| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.03469210754553339, |
| "eval_steps": 3, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.003469210754553339, |
| "grad_norm": 7.699210166931152, |
| "learning_rate": 2e-05, |
| "loss": 51.4533, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.006938421509106678, |
| "grad_norm": 15.918562889099121, |
| "learning_rate": 4e-05, |
| "loss": 51.817, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.010407632263660017, |
| "grad_norm": 14.194038391113281, |
| "learning_rate": 6e-05, |
| "loss": 52.3584, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.010407632263660017, |
| "eval_loss": 13.009323120117188, |
| "eval_runtime": 6.9443, |
| "eval_samples_per_second": 17.568, |
| "eval_steps_per_second": 8.784, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.013876843018213356, |
| "grad_norm": 14.6574125289917, |
| "learning_rate": 8e-05, |
| "loss": 52.6486, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.017346053772766695, |
| "grad_norm": 15.214132308959961, |
| "learning_rate": 0.0001, |
| "loss": 51.567, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.020815264527320035, |
| "grad_norm": 17.45503044128418, |
| "learning_rate": 0.00012, |
| "loss": 51.1741, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.020815264527320035, |
| "eval_loss": 12.606266021728516, |
| "eval_runtime": 7.5328, |
| "eval_samples_per_second": 16.196, |
| "eval_steps_per_second": 8.098, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.024284475281873375, |
| "grad_norm": 19.02105712890625, |
| "learning_rate": 0.00014, |
| "loss": 50.1376, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.027753686036426712, |
| "grad_norm": 13.59460735321045, |
| "learning_rate": 0.00016, |
| "loss": 49.2638, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.031222896790980052, |
| "grad_norm": 9.423663139343262, |
| "learning_rate": 0.00018, |
| "loss": 48.7117, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.031222896790980052, |
| "eval_loss": 12.042184829711914, |
| "eval_runtime": 7.0052, |
| "eval_samples_per_second": 17.416, |
| "eval_steps_per_second": 8.708, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03469210754553339, |
| "grad_norm": 3.8764379024505615, |
| "learning_rate": 0.0002, |
| "loss": 48.122, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 381542706708480.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
