| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0547945205479452, |
| "eval_steps": 0, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0182648401826484, |
| "grad_norm": 0.45940226316452026, |
| "learning_rate": 0.0001, |
| "loss": 3.7646, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0365296803652968, |
| "grad_norm": 0.056412823498249054, |
| "learning_rate": 0.0001, |
| "loss": 0.0326, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0547945205479452, |
| "grad_norm": 0.055685561150312424, |
| "learning_rate": 0.0001, |
| "loss": 0.0299, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0547945205479452, |
| "step": 30, |
| "total_flos": 1.6697353660111258e+17, |
| "train_loss": 1.2756919225056966, |
| "train_runtime": 450.633, |
| "train_samples_per_second": 10.652, |
| "train_steps_per_second": 0.067 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 30, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.6697353660111258e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
