| { | |
| "best_metric": 3.7954559326171875, | |
| "best_model_checkpoint": "cat_breed_image_detection/checkpoint-3811", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3811, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.641052911459718e-07, | |
| "loss": 3.8338, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.2422228130816273e-07, | |
| "loss": 3.8244, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.8433927147035363e-07, | |
| "loss": 3.8144, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.444562616325445e-07, | |
| "loss": 3.804, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.0457325179473543e-07, | |
| "loss": 3.7968, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.469024195692635e-08, | |
| "loss": 3.7917, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.4807232119117254e-08, | |
| "loss": 3.7878, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.09794803661056982, | |
| "eval_loss": 3.7954559326171875, | |
| "eval_runtime": 304.3948, | |
| "eval_samples_per_second": 89.016, | |
| "eval_steps_per_second": 2.783, | |
| "step": 3811 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3811, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.8905297684573454e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |