 0.6263403010939023, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9777777777777777, | |
| "eval_en_oof_Gov_acc": 0.9692307692307692, | |
| "eval_en_oof_Gov_f1": 0.9692307692307692, | |
| "eval_en_oof_Neu_acc": 0.9041095890410958, | |
| "eval_en_oof_Neu_f1": 0.9361702127659575, | |
| "eval_en_oof_Soc_acc": 0.9830508474576272, | |
| "eval_en_oof_Soc_f1": 0.9666666666666667, | |
| "eval_en_oof_cls_acc": 0.9619771863117871, | |
| "eval_en_oof_cls_f1": 0.9624613566102928, | |
| "eval_en_oof_loss": 2.1520252227783203, | |
| "eval_en_oof_runtime": 5.6075, | |
| "eval_en_oof_samples_per_second": 334.733, | |
| "eval_en_oof_steps_per_second": 3.567, | |
| "eval_en_oof_total_cls_tokens": 263, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 29.007653061224488, | |
| "eval_vi_All_acc": 0.7957825775412017, | |
| "eval_vi_Env_acc": 0.9736842105263158, | |
| "eval_vi_Env_f1": 0.9673202614379085, | |
| "eval_vi_Gov_acc": 0.9397590361445783, | |
| "eval_vi_Gov_f1": 0.9176470588235294, | |
| "eval_vi_Neu_acc": 0.8735632183908046, | |
| "eval_vi_Neu_f1": 0.9047619047619048, | |
| "eval_vi_Soc_acc": 0.9221556886227545, | |
| "eval_vi_Soc_f1": 0.9166666666666667, | |
| "eval_vi_cls_acc": 0.9256449165402124, | |
| "eval_vi_cls_f1": 0.9265989729225023, | |
| "eval_vi_loss": 0.9437111020088196, | |
| "eval_vi_runtime": 12.6243, | |
| "eval_vi_samples_per_second": 348.535, | |
| "eval_vi_steps_per_second": 3.644, | |
| "eval_vi_total_cls_tokens": 659, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 29.007653061224488, | |
| "eval_dan_All_acc": 0.6697268975749988, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.15384615384615385, | |
| "eval_dan_Neu_f1": 0.2666666666666667, | |
| "eval_dan_Soc_acc": 0.26666666666666666, | |
| "eval_dan_Soc_f1": 0.4210526315789474, | |
| "eval_dan_cls_acc": 0.2, | |
| "eval_dan_cls_f1": 0.23442982456140352, | |
| "eval_dan_loss": 2.09914493560791, | |
| "eval_dan_runtime": 8.93, | |
| "eval_dan_samples_per_second": 335.945, | |
| "eval_dan_steps_per_second": 3.583, | |
| "eval_dan_total_cls_tokens": 35, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 29.04591836734694, | |
| "grad_norm": 2.2843244075775146, | |
| "learning_rate": 3.0196429991372093e-06, | |
| "loss": 1.281, | |
| "step": 7610 | |
| }, | |
| { | |
| "epoch": 29.084183673469386, | |
| "grad_norm": 2.3510589599609375, | |
| "learning_rate": 2.977262187951793e-06, | |
| "loss": 1.2692, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 29.122448979591837, | |
| "grad_norm": 2.466482639312744, | |
| "learning_rate": 2.9351620527467204e-06, | |
| "loss": 1.3119, | |
| "step": 7630 | |
| }, | |
| { | |
| "epoch": 29.160714285714285, | |
| "grad_norm": 2.361607551574707, | |
| "learning_rate": 2.8933431300809415e-06, | |
| "loss": 1.2728, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 29.198979591836736, | |
| "grad_norm": 2.483651638031006, | |
| "learning_rate": 2.8518059529293844e-06, | |
| "loss": 1.2481, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 29.237244897959183, | |
| "grad_norm": 2.5592241287231445, | |
| "learning_rate": 2.810551050676166e-06, | |
| "loss": 1.2942, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 29.275510204081634, | |
| "grad_norm": 2.5464589595794678, | |
| "learning_rate": 2.769578949107893e-06, | |
| "loss": 1.2983, | |
| "step": 7670 | |
| }, | |
| { | |
| "epoch": 29.31377551020408, | |
| "grad_norm": 2.370872735977173, | |
| "learning_rate": 2.728890170406892e-06, | |
| "loss": 1.2534, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 29.352040816326532, | |
| "grad_norm": 2.526411533355713, | |
| "learning_rate": 2.6884852331446e-06, | |
| "loss": 1.2932, | |
| "step": 7690 | |
| }, | |
| { | |
| "epoch": 29.39030612244898, | |
| "grad_norm": 2.5207245349884033, | |
| "learning_rate": 2.648364652274962e-06, | |
| "loss": 1.2767, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 29.39030612244898, | |
| "eval_en_All_acc": 0.6403798954220468, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 1.0, | |
| "eval_en_Gov_acc": 0.9574468085106383, | |
| "eval_en_Gov_f1": 0.9574468085106385, | |
| "eval_en_Neu_acc": 0.9767441860465116, | |
| "eval_en_Neu_f1": 0.9767441860465116, | |
| "eval_en_Soc_acc": 0.9736842105263158, | |
| "eval_en_Soc_f1": 0.9736842105263158, | |
| "eval_en_cls_acc": 0.977859778597786, | |
| "eval_en_cls_f1": 0.9769688012708665, | |
| "eval_en_loss": 2.118499279022217, | |
| "eval_en_runtime": 5.6074, | |
| "eval_en_samples_per_second": 334.737, | |
| "eval_en_steps_per_second": 3.567, | |
| "eval_en_total_cls_tokens": 271, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 29.39030612244898, | |
| "eval_en_oof_All_acc": 0.6218131810007405, | |
| "eval_en_oof_Env_acc": 0.987012987012987, | |
| "eval_en_oof_Env_f1": 0.9743589743589742, | |
| "eval_en_oof_Gov_acc": 0.9655172413793104, | |
| "eval_en_oof_Gov_f1": 0.9739130434782608, | |
| "eval_en_oof_Neu_acc": 0.8695652173913043, | |
| "eval_en_oof_Neu_f1": 0.8695652173913043, | |
| "eval_en_oof_Soc_acc": 0.9130434782608695, | |
| "eval_en_oof_Soc_f1": 0.9197080291970804, | |
| "eval_en_oof_cls_acc": 0.9340659340659341, | |
| "eval_en_oof_cls_f1": 0.9343863161064049, | |
| "eval_en_oof_loss": 2.1867661476135254, | |
| "eval_en_oof_runtime": 5.5828, | |
| "eval_en_oof_samples_per_second": 336.214, | |
| "eval_en_oof_steps_per_second": 3.582, | |
| "eval_en_oof_total_cls_tokens": 273, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 29.39030612244898, | |
| "eval_vi_All_acc": 0.7973256627536345, | |
| "eval_vi_Env_acc": 0.9473684210526315, | |
| "eval_vi_Env_f1": 0.9381107491856677, | |
| "eval_vi_Gov_acc": 0.9205298013245033, | |
| "eval_vi_Gov_f1": 0.8881789137380192, | |
| "eval_vi_Neu_acc": 0.8833333333333333, | |
| "eval_vi_Neu_f1": 0.8932584269662921, | |
| "eval_vi_Soc_acc": 0.84375, | |
| "eval_vi_Soc_f1": 0.870967741935484, | |
| "eval_vi_cls_acc": 0.8973561430793157, | |
| "eval_vi_cls_f1": 0.8976289579563657, | |
| "eval_vi_loss": 0.9377827644348145, | |
| "eval_vi_runtime": 12.5844, | |
| "eval_vi_samples_per_second": 349.638, | |
| "eval_vi_steps_per_second": 3.655, | |
| "eval_vi_total_cls_tokens": 643, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 29.39030612244898, | |
| "eval_dan_All_acc": 0.6746196883525223, | |
| "eval_dan_Env_acc": 0.5, | |
| "eval_dan_Env_f1": 0.6666666666666666, | |
| "eval_dan_Gov_acc": 0.2857142857142857, | |
| "eval_dan_Gov_f1": 0.4444444444444445, | |
| "eval_dan_Neu_acc": 0.2222222222222222, | |
| "eval_dan_Neu_f1": 0.3636363636363636, | |
| "eval_dan_Soc_acc": 0.07692307692307693, | |
| "eval_dan_Soc_f1": 0.14285714285714288, | |
| "eval_dan_cls_acc": 0.2, | |
| "eval_dan_cls_f1": 0.4044011544011544, | |
| "eval_dan_loss": 2.1369268894195557, | |
| "eval_dan_runtime": 8.9168, | |
| "eval_dan_samples_per_second": 336.443, | |
| "eval_dan_steps_per_second": 3.589, | |
| "eval_dan_total_cls_tokens": 40, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 29.428571428571427, | |
| "grad_norm": 2.474670171737671, | |
| "learning_rate": 2.608528939127819e-06, | |
| "loss": 1.3146, | |
| "step": 7710 | |
| }, | |
| { | |
| "epoch": 29.466836734693878, | |
| "grad_norm": 2.506544828414917, | |
| "learning_rate": 2.5689786014024415e-06, | |
| "loss": 1.2761, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 29.505102040816325, | |
| "grad_norm": 2.377756357192993, | |
| "learning_rate": 2.529714143161049e-06, | |
| "loss": 1.268, | |
| "step": 7730 | |
| }, | |
| { | |
| "epoch": 29.543367346938776, | |
| "grad_norm": 2.469996452331543, | |
| "learning_rate": 2.4907360648223467e-06, | |
| "loss": 1.2712, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 29.581632653061224, | |
| "grad_norm": 2.449378490447998, | |
| "learning_rate": 2.4520448631552008e-06, | |
| "loss": 1.2664, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 29.619897959183675, | |
| "grad_norm": 2.497906446456909, | |
| "learning_rate": 2.413641031272276e-06, | |
| "loss": 1.2854, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 29.658163265306122, | |
| "grad_norm": 2.469510316848755, | |
| "learning_rate": 2.375525058623765e-06, | |
| "loss": 1.32, | |
| "step": 7770 | |
| }, | |
| { | |
| "epoch": 29.696428571428573, | |
| "grad_norm": 2.4468915462493896, | |
| "learning_rate": 2.3376974309911343e-06, | |
| "loss": 1.3012, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 29.73469387755102, | |
| "grad_norm": 2.532855987548828, | |
| "learning_rate": 2.30015863048095e-06, | |
| "loss": 1.2718, | |
| "step": 7790 | |
| }, | |
| { | |
| "epoch": 29.772959183673468, | |
| "grad_norm": 2.3264641761779785, | |
| "learning_rate": 2.262909135518726e-06, | |
| "loss": 1.2682, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 29.772959183673468, | |
| "eval_en_All_acc": 0.6234291799787007, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9767441860465117, | |
| "eval_en_Gov_acc": 1.0, | |
| "eval_en_Gov_f1": 0.967741935483871, | |
| "eval_en_Neu_acc": 0.8961038961038961, | |
| "eval_en_Neu_f1": 0.9261744966442952, | |
| "eval_en_Soc_acc": 0.9166666666666666, | |
| "eval_en_Soc_f1": 0.9295774647887323, | |
| "eval_en_cls_acc": 0.9485294117647058, | |
| "eval_en_cls_f1": 0.9500595207408525, | |
| "eval_en_loss": 2.2122418880462646, | |
| "eval_en_runtime": 5.5973, | |
| "eval_en_samples_per_second": 335.34, | |
| "eval_en_steps_per_second": 3.573, | |
| "eval_en_total_cls_tokens": 272, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 29.772959183673468, | |
| "eval_en_oof_All_acc": 0.6312957382694792, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9866666666666666, | |
| "eval_en_oof_Gov_acc": 0.96, | |
| "eval_en_oof_Gov_f1": 0.96, | |
| "eval_en_oof_Neu_acc": 0.9154929577464789, | |
| "eval_en_oof_Neu_f1": 0.9154929577464789, | |
| "eval_en_oof_Soc_acc": 0.9195402298850575, | |
| "eval_en_oof_Soc_f1": 0.9302325581395349, | |
| "eval_en_oof_cls_acc": 0.9478827361563518, | |
| "eval_en_oof_cls_f1": 0.9480980456381701, | |
| "eval_en_oof_loss": 2.114558696746826, | |
| "eval_en_oof_runtime": 5.6148, | |
| "eval_en_oof_samples_per_second": 334.294, | |
| "eval_en_oof_steps_per_second": 3.562, | |
| "eval_en_oof_total_cls_tokens": 307, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 29.772959183673468, | |
| "eval_vi_All_acc": 0.7965565616630532, | |
| "eval_vi_Env_acc": 0.9875776397515528, | |
| "eval_vi_Env_f1": 0.9754601226993865, | |
| "eval_vi_Gov_acc": 0.9151515151515152, | |
| "eval_vi_Gov_f1": 0.9014925373134329, | |
| "eval_vi_Neu_acc": 0.8670520231213873, | |
| "eval_vi_Neu_f1": 0.9036144578313252, | |
| "eval_vi_Soc_acc": 0.9064327485380117, | |
| "eval_vi_Soc_f1": 0.893371757925072, | |
| "eval_vi_cls_acc": 0.917910447761194, | |
| "eval_vi_cls_f1": 0.9184847189423042, | |
| "eval_vi_loss": 0.9523162841796875, | |
| "eval_vi_runtime": 12.7325, | |
| "eval_vi_samples_per_second": 345.574, | |
| "eval_vi_steps_per_second": 3.613, | |
| "eval_vi_total_cls_tokens": 670, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 29.772959183673468, | |
| "eval_dan_All_acc": 0.6733645288558583, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3333333333333333, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.36, | |
| "eval_dan_Neu_f1": 0.5294117647058824, | |
| "eval_dan_Soc_acc": 0.0, | |
| "eval_dan_Soc_f1": 0.0, | |
| "eval_dan_cls_acc": 0.2641509433962264, | |
| "eval_dan_cls_f1": 0.25735294117647056, | |
| "eval_dan_loss": 2.108767032623291, | |
| "eval_dan_runtime": 8.7921, | |
| "eval_dan_samples_per_second": 341.216, | |
| "eval_dan_steps_per_second": 3.64, | |
| "eval_dan_total_cls_tokens": 53, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 29.81122448979592, | |
| "grad_norm": 2.6106767654418945, | |
| "learning_rate": 2.225949420842827e-06, | |
| "loss": 1.2786, | |
| "step": 7810 | |
| }, | |
| { | |
| "epoch": 29.849489795918366, | |
| "grad_norm": 2.4067468643188477, | |
| "learning_rate": 2.189279957498416e-06, | |
| "loss": 1.2725, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 29.887755102040817, | |
| "grad_norm": 2.380922317504883, | |
| "learning_rate": 2.1529012128314542e-06, | |
| "loss": 1.3052, | |
| "step": 7830 | |
| }, | |
| { | |
| "epoch": 29.926020408163264, | |
| "grad_norm": 2.4297103881835938, | |
| "learning_rate": 2.1168136504827406e-06, | |
| "loss": 1.2338, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 29.964285714285715, | |
| "grad_norm": 2.4770681858062744, | |
| "learning_rate": 2.0810177303820176e-06, | |
| "loss": 1.2727, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 1.310848355293274, | |
| "learning_rate": 2.0455139087420807e-06, | |
| "loss": 1.1979, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 30.038265306122447, | |
| "grad_norm": 2.510467052459717, | |
| "learning_rate": 2.0103026380529964e-06, | |
| "loss": 1.2751, | |
| "step": 7870 | |
| }, | |
| { | |
| "epoch": 30.0765306122449, | |
| "grad_norm": 2.4628796577453613, | |
| "learning_rate": 1.975384367076308e-06, | |
| "loss": 1.2529, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 30.114795918367346, | |
| "grad_norm": 2.6376686096191406, | |
| "learning_rate": 1.940759540839329e-06, | |
| "loss": 1.2618, | |
| "step": 7890 | |
| }, | |
| { | |
| "epoch": 30.153061224489797, | |
| "grad_norm": 2.4633774757385254, | |
| "learning_rate": 1.9064286006294868e-06, | |
| "loss": 1.2801, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 30.153061224489797, | |
| "eval_en_All_acc": 0.6293014630125695, | |
| "eval_en_Env_acc": 0.9565217391304348, | |
| "eval_en_Env_f1": 0.9705882352941176, | |
| "eval_en_Gov_acc": 0.9459459459459459, | |
| "eval_en_Gov_f1": 0.9395973154362416, | |
| "eval_en_Neu_acc": 0.8809523809523809, | |
| "eval_en_Neu_f1": 0.8915662650602411, | |
| "eval_en_Soc_acc": 0.9577464788732394, | |
| "eval_en_Soc_f1": 0.9379310344827587, | |
| "eval_en_cls_acc": 0.9328859060402684, | |
| "eval_en_cls_f1": 0.9349207125683398, | |
| "eval_en_loss": 2.1491875648498535, | |
| "eval_en_runtime": 5.6311, | |
| "eval_en_samples_per_second": 333.329, | |
| "eval_en_steps_per_second": 3.552, | |
| "eval_en_total_cls_tokens": 298, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 30.153061224489797, | |
| "eval_en_oof_All_acc": 0.62, | |
| "eval_en_oof_Env_acc": 0.9852941176470589, | |
| "eval_en_oof_Env_f1": 0.9781021897810219, | |
| "eval_en_oof_Gov_acc": 0.9577464788732394, | |
| "eval_en_oof_Gov_f1": 0.951048951048951, | |
| "eval_en_oof_Neu_acc": 0.8333333333333334, | |
| "eval_en_oof_Neu_f1": 0.8823529411764706, | |
| "eval_en_oof_Soc_acc": 0.984375, | |
| "eval_en_oof_Soc_f1": 0.9402985074626866, | |
| "eval_en_oof_cls_acc": 0.9381818181818182, | |
| "eval_en_oof_cls_f1": 0.9379506473672826, | |
| "eval_en_oof_loss": 2.2039403915405273, | |
| "eval_en_oof_runtime": 5.6022, | |
| "eval_en_oof_samples_per_second": 335.047, | |
| "eval_en_oof_steps_per_second": 3.57, | |
| "eval_en_oof_total_cls_tokens": 275, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 30.153061224489797, | |
| "eval_vi_All_acc": 0.8032383321066924, | |
| "eval_vi_Env_acc": 0.9497206703910615, | |
| "eval_vi_Env_f1": 0.9604519774011299, | |
| "eval_vi_Gov_acc": 0.8947368421052632, | |
| "eval_vi_Gov_f1": 0.8793103448275862, | |
| "eval_vi_Neu_acc": 0.93125, | |
| "eval_vi_Neu_f1": 0.916923076923077, | |
| "eval_vi_Soc_acc": 0.8682634730538922, | |
| "eval_vi_Soc_f1": 0.8868501529051986, | |
| "eval_vi_cls_acc": 0.9113737075332349, | |
| "eval_vi_cls_f1": 0.9108838880142479, | |
| "eval_vi_loss": 0.9112982749938965, | |
| "eval_vi_runtime": 12.7478, | |
| "eval_vi_samples_per_second": 345.157, | |
| "eval_vi_steps_per_second": 3.608, | |
| "eval_vi_total_cls_tokens": 677, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 30.153061224489797, | |
| "eval_dan_All_acc": 0.6703338034790786, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.125, | |
| "eval_dan_Gov_f1": 0.2222222222222222, | |
| "eval_dan_Neu_acc": 0.125, | |
| "eval_dan_Neu_f1": 0.2222222222222222, | |
| "eval_dan_Soc_acc": 0.23076923076923078, | |
| "eval_dan_Soc_f1": 0.375, | |
| "eval_dan_cls_acc": 0.15789473684210525, | |
| "eval_dan_cls_f1": 0.2048611111111111, | |
| "eval_dan_loss": 2.0973074436187744, | |
| "eval_dan_runtime": 8.7747, | |
| "eval_dan_samples_per_second": 341.891, | |
| "eval_dan_steps_per_second": 3.647, | |
| "eval_dan_total_cls_tokens": 38, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 30.191326530612244, | |
| "grad_norm": 2.3728504180908203, | |
| "learning_rate": 1.8723919839886612e-06, | |
| "loss": 1.2398, | |
| "step": 7910 | |
| }, | |
| { | |
| "epoch": 30.229591836734695, | |
| "grad_norm": 2.570805311203003, | |
| "learning_rate": 1.8386501247076388e-06, | |
| "loss": 1.2645, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 30.267857142857142, | |
| "grad_norm": 2.34983229637146, | |
| "learning_rate": 1.8052034528205809e-06, | |
| "loss": 1.2479, | |
| "step": 7930 | |
| }, | |
| { | |
| "epoch": 30.306122448979593, | |
| "grad_norm": 2.3267157077789307, | |
| "learning_rate": 1.7720523945995215e-06, | |
| "loss": 1.2396, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 30.34438775510204, | |
| "grad_norm": 2.3945624828338623, | |
| "learning_rate": 1.7391973725489618e-06, | |
| "loss": 1.2321, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 30.382653061224488, | |
| "grad_norm": 2.529897928237915, | |
| "learning_rate": 1.7066388054004706e-06, | |
| "loss": 1.2215, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 30.42091836734694, | |
| "grad_norm": 2.406202793121338, | |
| "learning_rate": 1.6743771081073445e-06, | |
| "loss": 1.2817, | |
| "step": 7970 | |
| }, | |
| { | |
| "epoch": 30.459183673469386, | |
| "grad_norm": 2.316244125366211, | |
| "learning_rate": 1.6424126918393319e-06, | |
| "loss": 1.2382, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 30.497448979591837, | |
| "grad_norm": 2.4983139038085938, | |
| "learning_rate": 1.6107459639773835e-06, | |
| "loss": 1.2577, | |
| "step": 7990 | |
| }, | |
| { | |
| "epoch": 30.535714285714285, | |
| "grad_norm": 2.334211587905884, | |
| "learning_rate": 1.579377328108464e-06, | |
| "loss": 1.2628, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.535714285714285, | |
| "eval_en_All_acc": 0.629805615550756, | |
| "eval_en_Env_acc": 0.9726027397260274, | |
| "eval_en_Env_f1": 0.9726027397260274, | |
| "eval_en_Gov_acc": 0.9538461538461539, | |
| "eval_en_Gov_f1": 0.9538461538461539, | |
| "eval_en_Neu_acc": 0.8985507246376812, | |
| "eval_en_Neu_f1": 0.8920863309352518, | |
| "eval_en_Soc_acc": 0.918918918918919, | |
| "eval_en_Soc_f1": 0.9251700680272108, | |
| "eval_en_cls_acc": 0.9359430604982206, | |
| "eval_en_cls_f1": 0.935926323133661, | |
| "eval_en_loss": 2.137005090713501, | |
| "eval_en_runtime": 5.6436, | |
| "eval_en_samples_per_second": 332.589, | |
| "eval_en_steps_per_second": 3.544, | |
| "eval_en_total_cls_tokens": 281, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.535714285714285, | |
| "eval_en_oof_All_acc": 0.6296657986111112, | |
| "eval_en_oof_Env_acc": 0.9864864864864865, | |
| "eval_en_oof_Env_f1": 0.9864864864864865, | |
| "eval_en_oof_Gov_acc": 1.0, | |
| "eval_en_oof_Gov_f1": 1.0, | |
| "eval_en_oof_Neu_acc": 0.9714285714285714, | |
| "eval_en_oof_Neu_f1": 0.9784172661870504, | |
| "eval_en_oof_Soc_acc": 0.9821428571428571, | |
| "eval_en_oof_Soc_f1": 0.9734513274336283, | |
| "eval_en_oof_cls_acc": 0.9851301115241635, | |
| "eval_en_oof_cls_f1": 0.9845887700267913, | |
| "eval_en_oof_loss": 2.149400234222412, | |
| "eval_en_oof_runtime": 5.5949, | |
| "eval_en_oof_samples_per_second": 335.487, | |
| "eval_en_oof_steps_per_second": 3.575, | |
| "eval_en_oof_total_cls_tokens": 269, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.535714285714285, | |
| "eval_vi_All_acc": 0.7912360585285992, | |
| "eval_vi_Env_acc": 0.9709302325581395, | |
| "eval_vi_Env_f1": 0.9653179190751445, | |
| "eval_vi_Gov_acc": 0.907103825136612, | |
| "eval_vi_Gov_f1": 0.9095890410958904, | |
| "eval_vi_Neu_acc": 0.9112426035502958, | |
| "eval_vi_Neu_f1": 0.9361702127659575, | |
| "eval_vi_Soc_acc": 0.9144736842105263, | |
| "eval_vi_Soc_f1": 0.891025641025641, | |
| "eval_vi_cls_acc": 0.9260355029585798, | |
| "eval_vi_cls_f1": 0.9255257034906583, | |
| "eval_vi_loss": 0.9600545167922974, | |
| "eval_vi_runtime": 12.4404, | |
| "eval_vi_samples_per_second": 353.686, | |
| "eval_vi_steps_per_second": 3.698, | |
| "eval_vi_total_cls_tokens": 676, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.535714285714285, | |
| "eval_dan_All_acc": 0.676572607106028, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.36363636363636365, | |
| "eval_dan_Neu_f1": 0.5333333333333333, | |
| "eval_dan_Soc_acc": 0.1111111111111111, | |
| "eval_dan_Soc_f1": 0.19999999999999998, | |
| "eval_dan_cls_acc": 0.22916666666666666, | |
| "eval_dan_cls_f1": 0.24583333333333332, | |
| "eval_dan_loss": 2.0809309482574463, | |
| "eval_dan_runtime": 8.8366, | |
| "eval_dan_samples_per_second": 339.498, | |
| "eval_dan_steps_per_second": 3.621, | |
| "eval_dan_total_cls_tokens": 48, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.573979591836736, | |
| "grad_norm": 2.526324510574341, | |
| "learning_rate": 1.5483071840204062e-06, | |
| "loss": 1.2719, | |
| "step": 8010 | |
| }, | |
| { | |
| "epoch": 30.612244897959183, | |
| "grad_norm": 2.4830422401428223, | |
| "learning_rate": 1.5175359276968143e-06, | |
| "loss": 1.2884, | |
| "step": 8020 | |
| }, | |
| { | |
| "epoch": 30.650510204081634, | |
| "grad_norm": 2.5661821365356445, | |
| "learning_rate": 1.4870639513120288e-06, | |
| "loss": 1.3504, | |
| "step": 8030 | |
| }, | |
| { | |
| "epoch": 30.68877551020408, | |
| "grad_norm": 2.5559298992156982, | |
| "learning_rate": 1.4568916432261077e-06, | |
| "loss": 1.2969, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 30.727040816326532, | |
| "grad_norm": 2.6008408069610596, | |
| "learning_rate": 1.4270193879798888e-06, | |
| "loss": 1.2987, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 30.76530612244898, | |
| "grad_norm": 2.587313652038574, | |
| "learning_rate": 1.3974475662901026e-06, | |
| "loss": 1.2704, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 30.803571428571427, | |
| "grad_norm": 2.5685036182403564, | |
| "learning_rate": 1.3681765550444953e-06, | |
| "loss": 1.267, | |
| "step": 8070 | |
| }, | |
| { | |
| "epoch": 30.841836734693878, | |
| "grad_norm": 2.8258001804351807, | |
| "learning_rate": 1.3392067272970294e-06, | |
| "loss": 1.271, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 30.880102040816325, | |
| "grad_norm": 2.597419261932373, | |
| "learning_rate": 1.3105384522631491e-06, | |
| "loss": 1.2586, | |
| "step": 8090 | |
| }, | |
| { | |
| "epoch": 30.918367346938776, | |
| "grad_norm": 2.696305990219116, | |
| "learning_rate": 1.2821720953150595e-06, | |
| "loss": 1.2678, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 30.918367346938776, | |
| "eval_en_All_acc": 0.6340069833880013, | |
| "eval_en_Env_acc": 0.9696969696969697, | |
| "eval_en_Env_f1": 0.9696969696969697, | |
| "eval_en_Gov_acc": 0.9365079365079365, | |
| "eval_en_Gov_f1": 0.9365079365079365, | |
| "eval_en_Neu_acc": 0.9393939393939394, | |
| "eval_en_Neu_f1": 0.9117647058823529, | |
| "eval_en_Soc_acc": 0.925, | |
| "eval_en_Soc_f1": 0.9487179487179489, | |
| "eval_en_cls_acc": 0.9418181818181818, | |
| "eval_en_cls_f1": 0.941671890201302, | |
| "eval_en_loss": 2.0861620903015137, | |
| "eval_en_runtime": 5.6304, | |
| "eval_en_samples_per_second": 333.368, | |
| "eval_en_steps_per_second": 3.552, | |
| "eval_en_total_cls_tokens": 275, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 30.918367346938776, | |
| "eval_en_oof_All_acc": 0.6355968396327141, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 0.9801324503311257, | |
| "eval_en_oof_Gov_acc": 0.9705882352941176, | |
| "eval_en_oof_Gov_f1": 0.9777777777777777, | |
| "eval_en_oof_Neu_acc": 0.9176470588235294, | |
| "eval_en_oof_Neu_f1": 0.9341317365269461, | |
| "eval_en_oof_Soc_acc": 0.9571428571428572, | |
| "eval_en_oof_Soc_f1": 0.9503546099290779, | |
| "eval_en_oof_cls_acc": 0.9595959595959596, | |
| "eval_en_oof_cls_f1": 0.960599143641232, | |
| "eval_en_oof_loss": 2.1250226497650146, | |
| "eval_en_oof_runtime": 5.606, | |
| "eval_en_oof_samples_per_second": 334.817, | |
| "eval_en_oof_steps_per_second": 3.568, | |
| "eval_en_oof_total_cls_tokens": 297, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 30.918367346938776, | |
| "eval_vi_All_acc": 0.8003563701158203, | |
| "eval_vi_Env_acc": 0.9625, | |
| "eval_vi_Env_f1": 0.9625000000000001, | |
| "eval_vi_Gov_acc": 0.9375, | |
| "eval_vi_Gov_f1": 0.9090909090909091, | |
| "eval_vi_Neu_acc": 0.8541666666666666, | |
| "eval_vi_Neu_f1": 0.9044117647058825, | |
| "eval_vi_Soc_acc": 0.9259259259259259, | |
| "eval_vi_Soc_f1": 0.9090909090909091, | |
| "eval_vi_cls_acc": 0.9217252396166135, | |
| "eval_vi_cls_f1": 0.9212733957219252, | |
| "eval_vi_loss": 0.9167415499687195, | |
| "eval_vi_runtime": 12.7593, | |
| "eval_vi_samples_per_second": 344.846, | |
| "eval_vi_steps_per_second": 3.605, | |
| "eval_vi_total_cls_tokens": 626, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 30.918367346938776, | |
| "eval_dan_All_acc": 0.67104769057454, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.1111111111111111, | |
| "eval_dan_Gov_f1": 0.19999999999999998, | |
| "eval_dan_Neu_acc": 0.12, | |
| "eval_dan_Neu_f1": 0.21428571428571425, | |
| "eval_dan_Soc_acc": 0.21428571428571427, | |
| "eval_dan_Soc_f1": 0.35294117647058826, | |
| "eval_dan_cls_acc": 0.14, | |
| "eval_dan_cls_f1": 0.19180672268907561, | |
| "eval_dan_loss": 2.143995523452759, | |
| "eval_dan_runtime": 8.9341, | |
| "eval_dan_samples_per_second": 335.79, | |
| "eval_dan_steps_per_second": 3.582, | |
| "eval_dan_total_cls_tokens": 50, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 30.956632653061224, | |
| "grad_norm": 2.4832851886749268, | |
| "learning_rate": 1.2541080179770571e-06, | |
| "loss": 1.2791, | |
| "step": 8110 | |
| }, | |
| { | |
| "epoch": 30.994897959183675, | |
| "grad_norm": 2.575352668762207, | |
| "learning_rate": 1.2263465779209614e-06, | |
| "loss": 1.2975, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 31.03061224489796, | |
| "grad_norm": 2.4843716621398926, | |
| "learning_rate": 1.1988881289615145e-06, | |
| "loss": 1.2171, | |
| "step": 8130 | |
| }, | |
| { | |
| "epoch": 31.068877551020407, | |
| "grad_norm": 2.3828845024108887, | |
| "learning_rate": 1.1717330210518907e-06, | |
| "loss": 1.2773, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 31.107142857142858, | |
| "grad_norm": 2.4311370849609375, | |
| "learning_rate": 1.1448816002792435e-06, | |
| "loss": 1.2529, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 31.145408163265305, | |
| "grad_norm": 2.4948267936706543, | |
| "learning_rate": 1.1183342088602777e-06, | |
| "loss": 1.2838, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 31.183673469387756, | |
| "grad_norm": 2.548651933670044, | |
| "learning_rate": 1.0920911851369008e-06, | |
| "loss": 1.2744, | |
| "step": 8170 | |
| }, | |
| { | |
| "epoch": 31.221938775510203, | |
| "grad_norm": 2.4653067588806152, | |
| "learning_rate": 1.0661528635719093e-06, | |
| "loss": 1.273, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 31.260204081632654, | |
| "grad_norm": 2.512326955795288, | |
| "learning_rate": 1.0405195747447165e-06, | |
| "loss": 1.254, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 31.2984693877551, | |
| "grad_norm": 2.4684841632843018, | |
| "learning_rate": 1.0151916453471549e-06, | |
| "loss": 1.2751, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 31.2984693877551, | |
| "eval_en_All_acc": 0.6255273120605733, | |
| "eval_en_Env_acc": 0.9726027397260274, | |
| "eval_en_Env_f1": 0.9530201342281879, | |
| "eval_en_Gov_acc": 0.984375, | |
| "eval_en_Gov_f1": 0.9767441860465116, | |
| "eval_en_Neu_acc": 0.8533333333333334, | |
| "eval_en_Neu_f1": 0.8827586206896552, | |
| "eval_en_Soc_acc": 0.9090909090909091, | |
| "eval_en_Soc_f1": 0.9022556390977443, | |
| "eval_en_cls_acc": 0.9280575539568345, | |
| "eval_en_cls_f1": 0.9286946450155247, | |
| "eval_en_loss": 2.175037145614624, | |
| "eval_en_runtime": 5.6362, | |
| "eval_en_samples_per_second": 333.026, | |
| "eval_en_steps_per_second": 3.548, | |
| "eval_en_total_cls_tokens": 278, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 31.2984693877551, | |
| "eval_en_oof_All_acc": 0.6191598799828547, | |
| "eval_en_oof_Env_acc": 0.984375, | |
| "eval_en_oof_Env_f1": 0.9692307692307692, | |
| "eval_en_oof_Gov_acc": 0.9846153846153847, | |
| "eval_en_oof_Gov_f1": 0.9696969696969696, | |
| "eval_en_oof_Neu_acc": 0.8421052631578947, | |
| "eval_en_oof_Neu_f1": 0.8888888888888888, | |
| "eval_en_oof_Soc_acc": 0.9733333333333334, | |
| "eval_en_oof_Soc_f1": 0.948051948051948, | |
| "eval_en_oof_cls_acc": 0.9428571428571428, | |
| "eval_en_oof_cls_f1": 0.943967143967144, | |
| "eval_en_oof_loss": 2.1790900230407715, | |
| "eval_en_oof_runtime": 5.6128, | |
| "eval_en_oof_samples_per_second": 334.413, | |
| "eval_en_oof_steps_per_second": 3.563, | |
| "eval_en_oof_total_cls_tokens": 280, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 31.2984693877551, | |
| "eval_vi_All_acc": 0.7877034913484181, | |
| "eval_vi_Env_acc": 0.9662921348314607, | |
| "eval_vi_Env_f1": 0.9555555555555557, | |
| "eval_vi_Gov_acc": 0.8947368421052632, | |
| "eval_vi_Gov_f1": 0.8973607038123168, | |
| "eval_vi_Neu_acc": 0.8786127167630058, | |
| "eval_vi_Neu_f1": 0.9074626865671642, | |
| "eval_vi_Soc_acc": 0.9101796407185628, | |
| "eval_vi_Soc_f1": 0.888888888888889, | |
| "eval_vi_cls_acc": 0.9129172714078374, | |
| "eval_vi_cls_f1": 0.9123169587059814, | |
| "eval_vi_loss": 0.9763551950454712, | |
| "eval_vi_runtime": 12.787, | |
| "eval_vi_samples_per_second": 344.1, | |
| "eval_vi_steps_per_second": 3.597, | |
| "eval_vi_total_cls_tokens": 689, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 31.2984693877551, | |
| "eval_dan_All_acc": 0.6713041875892569, | |
| "eval_dan_Env_acc": 0.2, | |
| "eval_dan_Env_f1": 0.33333333333333337, | |
| "eval_dan_Gov_acc": 0.2, | |
| "eval_dan_Gov_f1": 0.33333333333333337, | |
| "eval_dan_Neu_acc": 0.09523809523809523, | |
| "eval_dan_Neu_f1": 0.17391304347826084, | |
| "eval_dan_Soc_acc": 0.3333333333333333, | |
| "eval_dan_Soc_f1": 0.5, | |
| "eval_dan_cls_acc": 0.1956521739130435, | |
| "eval_dan_cls_f1": 0.3351449275362319, | |
| "eval_dan_loss": 2.1237359046936035, | |
| "eval_dan_runtime": 8.868, | |
| "eval_dan_samples_per_second": 338.295, | |
| "eval_dan_steps_per_second": 3.608, | |
| "eval_dan_total_cls_tokens": 46, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 31.336734693877553, | |
| "grad_norm": 2.441315174102783, | |
| "learning_rate": 9.90169398179297e-07, | |
| "loss": 1.2801, | |
| "step": 8210 | |
| }, | |
| { | |
| "epoch": 31.375, | |
| "grad_norm": 2.475977897644043, | |
| "learning_rate": 9.654531521453513e-07, | |
| "loss": 1.2775, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 31.413265306122447, | |
| "grad_norm": 2.447601318359375, | |
| "learning_rate": 9.410432222495907e-07, | |
| "loss": 1.274, | |
| "step": 8230 | |
| }, | |
| { | |
| "epoch": 31.4515306122449, | |
| "grad_norm": 2.3988211154937744, | |
| "learning_rate": 9.169399195923523e-07, | |
| "loss": 1.2586, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 31.489795918367346, | |
| "grad_norm": 2.4692394733428955, | |
| "learning_rate": 8.931435513660463e-07, | |
| "loss": 1.2836, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 31.528061224489797, | |
| "grad_norm": 2.324320077896118, | |
| "learning_rate": 8.696544208512736e-07, | |
| "loss": 1.2432, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 31.566326530612244, | |
| "grad_norm": 2.583097219467163, | |
| "learning_rate": 8.464728274129308e-07, | |
| "loss": 1.2781, | |
| "step": 8270 | |
| }, | |
| { | |
| "epoch": 31.604591836734695, | |
| "grad_norm": 2.3600587844848633, | |
| "learning_rate": 8.235990664964166e-07, | |
| "loss": 1.2713, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 31.642857142857142, | |
| "grad_norm": 2.420513153076172, | |
| "learning_rate": 8.010334296238486e-07, | |
| "loss": 1.2321, | |
| "step": 8290 | |
| }, | |
| { | |
| "epoch": 31.681122448979593, | |
| "grad_norm": 2.4783313274383545, | |
| "learning_rate": 7.787762043903663e-07, | |
| "loss": 1.254, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 31.681122448979593, | |
| "eval_en_All_acc": 0.6177000529941706, | |
| "eval_en_Env_acc": 0.9830508474576272, | |
| "eval_en_Env_f1": 0.9586776859504132, | |
| "eval_en_Gov_acc": 0.9846153846153847, | |
| "eval_en_Gov_f1": 0.9770992366412214, | |
| "eval_en_Neu_acc": 0.8787878787878788, | |
| "eval_en_Neu_f1": 0.9133858267716536, | |
| "eval_en_Soc_acc": 0.96, | |
| "eval_en_Soc_f1": 0.9536423841059603, | |
| "eval_en_cls_acc": 0.9509433962264151, | |
| "eval_en_cls_f1": 0.9507012833673121, | |
| "eval_en_loss": 2.211453676223755, | |
| "eval_en_runtime": 5.6301, | |
| "eval_en_samples_per_second": 333.389, | |
| "eval_en_steps_per_second": 3.552, | |
| "eval_en_total_cls_tokens": 265, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 31.681122448979593, | |
| "eval_en_oof_All_acc": 0.6252644942869234, | |
| "eval_en_oof_Env_acc": 0.9310344827586207, | |
| "eval_en_oof_Env_f1": 0.9473684210526316, | |
| "eval_en_oof_Gov_acc": 0.9622641509433962, | |
| "eval_en_oof_Gov_f1": 0.9622641509433962, | |
| "eval_en_oof_Neu_acc": 0.9305555555555556, | |
| "eval_en_oof_Neu_f1": 0.9115646258503401, | |
| "eval_en_oof_Soc_acc": 0.9137931034482759, | |
| "eval_en_oof_Soc_f1": 0.9217391304347825, | |
| "eval_en_oof_cls_acc": 0.9336099585062241, | |
| "eval_en_oof_cls_f1": 0.9357340820702876, | |
| "eval_en_oof_loss": 2.175685405731201, | |
| "eval_en_oof_runtime": 5.6087, | |
| "eval_en_oof_samples_per_second": 334.657, | |
| "eval_en_oof_steps_per_second": 3.566, | |
| "eval_en_oof_total_cls_tokens": 241, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 31.681122448979593, | |
| "eval_vi_All_acc": 0.7942075912933981, | |
| "eval_vi_Env_acc": 0.9815950920245399, | |
| "eval_vi_Env_f1": 0.9667673716012085, | |
| "eval_vi_Gov_acc": 0.9251700680272109, | |
| "eval_vi_Gov_f1": 0.9220338983050848, | |
| "eval_vi_Neu_acc": 0.8848484848484849, | |
| "eval_vi_Neu_f1": 0.9125000000000001, | |
| "eval_vi_Soc_acc": 0.9210526315789473, | |
| "eval_vi_Soc_f1": 0.9090909090909091, | |
| "eval_vi_cls_acc": 0.9282296650717703, | |
| "eval_vi_cls_f1": 0.9275980447493006, | |
| "eval_vi_loss": 0.9519798159599304, | |
| "eval_vi_runtime": 12.7362, | |
| "eval_vi_samples_per_second": 345.473, | |
| "eval_vi_steps_per_second": 3.612, | |
| "eval_vi_total_cls_tokens": 627, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 31.681122448979593, | |
| "eval_dan_All_acc": 0.6790203929602384, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.3333333333333333, | |
| "eval_dan_Gov_f1": 0.5, | |
| "eval_dan_Neu_acc": 0.38461538461538464, | |
| "eval_dan_Neu_f1": 0.5555555555555556, | |
| "eval_dan_Soc_acc": 0.3333333333333333, | |
| "eval_dan_Soc_f1": 0.5, | |
| "eval_dan_cls_acc": 0.325, | |
| "eval_dan_cls_f1": 0.3888888888888889, | |
| "eval_dan_loss": 2.0610902309417725, | |
| "eval_dan_runtime": 8.8091, | |
| "eval_dan_samples_per_second": 340.555, | |
| "eval_dan_steps_per_second": 3.633, | |
| "eval_dan_total_cls_tokens": 40, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 31.71938775510204, | |
| "grad_norm": 2.4102530479431152, | |
| "learning_rate": 7.568276744604447e-07, | |
| "loss": 1.2695, | |
| "step": 8310 | |
| }, | |
| { | |
| "epoch": 31.757653061224488, | |
| "grad_norm": 2.534743547439575, | |
| "learning_rate": 7.35188119564309e-07, | |
| "loss": 1.2762, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 31.79591836734694, | |
| "grad_norm": 2.5279111862182617, | |
| "learning_rate": 7.138578154943288e-07, | |
| "loss": 1.2797, | |
| "step": 8330 | |
| }, | |
| { | |
| "epoch": 31.834183673469386, | |
| "grad_norm": 2.3807835578918457, | |
| "learning_rate": 6.928370341015373e-07, | |
| "loss": 1.3211, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 31.872448979591837, | |
| "grad_norm": 2.6007769107818604, | |
| "learning_rate": 6.721260432921622e-07, | |
| "loss": 1.2899, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 31.910714285714285, | |
| "grad_norm": 2.585308074951172, | |
| "learning_rate": 6.517251070241897e-07, | |
| "loss": 1.2833, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 31.948979591836736, | |
| "grad_norm": 2.378922939300537, | |
| "learning_rate": 6.316344853040168e-07, | |
| "loss": 1.2488, | |
| "step": 8370 | |
| }, | |
| { | |
| "epoch": 31.987244897959183, | |
| "grad_norm": 2.3598275184631348, | |
| "learning_rate": 6.118544341831456e-07, | |
| "loss": 1.3106, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 32.02295918367347, | |
| "grad_norm": 2.344395160675049, | |
| "learning_rate": 5.923852057549001e-07, | |
| "loss": 1.1974, | |
| "step": 8390 | |
| }, | |
| { | |
| "epoch": 32.06122448979592, | |
| "grad_norm": 2.2377734184265137, | |
| "learning_rate": 5.732270481512231e-07, | |
| "loss": 1.2556, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 32.06122448979592, | |
| "eval_en_All_acc": 0.6255779739386297, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.993006993006993, | |
| "eval_en_Gov_acc": 0.9692307692307692, | |
| "eval_en_Gov_f1": 0.9618320610687022, | |
| "eval_en_Neu_acc": 0.8656716417910447, | |
| "eval_en_Neu_f1": 0.8923076923076922, | |
| "eval_en_Soc_acc": 0.9393939393939394, | |
| "eval_en_Soc_f1": 0.9253731343283583, | |
| "eval_en_cls_acc": 0.9442379182156134, | |
| "eval_en_cls_f1": 0.9431299701779364, | |
| "eval_en_loss": 2.194854974746704, | |
| "eval_en_runtime": 5.6914, | |
| "eval_en_samples_per_second": 329.795, | |
| "eval_en_steps_per_second": 3.514, | |
| "eval_en_total_cls_tokens": 269, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 32.06122448979592, | |
| "eval_en_oof_All_acc": 0.6263982102908278, | |
| "eval_en_oof_Env_acc": 0.9875, | |
| "eval_en_oof_Env_f1": 0.9693251533742331, | |
| "eval_en_oof_Gov_acc": 1.0, | |
| "eval_en_oof_Gov_f1": 0.967741935483871, | |
| "eval_en_oof_Neu_acc": 0.8690476190476191, | |
| "eval_en_oof_Neu_f1": 0.9125000000000001, | |
| "eval_en_oof_Soc_acc": 0.9466666666666667, | |
| "eval_en_oof_Soc_f1": 0.9403973509933775, | |
| "eval_en_oof_cls_acc": 0.9464882943143813, | |
| "eval_en_oof_cls_f1": 0.9474911099628704, | |
| "eval_en_oof_loss": 2.1688730716705322, | |
| "eval_en_oof_runtime": 5.6025, | |
| "eval_en_oof_samples_per_second": 335.031, | |
| "eval_en_oof_steps_per_second": 3.57, | |
| "eval_en_oof_total_cls_tokens": 299, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 32.06122448979592, | |
| "eval_vi_All_acc": 0.7945459223051197, | |
| "eval_vi_Env_acc": 0.9738562091503268, | |
| "eval_vi_Env_f1": 0.964401294498382, | |
| "eval_vi_Gov_acc": 0.9071428571428571, | |
| "eval_vi_Gov_f1": 0.8850174216027874, | |
| "eval_vi_Neu_acc": 0.90625, | |
| "eval_vi_Neu_f1": 0.9206349206349206, | |
| "eval_vi_Soc_acc": 0.88, | |
| "eval_vi_Soc_f1": 0.8949152542372882, | |
| "eval_vi_cls_acc": 0.9170812603648425, | |
| "eval_vi_cls_f1": 0.9162422227433445, | |
| "eval_vi_loss": 0.9646561145782471, | |
| "eval_vi_runtime": 12.7279, | |
| "eval_vi_samples_per_second": 345.698, | |
| "eval_vi_steps_per_second": 3.614, | |
| "eval_vi_total_cls_tokens": 603, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 32.06122448979592, | |
| "eval_dan_All_acc": 0.6748124626075751, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.2222222222222222, | |
| "eval_dan_Neu_f1": 0.3636363636363636, | |
| "eval_dan_Soc_acc": 0.14285714285714285, | |
| "eval_dan_Soc_f1": 0.25, | |
| "eval_dan_cls_acc": 0.175, | |
| "eval_dan_cls_f1": 0.21590909090909088, | |
| "eval_dan_loss": 2.095426082611084, | |
| "eval_dan_runtime": 8.9314, | |
| "eval_dan_samples_per_second": 335.894, | |
| "eval_dan_steps_per_second": 3.583, | |
| "eval_dan_total_cls_tokens": 40, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 32.099489795918366, | |
| "grad_norm": 2.5343384742736816, | |
| "learning_rate": 5.543802055395203e-07, | |
| "loss": 1.2975, | |
| "step": 8410 | |
| }, | |
| { | |
| "epoch": 32.13775510204081, | |
| "grad_norm": 2.531794786453247, | |
| "learning_rate": 5.35844918119538e-07, | |
| "loss": 1.2916, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 32.17602040816327, | |
| "grad_norm": 2.5304081439971924, | |
| "learning_rate": 5.176214221202985e-07, | |
| "loss": 1.2579, | |
| "step": 8430 | |
| }, | |
| { | |
| "epoch": 32.214285714285715, | |
| "grad_norm": 2.4716649055480957, | |
| "learning_rate": 4.997099497971114e-07, | |
| "loss": 1.2781, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 32.25255102040816, | |
| "grad_norm": 2.543600559234619, | |
| "learning_rate": 4.821107294285837e-07, | |
| "loss": 1.2849, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 32.29081632653061, | |
| "grad_norm": 2.337658643722534, | |
| "learning_rate": 4.648239853137365e-07, | |
| "loss": 1.2227, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 32.329081632653065, | |
| "grad_norm": 2.41782808303833, | |
| "learning_rate": 4.478499377691292e-07, | |
| "loss": 1.2795, | |
| "step": 8470 | |
| }, | |
| { | |
| "epoch": 32.36734693877551, | |
| "grad_norm": 2.509282350540161, | |
| "learning_rate": 4.311888031260564e-07, | |
| "loss": 1.3193, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 32.40561224489796, | |
| "grad_norm": 2.4268441200256348, | |
| "learning_rate": 4.1484079372779706e-07, | |
| "loss": 1.2405, | |
| "step": 8490 | |
| }, | |
| { | |
| "epoch": 32.44387755102041, | |
| "grad_norm": 2.4831225872039795, | |
| "learning_rate": 3.9880611792689757e-07, | |
| "loss": 1.2419, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.44387755102041, | |
| "eval_en_All_acc": 0.6273178094006037, | |
| "eval_en_Env_acc": 0.9838709677419355, | |
| "eval_en_Env_f1": 0.9682539682539683, | |
| "eval_en_Gov_acc": 0.9855072463768116, | |
| "eval_en_Gov_f1": 0.9714285714285714, | |
| "eval_en_Neu_acc": 0.8571428571428571, | |
| "eval_en_Neu_f1": 0.9022556390977443, | |
| "eval_en_Soc_acc": 0.9552238805970149, | |
| "eval_en_Soc_f1": 0.9343065693430657, | |
| "eval_en_cls_acc": 0.9440298507462687, | |
| "eval_en_cls_f1": 0.9440611870308374, | |
| "eval_en_loss": 2.1661887168884277, | |
| "eval_en_runtime": 5.6364, | |
| "eval_en_samples_per_second": 333.011, | |
| "eval_en_steps_per_second": 3.548, | |
| "eval_en_total_cls_tokens": 268, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.44387755102041, | |
| "eval_en_oof_All_acc": 0.6350396696011303, | |
| "eval_en_oof_Env_acc": 0.9594594594594594, | |
| "eval_en_oof_Env_f1": 0.9659863945578231, | |
| "eval_en_oof_Gov_acc": 0.9836065573770492, | |
| "eval_en_oof_Gov_f1": 0.9677419354838709, | |
| "eval_en_oof_Neu_acc": 0.8717948717948718, | |
| "eval_en_oof_Neu_f1": 0.9006622516556291, | |
| "eval_en_oof_Soc_acc": 0.9473684210526315, | |
| "eval_en_oof_Soc_f1": 0.9152542372881356, | |
| "eval_en_oof_cls_acc": 0.937037037037037, | |
| "eval_en_oof_cls_f1": 0.9374112047463647, | |
| "eval_en_oof_loss": 2.096845865249634, | |
| "eval_en_oof_runtime": 5.5837, | |
| "eval_en_oof_samples_per_second": 336.155, | |
| "eval_en_oof_steps_per_second": 3.582, | |
| "eval_en_oof_total_cls_tokens": 270, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.44387755102041, | |
| "eval_vi_All_acc": 0.7989883947827873, | |
| "eval_vi_Env_acc": 0.9700598802395209, | |
| "eval_vi_Env_f1": 0.9614243323442137, | |
| "eval_vi_Gov_acc": 0.9176470588235294, | |
| "eval_vi_Gov_f1": 0.9069767441860465, | |
| "eval_vi_Neu_acc": 0.896969696969697, | |
| "eval_vi_Neu_f1": 0.9164086687306501, | |
| "eval_vi_Soc_acc": 0.9050279329608939, | |
| "eval_vi_Soc_f1": 0.9050279329608939, | |
| "eval_vi_cls_acc": 0.922173274596182, | |
| "eval_vi_cls_f1": 0.922459419555451, | |
| "eval_vi_loss": 0.9294496178627014, | |
| "eval_vi_runtime": 12.75, | |
| "eval_vi_samples_per_second": 345.097, | |
| "eval_vi_steps_per_second": 3.608, | |
| "eval_vi_total_cls_tokens": 681, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.44387755102041, | |
| "eval_dan_All_acc": 0.6847051198963059, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.2222222222222222, | |
| "eval_dan_Gov_f1": 0.3333333333333333, | |
| "eval_dan_Neu_acc": 0.22727272727272727, | |
| "eval_dan_Neu_f1": 0.37037037037037035, | |
| "eval_dan_Soc_acc": 0.3333333333333333, | |
| "eval_dan_Soc_f1": 0.5, | |
| "eval_dan_cls_acc": 0.24444444444444444, | |
| "eval_dan_cls_f1": 0.30092592592592593, | |
| "eval_dan_loss": 2.0085861682891846, | |
| "eval_dan_runtime": 8.9225, | |
| "eval_dan_samples_per_second": 336.228, | |
| "eval_dan_steps_per_second": 3.586, | |
| "eval_dan_total_cls_tokens": 45, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.482142857142854, | |
| "grad_norm": 2.6674482822418213, | |
| "learning_rate": 3.8308498008252925e-07, | |
| "loss": 1.2579, | |
| "step": 8510 | |
| }, | |
| { | |
| "epoch": 32.52040816326531, | |
| "grad_norm": 2.2774150371551514, | |
| "learning_rate": 3.6767758055786805e-07, | |
| "loss": 1.2689, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 32.558673469387756, | |
| "grad_norm": 2.603961229324341, | |
| "learning_rate": 3.5258411571755247e-07, | |
| "loss": 1.262, | |
| "step": 8530 | |
| }, | |
| { | |
| "epoch": 32.5969387755102, | |
| "grad_norm": 2.306577444076538, | |
| "learning_rate": 3.378047779251853e-07, | |
| "loss": 1.2464, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 32.63520408163265, | |
| "grad_norm": 2.572779417037964, | |
| "learning_rate": 3.233397555408607e-07, | |
| "loss": 1.2643, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 32.673469387755105, | |
| "grad_norm": 2.439983606338501, | |
| "learning_rate": 3.0918923291878844e-07, | |
| "loss": 1.3064, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 32.71173469387755, | |
| "grad_norm": 2.7076916694641113, | |
| "learning_rate": 2.953533904049233e-07, | |
| "loss": 1.3076, | |
| "step": 8570 | |
| }, | |
| { | |
| "epoch": 32.75, | |
| "grad_norm": 2.6378087997436523, | |
| "learning_rate": 2.8183240433469206e-07, | |
| "loss": 1.2754, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 32.78826530612245, | |
| "grad_norm": 2.4183127880096436, | |
| "learning_rate": 2.686264470307148e-07, | |
| "loss": 1.2754, | |
| "step": 8590 | |
| }, | |
| { | |
| "epoch": 32.826530612244895, | |
| "grad_norm": 2.5071794986724854, | |
| "learning_rate": 2.5573568680063164e-07, | |
| "loss": 1.2699, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 32.826530612244895, | |
| "eval_en_All_acc": 0.6139729555698648, | |
| "eval_en_Env_acc": 0.9714285714285714, | |
| "eval_en_Env_f1": 0.9714285714285714, | |
| "eval_en_Gov_acc": 0.9420289855072463, | |
| "eval_en_Gov_f1": 0.9489051094890512, | |
| "eval_en_Neu_acc": 0.9285714285714286, | |
| "eval_en_Neu_f1": 0.9176470588235294, | |
| "eval_en_Soc_acc": 0.9666666666666667, | |
| "eval_en_Soc_f1": 0.9747899159663865, | |
| "eval_en_cls_acc": 0.950530035335689, | |
| "eval_en_cls_f1": 0.9531926639268846, | |
| "eval_en_loss": 2.2267274856567383, | |
| "eval_en_runtime": 5.6304, | |
| "eval_en_samples_per_second": 333.369, | |
| "eval_en_steps_per_second": 3.552, | |
| "eval_en_total_cls_tokens": 283, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 32.826530612244895, | |
| "eval_en_oof_All_acc": 0.6170393133411042, | |
| "eval_en_oof_Env_acc": 0.9841269841269841, | |
| "eval_en_oof_Env_f1": 0.9612403100775193, | |
| "eval_en_oof_Gov_acc": 0.9807692307692307, | |
| "eval_en_oof_Gov_f1": 0.9807692307692307, | |
| "eval_en_oof_Neu_acc": 0.891566265060241, | |
| "eval_en_oof_Neu_f1": 0.9249999999999999, | |
| "eval_en_oof_Soc_acc": 0.9850746268656716, | |
| "eval_en_oof_Soc_f1": 0.9635036496350364, | |
| "eval_en_oof_cls_acc": 0.9547169811320755, | |
| "eval_en_oof_cls_f1": 0.9576282976204465, | |
| "eval_en_oof_loss": 2.1992604732513428, | |
| "eval_en_oof_runtime": 5.6317, | |
| "eval_en_oof_samples_per_second": 333.294, | |
| "eval_en_oof_steps_per_second": 3.551, | |
| "eval_en_oof_total_cls_tokens": 265, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 32.826530612244895, | |
| "eval_vi_All_acc": 0.8020999127175643, | |
| "eval_vi_Env_acc": 0.9578313253012049, | |
| "eval_vi_Env_f1": 0.9578313253012049, | |
| "eval_vi_Gov_acc": 0.9333333333333333, | |
| "eval_vi_Gov_f1": 0.9180327868852459, | |
| "eval_vi_Neu_acc": 0.8904109589041096, | |
| "eval_vi_Neu_f1": 0.9090909090909091, | |
| "eval_vi_Soc_acc": 0.8903225806451613, | |
| "eval_vi_Soc_f1": 0.887459807073955, | |
| "eval_vi_cls_acc": 0.9189627228525121, | |
| "eval_vi_cls_f1": 0.9181037070878287, | |
| "eval_vi_loss": 0.9115666151046753, | |
| "eval_vi_runtime": 12.6157, | |
| "eval_vi_samples_per_second": 348.772, | |
| "eval_vi_steps_per_second": 3.646, | |
| "eval_vi_total_cls_tokens": 617, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 32.826530612244895, | |
| "eval_dan_All_acc": 0.6709742927031892, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.23529411764705882, | |
| "eval_dan_Neu_acc": 0.21052631578947367, | |
| "eval_dan_Neu_f1": 0.34782608695652173, | |
| "eval_dan_Soc_acc": 0.2, | |
| "eval_dan_Soc_f1": 0.33333333333333337, | |
| "eval_dan_cls_acc": 0.17777777777777778, | |
| "eval_dan_cls_f1": 0.22911338448422847, | |
| "eval_dan_loss": 2.153042793273926, | |
| "eval_dan_runtime": 8.8198, | |
| "eval_dan_samples_per_second": 340.143, | |
| "eval_dan_steps_per_second": 3.628, | |
| "eval_dan_total_cls_tokens": 45, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 32.86479591836735, | |
| "grad_norm": 2.425464391708374, | |
| "learning_rate": 2.4316028793495147e-07, | |
| "loss": 1.2681, | |
| "step": 8610 | |
| }, | |
| { | |
| "epoch": 32.9030612244898, | |
| "grad_norm": 2.530996322631836, | |
| "learning_rate": 2.3090041070495393e-07, | |
| "loss": 1.2943, | |
| "step": 8620 | |
| }, | |
| { | |
| "epoch": 32.941326530612244, | |
| "grad_norm": 2.4895431995391846, | |
| "learning_rate": 2.1895621136064915e-07, | |
| "loss": 1.257, | |
| "step": 8630 | |
| }, | |
| { | |
| "epoch": 32.97959183673469, | |
| "grad_norm": 2.4547290802001953, | |
| "learning_rate": 2.0732784212879607e-07, | |
| "loss": 1.2844, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 33.015306122448976, | |
| "grad_norm": 2.494478940963745, | |
| "learning_rate": 1.9601545121094301e-07, | |
| "loss": 1.1854, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 33.05357142857143, | |
| "grad_norm": 2.492504358291626, | |
| "learning_rate": 1.8501918278155393e-07, | |
| "loss": 1.2458, | |
| "step": 8660 | |
| }, | |
| { | |
| "epoch": 33.09183673469388, | |
| "grad_norm": 2.3663291931152344, | |
| "learning_rate": 1.7433917698616575e-07, | |
| "loss": 1.2529, | |
| "step": 8670 | |
| }, | |
| { | |
| "epoch": 33.130102040816325, | |
| "grad_norm": 2.5483291149139404, | |
| "learning_rate": 1.639755699396034e-07, | |
| "loss": 1.2934, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 33.16836734693877, | |
| "grad_norm": 2.4679946899414062, | |
| "learning_rate": 1.53928493724248e-07, | |
| "loss": 1.2787, | |
| "step": 8690 | |
| }, | |
| { | |
| "epoch": 33.20663265306123, | |
| "grad_norm": 2.4459192752838135, | |
| "learning_rate": 1.4419807638833826e-07, | |
| "loss": 1.2673, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 33.20663265306123, | |
| "eval_en_All_acc": 0.6329264340499082, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9919999999999999, | |
| "eval_en_Gov_acc": 0.9508196721311475, | |
| "eval_en_Gov_f1": 0.943089430894309, | |
| "eval_en_Neu_acc": 0.8695652173913043, | |
| "eval_en_Neu_f1": 0.909090909090909, | |
| "eval_en_Soc_acc": 0.9466666666666667, | |
