| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002326758302164467, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.326758302164467e-05, | |
| "grad_norm": 2.352855920791626, | |
| "learning_rate": 2e-05, | |
| "loss": 5.1489, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.326758302164467e-05, | |
| "eval_loss": 5.181887149810791, | |
| "eval_runtime": 547.6005, | |
| "eval_samples_per_second": 33.048, | |
| "eval_steps_per_second": 16.525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.653516604328934e-05, | |
| "grad_norm": 3.078354835510254, | |
| "learning_rate": 4e-05, | |
| "loss": 6.1934, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.9802749064934e-05, | |
| "grad_norm": 2.2728238105773926, | |
| "learning_rate": 6e-05, | |
| "loss": 4.266, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.9802749064934e-05, | |
| "eval_loss": 5.163669586181641, | |
| "eval_runtime": 545.7629, | |
| "eval_samples_per_second": 33.159, | |
| "eval_steps_per_second": 16.58, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.307033208657868e-05, | |
| "grad_norm": 2.3003463745117188, | |
| "learning_rate": 8e-05, | |
| "loss": 4.8424, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011633791510822335, | |
| "grad_norm": 3.3803586959838867, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8717, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000139605498129868, | |
| "grad_norm": 3.241140604019165, | |
| "learning_rate": 0.00012, | |
| "loss": 4.9592, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000139605498129868, | |
| "eval_loss": 4.933403015136719, | |
| "eval_runtime": 545.6418, | |
| "eval_samples_per_second": 33.166, | |
| "eval_steps_per_second": 16.584, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016287308115151269, | |
| "grad_norm": 4.270029067993164, | |
| "learning_rate": 0.00014, | |
| "loss": 5.5466, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00018614066417315737, | |
| "grad_norm": 3.8886890411376953, | |
| "learning_rate": 0.00016, | |
| "loss": 4.0712, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00020940824719480202, | |
| "grad_norm": 3.9668190479278564, | |
| "learning_rate": 0.00018, | |
| "loss": 3.7893, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00020940824719480202, | |
| "eval_loss": 3.8334319591522217, | |
| "eval_runtime": 546.0531, | |
| "eval_samples_per_second": 33.141, | |
| "eval_steps_per_second": 16.572, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002326758302164467, | |
| "grad_norm": 11.864532470703125, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1003, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1689018496450560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |