| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016263468184590364, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004065867046147591, | |
| "grad_norm": 1.4972760677337646, | |
| "learning_rate": 9.959316517493899e-05, | |
| "loss": 0.0619, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008131734092295182, | |
| "grad_norm": 1.9904061555862427, | |
| "learning_rate": 9.918633034987795e-05, | |
| "loss": 0.0764, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012197601138442773, | |
| "grad_norm": 1.7890241146087646, | |
| "learning_rate": 9.877949552481694e-05, | |
| "loss": 0.0757, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016263468184590364, | |
| "grad_norm": 1.857191562652588, | |
| "learning_rate": 9.83726606997559e-05, | |
| "loss": 0.0837, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1229, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 361084771808640.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |