| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0989010989010989, |
| "eval_steps": 500, |
| "global_step": 15, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 1.092259407043457, |
| "learning_rate": 0.0, |
| "loss": 1.0581, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.0709208250045776, |
| "learning_rate": 9.56e-05, |
| "loss": 1.1072, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 0.958633303642273, |
| "learning_rate": 0.0001912, |
| "loss": 0.9974, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.1406344175338745, |
| "learning_rate": 0.0002868, |
| "loss": 1.0239, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.6300336122512817, |
| "learning_rate": 0.0003824, |
| "loss": 0.864, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.6665506958961487, |
| "learning_rate": 0.000478, |
| "loss": 0.9466, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.5092409253120422, |
| "learning_rate": 0.00047694013303769406, |
| "loss": 0.9307, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.4416404068470001, |
| "learning_rate": 0.00047588026607538804, |
| "loss": 0.8977, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.2995733320713043, |
| "learning_rate": 0.0004748203991130821, |
| "loss": 0.8339, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.3041072487831116, |
| "learning_rate": 0.00047376053215077607, |
| "loss": 0.8087, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.37241628766059875, |
| "learning_rate": 0.00047270066518847006, |
| "loss": 0.771, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.39393821358680725, |
| "learning_rate": 0.0004716407982261641, |
| "loss": 0.8849, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.3837544918060303, |
| "learning_rate": 0.00047058093126385814, |
| "loss": 0.8491, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.49497556686401367, |
| "learning_rate": 0.0004695210643015521, |
| "loss": 0.8303, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.5117122530937195, |
| "learning_rate": 0.00046846119733924617, |
| "loss": 0.8409, |
| "step": 15 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6863586493446144.0, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
