| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 7.938698333852073, | |
| "learning_rate": 5e-07, | |
| "loss": 1.4592, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7.651680054024693, | |
| "learning_rate": 8.742553740855505e-07, | |
| "loss": 1.4296, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.4870359897613525, | |
| "eval_runtime": 3.9957, | |
| "eval_samples_per_second": 11.262, | |
| "eval_steps_per_second": 0.751, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 6.421895096428511, | |
| "learning_rate": 3.2269755647873214e-07, | |
| "loss": 1.3958, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.4527603387832642, | |
| "eval_runtime": 4.1269, | |
| "eval_samples_per_second": 10.904, | |
| "eval_steps_per_second": 0.727, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.165632694186387, | |
| "learning_rate": 0.0, | |
| "loss": 1.3728, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.4498004913330078, | |
| "eval_runtime": 4.1113, | |
| "eval_samples_per_second": 10.945, | |
| "eval_steps_per_second": 0.73, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 15, | |
| "total_flos": 3088349921280.0, | |
| "train_loss": 1.4013684431711833, | |
| "train_runtime": 256.7817, | |
| "train_samples_per_second": 3.668, | |
| "train_steps_per_second": 0.058 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3088349921280.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |