| { | |
| "best_metric": 1.1877131462097168, | |
| "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-3/checkpoint-559", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 559, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.021621621621621623, | |
| "eval_f1": 0.004198740377886634, | |
| "eval_loss": 4.7169880867004395, | |
| "eval_precision": 0.003367003367003367, | |
| "eval_recall": 0.0055762081784386614, | |
| "eval_runtime": 0.3678, | |
| "eval_samples_per_second": 791.214, | |
| "eval_steps_per_second": 100.601, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.05795795795795796, | |
| "eval_f1": 0.006104328523862375, | |
| "eval_loss": 4.505440711975098, | |
| "eval_precision": 0.005527638190954774, | |
| "eval_recall": 0.006815365551425031, | |
| "eval_runtime": 0.3666, | |
| "eval_samples_per_second": 793.767, | |
| "eval_steps_per_second": 100.926, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.1810810810810811, | |
| "eval_f1": 0.03324099722991689, | |
| "eval_loss": 3.9866342544555664, | |
| "eval_precision": 0.03767660910518053, | |
| "eval_recall": 0.02973977695167286, | |
| "eval_runtime": 0.5428, | |
| "eval_samples_per_second": 536.084, | |
| "eval_steps_per_second": 68.162, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.34024024024024024, | |
| "eval_f1": 0.11464497041420119, | |
| "eval_loss": 3.2027747631073, | |
| "eval_precision": 0.14220183486238533, | |
| "eval_recall": 0.09603469640644362, | |
| "eval_runtime": 0.3773, | |
| "eval_samples_per_second": 771.175, | |
| "eval_steps_per_second": 98.053, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4690690690690691, | |
| "eval_f1": 0.209277238403452, | |
| "eval_loss": 2.483137607574463, | |
| "eval_precision": 0.2493573264781491, | |
| "eval_recall": 0.18029739776951673, | |
| "eval_runtime": 0.3632, | |
| "eval_samples_per_second": 801.163, | |
| "eval_steps_per_second": 101.866, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5315315315315315, | |
| "eval_f1": 0.27591085956844713, | |
| "eval_loss": 2.0224034786224365, | |
| "eval_precision": 0.3215169002473207, | |
| "eval_recall": 0.241635687732342, | |
| "eval_runtime": 0.4914, | |
| "eval_samples_per_second": 592.149, | |
| "eval_steps_per_second": 75.29, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6009009009009009, | |
| "eval_f1": 0.35639554505568677, | |
| "eval_loss": 1.7107059955596924, | |
| "eval_precision": 0.39140103780578206, | |
| "eval_recall": 0.3271375464684015, | |
| "eval_runtime": 0.3636, | |
| "eval_samples_per_second": 800.256, | |
| "eval_steps_per_second": 101.751, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6447447447447447, | |
| "eval_f1": 0.4060846560846561, | |
| "eval_loss": 1.520038366317749, | |
| "eval_precision": 0.43546099290780144, | |
| "eval_recall": 0.38042131350681535, | |
| "eval_runtime": 0.369, | |
| "eval_samples_per_second": 788.533, | |
| "eval_steps_per_second": 100.26, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6762762762762763, | |
| "eval_f1": 0.4531505060398302, | |
| "eval_loss": 1.3943836688995361, | |
| "eval_precision": 0.47895100069013113, | |
| "eval_recall": 0.42998760842627015, | |
| "eval_runtime": 0.3755, | |
| "eval_samples_per_second": 774.958, | |
| "eval_steps_per_second": 98.534, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6987987987987988, | |
| "eval_f1": 0.4735142118863049, | |
| "eval_loss": 1.2957558631896973, | |
| "eval_precision": 0.49460188933873145, | |
| "eval_recall": 0.4541511771995043, | |
| "eval_runtime": 0.3747, | |
| "eval_samples_per_second": 776.708, | |
| "eval_steps_per_second": 98.757, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7153153153153153, | |
| "eval_f1": 0.5008036001285762, | |
| "eval_loss": 1.233667016029358, | |
| "eval_precision": 0.520374081496326, | |
| "eval_recall": 0.4826517967781908, | |
| "eval_runtime": 0.3615, | |
| "eval_samples_per_second": 805.074, | |
| "eval_steps_per_second": 102.363, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 11.627906976744185, | |
| "grad_norm": 2.628671407699585, | |
| "learning_rate": 2.8277649116697046e-06, | |
| "loss": 2.6146, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7246246246246246, | |
| "eval_f1": 0.5097662504002561, | |
| "eval_loss": 1.1993160247802734, | |
| "eval_precision": 0.5275016567263088, | |
| "eval_recall": 0.49318463444857497, | |
| "eval_runtime": 0.373, | |
| "eval_samples_per_second": 780.069, | |
| "eval_steps_per_second": 99.184, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.727027027027027, | |
| "eval_f1": 0.5123436999038152, | |
| "eval_loss": 1.1877131462097168, | |
| "eval_precision": 0.5308970099667774, | |
| "eval_recall": 0.4950433705080545, | |
| "eval_runtime": 0.3608, | |
| "eval_samples_per_second": 806.568, | |
| "eval_steps_per_second": 102.553, | |
| "step": 559 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 559, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 13, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 140567218624704.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.6487307281599633e-05, | |
| "num_train_epochs": 13, | |
| "per_device_train_batch_size": 32, | |
| "warmup_steps": 215, | |
| "weight_decay": 0.11823639232883996 | |
| } | |
| } | |