| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5689900426742532, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05689900426742532, |
| "grad_norm": 1.586480975151062, |
| "learning_rate": 0.00018977272727272728, |
| "loss": 2.3126, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.11379800853485064, |
| "grad_norm": 1.5033866167068481, |
| "learning_rate": 0.00017840909090909092, |
| "loss": 1.4063, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.17069701280227595, |
| "grad_norm": 0.8315887451171875, |
| "learning_rate": 0.00016704545454545455, |
| "loss": 1.2727, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.22759601706970128, |
| "grad_norm": 0.9785130023956299, |
| "learning_rate": 0.00015568181818181818, |
| "loss": 1.2077, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2844950213371266, |
| "grad_norm": 1.313506841659546, |
| "learning_rate": 0.00014431818181818182, |
| "loss": 1.053, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3413940256045519, |
| "grad_norm": 1.4178889989852905, |
| "learning_rate": 0.00013295454545454548, |
| "loss": 0.9781, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.39829302987197723, |
| "grad_norm": 1.3828344345092773, |
| "learning_rate": 0.00012159090909090908, |
| "loss": 0.9663, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.45519203413940257, |
| "grad_norm": 1.5134751796722412, |
| "learning_rate": 0.00011022727272727273, |
| "loss": 0.8499, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5120910384068279, |
| "grad_norm": 1.5038443803787231, |
| "learning_rate": 9.886363636363637e-05, |
| "loss": 0.7966, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.5689900426742532, |
| "grad_norm": 1.4950088262557983, |
| "learning_rate": 8.75e-05, |
| "loss": 0.7796, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 176, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 829761537835008.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
