| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4, |
| "grad_norm": 1.50161874294281, |
| "learning_rate": 3.6e-05, |
| "loss": 3.9829, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 1.897646188735962, |
| "learning_rate": 7.6e-05, |
| "loss": 2.5299, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.8085771799087524, |
| "learning_rate": 0.000116, |
| "loss": 0.8638, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.7201354503631592, |
| "learning_rate": 0.00015600000000000002, |
| "loss": 0.4168, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.4432106614112854, |
| "learning_rate": 0.000196, |
| "loss": 0.3878, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.6234836578369141, |
| "learning_rate": 0.00012800000000000002, |
| "loss": 0.2927, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.530001699924469, |
| "learning_rate": 4.8e-05, |
| "loss": 0.2993, |
| "step": 70 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 75, |
| "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": 1.054510864662528e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
