| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 5, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0, |
| "loss": 1.3457, |
| "num_tokens": 1883460.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 5.753155982281568, |
| "learning_rate": 4e-05, |
| "loss": 1.2985, |
| "num_tokens": 3707598.0, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 5.753155982281568, |
| "learning_rate": 3.472792206135786e-05, |
| "loss": 1.2284, |
| "num_tokens": 5444750.0, |
| "step": 3 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 6.984997497242212, |
| "learning_rate": 2.2000000000000003e-05, |
| "loss": 1.0879, |
| "num_tokens": 7293078.0, |
| "step": 4 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 3.1839605353884575, |
| "learning_rate": 9.272077938642147e-06, |
| "loss": 1.0394, |
| "num_tokens": 9142813.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 5, |
| "total_flos": 7.389144736281395e+16, |
| "train_loss": 1.19997718334198, |
| "train_runtime": 569.9406, |
| "train_samples_per_second": 0.947, |
| "train_steps_per_second": 0.009 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 5, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.389144736281395e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
