| { |
| "best_metric": 0.3930445540895665, |
| "best_model_checkpoint": "outputs_xxlarge_v3_more_training_data/checkpoint-5469", |
| "epoch": 6.0, |
| "global_step": 10938, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.27, |
| "learning_rate": 4.773724629731213e-06, |
| "loss": 0.4121, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 4.54516364966173e-06, |
| "loss": 0.3291, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 4.317059791552387e-06, |
| "loss": 0.3095, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1_macro_0.1": 0.2866005698267807, |
| "eval_f1_macro_0.15": 0.32172872725801954, |
| "eval_f1_macro_0.2": 0.30427895120393694, |
| "eval_f1_macro_0.25": 0.3089312105851991, |
| "eval_f1_macro_0.3": 0.3166221253661463, |
| "eval_f1_macro_0.5": 0.3059322043668139, |
| "eval_loss": 0.25739067792892456, |
| "eval_runtime": 1.6723, |
| "eval_samples_per_second": 59.798, |
| "eval_steps_per_second": 7.774, |
| "step": 1823 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 4.088498811482904e-06, |
| "loss": 0.2919, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 3.86039495337356e-06, |
| "loss": 0.2784, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 3.6322910952642166e-06, |
| "loss": 0.3295, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 3.404644359115012e-06, |
| "loss": 0.3285, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1_macro_0.1": 0.3245306916332227, |
| "eval_f1_macro_0.15": 0.3462519135259274, |
| "eval_f1_macro_0.2": 0.3471287285580097, |
| "eval_f1_macro_0.25": 0.3534848512155072, |
| "eval_f1_macro_0.3": 0.3392095557344559, |
| "eval_f1_macro_0.5": 0.3154295682028095, |
| "eval_loss": 0.24675622582435608, |
| "eval_runtime": 1.6912, |
| "eval_samples_per_second": 59.129, |
| "eval_steps_per_second": 7.687, |
| "step": 3646 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 3.1765405010056686e-06, |
| "loss": 0.2672, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 2.947979520936186e-06, |
| "loss": 0.258, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 2.7194185408667033e-06, |
| "loss": 0.2567, |
| "step": 5000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1_macro_0.1": 0.32853168421942575, |
| "eval_f1_macro_0.15": 0.3526086331676818, |
| "eval_f1_macro_0.2": 0.3745172120925328, |
| "eval_f1_macro_0.25": 0.3930445540895665, |
| "eval_f1_macro_0.3": 0.39945462714109, |
| "eval_f1_macro_0.5": 0.39421318068629896, |
| "eval_loss": 0.2649226784706116, |
| "eval_runtime": 1.6748, |
| "eval_samples_per_second": 59.71, |
| "eval_steps_per_second": 7.762, |
| "step": 5469 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 2.490857560797221e-06, |
| "loss": 0.2534, |
| "step": 5500 |
| }, |
| { |
| "epoch": 3.29, |
| "learning_rate": 2.2622965807277383e-06, |
| "loss": 0.232, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.57, |
| "learning_rate": 2.033735600658256e-06, |
| "loss": 0.2299, |
| "step": 6500 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 1.8051746205887732e-06, |
| "loss": 0.2318, |
| "step": 7000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1_macro_0.1": 0.35079655833978507, |
| "eval_f1_macro_0.15": 0.38039324434173016, |
| "eval_f1_macro_0.2": 0.39654311115858437, |
| "eval_f1_macro_0.25": 0.3921489396516328, |
| "eval_f1_macro_0.3": 0.4062065290683711, |
| "eval_f1_macro_0.5": 0.3936553697794257, |
| "eval_loss": 0.2689317464828491, |
| "eval_runtime": 1.6822, |
| "eval_samples_per_second": 59.446, |
| "eval_steps_per_second": 7.728, |
| "step": 7292 |
| }, |
| { |
| "epoch": 4.11, |
| "learning_rate": 1.5766136405192905e-06, |
| "loss": 0.2223, |
| "step": 7500 |
| }, |
| { |
| "epoch": 4.39, |
| "learning_rate": 1.3480526604498082e-06, |
| "loss": 0.2048, |
| "step": 8000 |
| }, |
| { |
| "epoch": 4.66, |
| "learning_rate": 1.1194916803803256e-06, |
| "loss": 0.2096, |
| "step": 8500 |
| }, |
| { |
| "epoch": 4.94, |
| "learning_rate": 8.909307003108431e-07, |
| "loss": 0.2093, |
| "step": 9000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_f1_macro_0.1": 0.3408393886848195, |
| "eval_f1_macro_0.15": 0.3672072597449206, |
| "eval_f1_macro_0.2": 0.3803085988063426, |
| "eval_f1_macro_0.25": 0.37290997325486, |
| "eval_f1_macro_0.3": 0.39243163086913097, |
| "eval_f1_macro_0.5": 0.38791911234730964, |
| "eval_loss": 0.2839452922344208, |
| "eval_runtime": 1.6674, |
| "eval_samples_per_second": 59.972, |
| "eval_steps_per_second": 7.796, |
| "step": 9115 |
| }, |
| { |
| "epoch": 5.21, |
| "learning_rate": 6.623697202413605e-07, |
| "loss": 0.1957, |
| "step": 9500 |
| }, |
| { |
| "epoch": 5.49, |
| "learning_rate": 4.338087401718779e-07, |
| "loss": 0.1904, |
| "step": 10000 |
| }, |
| { |
| "epoch": 5.76, |
| "learning_rate": 2.0524776010239534e-07, |
| "loss": 0.1908, |
| "step": 10500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_f1_macro_0.1": 0.34349727342114267, |
| "eval_f1_macro_0.15": 0.37277833048223374, |
| "eval_f1_macro_0.2": 0.3884729444956168, |
| "eval_f1_macro_0.25": 0.38943834375899594, |
| "eval_f1_macro_0.3": 0.37247535938946696, |
| "eval_f1_macro_0.5": 0.3950890613363345, |
| "eval_loss": 0.2841152846813202, |
| "eval_runtime": 1.6795, |
| "eval_samples_per_second": 59.543, |
| "eval_steps_per_second": 7.741, |
| "step": 10938 |
| } |
| ], |
| "max_steps": 10938, |
| "num_train_epochs": 6, |
| "total_flos": 1.905896219955235e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
