| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 0, | |
| "global_step": 7, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 9.695966720581055, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 6.9794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 9.629921913146973, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 6.9358, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 9.6287841796875, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 6.9361, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 9.719982147216797, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 6.916, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 9.761648178100586, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 6.905, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 9.725138664245605, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 6.9355, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 9.787775993347168, | |
| "learning_rate": 0.0, | |
| "loss": 6.9039, | |
| "step": 7 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 7, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 673527443226624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |