| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9988041138483617, |
| "eval_steps": 500, |
| "global_step": 522, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.09567089213106912, |
| "grad_norm": 52.15945816040039, |
| "learning_rate": 2.5e-06, |
| "loss": 10.7426, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.19134178426213824, |
| "grad_norm": 38.14910125732422, |
| "learning_rate": 5e-06, |
| "loss": 10.0104, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.2870126763932074, |
| "grad_norm": 39.01994705200195, |
| "learning_rate": 7.5e-06, |
| "loss": 9.6031, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3826835685242765, |
| "grad_norm": 33.76708984375, |
| "learning_rate": 1e-05, |
| "loss": 9.1839, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4783544606553456, |
| "grad_norm": 35.43233108520508, |
| "learning_rate": 1.25e-05, |
| "loss": 8.7209, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5740253527864148, |
| "grad_norm": 29.526994705200195, |
| "learning_rate": 1.5e-05, |
| "loss": 8.2324, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6696962449174838, |
| "grad_norm": 35.25413131713867, |
| "learning_rate": 1.7500000000000002e-05, |
| "loss": 7.7545, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.765367137048553, |
| "grad_norm": 40.43191909790039, |
| "learning_rate": 2e-05, |
| "loss": 7.3315, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8610380291796221, |
| "grad_norm": 30.023365020751953, |
| "learning_rate": 2.2499999999999998e-05, |
| "loss": 6.963, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.9567089213106912, |
| "grad_norm": 31.878944396972656, |
| "learning_rate": 2.5e-05, |
| "loss": 6.7297, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9988041138483617, |
| "eval_accuracy": 0.0, |
| "eval_loss": 6.555630207061768, |
| "eval_normalizer": 94012.0, |
| "eval_runtime": 80.2813, |
| "eval_samples_per_second": 665.871, |
| "eval_steps_per_second": 1.308, |
| "step": 522 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 5220, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 8.269250051906765e+16, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
