| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5789473684210527, | |
| "eval_steps": 500, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8421052631578947, | |
| "eval_loss": 1.12687087059021, | |
| "eval_runtime": 5.0804, | |
| "eval_samples_per_second": 24.998, | |
| "eval_steps_per_second": 0.394, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.9210526315789473, | |
| "eval_loss": 1.0480140447616577, | |
| "eval_runtime": 5.0521, | |
| "eval_samples_per_second": 25.138, | |
| "eval_steps_per_second": 0.396, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 3.9423027095599776, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2259, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "eval_loss": 1.0243245363235474, | |
| "eval_runtime": 3.9651, | |
| "eval_samples_per_second": 32.029, | |
| "eval_steps_per_second": 0.504, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "step": 12, | |
| "total_flos": 19891067289600.0, | |
| "train_loss": 1.1892856359481812, | |
| "train_runtime": 997.0623, | |
| "train_samples_per_second": 7.236, | |
| "train_steps_per_second": 0.012 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 12, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 19891067289600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |