| { | |
| "best_metric": 0.29826417565345764, | |
| "best_model_checkpoint": "autotrain-nb4wh-9me5w/checkpoint-1362", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1362, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05506607929515418, | |
| "grad_norm": 17.699098587036133, | |
| "learning_rate": 8.02919708029197e-06, | |
| "loss": 1.789, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11013215859030837, | |
| "grad_norm": 24.31856918334961, | |
| "learning_rate": 1.715328467153285e-05, | |
| "loss": 1.6122, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16519823788546256, | |
| "grad_norm": 22.508787155151367, | |
| "learning_rate": 2.6277372262773724e-05, | |
| "loss": 1.3215, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.22026431718061673, | |
| "grad_norm": 20.886804580688477, | |
| "learning_rate": 3.467153284671533e-05, | |
| "loss": 1.0448, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2753303964757709, | |
| "grad_norm": 38.399627685546875, | |
| "learning_rate": 4.379562043795621e-05, | |
| "loss": 0.7886, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3303964757709251, | |
| "grad_norm": 26.71021842956543, | |
| "learning_rate": 4.967346938775511e-05, | |
| "loss": 0.5643, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3854625550660793, | |
| "grad_norm": 17.157649993896484, | |
| "learning_rate": 4.8653061224489796e-05, | |
| "loss": 0.5184, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.44052863436123346, | |
| "grad_norm": 27.793960571289062, | |
| "learning_rate": 4.763265306122449e-05, | |
| "loss": 0.4071, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4955947136563877, | |
| "grad_norm": 3.2827534675598145, | |
| "learning_rate": 4.6612244897959185e-05, | |
| "loss": 0.3605, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5506607929515418, | |
| "grad_norm": 14.194032669067383, | |
| "learning_rate": 4.559183673469388e-05, | |
| "loss": 0.3437, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6057268722466961, | |
| "grad_norm": 25.65274429321289, | |
| "learning_rate": 4.4571428571428574e-05, | |
| "loss": 0.5132, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6607929515418502, | |
| "grad_norm": 13.928115844726562, | |
| "learning_rate": 4.355102040816327e-05, | |
| "loss": 0.2919, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7158590308370044, | |
| "grad_norm": 14.263054847717285, | |
| "learning_rate": 4.253061224489796e-05, | |
| "loss": 0.3613, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7709251101321586, | |
| "grad_norm": 63.43931198120117, | |
| "learning_rate": 4.151020408163265e-05, | |
| "loss": 0.1767, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8259911894273128, | |
| "grad_norm": 13.402261734008789, | |
| "learning_rate": 4.048979591836735e-05, | |
| "loss": 0.4263, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8810572687224669, | |
| "grad_norm": 80.55384063720703, | |
| "learning_rate": 3.9469387755102045e-05, | |
| "loss": 0.3597, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9361233480176211, | |
| "grad_norm": 2.136183500289917, | |
| "learning_rate": 3.844897959183674e-05, | |
| "loss": 0.2739, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9911894273127754, | |
| "grad_norm": 34.432132720947266, | |
| "learning_rate": 3.742857142857143e-05, | |
| "loss": 0.4018, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8665195808052951, | |
| "eval_f1_macro": 0.8283997321654719, | |
| "eval_f1_micro": 0.8665195808052951, | |
| "eval_f1_weighted": 0.8686614641516474, | |
| "eval_loss": 0.3665294647216797, | |
| "eval_precision_macro": 0.851578163810387, | |
| "eval_precision_micro": 0.8665195808052951, | |
| "eval_precision_weighted": 0.8862860589163636, | |
| "eval_recall_macro": 0.8254227786088771, | |
| "eval_recall_micro": 0.8665195808052951, | |
| "eval_recall_weighted": 0.8665195808052951, | |
| "eval_runtime": 24.5021, | |
| "eval_samples_per_second": 147.987, | |
| "eval_steps_per_second": 9.265, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.0462555066079295, | |
| "grad_norm": 32.53194046020508, | |
| "learning_rate": 3.640816326530612e-05, | |
| "loss": 0.3578, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.1013215859030836, | |
| "grad_norm": 12.507505416870117, | |
| "learning_rate": 3.538775510204082e-05, | |
| "loss": 0.283, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1563876651982379, | |
| "grad_norm": 21.437583923339844, | |
| "learning_rate": 3.436734693877551e-05, | |
| "loss": 0.3169, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.2114537444933922, | |
| "grad_norm": 24.21172332763672, | |
| "learning_rate": 3.3346938775510205e-05, | |
| "loss": 0.2746, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2665198237885462, | |
| "grad_norm": 16.129947662353516, | |
| "learning_rate": 3.23265306122449e-05, | |
| "loss": 0.224, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.3215859030837005, | |
| "grad_norm": 0.1952405422925949, | |
| "learning_rate": 3.1306122448979594e-05, | |
| "loss": 0.2148, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.3766519823788546, | |
| "grad_norm": 8.216381072998047, | |
| "learning_rate": 3.0285714285714288e-05, | |
| "loss": 0.33, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.4317180616740088, | |
| "grad_norm": 14.885648727416992, | |
| "learning_rate": 2.9265306122448982e-05, | |
| "loss": 0.2717, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4867841409691631, | |
| "grad_norm": 40.765113830566406, | |
| "learning_rate": 2.8244897959183673e-05, | |
| "loss": 0.3455, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.5418502202643172, | |
| "grad_norm": 19.627338409423828, | |
| "learning_rate": 2.7224489795918368e-05, | |
| "loss": 0.262, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.5969162995594712, | |
| "grad_norm": 7.5291972160339355, | |
| "learning_rate": 2.620408163265306e-05, | |
| "loss": 0.4149, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.6519823788546255, | |
| "grad_norm": 18.426895141601562, | |
| "learning_rate": 2.518367346938776e-05, | |
| "loss": 0.2655, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7070484581497798, | |
| "grad_norm": 24.276607513427734, | |
| "learning_rate": 2.416326530612245e-05, | |
| "loss": 0.401, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.7621145374449338, | |
| "grad_norm": 4.47360372543335, | |
| "learning_rate": 2.3142857142857145e-05, | |
| "loss": 0.2396, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8171806167400881, | |
| "grad_norm": 89.49807739257812, | |
| "learning_rate": 2.2122448979591836e-05, | |
| "loss": 0.2951, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.8722466960352424, | |
| "grad_norm": 13.01455020904541, | |
| "learning_rate": 2.110204081632653e-05, | |
| "loss": 0.2654, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9273127753303965, | |
| "grad_norm": 0.8529973030090332, | |
| "learning_rate": 2.0081632653061225e-05, | |
| "loss": 0.3684, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.9823788546255505, | |
| "grad_norm": 18.54584503173828, | |
| "learning_rate": 1.906122448979592e-05, | |
| "loss": 0.3434, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8626585769442913, | |
| "eval_f1_macro": 0.8149603266772006, | |
| "eval_f1_micro": 0.8626585769442913, | |
| "eval_f1_weighted": 0.862521320160242, | |
| "eval_loss": 0.42735883593559265, | |
| "eval_precision_macro": 0.864044899871371, | |
| "eval_precision_micro": 0.8626585769442913, | |
| "eval_precision_weighted": 0.8869813676514895, | |
| "eval_recall_macro": 0.8017329444734634, | |
| "eval_recall_micro": 0.8626585769442913, | |
| "eval_recall_weighted": 0.8626585769442913, | |
| "eval_runtime": 24.5304, | |
| "eval_samples_per_second": 147.816, | |
| "eval_steps_per_second": 9.254, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 2.037444933920705, | |
| "grad_norm": 32.09855651855469, | |
| "learning_rate": 1.8040816326530614e-05, | |
| "loss": 0.3931, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.092511013215859, | |
| "grad_norm": 12.878518104553223, | |
| "learning_rate": 1.7020408163265305e-05, | |
| "loss": 0.2092, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.147577092511013, | |
| "grad_norm": 6.512836933135986, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.1755, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.202643171806167, | |
| "grad_norm": 13.462218284606934, | |
| "learning_rate": 1.4979591836734694e-05, | |
| "loss": 0.265, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.2577092511013217, | |
| "grad_norm": 6.5825347900390625, | |
| "learning_rate": 1.395918367346939e-05, | |
| "loss": 0.3132, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.3127753303964758, | |
| "grad_norm": 8.169792175292969, | |
| "learning_rate": 1.2938775510204082e-05, | |
| "loss": 0.2036, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.36784140969163, | |
| "grad_norm": 0.07600528746843338, | |
| "learning_rate": 1.1918367346938777e-05, | |
| "loss": 0.2417, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.4229074889867843, | |
| "grad_norm": 37.740264892578125, | |
| "learning_rate": 1.089795918367347e-05, | |
| "loss": 0.3434, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.4779735682819384, | |
| "grad_norm": 0.7481518983840942, | |
| "learning_rate": 9.877551020408164e-06, | |
| "loss": 0.3904, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.5330396475770924, | |
| "grad_norm": 19.178939819335938, | |
| "learning_rate": 8.857142857142857e-06, | |
| "loss": 0.2762, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.5881057268722465, | |
| "grad_norm": 31.451202392578125, | |
| "learning_rate": 7.836734693877551e-06, | |
| "loss": 0.1749, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.643171806167401, | |
| "grad_norm": 19.86487579345703, | |
| "learning_rate": 6.857142857142858e-06, | |
| "loss": 0.2828, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.698237885462555, | |
| "grad_norm": 26.013954162597656, | |
| "learning_rate": 5.8367346938775515e-06, | |
| "loss": 0.2932, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.753303964757709, | |
| "grad_norm": 9.863497734069824, | |
| "learning_rate": 4.816326530612245e-06, | |
| "loss": 0.1348, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.8083700440528636, | |
| "grad_norm": 5.155836582183838, | |
| "learning_rate": 3.7959183673469385e-06, | |
| "loss": 0.1825, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.8634361233480177, | |
| "grad_norm": 34.157859802246094, | |
| "learning_rate": 2.775510204081633e-06, | |
| "loss": 0.2959, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9185022026431717, | |
| "grad_norm": 18.83913803100586, | |
| "learning_rate": 1.7551020408163264e-06, | |
| "loss": 0.147, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.9735682819383262, | |
| "grad_norm": 23.70765495300293, | |
| "learning_rate": 7.346938775510204e-07, | |
| "loss": 0.3109, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9117484831770546, | |
| "eval_f1_macro": 0.8819634453630242, | |
| "eval_f1_micro": 0.9117484831770546, | |
| "eval_f1_weighted": 0.9111571757544475, | |
| "eval_loss": 0.29826417565345764, | |
| "eval_precision_macro": 0.9005385696343319, | |
| "eval_precision_micro": 0.9117484831770546, | |
| "eval_precision_weighted": 0.917903672857539, | |
| "eval_recall_macro": 0.872875172834113, | |
| "eval_recall_micro": 0.9117484831770546, | |
| "eval_recall_weighted": 0.9117484831770546, | |
| "eval_runtime": 24.4755, | |
| "eval_samples_per_second": 148.148, | |
| "eval_steps_per_second": 9.275, | |
| "step": 1362 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1362, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7382422149074944e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |