| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 555, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_f1": 0.35766423357664234, | |
| "eval_fn": 1724, | |
| "eval_fp": 740, | |
| "eval_loss": 0.6976209878921509, | |
| "eval_precision": 0.48106591865357645, | |
| "eval_recall": 0.2846473029045643, | |
| "eval_runtime": 68.4179, | |
| "eval_samples_per_second": 68.301, | |
| "eval_steps_per_second": 4.283, | |
| "eval_tn": 1523, | |
| "eval_tp": 686, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.018026137899954935, | |
| "grad_norm": 9.306479454040527, | |
| "learning_rate": 4.981949458483755e-05, | |
| "loss": 0.6855, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03605227579990987, | |
| "grad_norm": 3.271188497543335, | |
| "learning_rate": 4.963898916967509e-05, | |
| "loss": 0.667, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054078413699864804, | |
| "grad_norm": 7.420863628387451, | |
| "learning_rate": 4.945848375451264e-05, | |
| "loss": 0.6415, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07210455159981974, | |
| "grad_norm": 3.4994685649871826, | |
| "learning_rate": 4.927797833935018e-05, | |
| "loss": 0.6188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09013068949977468, | |
| "grad_norm": 12.319598197937012, | |
| "learning_rate": 4.909747292418773e-05, | |
| "loss": 0.6083, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10815682739972961, | |
| "grad_norm": 5.15464448928833, | |
| "learning_rate": 4.891696750902527e-05, | |
| "loss": 0.5685, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12618296529968454, | |
| "grad_norm": 8.32410717010498, | |
| "learning_rate": 4.873646209386282e-05, | |
| "loss": 0.5153, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14420910319963948, | |
| "grad_norm": 26.5758113861084, | |
| "learning_rate": 4.855595667870036e-05, | |
| "loss": 0.518, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16223524109959442, | |
| "grad_norm": 10.276503562927246, | |
| "learning_rate": 4.837545126353791e-05, | |
| "loss": 0.4902, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18026137899954936, | |
| "grad_norm": 8.947182655334473, | |
| "learning_rate": 4.819494584837546e-05, | |
| "loss": 0.4889, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19828751689950427, | |
| "grad_norm": 8.54738998413086, | |
| "learning_rate": 4.8014440433213e-05, | |
| "loss": 0.4671, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21631365479945922, | |
| "grad_norm": 10.866387367248535, | |
| "learning_rate": 4.783393501805055e-05, | |
| "loss": 0.4543, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23433979269941416, | |
| "grad_norm": 38.420108795166016, | |
| "learning_rate": 4.765342960288809e-05, | |
| "loss": 0.4354, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.25236593059936907, | |
| "grad_norm": 13.113662719726562, | |
| "learning_rate": 4.747292418772563e-05, | |
| "loss": 0.5018, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.270392068499324, | |
| "grad_norm": 36.51860809326172, | |
| "learning_rate": 4.7292418772563177e-05, | |
| "loss": 0.4681, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.28841820639927895, | |
| "grad_norm": 40.15293502807617, | |
| "learning_rate": 4.711191335740072e-05, | |
| "loss": 0.4798, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3064443442992339, | |
| "grad_norm": 12.45967960357666, | |
| "learning_rate": 4.693140794223827e-05, | |
| "loss": 0.4849, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32447048219918884, | |
| "grad_norm": 10.393397331237793, | |
| "learning_rate": 4.675090252707581e-05, | |
| "loss": 0.4496, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3424966200991438, | |
| "grad_norm": 8.426735877990723, | |
| "learning_rate": 4.657039711191336e-05, | |
| "loss": 0.4799, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3605227579990987, | |
| "grad_norm": 10.40811824798584, | |
| "learning_rate": 4.63898916967509e-05, | |
| "loss": 0.45, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3785488958990536, | |
| "grad_norm": 10.157293319702148, | |
| "learning_rate": 4.620938628158845e-05, | |
| "loss": 0.4516, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.39657503379900855, | |
| "grad_norm": 9.582480430603027, | |
| "learning_rate": 4.602888086642599e-05, | |
| "loss": 0.4491, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4146011716989635, | |
| "grad_norm": 17.83095359802246, | |
| "learning_rate": 4.584837545126354e-05, | |
| "loss": 0.4575, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.43262730959891843, | |
| "grad_norm": 10.945122718811035, | |
| "learning_rate": 4.566787003610109e-05, | |
| "loss": 0.4324, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.45065344749887337, | |
| "grad_norm": 5.155959606170654, | |
| "learning_rate": 4.548736462093863e-05, | |
| "loss": 0.421, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4686795853988283, | |
| "grad_norm": 12.092293739318848, | |
| "learning_rate": 4.530685920577618e-05, | |
| "loss": 0.4406, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.48670572329878325, | |
| "grad_norm": 12.724702835083008, | |
| "learning_rate": 4.5126353790613716e-05, | |
| "loss": 0.3947, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5047318611987381, | |
| "grad_norm": 26.710527420043945, | |
| "learning_rate": 4.494584837545127e-05, | |
| "loss": 0.4068, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5227579990986931, | |
| "grad_norm": 8.311524391174316, | |
| "learning_rate": 4.4765342960288806e-05, | |
| "loss": 0.4483, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.540784136998648, | |
| "grad_norm": 12.505125045776367, | |
| "learning_rate": 4.458483754512636e-05, | |
| "loss": 0.3945, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.558810274898603, | |
| "grad_norm": 10.924736976623535, | |
| "learning_rate": 4.44043321299639e-05, | |
| "loss": 0.4386, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5768364127985579, | |
| "grad_norm": 9.005159378051758, | |
| "learning_rate": 4.422382671480145e-05, | |
| "loss": 0.4157, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5948625506985128, | |
| "grad_norm": 13.740028381347656, | |
| "learning_rate": 4.404332129963899e-05, | |
| "loss": 0.4392, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6128886885984678, | |
| "grad_norm": 58.44659423828125, | |
| "learning_rate": 4.386281588447654e-05, | |
| "loss": 0.4345, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 8.443741798400879, | |
| "learning_rate": 4.368231046931408e-05, | |
| "loss": 0.4439, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6489409643983777, | |
| "grad_norm": 7.2340521812438965, | |
| "learning_rate": 4.350180505415163e-05, | |
| "loss": 0.4026, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6669671022983326, | |
| "grad_norm": 7.140610218048096, | |
| "learning_rate": 4.332129963898917e-05, | |
| "loss": 0.4284, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6849932401982876, | |
| "grad_norm": 26.290523529052734, | |
| "learning_rate": 4.314079422382672e-05, | |
| "loss": 0.3861, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7030193780982424, | |
| "grad_norm": 18.140789031982422, | |
| "learning_rate": 4.296028880866426e-05, | |
| "loss": 0.4209, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7210455159981974, | |
| "grad_norm": 9.561443328857422, | |
| "learning_rate": 4.277978339350181e-05, | |
| "loss": 0.4432, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7390716538981523, | |
| "grad_norm": 11.68012809753418, | |
| "learning_rate": 4.259927797833935e-05, | |
| "loss": 0.4329, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "grad_norm": 13.150470733642578, | |
| "learning_rate": 4.24187725631769e-05, | |
| "loss": 0.4157, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7751239296980622, | |
| "grad_norm": 11.43278980255127, | |
| "learning_rate": 4.223826714801444e-05, | |
| "loss": 0.4084, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7931500675980171, | |
| "grad_norm": 6.537344455718994, | |
| "learning_rate": 4.205776173285199e-05, | |
| "loss": 0.4095, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8111762054979721, | |
| "grad_norm": 8.772361755371094, | |
| "learning_rate": 4.187725631768953e-05, | |
| "loss": 0.3763, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.829202343397927, | |
| "grad_norm": 7.250331878662109, | |
| "learning_rate": 4.169675090252708e-05, | |
| "loss": 0.4262, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.847228481297882, | |
| "grad_norm": 8.936566352844238, | |
| "learning_rate": 4.151624548736462e-05, | |
| "loss": 0.3947, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8652546191978369, | |
| "grad_norm": 8.440159797668457, | |
| "learning_rate": 4.1335740072202167e-05, | |
| "loss": 0.4056, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8832807570977917, | |
| "grad_norm": 9.320460319519043, | |
| "learning_rate": 4.115523465703972e-05, | |
| "loss": 0.4019, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9013068949977467, | |
| "grad_norm": 6.329681873321533, | |
| "learning_rate": 4.0974729241877256e-05, | |
| "loss": 0.4092, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9193330328977016, | |
| "grad_norm": 16.446720123291016, | |
| "learning_rate": 4.079422382671481e-05, | |
| "loss": 0.4132, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9373591707976566, | |
| "grad_norm": 7.657299041748047, | |
| "learning_rate": 4.0613718411552346e-05, | |
| "loss": 0.4091, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9553853086976115, | |
| "grad_norm": 8.183615684509277, | |
| "learning_rate": 4.043321299638989e-05, | |
| "loss": 0.3985, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9734114465975665, | |
| "grad_norm": 7.5413384437561035, | |
| "learning_rate": 4.0252707581227436e-05, | |
| "loss": 0.4404, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9914375844975214, | |
| "grad_norm": 10.21881103515625, | |
| "learning_rate": 4.007220216606498e-05, | |
| "loss": 0.421, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.8386043664558254, | |
| "eval_fn": 355, | |
| "eval_fp": 436, | |
| "eval_loss": 0.3710826635360718, | |
| "eval_precision": 0.8249698916097953, | |
| "eval_recall": 0.8526970954356846, | |
| "eval_runtime": 78.3531, | |
| "eval_samples_per_second": 59.64, | |
| "eval_steps_per_second": 3.739, | |
| "eval_tn": 1827, | |
| "eval_tp": 2055, | |
| "step": 555 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2770, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.84912704311296e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |