| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026666666666666666, | |
| "grad_norm": 5.623929977416992, | |
| "learning_rate": 7.866666666666666e-05, | |
| "loss": 1.6954, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005333333333333333, | |
| "grad_norm": 12.521541595458984, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.3676, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 4.538773536682129, | |
| "learning_rate": 2.5333333333333337e-05, | |
| "loss": 1.4185, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "step": 75, | |
| "total_flos": 224409155534848.0, | |
| "train_loss": 1.4469718933105469, | |
| "train_runtime": 40.798, | |
| "train_samples_per_second": 1.838, | |
| "train_steps_per_second": 1.838 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 224409155534848.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |