| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.333333333333333, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 9.33104419708252, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.2688, | |
| "num_input_tokens_seen": 15040, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 3.3082003593444824, | |
| "learning_rate": 0.0, | |
| "loss": 0.3328, | |
| "num_input_tokens_seen": 30064, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "num_input_tokens_seen": 30064, | |
| "step": 10, | |
| "total_flos": 1361582439923712.0, | |
| "train_loss": 0.8007891654968262, | |
| "train_runtime": 131.0059, | |
| "train_samples_per_second": 2.29, | |
| "train_steps_per_second": 0.076 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 30064, | |
| "num_train_epochs": 10, | |
| "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": 1361582439923712.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |