| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 72, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.43243243243243246, |
| "grad_norm": 2.298657178878784, |
| "learning_rate": 9e-05, |
| "loss": 2.9776512145996095, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8648648648648649, |
| "grad_norm": 2.332467794418335, |
| "learning_rate": 0.00019, |
| "loss": 2.224751853942871, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.2594594594594595, |
| "grad_norm": 10.535177230834961, |
| "learning_rate": 0.00018557812723014476, |
| "loss": 1.2766617774963378, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.691891891891892, |
| "grad_norm": 2.650754451751709, |
| "learning_rate": 0.0001410412805452757, |
| "loss": 0.8857287406921387, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0864864864864865, |
| "grad_norm": 1.1251181364059448, |
| "learning_rate": 8.197449621860943e-05, |
| "loss": 0.7955132484436035, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.518918918918919, |
| "grad_norm": 1.2823196649551392, |
| "learning_rate": 2.9289321881345254e-05, |
| "loss": 0.7014316558837891, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.9513513513513514, |
| "grad_norm": 1.0464814901351929, |
| "learning_rate": 1.6380093052856483e-06, |
| "loss": 0.6683882713317871, |
| "step": 70 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 72, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.425840264544256e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
