| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.034129692832764506, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0034129692832764505, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.1485, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034129692832764505, | |
| "eval_loss": 6.436328887939453, | |
| "eval_runtime": 11.6258, | |
| "eval_samples_per_second": 21.246, | |
| "eval_steps_per_second": 5.333, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006825938566552901, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.5176, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010238907849829351, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.1706, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010238907849829351, | |
| "eval_loss": 6.436328887939453, | |
| "eval_runtime": 10.9127, | |
| "eval_samples_per_second": 22.634, | |
| "eval_steps_per_second": 5.681, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.3275, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017064846416382253, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.3643, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020477815699658702, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.2644, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020477815699658702, | |
| "eval_loss": 6.436328887939453, | |
| "eval_runtime": 10.8985, | |
| "eval_samples_per_second": 22.664, | |
| "eval_steps_per_second": 5.689, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023890784982935155, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.8239, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027303754266211604, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.3094, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.030716723549488054, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.3671, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030716723549488054, | |
| "eval_loss": 6.436328887939453, | |
| "eval_runtime": 10.8975, | |
| "eval_samples_per_second": 22.666, | |
| "eval_steps_per_second": 5.689, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.034129692832764506, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 6.0825, | |
| "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": 1.47552863256576e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |