| { | |
| "best_metric": 2.4194676876068115, | |
| "best_model_checkpoint": "cat_breed_image_detection/checkpoint-2541", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2541, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19677292404565133, | |
| "grad_norm": 3.4110498428344727, | |
| "learning_rate": 2.458048976314733e-07, | |
| "loss": 2.4155, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39354584809130266, | |
| "grad_norm": 3.347660779953003, | |
| "learning_rate": 1.855881172219992e-07, | |
| "loss": 2.4064, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5903187721369539, | |
| "grad_norm": 2.8864846229553223, | |
| "learning_rate": 1.2537133681252508e-07, | |
| "loss": 2.4031, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7870916961826053, | |
| "grad_norm": 3.3635642528533936, | |
| "learning_rate": 6.515455640305099e-08, | |
| "loss": 2.3925, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9838646202282566, | |
| "grad_norm": 2.585705041885376, | |
| "learning_rate": 4.937775993576876e-09, | |
| "loss": 2.3845, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.43109684086211986, | |
| "eval_loss": 2.4194676876068115, | |
| "eval_runtime": 1203.7518, | |
| "eval_samples_per_second": 90.038, | |
| "eval_steps_per_second": 2.814, | |
| "step": 2541 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2541, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.2603531789715636e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |