| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.96, |
| "eval_steps": 500, |
| "global_step": 186, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6321775913238525, |
| "learning_rate": 5.2631578947368424e-05, |
| "loss": 1.6822, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.44690731167793274, |
| "learning_rate": 9.999115304121457e-05, |
| "loss": 1.3559, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.36956608295440674, |
| "learning_rate": 9.893330096656574e-05, |
| "loss": 1.1093, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.35848182439804077, |
| "learning_rate": 9.614885510995047e-05, |
| "loss": 1.0507, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.29430824518203735, |
| "learning_rate": 9.173606363381219e-05, |
| "loss": 1.0246, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.29825249314308167, |
| "learning_rate": 8.585063028536016e-05, |
| "loss": 0.9855, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.112, |
| "grad_norm": 0.28768375515937805, |
| "learning_rate": 7.870022044630569e-05, |
| "loss": 0.9724, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.272, |
| "grad_norm": 0.3590382933616638, |
| "learning_rate": 7.053713373516538e-05, |
| "loss": 0.9609, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.432, |
| "grad_norm": 0.3577307462692261, |
| "learning_rate": 6.164940170670266e-05, |
| "loss": 0.9283, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.592, |
| "grad_norm": 0.36449816823005676, |
| "learning_rate": 5.2350624762954884e-05, |
| "loss": 0.9546, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.752, |
| "grad_norm": 0.359261155128479, |
| "learning_rate": 4.29689068767551e-05, |
| "loss": 0.9381, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.912, |
| "grad_norm": 0.38183584809303284, |
| "learning_rate": 3.38352785620174e-05, |
| "loss": 0.9322, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.064, |
| "grad_norm": 0.35306838154792786, |
| "learning_rate": 2.5272016582081236e-05, |
| "loss": 0.9331, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.224, |
| "grad_norm": 0.3385419249534607, |
| "learning_rate": 1.7581272530970667e-05, |
| "loss": 0.8962, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.384, |
| "grad_norm": 0.3401263952255249, |
| "learning_rate": 1.103441152395588e-05, |
| "loss": 0.9066, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.544, |
| "grad_norm": 0.35029909014701843, |
| "learning_rate": 5.86243717785463e-06, |
| "loss": 0.9002, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.7039999999999997, |
| "grad_norm": 0.36441105604171753, |
| "learning_rate": 2.2478407321721296e-06, |
| "loss": 0.9316, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.864, |
| "grad_norm": 0.3668910264968872, |
| "learning_rate": 3.1816191188415166e-07, |
| "loss": 0.896, |
| "step": 180 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 186, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1.646271127777444e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
