| { | |
| "best_metric": 1.43010413646698, | |
| "best_model_checkpoint": "clothes_image_detection/checkpoint-4230", | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 4230, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.21566666666666667, | |
| "eval_loss": 2.645193338394165, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 60.5917, | |
| "eval_samples_per_second": 49.512, | |
| "eval_steps_per_second": 6.189, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.38333333333333336, | |
| "eval_loss": 2.5685439109802246, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.8482, | |
| "eval_samples_per_second": 50.127, | |
| "eval_steps_per_second": 6.266, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5196666666666667, | |
| "eval_loss": 2.4840424060821533, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 56.8548, | |
| "eval_samples_per_second": 52.766, | |
| "eval_steps_per_second": 6.596, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 3.546099290780142, | |
| "grad_norm": 1.593246579170227, | |
| "learning_rate": 2.6770334928229665e-06, | |
| "loss": 2.5827, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.594, | |
| "eval_loss": 2.3924148082733154, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.5738, | |
| "eval_samples_per_second": 50.358, | |
| "eval_steps_per_second": 6.295, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.637, | |
| "eval_loss": 2.2984158992767334, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.8179, | |
| "eval_samples_per_second": 50.152, | |
| "eval_steps_per_second": 6.269, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6786666666666666, | |
| "eval_loss": 2.204831123352051, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.5967, | |
| "eval_samples_per_second": 50.338, | |
| "eval_steps_per_second": 6.292, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7026666666666667, | |
| "eval_loss": 2.114955186843872, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 58.0933, | |
| "eval_samples_per_second": 51.641, | |
| "eval_steps_per_second": 6.455, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 7.092198581560283, | |
| "grad_norm": 1.663735032081604, | |
| "learning_rate": 2.318181818181818e-06, | |
| "loss": 2.2373, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7193333333333334, | |
| "eval_loss": 2.0335097312927246, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 58.4613, | |
| "eval_samples_per_second": 51.316, | |
| "eval_steps_per_second": 6.414, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.732, | |
| "eval_loss": 1.9591959714889526, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 60.8155, | |
| "eval_samples_per_second": 49.33, | |
| "eval_steps_per_second": 6.166, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7413333333333333, | |
| "eval_loss": 1.8956468105316162, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 58.6099, | |
| "eval_samples_per_second": 51.186, | |
| "eval_steps_per_second": 6.398, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 10.638297872340425, | |
| "grad_norm": 2.2240982055664062, | |
| "learning_rate": 1.95933014354067e-06, | |
| "loss": 1.9201, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7506666666666667, | |
| "eval_loss": 1.8356391191482544, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 61.3536, | |
| "eval_samples_per_second": 48.897, | |
| "eval_steps_per_second": 6.112, | |
| "step": 1551 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7506666666666667, | |
| "eval_loss": 1.7848457098007202, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.2943, | |
| "eval_samples_per_second": 50.595, | |
| "eval_steps_per_second": 6.324, | |
| "step": 1692 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.764, | |
| "eval_loss": 1.736997365951538, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 58.9962, | |
| "eval_samples_per_second": 50.851, | |
| "eval_steps_per_second": 6.356, | |
| "step": 1833 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7626666666666667, | |
| "eval_loss": 1.6969176530838013, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.8754, | |
| "eval_samples_per_second": 50.104, | |
| "eval_steps_per_second": 6.263, | |
| "step": 1974 | |
| }, | |
| { | |
| "epoch": 14.184397163120567, | |
| "grad_norm": 2.2442896366119385, | |
| "learning_rate": 1.6004784688995215e-06, | |
| "loss": 1.7006, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.768, | |
| "eval_loss": 1.6571820974349976, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 58.7702, | |
| "eval_samples_per_second": 51.046, | |
| "eval_steps_per_second": 6.381, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7653333333333333, | |
| "eval_loss": 1.6255625486373901, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.8291, | |
| "eval_samples_per_second": 50.143, | |
| "eval_steps_per_second": 6.268, | |
| "step": 2256 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.771, | |
| "eval_loss": 1.5948454141616821, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 56.7649, | |
| "eval_samples_per_second": 52.85, | |
| "eval_steps_per_second": 6.606, | |
| "step": 2397 | |
| }, | |
| { | |
| "epoch": 17.73049645390071, | |
| "grad_norm": 2.0100739002227783, | |
| "learning_rate": 1.2416267942583733e-06, | |
| "loss": 1.5525, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7736666666666666, | |
| "eval_loss": 1.5684410333633423, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.7778, | |
| "eval_samples_per_second": 50.186, | |
| "eval_steps_per_second": 6.273, | |
| "step": 2538 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7746666666666666, | |
| "eval_loss": 1.5451995134353638, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 56.7165, | |
| "eval_samples_per_second": 52.895, | |
| "eval_steps_per_second": 6.612, | |
| "step": 2679 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.776, | |
| "eval_loss": 1.5241280794143677, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.6632, | |
| "eval_samples_per_second": 50.282, | |
| "eval_steps_per_second": 6.285, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.778, | |
| "eval_loss": 1.5055561065673828, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 61.0991, | |
| "eval_samples_per_second": 49.101, | |
| "eval_steps_per_second": 6.138, | |
| "step": 2961 | |
| }, | |
| { | |
| "epoch": 21.27659574468085, | |
| "grad_norm": 2.603900194168091, | |
| "learning_rate": 8.827751196172249e-07, | |
| "loss": 1.4511, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7773333333333333, | |
| "eval_loss": 1.4899275302886963, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 60.2357, | |
| "eval_samples_per_second": 49.804, | |
| "eval_steps_per_second": 6.226, | |
| "step": 3102 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.779, | |
| "eval_loss": 1.4755609035491943, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 58.2979, | |
| "eval_samples_per_second": 51.46, | |
| "eval_steps_per_second": 6.432, | |
| "step": 3243 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7796666666666666, | |
| "eval_loss": 1.4629756212234497, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.4982, | |
| "eval_samples_per_second": 50.422, | |
| "eval_steps_per_second": 6.303, | |
| "step": 3384 | |
| }, | |
| { | |
| "epoch": 24.822695035460992, | |
| "grad_norm": 2.867500066757202, | |
| "learning_rate": 5.239234449760765e-07, | |
| "loss": 1.3856, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7803333333333333, | |
| "eval_loss": 1.452785849571228, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 61.5325, | |
| "eval_samples_per_second": 48.755, | |
| "eval_steps_per_second": 6.094, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.783, | |
| "eval_loss": 1.4447195529937744, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 59.5703, | |
| "eval_samples_per_second": 50.361, | |
| "eval_steps_per_second": 6.295, | |
| "step": 3666 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7823333333333333, | |
| "eval_loss": 1.438262701034546, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 60.0356, | |
| "eval_samples_per_second": 49.97, | |
| "eval_steps_per_second": 6.246, | |
| "step": 3807 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.783, | |
| "eval_loss": 1.4334560632705688, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 60.0215, | |
| "eval_samples_per_second": 49.982, | |
| "eval_steps_per_second": 6.248, | |
| "step": 3948 | |
| }, | |
| { | |
| "epoch": 28.368794326241133, | |
| "grad_norm": 3.527007579803467, | |
| "learning_rate": 1.6507177033492823e-07, | |
| "loss": 1.3468, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.784, | |
| "eval_loss": 1.4309223890304565, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 57.775, | |
| "eval_samples_per_second": 51.926, | |
| "eval_steps_per_second": 6.491, | |
| "step": 4089 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7846666666666666, | |
| "eval_loss": 1.43010413646698, | |
| "eval_model_preparation_time": 0.0034, | |
| "eval_runtime": 60.9928, | |
| "eval_samples_per_second": 49.186, | |
| "eval_steps_per_second": 6.148, | |
| "step": 4230 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4230, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.046263750898688e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |