| { | |
| "best_metric": 0.6467268466949463, | |
| "best_model_checkpoint": "mushrooms_image_detection/checkpoint-16417", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 16417, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 8.049397468566895, | |
| "learning_rate": 2.91751695484817e-07, | |
| "loss": 0.8253, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 7.857975006103516, | |
| "learning_rate": 2.8258691269016923e-07, | |
| "loss": 0.8015, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 7.778552532196045, | |
| "learning_rate": 2.7342212989552147e-07, | |
| "loss": 0.7987, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 4.841355800628662, | |
| "learning_rate": 2.642573471008737e-07, | |
| "loss": 0.7851, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 8.00484561920166, | |
| "learning_rate": 2.5509256430622594e-07, | |
| "loss": 0.792, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 6.747846603393555, | |
| "learning_rate": 2.459277815115782e-07, | |
| "loss": 0.7707, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 6.744095325469971, | |
| "learning_rate": 2.367629987169304e-07, | |
| "loss": 0.7587, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 8.05142593383789, | |
| "learning_rate": 2.2759821592228265e-07, | |
| "loss": 0.765, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 6.42706823348999, | |
| "learning_rate": 2.1843343312763486e-07, | |
| "loss": 0.7582, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 5.361758708953857, | |
| "learning_rate": 2.092686503329871e-07, | |
| "loss": 0.7529, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 4.248225688934326, | |
| "learning_rate": 2.0010386753833933e-07, | |
| "loss": 0.7569, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 5.882041931152344, | |
| "learning_rate": 1.9093908474369157e-07, | |
| "loss": 0.7482, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 5.1786789894104, | |
| "learning_rate": 1.8177430194904378e-07, | |
| "loss": 0.7436, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 6.051706790924072, | |
| "learning_rate": 1.7260951915439604e-07, | |
| "loss": 0.7456, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 6.605566501617432, | |
| "learning_rate": 1.6344473635974827e-07, | |
| "loss": 0.7501, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 7.946951866149902, | |
| "learning_rate": 1.5427995356510048e-07, | |
| "loss": 0.7314, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 4.332089900970459, | |
| "learning_rate": 1.4511517077045272e-07, | |
| "loss": 0.7377, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 4.352112770080566, | |
| "learning_rate": 1.3595038797580498e-07, | |
| "loss": 0.7435, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 5.780616283416748, | |
| "learning_rate": 1.2678560518115722e-07, | |
| "loss": 0.7334, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 7.098005771636963, | |
| "learning_rate": 1.1762082238650944e-07, | |
| "loss": 0.7303, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 8.055667877197266, | |
| "learning_rate": 1.0845603959186168e-07, | |
| "loss": 0.7309, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 5.323170185089111, | |
| "learning_rate": 9.92912567972139e-08, | |
| "loss": 0.7256, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 8.01367473602295, | |
| "learning_rate": 9.012647400256613e-08, | |
| "loss": 0.7364, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 9.924859046936035, | |
| "learning_rate": 8.096169120791837e-08, | |
| "loss": 0.7335, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 4.085466384887695, | |
| "learning_rate": 7.17969084132706e-08, | |
| "loss": 0.7413, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 8.35221004486084, | |
| "learning_rate": 6.263212561862284e-08, | |
| "loss": 0.7172, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 5.808855056762695, | |
| "learning_rate": 5.3467342823975064e-08, | |
| "loss": 0.7241, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 3.8887059688568115, | |
| "learning_rate": 4.43025600293273e-08, | |
| "loss": 0.7269, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 7.963931560516357, | |
| "learning_rate": 3.5137777234679536e-08, | |
| "loss": 0.7372, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 4.434300899505615, | |
| "learning_rate": 2.597299444003177e-08, | |
| "loss": 0.7298, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 7.138937950134277, | |
| "learning_rate": 1.6808211645384004e-08, | |
| "loss": 0.7175, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 9.876811027526855, | |
| "learning_rate": 7.643428850736237e-09, | |
| "loss": 0.7165, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8796813431557307, | |
| "eval_loss": 0.6467268466949463, | |
| "eval_runtime": 723.0305, | |
| "eval_samples_per_second": 80.73, | |
| "eval_steps_per_second": 10.092, | |
| "step": 16417 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 16417, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 4.0744623252612465e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |