| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 100, |
| "global_step": 220, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.09090909090909091, |
| "learning_rate": 1.8272727272727275e-05, |
| "loss": 4.192038345336914, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "learning_rate": 1.6454545454545455e-05, |
| "loss": 4.528066253662109, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "learning_rate": 1.4636363636363637e-05, |
| "loss": 8.006786346435547, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "learning_rate": 1.281818181818182e-05, |
| "loss": 2.5653614044189452, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "learning_rate": 1.1000000000000001e-05, |
| "loss": 1.6608339309692384, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "eval_loss": 1.4873225688934326, |
| "eval_runtime": 10.5675, |
| "eval_samples_per_second": 20.819, |
| "eval_steps_per_second": 20.819, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "learning_rate": 9.181818181818184e-06, |
| "loss": 1.3502293586730958, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "learning_rate": 7.363636363636364e-06, |
| "loss": 0.9081875801086425, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "learning_rate": 5.545454545454546e-06, |
| "loss": 0.8325765609741211, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.8181818181818182, |
| "learning_rate": 3.727272727272728e-06, |
| "loss": 0.6824351787567139, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "learning_rate": 1.9090909090909095e-06, |
| "loss": 0.6751256942749023, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "eval_loss": 0.5427442193031311, |
| "eval_runtime": 10.1136, |
| "eval_samples_per_second": 21.753, |
| "eval_steps_per_second": 21.753, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 9.090909090909091e-08, |
| "loss": 0.493731164932251, |
| "step": 220 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 220, |
| "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": 44000091820800.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
