| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 50.0, |
| "eval_steps": 10, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 5.0, |
| "grad_norm": 24.885208129882812, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 5.3257, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 4.660707473754883, |
| "eval_runtime": 2.2119, |
| "eval_samples_per_second": 7.233, |
| "eval_steps_per_second": 0.904, |
| "step": 10 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 25.837661743164062, |
| "learning_rate": 2.4e-05, |
| "loss": 3.7863, |
| "step": 20 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 2.922464609146118, |
| "eval_runtime": 2.1674, |
| "eval_samples_per_second": 7.382, |
| "eval_steps_per_second": 0.923, |
| "step": 20 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 18.91794204711914, |
| "learning_rate": 2.1e-05, |
| "loss": 2.1825, |
| "step": 30 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 1.5030847787857056, |
| "eval_runtime": 2.1465, |
| "eval_samples_per_second": 7.454, |
| "eval_steps_per_second": 0.932, |
| "step": 30 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 8.712701797485352, |
| "learning_rate": 1.8e-05, |
| "loss": 1.1117, |
| "step": 40 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.7606693506240845, |
| "eval_runtime": 2.159, |
| "eval_samples_per_second": 7.411, |
| "eval_steps_per_second": 0.926, |
| "step": 40 |
| }, |
| { |
| "epoch": 25.0, |
| "grad_norm": 4.18818473815918, |
| "learning_rate": 1.5e-05, |
| "loss": 0.6219, |
| "step": 50 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_loss": 0.4770106077194214, |
| "eval_runtime": 2.1468, |
| "eval_samples_per_second": 7.453, |
| "eval_steps_per_second": 0.932, |
| "step": 50 |
| }, |
| { |
| "epoch": 30.0, |
| "grad_norm": 1.5589721202850342, |
| "learning_rate": 1.2e-05, |
| "loss": 0.4492, |
| "step": 60 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_loss": 0.39624011516571045, |
| "eval_runtime": 2.1523, |
| "eval_samples_per_second": 7.434, |
| "eval_steps_per_second": 0.929, |
| "step": 60 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 0.649561882019043, |
| "learning_rate": 9e-06, |
| "loss": 0.3989, |
| "step": 70 |
| }, |
| { |
| "epoch": 35.0, |
| "eval_loss": 0.37899789214134216, |
| "eval_runtime": 2.1565, |
| "eval_samples_per_second": 7.419, |
| "eval_steps_per_second": 0.927, |
| "step": 70 |
| }, |
| { |
| "epoch": 40.0, |
| "grad_norm": 0.5878287553787231, |
| "learning_rate": 6e-06, |
| "loss": 0.3854, |
| "step": 80 |
| }, |
| { |
| "epoch": 40.0, |
| "eval_loss": 0.37336358428001404, |
| "eval_runtime": 2.1545, |
| "eval_samples_per_second": 7.426, |
| "eval_steps_per_second": 0.928, |
| "step": 80 |
| }, |
| { |
| "epoch": 45.0, |
| "grad_norm": 0.33563297986984253, |
| "learning_rate": 3e-06, |
| "loss": 0.3811, |
| "step": 90 |
| }, |
| { |
| "epoch": 45.0, |
| "eval_loss": 0.3726198375225067, |
| "eval_runtime": 2.141, |
| "eval_samples_per_second": 7.473, |
| "eval_steps_per_second": 0.934, |
| "step": 90 |
| }, |
| { |
| "epoch": 50.0, |
| "grad_norm": 0.4097728133201599, |
| "learning_rate": 0.0, |
| "loss": 0.3792, |
| "step": 100 |
| }, |
| { |
| "epoch": 50.0, |
| "eval_loss": 0.37181615829467773, |
| "eval_runtime": 2.1515, |
| "eval_samples_per_second": 7.437, |
| "eval_steps_per_second": 0.93, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5186039668736e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
