| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 111, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2702702702702703, |
| "grad_norm": 1632407.625, |
| "learning_rate": 2.976784795504466e-05, |
| "loss": 0.9766, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5405405405405406, |
| "grad_norm": 1878771.875, |
| "learning_rate": 2.8375080559518636e-05, |
| "loss": 0.9078, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8108108108108109, |
| "grad_norm": 1555931.875, |
| "learning_rate": 2.5837574131992033e-05, |
| "loss": 0.896, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0810810810810811, |
| "grad_norm": 1043145.8125, |
| "learning_rate": 2.2372507375697017e-05, |
| "loss": 0.8057, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.3513513513513513, |
| "grad_norm": 1184939.875, |
| "learning_rate": 1.8276446516666194e-05, |
| "loss": 0.786, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.6216216216216215, |
| "grad_norm": 1340799.0, |
| "learning_rate": 1.3899962956837443e-05, |
| "loss": 0.8057, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.8918918918918919, |
| "grad_norm": 1453077.125, |
| "learning_rate": 9.617628761892964e-06, |
| "loss": 0.7905, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.1621621621621623, |
| "grad_norm": 1050501.375, |
| "learning_rate": 5.795957993502093e-06, |
| "loss": 0.7805, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.4324324324324325, |
| "grad_norm": 1098550.75, |
| "learning_rate": 2.7620377055756426e-06, |
| "loss": 0.7298, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.7027027027027026, |
| "grad_norm": 1329552.75, |
| "learning_rate": 7.755333975558704e-07, |
| "loss": 0.7225, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.972972972972973, |
| "grad_norm": 978739.75, |
| "learning_rate": 6.464906595023967e-09, |
| "loss": 0.7825, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 111, |
| "total_flos": 165287200555008.0, |
| "train_loss": 0.816560663618483, |
| "train_runtime": 12.3577, |
| "train_samples_per_second": 285.49, |
| "train_steps_per_second": 8.982 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 111, |
| "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": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 165287200555008.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
