| { | |
| "best_metric": 0.9738104939460754, | |
| "best_model_checkpoint": "autotrain-e3who-rl7wb/checkpoint-1248", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1248, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04807692307692308, | |
| "grad_norm": 11.674389839172363, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.0847, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09615384615384616, | |
| "grad_norm": 10.00346851348877, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.0137, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14423076923076922, | |
| "grad_norm": 9.38170337677002, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.9327, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 8.871125221252441, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.879, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2403846153846154, | |
| "grad_norm": 5.923038959503174, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7245, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28846153846153844, | |
| "grad_norm": 7.439846038818359, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.5266, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33653846153846156, | |
| "grad_norm": 6.5186991691589355, | |
| "learning_rate": 4.9332146037399826e-05, | |
| "loss": 1.551, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 19.113332748413086, | |
| "learning_rate": 4.844167408726625e-05, | |
| "loss": 1.5237, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4326923076923077, | |
| "grad_norm": 5.98344087600708, | |
| "learning_rate": 4.755120213713268e-05, | |
| "loss": 1.5078, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4807692307692308, | |
| "grad_norm": 6.7967047691345215, | |
| "learning_rate": 4.666073018699911e-05, | |
| "loss": 1.5408, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5288461538461539, | |
| "grad_norm": 8.644440650939941, | |
| "learning_rate": 4.577025823686554e-05, | |
| "loss": 1.5727, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 13.624725341796875, | |
| "learning_rate": 4.487978628673197e-05, | |
| "loss": 1.5456, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 8.256715774536133, | |
| "learning_rate": 4.39893143365984e-05, | |
| "loss": 1.5259, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6730769230769231, | |
| "grad_norm": 5.904226779937744, | |
| "learning_rate": 4.309884238646483e-05, | |
| "loss": 1.5871, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7211538461538461, | |
| "grad_norm": 6.76925802230835, | |
| "learning_rate": 4.2208370436331254e-05, | |
| "loss": 1.478, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 6.825554847717285, | |
| "learning_rate": 4.1317898486197685e-05, | |
| "loss": 1.4111, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8173076923076923, | |
| "grad_norm": 6.132884502410889, | |
| "learning_rate": 4.0427426536064116e-05, | |
| "loss": 1.3338, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8653846153846154, | |
| "grad_norm": 12.595861434936523, | |
| "learning_rate": 3.953695458593055e-05, | |
| "loss": 1.4382, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9134615384615384, | |
| "grad_norm": 7.732487678527832, | |
| "learning_rate": 3.864648263579698e-05, | |
| "loss": 1.5317, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 7.2850446701049805, | |
| "learning_rate": 3.77560106856634e-05, | |
| "loss": 1.4916, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4362980769230769, | |
| "eval_f1_macro": 0.38823820729318503, | |
| "eval_f1_micro": 0.4362980769230769, | |
| "eval_f1_weighted": 0.38644947334537555, | |
| "eval_loss": 1.4391758441925049, | |
| "eval_precision_macro": 0.4372530277536922, | |
| "eval_precision_micro": 0.4362980769230769, | |
| "eval_precision_weighted": 0.4252989320853903, | |
| "eval_recall_macro": 0.42858524320512215, | |
| "eval_recall_micro": 0.4362980769230769, | |
| "eval_recall_weighted": 0.4362980769230769, | |
| "eval_runtime": 134.6918, | |
| "eval_samples_per_second": 6.177, | |
| "eval_steps_per_second": 0.386, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.0096153846153846, | |
| "grad_norm": 7.571177959442139, | |
| "learning_rate": 3.6865538735529834e-05, | |
| "loss": 1.4211, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0576923076923077, | |
| "grad_norm": 10.535785675048828, | |
| "learning_rate": 3.597506678539626e-05, | |
| "loss": 1.3545, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.1057692307692308, | |
| "grad_norm": 5.157609939575195, | |
| "learning_rate": 3.508459483526269e-05, | |
| "loss": 1.3541, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 5.49186372756958, | |
| "learning_rate": 3.419412288512912e-05, | |
| "loss": 1.3949, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.2019230769230769, | |
| "grad_norm": 8.001138687133789, | |
| "learning_rate": 3.330365093499555e-05, | |
| "loss": 1.4223, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 5.453105449676514, | |
| "learning_rate": 3.241317898486198e-05, | |
| "loss": 1.4336, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2980769230769231, | |
| "grad_norm": 9.639703750610352, | |
| "learning_rate": 3.1522707034728406e-05, | |
| "loss": 1.3314, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3461538461538463, | |
| "grad_norm": 8.409910202026367, | |
| "learning_rate": 3.063223508459484e-05, | |
| "loss": 1.3744, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3942307692307692, | |
| "grad_norm": 8.238600730895996, | |
| "learning_rate": 2.9741763134461265e-05, | |
| "loss": 1.3158, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.4423076923076923, | |
| "grad_norm": 11.363844871520996, | |
| "learning_rate": 2.8851291184327693e-05, | |
| "loss": 1.23, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4903846153846154, | |
| "grad_norm": 9.3771390914917, | |
| "learning_rate": 2.7960819234194124e-05, | |
| "loss": 1.3987, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 6.3942341804504395, | |
| "learning_rate": 2.7070347284060555e-05, | |
| "loss": 1.2284, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5865384615384617, | |
| "grad_norm": 11.658981323242188, | |
| "learning_rate": 2.6179875333926983e-05, | |
| "loss": 1.2952, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.6346153846153846, | |
| "grad_norm": 13.555744171142578, | |
| "learning_rate": 2.5289403383793414e-05, | |
| "loss": 1.2832, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6826923076923077, | |
| "grad_norm": 14.48792552947998, | |
| "learning_rate": 2.439893143365984e-05, | |
| "loss": 1.1761, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.7307692307692308, | |
| "grad_norm": 8.11705207824707, | |
| "learning_rate": 2.3508459483526273e-05, | |
| "loss": 1.1465, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7788461538461537, | |
| "grad_norm": 9.193824768066406, | |
| "learning_rate": 2.2617987533392697e-05, | |
| "loss": 1.2465, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.8269230769230769, | |
| "grad_norm": 8.696285247802734, | |
| "learning_rate": 2.1727515583259128e-05, | |
| "loss": 1.1355, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 11.617859840393066, | |
| "learning_rate": 2.083704363312556e-05, | |
| "loss": 1.0957, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 8.226522445678711, | |
| "learning_rate": 1.9946571682991987e-05, | |
| "loss": 1.1555, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9711538461538463, | |
| "grad_norm": 8.735304832458496, | |
| "learning_rate": 1.9056099732858414e-05, | |
| "loss": 0.9817, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5709134615384616, | |
| "eval_f1_macro": 0.5526372725386915, | |
| "eval_f1_micro": 0.5709134615384616, | |
| "eval_f1_weighted": 0.5547700852360117, | |
| "eval_loss": 1.1667430400848389, | |
| "eval_precision_macro": 0.6115987390351798, | |
| "eval_precision_micro": 0.5709134615384616, | |
| "eval_precision_weighted": 0.6030497639852268, | |
| "eval_recall_macro": 0.5580461856746055, | |
| "eval_recall_micro": 0.5709134615384616, | |
| "eval_recall_weighted": 0.5709134615384616, | |
| "eval_runtime": 192.9893, | |
| "eval_samples_per_second": 4.311, | |
| "eval_steps_per_second": 0.269, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 2.019230769230769, | |
| "grad_norm": 9.844583511352539, | |
| "learning_rate": 1.8165627782724845e-05, | |
| "loss": 1.2267, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.0673076923076925, | |
| "grad_norm": 8.707366943359375, | |
| "learning_rate": 1.7275155832591277e-05, | |
| "loss": 1.027, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.1153846153846154, | |
| "grad_norm": 9.87036418914795, | |
| "learning_rate": 1.63846838824577e-05, | |
| "loss": 0.9735, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.1634615384615383, | |
| "grad_norm": 12.08313274383545, | |
| "learning_rate": 1.5494211932324132e-05, | |
| "loss": 1.0652, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.2115384615384617, | |
| "grad_norm": 14.892265319824219, | |
| "learning_rate": 1.4603739982190561e-05, | |
| "loss": 1.0136, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.2596153846153846, | |
| "grad_norm": 9.868454933166504, | |
| "learning_rate": 1.3713268032056992e-05, | |
| "loss": 1.0157, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 12.881400108337402, | |
| "learning_rate": 1.2822796081923418e-05, | |
| "loss": 0.9707, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.355769230769231, | |
| "grad_norm": 13.381880760192871, | |
| "learning_rate": 1.193232413178985e-05, | |
| "loss": 0.9967, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.4038461538461537, | |
| "grad_norm": 16.189842224121094, | |
| "learning_rate": 1.1041852181656279e-05, | |
| "loss": 0.96, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.451923076923077, | |
| "grad_norm": 8.050971984863281, | |
| "learning_rate": 1.0151380231522706e-05, | |
| "loss": 1.0216, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 8.997209548950195, | |
| "learning_rate": 9.260908281389138e-06, | |
| "loss": 1.0242, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.5480769230769234, | |
| "grad_norm": 9.797513961791992, | |
| "learning_rate": 8.370436331255565e-06, | |
| "loss": 0.9184, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5961538461538463, | |
| "grad_norm": 11.301565170288086, | |
| "learning_rate": 7.4799643811219954e-06, | |
| "loss": 0.9896, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.644230769230769, | |
| "grad_norm": 7.524016380310059, | |
| "learning_rate": 6.589492430988424e-06, | |
| "loss": 0.9413, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 11.047348976135254, | |
| "learning_rate": 5.699020480854853e-06, | |
| "loss": 0.9651, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.7403846153846154, | |
| "grad_norm": 16.3375301361084, | |
| "learning_rate": 4.808548530721283e-06, | |
| "loss": 0.945, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.7884615384615383, | |
| "grad_norm": 11.701908111572266, | |
| "learning_rate": 3.918076580587711e-06, | |
| "loss": 1.0429, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.8365384615384617, | |
| "grad_norm": 15.336776733398438, | |
| "learning_rate": 3.0276046304541406e-06, | |
| "loss": 0.8851, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.8846153846153846, | |
| "grad_norm": 12.694565773010254, | |
| "learning_rate": 2.13713268032057e-06, | |
| "loss": 0.9671, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.9326923076923075, | |
| "grad_norm": 8.017022132873535, | |
| "learning_rate": 1.2466607301869992e-06, | |
| "loss": 0.9224, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.980769230769231, | |
| "grad_norm": 8.045291900634766, | |
| "learning_rate": 3.5618878005342833e-07, | |
| "loss": 0.8915, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6706730769230769, | |
| "eval_f1_macro": 0.6658494548344828, | |
| "eval_f1_micro": 0.6706730769230769, | |
| "eval_f1_weighted": 0.6675736368483096, | |
| "eval_loss": 0.9738104939460754, | |
| "eval_precision_macro": 0.6694452026078725, | |
| "eval_precision_micro": 0.6706730769230769, | |
| "eval_precision_weighted": 0.6700176765328316, | |
| "eval_recall_macro": 0.667714178467355, | |
| "eval_recall_micro": 0.6706730769230769, | |
| "eval_recall_weighted": 0.6706730769230769, | |
| "eval_runtime": 136.1128, | |
| "eval_samples_per_second": 6.113, | |
| "eval_steps_per_second": 0.382, | |
| "step": 1248 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 1248, | |
| "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": 656563229079552.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |