| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.012799180852425445, |
| "eval_steps": 1000, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0012799180852425445, |
| "grad_norm": 1.2002202272415161, |
| "learning_rate": 1.4404609475032012e-07, |
| "loss": 0.714, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002559836170485089, |
| "grad_norm": 1.0710716247558594, |
| "learning_rate": 3.040973111395647e-07, |
| "loss": 0.7181, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0038397542557276334, |
| "grad_norm": 1.0631524324417114, |
| "learning_rate": 4.641485275288093e-07, |
| "loss": 0.7114, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.005119672340970178, |
| "grad_norm": 1.1470946073532104, |
| "learning_rate": 6.241997439180538e-07, |
| "loss": 0.7083, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.006399590426212722, |
| "grad_norm": 1.1680080890655518, |
| "learning_rate": 7.842509603072984e-07, |
| "loss": 0.7109, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.007679508511455267, |
| "grad_norm": 0.6832358241081238, |
| "learning_rate": 9.44302176696543e-07, |
| "loss": 0.7131, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.008959426596697812, |
| "grad_norm": 1.8029249906539917, |
| "learning_rate": 1.1043533930857875e-06, |
| "loss": 0.7092, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.010239344681940356, |
| "grad_norm": 1.795204758644104, |
| "learning_rate": 1.264404609475032e-06, |
| "loss": 0.7063, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.011519262767182901, |
| "grad_norm": 1.2713547945022583, |
| "learning_rate": 1.4244558258642767e-06, |
| "loss": 0.7126, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.012799180852425445, |
| "grad_norm": 1.2709708213806152, |
| "learning_rate": 1.5845070422535212e-06, |
| "loss": 0.7069, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 31252, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1683910754304000.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
