| { | |
| "best_metric": 0.5703577995300293, | |
| "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-2/checkpoint-765", | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 935, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.15225225225225225, | |
| "eval_f1": 0.02484055052030883, | |
| "eval_loss": 4.083955764770508, | |
| "eval_precision": 0.027106227106227107, | |
| "eval_recall": 0.02292441140024783, | |
| "eval_runtime": 0.593, | |
| "eval_samples_per_second": 490.762, | |
| "eval_steps_per_second": 62.399, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5099099099099099, | |
| "eval_f1": 0.2670894996476392, | |
| "eval_loss": 2.187363862991333, | |
| "eval_precision": 0.309640522875817, | |
| "eval_recall": 0.23482032218091697, | |
| "eval_runtime": 0.3979, | |
| "eval_samples_per_second": 731.333, | |
| "eval_steps_per_second": 92.987, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.693993993993994, | |
| "eval_f1": 0.47863247863247865, | |
| "eval_loss": 1.2897497415542603, | |
| "eval_precision": 0.4893203883495146, | |
| "eval_recall": 0.4684014869888476, | |
| "eval_runtime": 0.3852, | |
| "eval_samples_per_second": 755.539, | |
| "eval_steps_per_second": 96.065, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8027027027027027, | |
| "eval_f1": 0.6448598130841122, | |
| "eval_loss": 0.8646674752235413, | |
| "eval_precision": 0.6484962406015038, | |
| "eval_recall": 0.6412639405204461, | |
| "eval_runtime": 0.3916, | |
| "eval_samples_per_second": 743.07, | |
| "eval_steps_per_second": 94.48, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8414414414414414, | |
| "eval_f1": 0.7013867488443759, | |
| "eval_loss": 0.6896626353263855, | |
| "eval_precision": 0.69773145309626, | |
| "eval_recall": 0.7050805452292441, | |
| "eval_runtime": 0.3661, | |
| "eval_samples_per_second": 794.894, | |
| "eval_steps_per_second": 101.069, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 2.5530731678009033, | |
| "learning_rate": 2.9078560805542346e-05, | |
| "loss": 1.93, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.854954954954955, | |
| "eval_f1": 0.726438188494492, | |
| "eval_loss": 0.6046374440193176, | |
| "eval_precision": 0.7176541717049577, | |
| "eval_recall": 0.7354399008674102, | |
| "eval_runtime": 0.3596, | |
| "eval_samples_per_second": 809.317, | |
| "eval_steps_per_second": 102.903, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8627627627627628, | |
| "eval_f1": 0.7468046256847231, | |
| "eval_loss": 0.5833075642585754, | |
| "eval_precision": 0.7338516746411483, | |
| "eval_recall": 0.7602230483271375, | |
| "eval_runtime": 0.3671, | |
| "eval_samples_per_second": 792.677, | |
| "eval_steps_per_second": 100.787, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8642642642642643, | |
| "eval_f1": 0.754983134007973, | |
| "eval_loss": 0.5721613168716431, | |
| "eval_precision": 0.7474195506982392, | |
| "eval_recall": 0.7627013630731103, | |
| "eval_runtime": 0.3697, | |
| "eval_samples_per_second": 787.048, | |
| "eval_steps_per_second": 100.071, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8693693693693694, | |
| "eval_f1": 0.7570862541907954, | |
| "eval_loss": 0.5703577995300293, | |
| "eval_precision": 0.7450509898020395, | |
| "eval_recall": 0.7695167286245354, | |
| "eval_runtime": 0.6083, | |
| "eval_samples_per_second": 478.361, | |
| "eval_steps_per_second": 60.823, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8714714714714715, | |
| "eval_f1": 0.7621654501216546, | |
| "eval_loss": 0.580158531665802, | |
| "eval_precision": 0.7485065710872163, | |
| "eval_recall": 0.7763320941759604, | |
| "eval_runtime": 0.366, | |
| "eval_samples_per_second": 795.013, | |
| "eval_steps_per_second": 101.084, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8753753753753754, | |
| "eval_f1": 0.7685297691373025, | |
| "eval_loss": 0.572295606136322, | |
| "eval_precision": 0.7538736591179976, | |
| "eval_recall": 0.7837670384138785, | |
| "eval_runtime": 0.3726, | |
| "eval_samples_per_second": 780.913, | |
| "eval_steps_per_second": 99.291, | |
| "step": 935 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1020, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 64294017133920.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 4.546321141328063e-05, | |
| "num_train_epochs": 12, | |
| "per_device_train_batch_size": 16, | |
| "warmup_steps": 207, | |
| "weight_decay": 0.23618328311920675 | |
| } | |
| } | |