| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 57, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08771929824561403, |
| "grad_norm": 9.328929901123047, |
| "learning_rate": 9.986505025774137e-06, |
| "loss": 1.0312, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.17543859649122806, |
| "grad_norm": 3.4733898639678955, |
| "learning_rate": 9.931806517013612e-06, |
| "loss": 0.194, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2631578947368421, |
| "grad_norm": 2.149510383605957, |
| "learning_rate": 9.835521911952554e-06, |
| "loss": 0.1074, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.3508771929824561, |
| "grad_norm": 3.1549360752105713, |
| "learning_rate": 9.698463103929542e-06, |
| "loss": 0.1067, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.43859649122807015, |
| "grad_norm": 2.0819382667541504, |
| "learning_rate": 9.521785803487888e-06, |
| "loss": 0.0831, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 2.512042999267578, |
| "learning_rate": 9.306979793165682e-06, |
| "loss": 0.0777, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6140350877192983, |
| "grad_norm": 1.5260273218154907, |
| "learning_rate": 9.055856365316012e-06, |
| "loss": 0.0689, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.7017543859649122, |
| "grad_norm": 1.9269893169403076, |
| "learning_rate": 8.770533048884483e-06, |
| "loss": 0.0631, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7894736842105263, |
| "grad_norm": 1.1491817235946655, |
| "learning_rate": 8.453415753931223e-06, |
| "loss": 0.0516, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.8771929824561403, |
| "grad_norm": 1.4330883026123047, |
| "learning_rate": 8.107178484458825e-06, |
| "loss": 0.0599, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9649122807017544, |
| "grad_norm": 1.450872778892517, |
| "learning_rate": 7.734740790612137e-06, |
| "loss": 0.0568, |
| "step": 55 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 171, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.8031366314655744e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
