| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9473684210526315, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 29.249841690063477, | |
| "learning_rate": 5.0000000000000004e-08, | |
| "loss": 2.3522, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 28.9044246673584, | |
| "learning_rate": 1.0000000000000001e-07, | |
| "loss": 2.3252, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 29.364099502563477, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 2.3516, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 29.600059509277344, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 2.3531, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 28.67375373840332, | |
| "learning_rate": 2.5000000000000004e-07, | |
| "loss": 2.2996, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 28.520565032958984, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 2.261, | |
| "step": 6 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 6, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.859909958141215e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |