| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 125, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4, |
| "grad_norm": 9.0625, |
| "learning_rate": 4.64e-05, |
| "loss": 2.3787, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 4.96875, |
| "learning_rate": 4.24e-05, |
| "loss": 1.6716, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 4.78125, |
| "learning_rate": 3.8400000000000005e-05, |
| "loss": 1.61, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 5.28125, |
| "learning_rate": 3.4399999999999996e-05, |
| "loss": 1.5436, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 4.28125, |
| "learning_rate": 3.04e-05, |
| "loss": 1.501, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 5.21875, |
| "learning_rate": 2.64e-05, |
| "loss": 1.2763, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 11.9375, |
| "learning_rate": 2.2400000000000002e-05, |
| "loss": 1.2895, |
| "step": 70 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 8.0625, |
| "learning_rate": 1.84e-05, |
| "loss": 1.2817, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 5.46875, |
| "learning_rate": 1.44e-05, |
| "loss": 1.0921, |
| "step": 90 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 9.9375, |
| "learning_rate": 1.04e-05, |
| "loss": 1.1077, |
| "step": 100 |
| }, |
| { |
| "epoch": 4.4, |
| "grad_norm": 9.375, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 1.0527, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 9.625, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.8909, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 125, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 267992088576000.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
