| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.960662525879917, |
| "eval_steps": 500, |
| "global_step": 180, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16563146997929606, |
| "grad_norm": 1.1045403480529785, |
| "learning_rate": 5.555555555555556e-05, |
| "loss": 0.7952, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.33126293995859213, |
| "grad_norm": 0.3828948438167572, |
| "learning_rate": 9.996239762521151e-05, |
| "loss": 0.5763, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4968944099378882, |
| "grad_norm": 0.315212219953537, |
| "learning_rate": 9.865224352899119e-05, |
| "loss": 0.5143, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6625258799171843, |
| "grad_norm": 0.28653863072395325, |
| "learning_rate": 9.551814704830734e-05, |
| "loss": 0.4931, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8281573498964804, |
| "grad_norm": 0.26458311080932617, |
| "learning_rate": 9.067760351314838e-05, |
| "loss": 0.4686, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9937888198757764, |
| "grad_norm": 0.25187617540359497, |
| "learning_rate": 8.43120818934367e-05, |
| "loss": 0.474, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.1490683229813665, |
| "grad_norm": 0.25587961077690125, |
| "learning_rate": 7.666022164008457e-05, |
| "loss": 0.4457, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.3146997929606625, |
| "grad_norm": 0.27590256929397583, |
| "learning_rate": 6.800888624023553e-05, |
| "loss": 0.4406, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.4803312629399585, |
| "grad_norm": 0.25824370980262756, |
| "learning_rate": 5.868240888334653e-05, |
| "loss": 0.4363, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.6459627329192545, |
| "grad_norm": 0.24047276377677917, |
| "learning_rate": 4.903043341140879e-05, |
| "loss": 0.4315, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.8115942028985508, |
| "grad_norm": 0.2541721761226654, |
| "learning_rate": 3.941480638852948e-05, |
| "loss": 0.4356, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.9772256728778468, |
| "grad_norm": 0.26237165927886963, |
| "learning_rate": 3.019601169804216e-05, |
| "loss": 0.4263, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.132505175983437, |
| "grad_norm": 0.23833103477954865, |
| "learning_rate": 2.171965622567308e-05, |
| "loss": 0.4202, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.298136645962733, |
| "grad_norm": 0.2733284831047058, |
| "learning_rate": 1.4303513272105057e-05, |
| "loss": 0.4178, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.463768115942029, |
| "grad_norm": 0.2536739110946655, |
| "learning_rate": 8.225609429353187e-06, |
| "loss": 0.4221, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.629399585921325, |
| "grad_norm": 0.22531658411026, |
| "learning_rate": 3.7138015365554833e-06, |
| "loss": 0.4202, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.795031055900621, |
| "grad_norm": 0.23673856258392334, |
| "learning_rate": 9.372344686307655e-07, |
| "loss": 0.4125, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.960662525879917, |
| "grad_norm": 0.2418087124824524, |
| "learning_rate": 0.0, |
| "loss": 0.4152, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.960662525879917, |
| "step": 180, |
| "total_flos": 4.858579275680317e+18, |
| "train_loss": 0.46919142405192055, |
| "train_runtime": 5669.8178, |
| "train_samples_per_second": 6.132, |
| "train_steps_per_second": 0.032 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 180, |
| "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": 4.858579275680317e+18, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
