| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 17, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.8823225498199463, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 0.6753513813018799, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.0209, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.499729186296463, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.0693, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 0.993525505065918, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.0604, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0393339395523071, | |
| "eval_runtime": 9748.8038, | |
| "eval_samples_per_second": 1.575, | |
| "eval_steps_per_second": 0.197, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 17, | |
| "total_flos": 1.1953201746018304e+16, | |
| "train_loss": 1.045757819624508, | |
| "train_runtime": 10046.7574, | |
| "train_samples_per_second": 0.014, | |
| "train_steps_per_second": 0.002 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 17, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1953201746018304e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |