| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2738225629791895, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.054764512595837894, | |
| "grad_norm": 3.8052456378936768, | |
| "learning_rate": 1.8248175182481753e-05, | |
| "loss": 2.2411, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10952902519167579, | |
| "grad_norm": 2.646080255508423, | |
| "learning_rate": 3.649635036496351e-05, | |
| "loss": 1.8231, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16429353778751368, | |
| "grad_norm": 2.700340986251831, | |
| "learning_rate": 5.474452554744526e-05, | |
| "loss": 1.7334, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21905805038335158, | |
| "grad_norm": 3.046970844268799, | |
| "learning_rate": 7.299270072992701e-05, | |
| "loss": 1.6861, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2738225629791895, | |
| "grad_norm": 2.5365347862243652, | |
| "learning_rate": 9.124087591240877e-05, | |
| "loss": 1.6711, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 5478, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.4419524014322483e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |