| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18691588785046728, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 12.641100883483887, | |
| "learning_rate": 2e-05, | |
| "loss": 8.4188, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "eval_loss": 8.402215003967285, | |
| "eval_runtime": 0.6537, | |
| "eval_samples_per_second": 35.182, | |
| "eval_steps_per_second": 18.356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 13.078154563903809, | |
| "learning_rate": 4e-05, | |
| "loss": 8.3372, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 13.144291877746582, | |
| "learning_rate": 6e-05, | |
| "loss": 8.3199, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "eval_loss": 8.365829467773438, | |
| "eval_runtime": 0.639, | |
| "eval_samples_per_second": 35.994, | |
| "eval_steps_per_second": 18.78, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 12.276077270507812, | |
| "learning_rate": 8e-05, | |
| "loss": 8.4937, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 13.09289836883545, | |
| "learning_rate": 0.0001, | |
| "loss": 8.1714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 12.53107738494873, | |
| "learning_rate": 0.00012, | |
| "loss": 8.1098, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "eval_loss": 7.94780158996582, | |
| "eval_runtime": 0.6902, | |
| "eval_samples_per_second": 33.324, | |
| "eval_steps_per_second": 17.387, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 11.74576187133789, | |
| "learning_rate": 0.00014, | |
| "loss": 8.0594, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 13.39953899383545, | |
| "learning_rate": 0.00016, | |
| "loss": 7.7191, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 13.288470268249512, | |
| "learning_rate": 0.00018, | |
| "loss": 7.3536, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "eval_loss": 7.272299766540527, | |
| "eval_runtime": 0.6821, | |
| "eval_samples_per_second": 33.717, | |
| "eval_steps_per_second": 17.592, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 11.965997695922852, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4087, | |
| "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": 5429904015360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |