| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07142857142857142, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014285714285714285, | |
| "grad_norm": 2.227086305618286, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.7252, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 1.4889636039733887, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 2.3403, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04285714285714286, | |
| "grad_norm": 1.5255998373031616, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.8291, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 1.5801162719726562, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 1.3369, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 1.558049201965332, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 1.0358, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 1400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 601363788595200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |