| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 2000, |
| "global_step": 8461, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00011818933932159319, |
| "grad_norm": 7.239190101623535, |
| "learning_rate": 0.0, |
| "loss": 3.9597, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.23637867864318637, |
| "grad_norm": 4.569056034088135, |
| "learning_rate": 7.088652482269504e-06, |
| "loss": 3.3526, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.23637867864318637, |
| "eval_cosine_accuracy": 0.9351803064346313, |
| "eval_loss": 1.1521742343902588, |
| "eval_runtime": 22.8749, |
| "eval_samples_per_second": 413.423, |
| "eval_steps_per_second": 1.617, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.47275735728637275, |
| "grad_norm": 4.866804599761963, |
| "learning_rate": 1.4180851063829787e-05, |
| "loss": 2.6297, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.47275735728637275, |
| "eval_cosine_accuracy": 0.9370836615562439, |
| "eval_loss": 1.1368498802185059, |
| "eval_runtime": 24.2219, |
| "eval_samples_per_second": 390.433, |
| "eval_steps_per_second": 1.528, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.7091360359295592, |
| "grad_norm": 4.78344202041626, |
| "learning_rate": 2.126950354609929e-05, |
| "loss": 2.27, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.7091360359295592, |
| "eval_cosine_accuracy": 0.9424764513969421, |
| "eval_loss": 1.088667392730713, |
| "eval_runtime": 23.9037, |
| "eval_samples_per_second": 395.63, |
| "eval_steps_per_second": 1.548, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.9455147145727455, |
| "grad_norm": 4.2486572265625, |
| "learning_rate": 2.8358156028368792e-05, |
| "loss": 2.0264, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.9455147145727455, |
| "eval_cosine_accuracy": 0.9423707127571106, |
| "eval_loss": 1.0786563158035278, |
| "eval_runtime": 23.6661, |
| "eval_samples_per_second": 399.601, |
| "eval_steps_per_second": 1.563, |
| "step": 8000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 33844, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
