| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.025, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0025, |
| "grad_norm": 7.581125259399414, |
| "learning_rate": 1.6e-07, |
| "loss": 86.44205322265626, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.005, |
| "grad_norm": 870.7899169921875, |
| "learning_rate": 3.6e-07, |
| "loss": 305.9718505859375, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.005, |
| "eval_accuracy": 0.029019607843137254, |
| "eval_loss": 68.04701232910156, |
| "eval_runtime": 35.4394, |
| "eval_samples_per_second": 14.109, |
| "eval_steps_per_second": 1.778, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0075, |
| "grad_norm": 225.20162963867188, |
| "learning_rate": 5.6e-07, |
| "loss": 179.27216796875, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 79.13408660888672, |
| "learning_rate": 7.599999999999999e-07, |
| "loss": 130.82646484375, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.01, |
| "eval_accuracy": 0.02961176470588235, |
| "eval_loss": 31.59725570678711, |
| "eval_runtime": 36.9264, |
| "eval_samples_per_second": 13.54, |
| "eval_steps_per_second": 1.706, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0125, |
| "grad_norm": 72.2133560180664, |
| "learning_rate": 9.6e-07, |
| "loss": 124.6850830078125, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.015, |
| "grad_norm": 94.8714828491211, |
| "learning_rate": 1.16e-06, |
| "loss": 123.9353515625, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.015, |
| "eval_accuracy": 0.04030196078431372, |
| "eval_loss": 30.649425506591797, |
| "eval_runtime": 38.2598, |
| "eval_samples_per_second": 13.069, |
| "eval_steps_per_second": 1.647, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0175, |
| "grad_norm": 54.928829193115234, |
| "learning_rate": 1.3600000000000001e-06, |
| "loss": 125.992138671875, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 70.58757019042969, |
| "learning_rate": 1.5599999999999999e-06, |
| "loss": 120.77716064453125, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.02, |
| "eval_accuracy": 0.04015686274509804, |
| "eval_loss": 29.560930252075195, |
| "eval_runtime": 37.9793, |
| "eval_samples_per_second": 13.165, |
| "eval_steps_per_second": 1.659, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0225, |
| "grad_norm": 81.62490844726562, |
| "learning_rate": 1.7599999999999999e-06, |
| "loss": 121.851220703125, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 65.93287658691406, |
| "learning_rate": 1.96e-06, |
| "loss": 120.95302734375, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.025, |
| "eval_accuracy": 0.04131764705882353, |
| "eval_loss": 28.05109977722168, |
| "eval_runtime": 38.147, |
| "eval_samples_per_second": 13.107, |
| "eval_steps_per_second": 1.652, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 2000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 50, |
| "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": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
