| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5593611598014832, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 1.2689, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.0512828826904297, |
| "eval_runtime": 12.6897, |
| "eval_samples_per_second": 0.158, |
| "eval_steps_per_second": 0.158, |
| "step": 7 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.7200060486793518, |
| "learning_rate": 5e-05, |
| "loss": 1.1285, |
| "step": 14 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.0476089715957642, |
| "eval_runtime": 12.7159, |
| "eval_samples_per_second": 0.157, |
| "eval_steps_per_second": 0.157, |
| "step": 14 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.7220091819763184, |
| "learning_rate": 2.5e-05, |
| "loss": 1.0452, |
| "step": 21 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.0489338636398315, |
| "eval_runtime": 12.7071, |
| "eval_samples_per_second": 0.157, |
| "eval_steps_per_second": 0.157, |
| "step": 21 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 28, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 1.6754170001006592e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
