| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.564102564102564, | |
| "eval_steps": 100, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 92.9238510131836, | |
| "learning_rate": 9.9907e-06, | |
| "loss": 2.4016, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "eval_loss": 2.1255013942718506, | |
| "eval_runtime": 34.4318, | |
| "eval_samples_per_second": 11.414, | |
| "eval_steps_per_second": 1.452, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 47.019439697265625, | |
| "learning_rate": 9.980700000000001e-06, | |
| "loss": 2.0696, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "eval_loss": 1.9405728578567505, | |
| "eval_runtime": 34.0713, | |
| "eval_samples_per_second": 11.535, | |
| "eval_steps_per_second": 1.468, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 52.230751037597656, | |
| "learning_rate": 9.970700000000001e-06, | |
| "loss": 1.9983, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": 1.900020718574524, | |
| "eval_runtime": 34.1694, | |
| "eval_samples_per_second": 11.502, | |
| "eval_steps_per_second": 1.463, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 39.62374496459961, | |
| "learning_rate": 9.960800000000001e-06, | |
| "loss": 1.8888, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "eval_loss": 1.8164124488830566, | |
| "eval_runtime": 34.1213, | |
| "eval_samples_per_second": 11.518, | |
| "eval_steps_per_second": 1.465, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 39.697731018066406, | |
| "learning_rate": 9.9508e-06, | |
| "loss": 1.8456, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "eval_loss": 1.7753618955612183, | |
| "eval_runtime": 34.149, | |
| "eval_samples_per_second": 11.508, | |
| "eval_steps_per_second": 1.464, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 100000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 513, | |
| "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": 1.91121583104e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |