| { | |
| "best_metric": 0.7929836748871136, | |
| "best_model_checkpoint": "logs/indian_build_rr/roberta-base/seed_1/checkpoint-992", | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 1364, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7155262243834665, | |
| "eval_loss": 0.9702894687652588, | |
| "eval_macro-f1": 0.3565778389617827, | |
| "eval_micro-f1": 0.7155262243834665, | |
| "eval_precision-macro": 0.5485369419220343, | |
| "eval_precision-micro": 0.7155262243834665, | |
| "eval_recall-macro": 0.34472385514524134, | |
| "eval_recall-micro": 0.7155262243834665, | |
| "eval_runtime": 3.534, | |
| "eval_samples_per_second": 8.489, | |
| "eval_steps_per_second": 4.244, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7353247655435915, | |
| "eval_loss": 0.8005266189575195, | |
| "eval_macro-f1": 0.5080224547196512, | |
| "eval_micro-f1": 0.7353247655435915, | |
| "eval_precision-macro": 0.5180988726198199, | |
| "eval_precision-micro": 0.7353247655435915, | |
| "eval_recall-macro": 0.5222058583864981, | |
| "eval_recall-micro": 0.7353247655435915, | |
| "eval_runtime": 3.5582, | |
| "eval_samples_per_second": 8.431, | |
| "eval_steps_per_second": 4.216, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7453977075373394, | |
| "eval_loss": 0.815595269203186, | |
| "eval_macro-f1": 0.5288442820595285, | |
| "eval_micro-f1": 0.7453977075373394, | |
| "eval_precision-macro": 0.5625997012224085, | |
| "eval_precision-micro": 0.7453977075373394, | |
| "eval_recall-macro": 0.532191762651922, | |
| "eval_recall-micro": 0.7453977075373394, | |
| "eval_runtime": 3.3982, | |
| "eval_samples_per_second": 8.828, | |
| "eval_steps_per_second": 4.414, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7704063911080237, | |
| "eval_loss": 0.7056049108505249, | |
| "eval_macro-f1": 0.5179788731015686, | |
| "eval_micro-f1": 0.7704063911080237, | |
| "eval_precision-macro": 0.5880911415103544, | |
| "eval_precision-micro": 0.7704063911080237, | |
| "eval_recall-macro": 0.5197063822818007, | |
| "eval_recall-micro": 0.7704063911080237, | |
| "eval_runtime": 3.325, | |
| "eval_samples_per_second": 9.023, | |
| "eval_steps_per_second": 4.511, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 4.032258064516129, | |
| "grad_norm": 7.048013210296631, | |
| "learning_rate": 2.398790322580645e-05, | |
| "loss": 1.0549, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7641542202153525, | |
| "eval_loss": 0.7525667548179626, | |
| "eval_macro-f1": 0.5774815867474451, | |
| "eval_micro-f1": 0.7641542202153525, | |
| "eval_precision-macro": 0.5877505487951785, | |
| "eval_precision-micro": 0.7641542202153525, | |
| "eval_recall-macro": 0.5905806919233985, | |
| "eval_recall-micro": 0.7641542202153525, | |
| "eval_runtime": 3.7943, | |
| "eval_samples_per_second": 7.907, | |
| "eval_steps_per_second": 3.953, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7811740187565127, | |
| "eval_loss": 0.7093824148178101, | |
| "eval_macro-f1": 0.564925492252011, | |
| "eval_micro-f1": 0.7811740187565127, | |
| "eval_precision-macro": 0.6335954751289583, | |
| "eval_precision-micro": 0.7811740187565127, | |
| "eval_recall-macro": 0.5394598039562246, | |
| "eval_recall-micro": 0.7811740187565127, | |
| "eval_runtime": 3.6662, | |
| "eval_samples_per_second": 8.183, | |
| "eval_steps_per_second": 4.091, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.780826675929142, | |
| "eval_loss": 0.7391286492347717, | |
| "eval_macro-f1": 0.5535439959165813, | |
| "eval_micro-f1": 0.780826675929142, | |
| "eval_precision-macro": 0.6475047138793736, | |
| "eval_precision-micro": 0.780826675929142, | |
| "eval_recall-macro": 0.5338983669485645, | |
| "eval_recall-micro": 0.780826675929142, | |
| "eval_runtime": 3.3578, | |
| "eval_samples_per_second": 8.934, | |
| "eval_steps_per_second": 4.467, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7929836748871136, | |
| "eval_loss": 0.7354127168655396, | |
| "eval_macro-f1": 0.5881256788610278, | |
| "eval_micro-f1": 0.7929836748871136, | |
| "eval_precision-macro": 0.616862114635611, | |
| "eval_precision-micro": 0.7929836748871136, | |
| "eval_recall-macro": 0.5756480546409108, | |
| "eval_recall-micro": 0.7929836748871136, | |
| "eval_runtime": 3.5028, | |
| "eval_samples_per_second": 8.565, | |
| "eval_steps_per_second": 4.282, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 8.064516129032258, | |
| "grad_norm": 4.143438339233398, | |
| "learning_rate": 1.7951612903225806e-05, | |
| "loss": 0.545, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7804793331017714, | |
| "eval_loss": 0.8143337965011597, | |
| "eval_macro-f1": 0.5927580984411855, | |
| "eval_micro-f1": 0.7804793331017714, | |
| "eval_precision-macro": 0.5950513529543718, | |
| "eval_precision-micro": 0.7804793331017714, | |
| "eval_recall-macro": 0.5963301506624595, | |
| "eval_recall-micro": 0.7804793331017714, | |
| "eval_runtime": 3.3219, | |
| "eval_samples_per_second": 9.031, | |
| "eval_steps_per_second": 4.515, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7794373046196597, | |
| "eval_loss": 0.8351579904556274, | |
| "eval_macro-f1": 0.5917556551043053, | |
| "eval_micro-f1": 0.7794373046196597, | |
| "eval_precision-macro": 0.602885463862158, | |
| "eval_precision-micro": 0.7794373046196597, | |
| "eval_recall-macro": 0.5915247045666512, | |
| "eval_recall-micro": 0.7794373046196597, | |
| "eval_runtime": 3.5978, | |
| "eval_samples_per_second": 8.339, | |
| "eval_steps_per_second": 4.169, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7870788468218132, | |
| "eval_loss": 0.8609802722930908, | |
| "eval_macro-f1": 0.5742187338887501, | |
| "eval_micro-f1": 0.7870788468218132, | |
| "eval_precision-macro": 0.60147377967397, | |
| "eval_precision-micro": 0.7870788468218132, | |
| "eval_recall-macro": 0.5642213023272796, | |
| "eval_recall-micro": 0.7870788468218132, | |
| "eval_runtime": 24.3263, | |
| "eval_samples_per_second": 1.233, | |
| "eval_steps_per_second": 0.617, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "step": 1364, | |
| "total_flos": 5.301416432939827e+16, | |
| "train_loss": 0.6726446291568342, | |
| "train_runtime": 895.6751, | |
| "train_samples_per_second": 5.515, | |
| "train_steps_per_second": 2.769 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "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": 5.301416432939827e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |