| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.3076923076923075, |
| "eval_steps": 50, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 38.090023040771484, |
| "learning_rate": 7.75e-06, |
| "loss": 3.4036, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "eval_loss": 2.0667002201080322, |
| "eval_runtime": 12.5463, |
| "eval_samples_per_second": 10.441, |
| "eval_steps_per_second": 1.355, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 76.00936889648438, |
| "learning_rate": 5.300000000000001e-06, |
| "loss": 2.1551, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "eval_loss": 1.8017847537994385, |
| "eval_runtime": 12.1789, |
| "eval_samples_per_second": 10.756, |
| "eval_steps_per_second": 1.396, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 51.53462219238281, |
| "learning_rate": 2.8000000000000003e-06, |
| "loss": 1.8526, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "eval_loss": 1.7186994552612305, |
| "eval_runtime": 12.3313, |
| "eval_samples_per_second": 10.623, |
| "eval_steps_per_second": 1.379, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.73364749312e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
