| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006006006006006006, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006006006006006006, | |
| "grad_norm": 0.11140316724777222, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8506, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006006006006006006, | |
| "eval_loss": 10.838886260986328, | |
| "eval_runtime": 5.1969, | |
| "eval_samples_per_second": 134.888, | |
| "eval_steps_per_second": 67.54, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012012012012012011, | |
| "grad_norm": 0.1172875240445137, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8424, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018018018018018018, | |
| "grad_norm": 0.1299639642238617, | |
| "learning_rate": 6e-05, | |
| "loss": 10.844, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018018018018018018, | |
| "eval_loss": 10.838818550109863, | |
| "eval_runtime": 4.3327, | |
| "eval_samples_per_second": 161.792, | |
| "eval_steps_per_second": 81.011, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024024024024024023, | |
| "grad_norm": 0.12317405641078949, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8305, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003003003003003003, | |
| "grad_norm": 0.13242821395397186, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8532, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036036036036036037, | |
| "grad_norm": 0.14363403618335724, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8339, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0036036036036036037, | |
| "eval_loss": 10.838208198547363, | |
| "eval_runtime": 4.3806, | |
| "eval_samples_per_second": 160.025, | |
| "eval_steps_per_second": 80.126, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004204204204204204, | |
| "grad_norm": 0.10223779827356339, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8398, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004804804804804805, | |
| "grad_norm": 0.1232127845287323, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8399, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005405405405405406, | |
| "grad_norm": 0.13759197294712067, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8265, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005405405405405406, | |
| "eval_loss": 10.837149620056152, | |
| "eval_runtime": 4.3583, | |
| "eval_samples_per_second": 160.844, | |
| "eval_steps_per_second": 80.537, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006006006006006006, | |
| "grad_norm": 0.1195223331451416, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8288, | |
| "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": 820295761920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |