| { | |
| "best_metric": 0.9552567237163814, | |
| "best_model_checkpoint": "ky-finetuned-skindiseasefinal/checkpoint-2870", | |
| "epoch": 9.997393570807994, | |
| "eval_steps": 500, | |
| "global_step": 2870, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9973935708079931, | |
| "grad_norm": 157.15570068359375, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4949, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.9973935708079931, | |
| "eval_accuracy": 0.7770171149144254, | |
| "eval_loss": 0.6911987662315369, | |
| "eval_runtime": 57.7326, | |
| "eval_samples_per_second": 70.844, | |
| "eval_steps_per_second": 2.217, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.997393570807993, | |
| "grad_norm": 102.32886505126953, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.7268, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.997393570807993, | |
| "eval_accuracy": 0.8775061124694377, | |
| "eval_loss": 0.3927457332611084, | |
| "eval_runtime": 57.5408, | |
| "eval_samples_per_second": 71.08, | |
| "eval_steps_per_second": 2.225, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 2.997393570807993, | |
| "grad_norm": 66.3480224609375, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.5179, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 2.997393570807993, | |
| "eval_accuracy": 0.8982885085574572, | |
| "eval_loss": 0.3185364305973053, | |
| "eval_runtime": 57.3788, | |
| "eval_samples_per_second": 71.281, | |
| "eval_steps_per_second": 2.231, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 3.997393570807993, | |
| "grad_norm": 62.946006774902344, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4193, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 3.997393570807993, | |
| "eval_accuracy": 0.9190709046454768, | |
| "eval_loss": 0.24387270212173462, | |
| "eval_runtime": 57.2167, | |
| "eval_samples_per_second": 71.483, | |
| "eval_steps_per_second": 2.237, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 4.9973935708079935, | |
| "grad_norm": 67.98648834228516, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3576, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 4.9973935708079935, | |
| "eval_accuracy": 0.9300733496332518, | |
| "eval_loss": 0.210697740316391, | |
| "eval_runtime": 57.3323, | |
| "eval_samples_per_second": 71.339, | |
| "eval_steps_per_second": 2.233, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 5.9973935708079935, | |
| "grad_norm": 47.05820083618164, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.3015, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 5.9973935708079935, | |
| "eval_accuracy": 0.9386308068459658, | |
| "eval_loss": 0.1821407824754715, | |
| "eval_runtime": 57.2098, | |
| "eval_samples_per_second": 71.491, | |
| "eval_steps_per_second": 2.237, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 6.9973935708079935, | |
| "grad_norm": 60.36362838745117, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.2648, | |
| "step": 2009 | |
| }, | |
| { | |
| "epoch": 6.9973935708079935, | |
| "eval_accuracy": 0.9410757946210269, | |
| "eval_loss": 0.16846108436584473, | |
| "eval_runtime": 57.4289, | |
| "eval_samples_per_second": 71.218, | |
| "eval_steps_per_second": 2.229, | |
| "step": 2009 | |
| }, | |
| { | |
| "epoch": 7.9973935708079935, | |
| "grad_norm": 49.73932647705078, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.2228, | |
| "step": 2296 | |
| }, | |
| { | |
| "epoch": 7.9973935708079935, | |
| "eval_accuracy": 0.9486552567237164, | |
| "eval_loss": 0.1497160643339157, | |
| "eval_runtime": 57.6175, | |
| "eval_samples_per_second": 70.985, | |
| "eval_steps_per_second": 2.222, | |
| "step": 2296 | |
| }, | |
| { | |
| "epoch": 8.997393570807994, | |
| "grad_norm": 32.87363052368164, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.1946, | |
| "step": 2583 | |
| }, | |
| { | |
| "epoch": 8.997393570807994, | |
| "eval_accuracy": 0.9493887530562347, | |
| "eval_loss": 0.140727236866951, | |
| "eval_runtime": 57.5534, | |
| "eval_samples_per_second": 71.064, | |
| "eval_steps_per_second": 2.224, | |
| "step": 2583 | |
| }, | |
| { | |
| "epoch": 9.997393570807994, | |
| "grad_norm": 49.652774810791016, | |
| "learning_rate": 0.0, | |
| "loss": 0.1625, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 9.997393570807994, | |
| "eval_accuracy": 0.9552567237163814, | |
| "eval_loss": 0.13006699085235596, | |
| "eval_runtime": 57.869, | |
| "eval_samples_per_second": 70.677, | |
| "eval_steps_per_second": 2.212, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 9.997393570807994, | |
| "step": 2870, | |
| "total_flos": 3.760030331457189e+19, | |
| "train_loss": 0.4662683892333134, | |
| "train_runtime": 8157.4316, | |
| "train_samples_per_second": 45.124, | |
| "train_steps_per_second": 0.352 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2870, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.760030331457189e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |