| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 2226, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9968553459119497, | |
| "grad_norm": 0.651012659072876, | |
| "learning_rate": 1.7151841868823e-05, | |
| "loss": 0.4255, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.582258064516129, | |
| "eval_loss": 0.21653978526592255, | |
| "eval_runtime": 1.3708, | |
| "eval_samples_per_second": 2261.474, | |
| "eval_steps_per_second": 47.418, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.9937106918238994, | |
| "grad_norm": 0.5428839921951294, | |
| "learning_rate": 1.4303683737646003e-05, | |
| "loss": 0.1801, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8283870967741935, | |
| "eval_loss": 0.10531355440616608, | |
| "eval_runtime": 1.3912, | |
| "eval_samples_per_second": 2228.343, | |
| "eval_steps_per_second": 46.723, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 2.990566037735849, | |
| "grad_norm": 0.4809139668941498, | |
| "learning_rate": 1.1455525606469004e-05, | |
| "loss": 0.1126, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8767741935483871, | |
| "eval_loss": 0.07007700949907303, | |
| "eval_runtime": 1.5865, | |
| "eval_samples_per_second": 1953.985, | |
| "eval_steps_per_second": 40.971, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.9874213836477987, | |
| "grad_norm": 0.44946882128715515, | |
| "learning_rate": 8.607367475292004e-06, | |
| "loss": 0.0855, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8945161290322581, | |
| "eval_loss": 0.05405474826693535, | |
| "eval_runtime": 1.4106, | |
| "eval_samples_per_second": 2197.569, | |
| "eval_steps_per_second": 46.078, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.984276729559748, | |
| "grad_norm": 0.3417286276817322, | |
| "learning_rate": 5.759209344115006e-06, | |
| "loss": 0.0716, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9009677419354839, | |
| "eval_loss": 0.04606756940484047, | |
| "eval_runtime": 1.8032, | |
| "eval_samples_per_second": 1719.19, | |
| "eval_steps_per_second": 36.048, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 5.981132075471698, | |
| "grad_norm": 0.40348735451698303, | |
| "learning_rate": 2.911051212938006e-06, | |
| "loss": 0.0642, | |
| "step": 1902 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9077419354838709, | |
| "eval_loss": 0.04166542738676071, | |
| "eval_runtime": 1.4305, | |
| "eval_samples_per_second": 2167.113, | |
| "eval_steps_per_second": 45.439, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 6.977987421383648, | |
| "grad_norm": 0.2649574875831604, | |
| "learning_rate": 6.289308176100629e-08, | |
| "loss": 0.0608, | |
| "step": 2219 | |
| } | |
| ], | |
| "logging_steps": 317, | |
| "max_steps": 2226, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 1000000000.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 578219881979544.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.29751743436581246, | |
| "num_train_epochs": 7, | |
| "temperature": 7 | |
| } | |
| } | |