| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05333333333333334, | |
| "eval_steps": 500, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010666666666666666, | |
| "grad_norm": 35.01042766479374, | |
| "learning_rate": 0.0, | |
| "loss": 3.8898, | |
| "num_tokens": 8192.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021333333333333333, | |
| "grad_norm": 35.01042766479374, | |
| "learning_rate": 4e-05, | |
| "loss": 3.8898, | |
| "num_tokens": 16384.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 14.53219290690257, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.9314, | |
| "num_tokens": 24576.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.042666666666666665, | |
| "grad_norm": 8.006347633901225, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.6656, | |
| "num_tokens": 16384.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "grad_norm": 5.453530009146217, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.8817, | |
| "num_tokens": 65536.0, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 3, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 174091495538688.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |