| { | |
| "best_global_step": 200, | |
| "best_metric": 0.15831586718559265, | |
| "best_model_checkpoint": "/tmp/results/checkpoint-200", | |
| "epoch": 0.22032497934453318, | |
| "eval_steps": 200, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.055081244836133296, | |
| "grad_norm": 0.15732981264591217, | |
| "learning_rate": 0.00019640234948604994, | |
| "loss": 1.2703, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11016248967226659, | |
| "grad_norm": 0.13457506895065308, | |
| "learning_rate": 0.00019273127753303965, | |
| "loss": 0.2101, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16524373450839988, | |
| "grad_norm": 0.11798923462629318, | |
| "learning_rate": 0.00018906020558002938, | |
| "loss": 0.1801, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22032497934453318, | |
| "grad_norm": 0.10562872886657715, | |
| "learning_rate": 0.00018538913362701911, | |
| "loss": 0.1621, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22032497934453318, | |
| "eval_loss": 0.15831586718559265, | |
| "eval_runtime": 95.9669, | |
| "eval_samples_per_second": 33.626, | |
| "eval_steps_per_second": 4.21, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2724, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 41176793088000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |