| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 120.0, |
| "eval_steps": 0, |
| "global_step": 120, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 7.0, |
| "grad_norm": 1.4509721466659486, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": -0.0208, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 2.0680431110081017, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": -0.0417, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 2.5411941917939216, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -0.0893, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 2.6622024938993234, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -0.1585, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 2.8306305841602386, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -0.2474, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 2.8999630954661053, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -0.346, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 3.5141387061038296, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -0.47, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 5.606981099292785, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -0.5925, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 6.490749182489264, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -0.7737, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 6.885141160296578, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -0.9615, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 6.349110578888062, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -1.1828, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 6.247667889813732, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -1.3452, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 6.860309243873525, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -1.5043, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 7.4199586479904855, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -1.6657, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 10.042397238569004, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -1.8363, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 11.340757841409685, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -2.0132, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 12.654648200102347, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -2.1925, |
| "step": 119 |
| } |
| ], |
| "logging_steps": 7, |
| "max_steps": 150, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 150, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
