| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.075, |
| "eval_steps": 500, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005, |
| "grad_norm": 4.4095964431762695, |
| "learning_rate": 4.9800000000000004e-05, |
| "loss": 5.4329, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.658348798751831, |
| "learning_rate": 4.9550000000000005e-05, |
| "loss": 4.6734, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.015, |
| "grad_norm": 3.4242470264434814, |
| "learning_rate": 4.93e-05, |
| "loss": 4.8327, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 4.363213539123535, |
| "learning_rate": 4.905e-05, |
| "loss": 4.4238, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 2.531619071960449, |
| "learning_rate": 4.88e-05, |
| "loss": 3.9284, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 4.686695098876953, |
| "learning_rate": 4.855e-05, |
| "loss": 4.6794, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.035, |
| "grad_norm": 4.860099792480469, |
| "learning_rate": 4.83e-05, |
| "loss": 5.0624, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 8.296855926513672, |
| "learning_rate": 4.805e-05, |
| "loss": 4.8011, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.045, |
| "grad_norm": 4.80878210067749, |
| "learning_rate": 4.78e-05, |
| "loss": 5.495, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 4.766687393188477, |
| "learning_rate": 4.755e-05, |
| "loss": 4.6778, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.055, |
| "grad_norm": 2.7137186527252197, |
| "learning_rate": 4.73e-05, |
| "loss": 4.5044, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 9.891243934631348, |
| "learning_rate": 4.705e-05, |
| "loss": 4.4744, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.065, |
| "grad_norm": 3.6516237258911133, |
| "learning_rate": 4.6800000000000006e-05, |
| "loss": 4.6576, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 5.687813758850098, |
| "learning_rate": 4.655000000000001e-05, |
| "loss": 5.1204, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 4.273693561553955, |
| "learning_rate": 4.630000000000001e-05, |
| "loss": 5.361, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 25503046041600.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