| "eval_en_Soc_f1": 0.9102564102564102, | |
| "eval_en_cls_acc": 0.9344827586206896, | |
| "eval_en_cls_f1": 0.938609187560407, | |
| "eval_en_loss": 2.1034352779388428, | |
| "eval_en_runtime": 5.5975, | |
| "eval_en_samples_per_second": 335.33, | |
| "eval_en_steps_per_second": 3.573, | |
| "eval_en_total_cls_tokens": 290, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 33.20663265306123, | |
| "eval_en_oof_All_acc": 0.6279220779220779, | |
| "eval_en_oof_Env_acc": 0.96875, | |
| "eval_en_oof_Env_f1": 0.9612403100775193, | |
| "eval_en_oof_Gov_acc": 0.974025974025974, | |
| "eval_en_oof_Gov_f1": 0.949367088607595, | |
| "eval_en_oof_Neu_acc": 0.8875, | |
| "eval_en_oof_Neu_f1": 0.9102564102564101, | |
| "eval_en_oof_Soc_acc": 0.9259259259259259, | |
| "eval_en_oof_Soc_f1": 0.9316770186335404, | |
| "eval_en_oof_cls_acc": 0.9370860927152318, | |
| "eval_en_oof_cls_f1": 0.9381352068937662, | |
| "eval_en_oof_loss": 2.1350655555725098, | |
| "eval_en_oof_runtime": 5.5894, | |
| "eval_en_oof_samples_per_second": 335.815, | |
| "eval_en_oof_steps_per_second": 3.578, | |
| "eval_en_oof_total_cls_tokens": 302, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 33.20663265306123, | |
| "eval_vi_All_acc": 0.7993189441073303, | |
| "eval_vi_Env_acc": 0.956989247311828, | |
| "eval_vi_Env_f1": 0.9595687331536389, | |
| "eval_vi_Gov_acc": 0.9144736842105263, | |
| "eval_vi_Gov_f1": 0.8853503184713376, | |
| "eval_vi_Neu_acc": 0.8841463414634146, | |
| "eval_vi_Neu_f1": 0.8950617283950617, | |
| "eval_vi_Soc_acc": 0.8345323741007195, | |
| "eval_vi_Soc_f1": 0.8498168498168498, | |
| "eval_vi_cls_acc": 0.9017160686427457, | |
| "eval_vi_cls_f1": 0.897449407459222, | |
| "eval_vi_loss": 0.9217258095741272, | |
| "eval_vi_runtime": 12.7025, | |
| "eval_vi_samples_per_second": 346.389, | |
| "eval_vi_steps_per_second": 3.621, | |
| "eval_vi_total_cls_tokens": 641, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 33.20663265306123, | |
| "eval_dan_All_acc": 0.6783161971506293, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.5, | |
| "eval_dan_Gov_f1": 0.6666666666666666, | |
| "eval_dan_Neu_acc": 0.0, | |
| "eval_dan_Neu_f1": 0.0, | |
| "eval_dan_Soc_acc": 0.2857142857142857, | |
| "eval_dan_Soc_f1": 0.4444444444444445, | |
| "eval_dan_cls_acc": 0.23255813953488372, | |
| "eval_dan_cls_f1": 0.2777777777777778, | |
| "eval_dan_loss": 2.035857915878296, | |
| "eval_dan_runtime": 8.8179, | |
| "eval_dan_samples_per_second": 340.216, | |
| "eval_dan_steps_per_second": 3.629, | |
| "eval_dan_total_cls_tokens": 43, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 33.244897959183675, | |
| "grad_norm": 2.4434103965759277, | |
| "learning_rate": 1.3478444194436612e-07, | |
| "loss": 1.3077, | |
| "step": 8710 | |
| }, | |
| { | |
| "epoch": 33.28316326530612, | |
| "grad_norm": 2.6144521236419678, | |
| "learning_rate": 1.2568771036746975e-07, | |
| "loss": 1.2407, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 33.32142857142857, | |
| "grad_norm": 2.4272680282592773, | |
| "learning_rate": 1.1690799759391802e-07, | |
| "loss": 1.2191, | |
| "step": 8730 | |
| }, | |
| { | |
| "epoch": 33.359693877551024, | |
| "grad_norm": 2.4681525230407715, | |
| "learning_rate": 1.0844541551962851e-07, | |
| "loss": 1.284, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 33.39795918367347, | |
| "grad_norm": 2.44254469871521, | |
| "learning_rate": 1.0030007199874903e-07, | |
| "loss": 1.2917, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 33.43622448979592, | |
| "grad_norm": 2.42927622795105, | |
| "learning_rate": 9.247207084226717e-08, | |
| "loss": 1.246, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 33.474489795918366, | |
| "grad_norm": 2.2745299339294434, | |
| "learning_rate": 8.496151181670852e-08, | |
| "loss": 1.2692, | |
| "step": 8770 | |
| }, | |
| { | |
| "epoch": 33.51275510204081, | |
| "grad_norm": 2.608823776245117, | |
| "learning_rate": 7.776849064284053e-08, | |
| "loss": 1.2636, | |
| "step": 8780 | |
| }, | |
| { | |
| "epoch": 33.55102040816327, | |
| "grad_norm": 2.614380359649658, | |
| "learning_rate": 7.089309899447339e-08, | |
| "loss": 1.2864, | |
| "step": 8790 | |
| }, | |
| { | |
| "epoch": 33.589285714285715, | |
| "grad_norm": 2.5096449851989746, | |
| "learning_rate": 6.433542449729158e-08, | |
| "loss": 1.2538, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 33.589285714285715, | |
| "eval_en_All_acc": 0.6309947192585408, | |
| "eval_en_Env_acc": 0.9722222222222222, | |
| "eval_en_Env_f1": 0.979020979020979, | |
| "eval_en_Gov_acc": 0.9253731343283582, | |
| "eval_en_Gov_f1": 0.9253731343283582, | |
| "eval_en_Neu_acc": 0.9, | |
| "eval_en_Neu_f1": 0.9064748201438848, | |
| "eval_en_Soc_acc": 1.0, | |
| "eval_en_Soc_f1": 0.9772727272727273, | |
| "eval_en_cls_acc": 0.9444444444444444, | |
| "eval_en_cls_f1": 0.9470354151914873, | |
| "eval_en_loss": 2.111346960067749, | |
| "eval_en_runtime": 5.5706, | |
| "eval_en_samples_per_second": 336.946, | |
| "eval_en_steps_per_second": 3.59, | |
| "eval_en_total_cls_tokens": 252, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 33.589285714285715, | |
| "eval_en_oof_All_acc": 0.6344880008687154, | |
| "eval_en_oof_Env_acc": 0.9878048780487805, | |
| "eval_en_oof_Env_f1": 0.9759036144578312, | |
| "eval_en_oof_Gov_acc": 0.9259259259259259, | |
| "eval_en_oof_Gov_f1": 0.9523809523809523, | |
| "eval_en_oof_Neu_acc": 0.9180327868852459, | |
| "eval_en_oof_Neu_f1": 0.9180327868852459, | |
| "eval_en_oof_Soc_acc": 0.9647058823529412, | |
| "eval_en_oof_Soc_f1": 0.9590643274853802, | |
| "eval_en_oof_cls_acc": 0.9539007092198581, | |
| "eval_en_oof_cls_f1": 0.9513454203023524, | |
| "eval_en_oof_loss": 2.139563798904419, | |
| "eval_en_oof_runtime": 5.6195, | |
| "eval_en_oof_samples_per_second": 334.013, | |
| "eval_en_oof_steps_per_second": 3.559, | |
| "eval_en_oof_total_cls_tokens": 282, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 33.589285714285715, | |
| "eval_vi_All_acc": 0.7982807287657172, | |
| "eval_vi_Env_acc": 0.9570552147239264, | |
| "eval_vi_Env_f1": 0.9659442724458206, | |
| "eval_vi_Gov_acc": 0.9403973509933775, | |
| "eval_vi_Gov_f1": 0.9250814332247558, | |
| "eval_vi_Neu_acc": 0.8607594936708861, | |
| "eval_vi_Neu_f1": 0.8918032786885246, | |
| "eval_vi_Soc_acc": 0.9375, | |
| "eval_vi_Soc_f1": 0.9090909090909091, | |
| "eval_vi_cls_acc": 0.9237012987012987, | |
| "eval_vi_cls_f1": 0.9229799733625025, | |
| "eval_vi_loss": 0.9271857738494873, | |
| "eval_vi_runtime": 12.6978, | |
| "eval_vi_samples_per_second": 346.518, | |
| "eval_vi_steps_per_second": 3.623, | |
| "eval_vi_total_cls_tokens": 616, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 33.589285714285715, | |
| "eval_dan_All_acc": 0.6694100878201297, | |
| "eval_dan_Env_acc": 0.25, | |
| "eval_dan_Env_f1": 0.4, | |
| "eval_dan_Gov_acc": 0.21428571428571427, | |
| "eval_dan_Gov_f1": 0.35294117647058826, | |
| "eval_dan_Neu_acc": 0.21428571428571427, | |
| "eval_dan_Neu_f1": 0.35294117647058826, | |
| "eval_dan_Soc_acc": 0.17647058823529413, | |
| "eval_dan_Soc_f1": 0.3, | |
| "eval_dan_cls_acc": 0.20408163265306123, | |
| "eval_dan_cls_f1": 0.35147058823529415, | |
| "eval_dan_loss": 2.141073703765869, | |
| "eval_dan_runtime": 8.7367, | |
| "eval_dan_samples_per_second": 343.381, | |
| "eval_dan_steps_per_second": 3.663, | |
| "eval_dan_total_cls_tokens": 49, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 33.62755102040816, | |
| "grad_norm": 2.44230318069458, | |
| "learning_rate": 5.809555072771033e-08, | |
| "loss": 1.2562, | |
| "step": 8810 | |
| }, | |
| { | |
| "epoch": 33.66581632653061, | |
| "grad_norm": 2.687701463699341, | |
| "learning_rate": 5.2173557211848686e-08, | |
| "loss": 1.3234, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 33.704081632653065, | |
| "grad_norm": 2.520667314529419, | |
| "learning_rate": 4.6569519424483066e-08, | |
| "loss": 1.254, | |
| "step": 8830 | |
| }, | |
| { | |
| "epoch": 33.74234693877551, | |
| "grad_norm": 2.5013606548309326, | |
| "learning_rate": 4.128350878810916e-08, | |
| "loss": 1.2624, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 33.78061224489796, | |
| "grad_norm": 2.5768094062805176, | |
| "learning_rate": 3.631559267201212e-08, | |
| "loss": 1.2792, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 33.81887755102041, | |
| "grad_norm": 2.4427454471588135, | |
| "learning_rate": 3.166583439142834e-08, | |
| "loss": 1.2839, | |
| "step": 8860 | |
| }, | |
| { | |
| "epoch": 33.857142857142854, | |
| "grad_norm": 2.3767380714416504, | |
| "learning_rate": 2.733429320671832e-08, | |
| "loss": 1.2541, | |
| "step": 8870 | |
| }, | |
