| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11204481792717087, |
| "grad_norm": 40.25, |
| "learning_rate": 1e-05, |
| "loss": 2.609230613708496, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22408963585434175, |
| "grad_norm": 14.0625, |
| "learning_rate": 9.628619846344453e-06, |
| "loss": 2.171901512145996, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.33613445378151263, |
| "grad_norm": 13.375, |
| "learning_rate": 8.569648672789496e-06, |
| "loss": 2.157339096069336, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.4481792717086835, |
| "grad_norm": 37.0, |
| "learning_rate": 6.980398830195785e-06, |
| "loss": 2.139277458190918, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5602240896358543, |
| "grad_norm": 11.375, |
| "learning_rate": 5.096956658859122e-06, |
| "loss": 2.022007942199707, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6722689075630253, |
| "grad_norm": 11.5625, |
| "learning_rate": 3.1991113759764493e-06, |
| "loss": 2.084817314147949, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7843137254901961, |
| "grad_norm": 11.875, |
| "learning_rate": 1.5687918106563326e-06, |
| "loss": 2.074056053161621, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.896358543417367, |
| "grad_norm": 12.5, |
| "learning_rate": 4.481852951692672e-07, |
| "loss": 2.1064525604248048, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 61.5, |
| "learning_rate": 3.760237478849793e-09, |
| "loss": 2.1725065231323244, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.973793625831604, |
| "eval_runtime": 3.3988, |
| "eval_samples_per_second": 21.184, |
| "eval_steps_per_second": 2.648, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 90, |
| "total_flos": 9299379063137280.0, |
| "train_loss": 2.1708432303534613, |
| "train_runtime": 176.9852, |
| "train_samples_per_second": 20.132, |
| "train_steps_per_second": 0.509 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 90, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9299379063137280.0, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
