| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012805736970162632, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025611473940325265, | |
| "eval_loss": 2.799381732940674, | |
| "eval_runtime": 101.6659, | |
| "eval_samples_per_second": 16.18, | |
| "eval_steps_per_second": 8.095, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012805736970162632, | |
| "grad_norm": 0.9979268312454224, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025611473940325264, | |
| "grad_norm": 1.6991825103759766, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025611473940325264, | |
| "eval_loss": 2.598128318786621, | |
| "eval_runtime": 101.9463, | |
| "eval_samples_per_second": 16.136, | |
| "eval_steps_per_second": 8.073, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00384172109104879, | |
| "grad_norm": 1.3118422031402588, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1664, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005122294788065053, | |
| "grad_norm": 1.5301647186279297, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7457, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005122294788065053, | |
| "eval_loss": 1.425940990447998, | |
| "eval_runtime": 102.2161, | |
| "eval_samples_per_second": 16.093, | |
| "eval_steps_per_second": 8.052, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006402868485081316, | |
| "grad_norm": 1.5818004608154297, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1811, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00768344218209758, | |
| "grad_norm": 1.4275416135787964, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9989, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00768344218209758, | |
| "eval_loss": 0.9753066301345825, | |
| "eval_runtime": 102.0702, | |
| "eval_samples_per_second": 16.116, | |
| "eval_steps_per_second": 8.063, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008964015879113843, | |
| "grad_norm": 1.6801331043243408, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9475, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010244589576130106, | |
| "grad_norm": 1.6221517324447632, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8085, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010244589576130106, | |
| "eval_loss": 0.8038530945777893, | |
| "eval_runtime": 101.9922, | |
| "eval_samples_per_second": 16.129, | |
| "eval_steps_per_second": 8.069, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01152516327314637, | |
| "grad_norm": 1.737411618232727, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7328, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012805736970162632, | |
| "grad_norm": 1.6363757848739624, | |
| "learning_rate": 0.0, | |
| "loss": 0.5978, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012805736970162632, | |
| "eval_loss": 0.7750456929206848, | |
| "eval_runtime": 102.061, | |
| "eval_samples_per_second": 16.118, | |
| "eval_steps_per_second": 8.064, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8713180230451200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |