| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 94, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10638297872340426, |
| "grad_norm": 6.875, |
| "learning_rate": 8.8845e-06, |
| "loss": 2.3619, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2127659574468085, |
| "grad_norm": 4.96875, |
| "learning_rate": 1.9990125e-05, |
| "loss": 2.1355, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3191489361702128, |
| "grad_norm": 4.75, |
| "learning_rate": 3.1095750000000005e-05, |
| "loss": 1.9609, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.425531914893617, |
| "grad_norm": 3.9375, |
| "learning_rate": 4.2201375e-05, |
| "loss": 1.8411, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5319148936170213, |
| "grad_norm": 3.890625, |
| "learning_rate": 5.3307e-05, |
| "loss": 1.7944, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.6382978723404256, |
| "grad_norm": 3.9375, |
| "learning_rate": 6.4412625e-05, |
| "loss": 1.7092, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7446808510638298, |
| "grad_norm": 3.703125, |
| "learning_rate": 7.551825e-05, |
| "loss": 1.679, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.851063829787234, |
| "grad_norm": 3.75, |
| "learning_rate": 7.753475804658967e-05, |
| "loss": 1.65, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9574468085106383, |
| "grad_norm": 3.28125, |
| "learning_rate": 7.670842209011892e-05, |
| "loss": 1.6324, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.5718683004379272, |
| "eval_runtime": 5.0419, |
| "eval_samples_per_second": 39.668, |
| "eval_steps_per_second": 39.668, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.0638297872340425, |
| "grad_norm": 3.5625, |
| "learning_rate": 7.526567749442305e-05, |
| "loss": 1.4548, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.1702127659574468, |
| "grad_norm": 3.203125, |
| "learning_rate": 7.323814868052365e-05, |
| "loss": 1.3195, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.2765957446808511, |
| "grad_norm": 3.515625, |
| "learning_rate": 7.067027832041926e-05, |
| "loss": 1.3081, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.3829787234042552, |
| "grad_norm": 3.28125, |
| "learning_rate": 6.761835317036523e-05, |
| "loss": 1.3275, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.4893617021276595, |
| "grad_norm": 3.140625, |
| "learning_rate": 6.414927028626436e-05, |
| "loss": 1.2813, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.5957446808510638, |
| "grad_norm": 3.265625, |
| "learning_rate": 6.033907066526388e-05, |
| "loss": 1.2849, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.702127659574468, |
| "grad_norm": 2.859375, |
| "learning_rate": 5.627127245558645e-05, |
| "loss": 1.2558, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.8085106382978724, |
| "grad_norm": 2.90625, |
| "learning_rate": 5.203504027001068e-05, |
| "loss": 1.2672, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.9148936170212765, |
| "grad_norm": 2.875, |
| "learning_rate": 4.7723230730964036e-05, |
| "loss": 1.2442, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.4226864576339722, |
| "eval_runtime": 4.9284, |
| "eval_samples_per_second": 40.581, |
| "eval_steps_per_second": 40.581, |
| "step": 94 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 141, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.124053825880064e+17, |
| "train_batch_size": 100, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