| { | |
| "epoch": 33.89540816326531, | |
| "grad_norm": 2.4340059757232666, | |
| "learning_rate": 2.3321024322625617e-08, | |
| "loss": 1.2624, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 33.933673469387756, | |
| "grad_norm": 2.4068572521209717, | |
| "learning_rate": 1.9626078887569067e-08, | |
| "loss": 1.2613, | |
| "step": 8890 | |
| }, | |
| { | |
| "epoch": 33.9719387755102, | |
| "grad_norm": 2.454845905303955, | |
| "learning_rate": 1.624950399298497e-08, | |
| "loss": 1.2734, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 33.9719387755102, | |
| "eval_en_All_acc": 0.6358923450253695, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.9784172661870503, | |
| "eval_en_Gov_acc": 0.9818181818181818, | |
| "eval_en_Gov_f1": 0.972972972972973, | |
| "eval_en_Neu_acc": 0.9142857142857143, | |
| "eval_en_Neu_f1": 0.9343065693430657, | |
| "eval_en_Soc_acc": 0.9433962264150944, | |
| "eval_en_Soc_f1": 0.9523809523809524, | |
| "eval_en_cls_acc": 0.959349593495935, | |
| "eval_en_cls_f1": 0.9595194402210103, | |
| "eval_en_loss": 2.1219325065612793, | |
| "eval_en_runtime": 5.5747, | |
| "eval_en_samples_per_second": 336.702, | |
| "eval_en_steps_per_second": 3.588, | |
| "eval_en_total_cls_tokens": 246, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 33.9719387755102, | |
| "eval_en_oof_All_acc": 0.626545573913995, | |
| "eval_en_oof_Env_acc": 1.0, | |
| "eval_en_oof_Env_f1": 1.0, | |
| "eval_en_oof_Gov_acc": 0.984375, | |
| "eval_en_oof_Gov_f1": 0.9618320610687023, | |
| "eval_en_oof_Neu_acc": 0.9538461538461539, | |
| "eval_en_oof_Neu_f1": 0.9538461538461539, | |
| "eval_en_oof_Soc_acc": 0.9130434782608695, | |
| "eval_en_oof_Soc_f1": 0.9333333333333332, | |
| "eval_en_oof_cls_acc": 0.9610894941634242, | |
| "eval_en_oof_cls_f1": 0.9622528870620474, | |
| "eval_en_oof_loss": 2.1445038318634033, | |
| "eval_en_oof_runtime": 5.6165, | |
| "eval_en_oof_samples_per_second": 334.195, | |
| "eval_en_oof_steps_per_second": 3.561, | |
| "eval_en_oof_total_cls_tokens": 257, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 33.9719387755102, | |
| "eval_vi_All_acc": 0.7957096214671973, | |
| "eval_vi_Env_acc": 0.9813664596273292, | |
| "eval_vi_Env_f1": 0.9693251533742331, | |
| "eval_vi_Gov_acc": 0.9320987654320988, | |
| "eval_vi_Gov_f1": 0.9179331306990882, | |
| "eval_vi_Neu_acc": 0.9032258064516129, | |
| "eval_vi_Neu_f1": 0.9271523178807947, | |
| "eval_vi_Soc_acc": 0.9036144578313253, | |
| "eval_vi_Soc_f1": 0.9063444108761329, | |
| "eval_vi_cls_acc": 0.9301242236024845, | |
| "eval_vi_cls_f1": 0.9301887532075622, | |
| "eval_vi_loss": 0.9395124912261963, | |
| "eval_vi_runtime": 12.5956, | |
| "eval_vi_samples_per_second": 349.329, | |
| "eval_vi_steps_per_second": 3.652, | |
| "eval_vi_total_cls_tokens": 644, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 33.9719387755102, | |
| "eval_dan_All_acc": 0.6706664205279675, | |
| "eval_dan_Env_acc": 0.0, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Gov_acc": 0.38461538461538464, | |
| "eval_dan_Gov_f1": 0.5555555555555556, | |
| "eval_dan_Neu_acc": 0.15789473684210525, | |
| "eval_dan_Neu_f1": 0.2727272727272727, | |
| "eval_dan_Soc_acc": 0.0, | |
| "eval_dan_Soc_f1": 0.0, | |
| "eval_dan_cls_acc": 0.17777777777777778, | |
| "eval_dan_cls_f1": 0.20707070707070707, | |
| "eval_dan_loss": 2.132955312728882, | |
| "eval_dan_runtime": 8.9368, | |
| "eval_dan_samples_per_second": 335.692, | |
| "eval_dan_steps_per_second": 3.581, | |
| "eval_dan_total_cls_tokens": 45, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 34.00765306122449, | |
| "grad_norm": 2.5436296463012695, | |
| "learning_rate": 1.3191342672738693e-08, | |
| "loss": 1.2261, | |
| "step": 8910 | |
| }, | |
| { | |
| "epoch": 34.045918367346935, | |
| "grad_norm": 2.4330625534057617, | |
| "learning_rate": 1.0451633902563984e-08, | |
| "loss": 1.2915, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 34.08418367346939, | |
| "grad_norm": 2.499825954437256, | |
| "learning_rate": 8.030412599577263e-09, | |
| "loss": 1.274, | |
| "step": 8930 | |
| }, | |
| { | |
| "epoch": 34.12244897959184, | |
| "grad_norm": 2.667311668395996, | |
| "learning_rate": 5.92770962182243e-09, | |
| "loss": 1.2975, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 34.160714285714285, | |
| "grad_norm": 2.52168869972229, | |
| "learning_rate": 4.143551767887832e-09, | |
| "loss": 1.2945, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 34.19897959183673, | |
| "grad_norm": 2.6020421981811523, | |
| "learning_rate": 2.6779617765537722e-09, | |
| "loss": 1.3284, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 34.23724489795919, | |
| "grad_norm": 2.3341360092163086, | |
| "learning_rate": 1.530958326514953e-09, | |
| "loss": 1.2787, | |
| "step": 8970 | |
| }, | |
| { | |
| "epoch": 34.275510204081634, | |
| "grad_norm": 2.416560411453247, | |
| "learning_rate": 7.025560361251237e-10, | |
| "loss": 1.2707, | |
| "step": 8980 | |
| }, | |
| { | |
| "epoch": 34.31377551020408, | |
| "grad_norm": 2.5830132961273193, | |
| "learning_rate": 1.9276546323609978e-10, | |
| "loss": 1.2754, | |
| "step": 8990 | |
| }, | |
| { | |
| "epoch": 34.35204081632653, | |
| "grad_norm": 2.5007314682006836, | |
| "learning_rate": 1.5931050312278927e-12, | |
| "loss": 1.2735, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 34.35204081632653, | |
| "eval_en_All_acc": 0.6417878064656107, | |
| "eval_en_Env_acc": 1.0, | |
| "eval_en_Env_f1": 0.949640287769784, | |
| "eval_en_Gov_acc": 0.9180327868852459, | |
| "eval_en_Gov_f1": 0.9572649572649572, | |
| "eval_en_Neu_acc": 0.8939393939393939, | |
| "eval_en_Neu_f1": 0.9076923076923077, | |
| "eval_en_Soc_acc": 0.9516129032258065, | |
| "eval_en_Soc_f1": 0.9516129032258065, | |
| "eval_en_cls_acc": 0.9411764705882353, | |
| "eval_en_cls_f1": 0.9415526139882139, | |
| "eval_en_loss": 2.0844380855560303, | |
| "eval_en_runtime": 5.6216, | |
| "eval_en_samples_per_second": 333.888, | |
| "eval_en_steps_per_second": 3.558, | |
| "eval_en_total_cls_tokens": 255, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 34.35204081632653, | |
| "eval_en_oof_All_acc": 0.6303948080043267, | |
| "eval_en_oof_Env_acc": 0.9873417721518988, | |
| "eval_en_oof_Env_f1": 0.9570552147239264, | |
| "eval_en_oof_Gov_acc": 0.9538461538461539, | |
| "eval_en_oof_Gov_f1": 0.9323308270676691, | |
| "eval_en_oof_Neu_acc": 0.7671232876712328, | |
| "eval_en_oof_Neu_f1": 0.8296296296296296, | |
| "eval_en_oof_Soc_acc": 0.9577464788732394, | |
| "eval_en_oof_Soc_f1": 0.9379310344827587, | |
| "eval_en_oof_cls_acc": 0.9166666666666666, | |
| "eval_en_oof_cls_f1": 0.9142366764759959, | |
| "eval_en_oof_loss": 2.131823778152466, | |
| "eval_en_oof_runtime": 5.6091, | |
| "eval_en_oof_samples_per_second": 334.633, | |
| "eval_en_oof_steps_per_second": 3.566, | |
| "eval_en_oof_total_cls_tokens": 288, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 34.35204081632653, | |
| "eval_vi_All_acc": 0.7977955150133029, | |
| "eval_vi_Env_acc": 0.9401197604790419, | |
| "eval_vi_Env_f1": 0.9486404833836858, | |
| "eval_vi_Gov_acc": 0.950920245398773, | |
| "eval_vi_Gov_f1": 0.9281437125748503, | |
| "eval_vi_Neu_acc": 0.8940397350993378, | |
| "eval_vi_Neu_f1": 0.9090909090909091, | |
| "eval_vi_Soc_acc": 0.89171974522293, | |
| "eval_vi_Soc_f1": 0.89171974522293, | |
| "eval_vi_cls_acc": 0.9200626959247649, | |
| "eval_vi_cls_f1": 0.9193987125680938, | |
| "eval_vi_loss": 0.9284259676933289, | |
| "eval_vi_runtime": 12.7462, | |
| "eval_vi_samples_per_second": 345.202, | |
| "eval_vi_steps_per_second": 3.609, | |
| "eval_vi_total_cls_tokens": 638, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 34.35204081632653, | |
| "eval_dan_All_acc": 0.6752184163084177, | |
| "eval_dan_Env_f1": 0.0, | |
| "eval_dan_Environmental_wrong_?_acc": 0.0, | |
| "eval_dan_Gov_acc": 0.14285714285714285, | |
| "eval_dan_Gov_f1": 0.25, | |
| "eval_dan_Neu_acc": 0.26666666666666666, | |
| "eval_dan_Neu_f1": 0.4210526315789474, | |
| "eval_dan_Soc_acc": 0.3125, | |
| "eval_dan_Soc_f1": 0.47619047619047616, | |
| "eval_dan_cls_acc": 0.2631578947368421, | |
| "eval_dan_cls_f1": 0.2868107769423559, | |
| "eval_dan_loss": 2.105409622192383, | |
| "eval_dan_runtime": 8.8548, | |
| "eval_dan_samples_per_second": 338.8, | |
| "eval_dan_steps_per_second": 3.614, | |
| "eval_dan_total_cls_tokens": 38, | |
| "step": 9000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 9000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 35, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.4344025397500314e+17, | |
| "train_batch_size": 24, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |