| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 530, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 0.411266952753067, | |
| "learning_rate": 0.0008742138364779874, | |
| "loss": 1.6882, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 0.48857933282852173, | |
| "learning_rate": 0.0007484276729559748, | |
| "loss": 0.4202, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1320754716981132, | |
| "grad_norm": 0.2623351216316223, | |
| "learning_rate": 0.0006226415094339623, | |
| "loss": 0.2593, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.509433962264151, | |
| "grad_norm": 0.36103516817092896, | |
| "learning_rate": 0.0004968553459119497, | |
| "loss": 0.2006, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "grad_norm": 0.41828280687332153, | |
| "learning_rate": 0.0003710691823899371, | |
| "loss": 0.17, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 795, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 135428155637760.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |