| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.0, |
| "eval_steps": 500, |
| "global_step": 9, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 17.33441162109375, |
| "learning_rate": 0.0, |
| "loss": 2.4771, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.40109243988990784, |
| "eval_runtime": 0.2966, |
| "eval_samples_per_second": 84.299, |
| "eval_steps_per_second": 3.372, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 17.471435546875, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 2.5696, |
| "step": 2 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.3977726995944977, |
| "eval_runtime": 0.3347, |
| "eval_samples_per_second": 74.701, |
| "eval_steps_per_second": 2.988, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 16.502605438232422, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 2.4096, |
| "step": 3 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.3917332589626312, |
| "eval_runtime": 0.3382, |
| "eval_samples_per_second": 73.931, |
| "eval_steps_per_second": 2.957, |
| "step": 3 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 15.583235740661621, |
| "learning_rate": 1.5e-06, |
| "loss": 2.4025, |
| "step": 4 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.38322871923446655, |
| "eval_runtime": 0.3277, |
| "eval_samples_per_second": 76.279, |
| "eval_steps_per_second": 3.051, |
| "step": 4 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 15.021787643432617, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 2.2429, |
| "step": 5 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.37303000688552856, |
| "eval_runtime": 0.3473, |
| "eval_samples_per_second": 71.987, |
| "eval_steps_per_second": 2.879, |
| "step": 5 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 14.483270645141602, |
| "learning_rate": 2.5e-06, |
| "loss": 2.1532, |
| "step": 6 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.3615022897720337, |
| "eval_runtime": 0.3447, |
| "eval_samples_per_second": 72.53, |
| "eval_steps_per_second": 2.901, |
| "step": 6 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 13.854901313781738, |
| "learning_rate": 3e-06, |
| "loss": 2.0347, |
| "step": 7 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.3498750925064087, |
| "eval_runtime": 0.3575, |
| "eval_samples_per_second": 69.926, |
| "eval_steps_per_second": 2.797, |
| "step": 7 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 13.282709121704102, |
| "learning_rate": 3.5000000000000004e-06, |
| "loss": 1.8817, |
| "step": 8 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.33841240406036377, |
| "eval_runtime": 0.3574, |
| "eval_samples_per_second": 69.957, |
| "eval_steps_per_second": 2.798, |
| "step": 8 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 12.319931983947754, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.7143, |
| "step": 9 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.3276784420013428, |
| "eval_runtime": 0.3673, |
| "eval_samples_per_second": 68.066, |
| "eval_steps_per_second": 2.723, |
| "step": 9 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 0.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
