| { | |
| "best_metric": 0.8303472995758057, | |
| "best_model_checkpoint": "face_emotions_image_detection/checkpoint-6800", | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 6800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5581299131154324, | |
| "eval_loss": 1.5780813694000244, | |
| "eval_runtime": 34.4094, | |
| "eval_samples_per_second": 70.242, | |
| "eval_steps_per_second": 2.209, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.333333333333333e-07, | |
| "loss": 1.5754, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6235002068680182, | |
| "eval_loss": 1.4531924724578857, | |
| "eval_runtime": 33.5063, | |
| "eval_samples_per_second": 72.136, | |
| "eval_steps_per_second": 2.268, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 8.592592592592592e-07, | |
| "loss": 1.3718, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6607364501448076, | |
| "eval_loss": 1.335525631904602, | |
| "eval_runtime": 33.5199, | |
| "eval_samples_per_second": 72.107, | |
| "eval_steps_per_second": 2.267, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.676458419528341, | |
| "eval_loss": 1.2385190725326538, | |
| "eval_runtime": 33.0393, | |
| "eval_samples_per_second": 73.155, | |
| "eval_steps_per_second": 2.3, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 7.851851851851852e-07, | |
| "loss": 1.2055, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6830781961108813, | |
| "eval_loss": 1.1576205492019653, | |
| "eval_runtime": 34.4609, | |
| "eval_samples_per_second": 70.137, | |
| "eval_steps_per_second": 2.205, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 7.111111111111111e-07, | |
| "loss": 1.0902, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6963177492759619, | |
| "eval_loss": 1.0941061973571777, | |
| "eval_runtime": 33.7137, | |
| "eval_samples_per_second": 71.692, | |
| "eval_steps_per_second": 2.254, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7136946628051303, | |
| "eval_loss": 1.0437400341033936, | |
| "eval_runtime": 34.1074, | |
| "eval_samples_per_second": 70.864, | |
| "eval_steps_per_second": 2.228, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 6.37037037037037e-07, | |
| "loss": 0.9981, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7194869673148532, | |
| "eval_loss": 0.999989926815033, | |
| "eval_runtime": 34.4809, | |
| "eval_samples_per_second": 70.097, | |
| "eval_steps_per_second": 2.204, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 5.62962962962963e-07, | |
| "loss": 0.9352, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7273479520066197, | |
| "eval_loss": 0.9669674634933472, | |
| "eval_runtime": 34.4622, | |
| "eval_samples_per_second": 70.135, | |
| "eval_steps_per_second": 2.205, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7290028961522549, | |
| "eval_loss": 0.9405105113983154, | |
| "eval_runtime": 33.8763, | |
| "eval_samples_per_second": 71.348, | |
| "eval_steps_per_second": 2.243, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 4.888888888888889e-07, | |
| "loss": 0.8851, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7343814646255689, | |
| "eval_loss": 0.9163816571235657, | |
| "eval_runtime": 34.0893, | |
| "eval_samples_per_second": 70.902, | |
| "eval_steps_per_second": 2.229, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 4.1481481481481476e-07, | |
| "loss": 0.8465, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7347952006619777, | |
| "eval_loss": 0.8966172933578491, | |
| "eval_runtime": 34.3056, | |
| "eval_samples_per_second": 70.455, | |
| "eval_steps_per_second": 2.215, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7422424493173355, | |
| "eval_loss": 0.8790085911750793, | |
| "eval_runtime": 34.0958, | |
| "eval_samples_per_second": 70.888, | |
| "eval_steps_per_second": 2.229, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 3.407407407407407e-07, | |
| "loss": 0.8165, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7480347538270583, | |
| "eval_loss": 0.8644098043441772, | |
| "eval_runtime": 34.0216, | |
| "eval_samples_per_second": 71.043, | |
| "eval_steps_per_second": 2.234, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 2.6666666666666667e-07, | |
| "loss": 0.7954, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.750517170045511, | |
| "eval_loss": 0.8529735803604126, | |
| "eval_runtime": 34.2111, | |
| "eval_samples_per_second": 70.649, | |
| "eval_steps_per_second": 2.221, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7509309060819197, | |
| "eval_loss": 0.8457837104797363, | |
| "eval_runtime": 33.6533, | |
| "eval_samples_per_second": 71.821, | |
| "eval_steps_per_second": 2.258, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 1.9259259259259257e-07, | |
| "loss": 0.7811, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7534133223003724, | |
| "eval_loss": 0.8384882211685181, | |
| "eval_runtime": 33.6326, | |
| "eval_samples_per_second": 71.865, | |
| "eval_steps_per_second": 2.26, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 1.1851851851851851e-07, | |
| "loss": 0.7673, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7550682664460074, | |
| "eval_loss": 0.8335217237472534, | |
| "eval_runtime": 33.2974, | |
| "eval_samples_per_second": 72.588, | |
| "eval_steps_per_second": 2.282, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7529995862639636, | |
| "eval_loss": 0.8314878940582275, | |
| "eval_runtime": 33.8017, | |
| "eval_samples_per_second": 71.505, | |
| "eval_steps_per_second": 2.248, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 19.12, | |
| "learning_rate": 4.444444444444444e-08, | |
| "loss": 0.7594, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7538270583367811, | |
| "eval_loss": 0.8303472995758057, | |
| "eval_runtime": 34.3877, | |
| "eval_samples_per_second": 70.287, | |
| "eval_steps_per_second": 2.21, | |
| "step": 6800 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 3.3702474498545664e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |