| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.011611030478955007, |
| "eval_steps": 2, |
| "global_step": 2, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005805515239477504, |
| "grad_norm": 0.02747248113155365, |
| "learning_rate": 1e-05, |
| "loss": 10.3776, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.005805515239477504, |
| "eval_loss": 10.377151489257812, |
| "eval_runtime": 29.442, |
| "eval_samples_per_second": 9.884, |
| "eval_steps_per_second": 4.959, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.011611030478955007, |
| "grad_norm": 0.028352981433272362, |
| "learning_rate": 2e-05, |
| "loss": 10.3759, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.011611030478955007, |
| "eval_loss": 10.377142906188965, |
| "eval_runtime": 0.6078, |
| "eval_samples_per_second": 478.776, |
| "eval_steps_per_second": 240.21, |
| "step": 2 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 5, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 2, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 203661803520.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
