| { |
| "best_global_step": 264, |
| "best_metric": 0.45999741554260254, |
| "best_model_checkpoint": "distilbert_km_50_v1_sst2/checkpoint-264", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1584, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 8.881397247314453, |
| "learning_rate": 4.9e-05, |
| "loss": 0.4236, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8004587155963303, |
| "eval_loss": 0.45999741554260254, |
| "eval_runtime": 0.3731, |
| "eval_samples_per_second": 2337.022, |
| "eval_steps_per_second": 10.72, |
| "step": 264 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 10.597502708435059, |
| "learning_rate": 4.8e-05, |
| "loss": 0.2316, |
| "step": 528 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.786697247706422, |
| "eval_loss": 0.5004534125328064, |
| "eval_runtime": 0.3782, |
| "eval_samples_per_second": 2305.782, |
| "eval_steps_per_second": 10.577, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 5.888200283050537, |
| "learning_rate": 4.7e-05, |
| "loss": 0.1712, |
| "step": 792 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.801605504587156, |
| "eval_loss": 0.5798093676567078, |
| "eval_runtime": 0.3776, |
| "eval_samples_per_second": 2309.496, |
| "eval_steps_per_second": 10.594, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 6.170644760131836, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.128, |
| "step": 1056 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8061926605504587, |
| "eval_loss": 0.6200693249702454, |
| "eval_runtime": 0.3688, |
| "eval_samples_per_second": 2364.112, |
| "eval_steps_per_second": 10.845, |
| "step": 1056 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 8.139678001403809, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0962, |
| "step": 1320 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_loss": 0.6694067716598511, |
| "eval_runtime": 0.3677, |
| "eval_samples_per_second": 2371.249, |
| "eval_steps_per_second": 10.877, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 5.770256996154785, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.0717, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.7958715596330275, |
| "eval_loss": 0.8140739798545837, |
| "eval_runtime": 0.3737, |
| "eval_samples_per_second": 2333.716, |
| "eval_steps_per_second": 10.705, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 1584, |
| "total_flos": 2.676464049624883e+16, |
| "train_loss": 0.18704375112899627, |
| "train_runtime": 376.2854, |
| "train_samples_per_second": 8949.19, |
| "train_steps_per_second": 35.08 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 13200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 5 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.676464049624883e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
