| { |
| "best_metric": 0.7128137350082397, |
| "best_model_checkpoint": "./vit-base-beans/checkpoint-200", |
| "epoch": 4.081632653061225, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00019183673469387756, |
| "loss": 1.948, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.00018367346938775512, |
| "loss": 1.6543, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00017551020408163265, |
| "loss": 1.4346, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00016734693877551023, |
| "loss": 1.2276, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.82, |
| "eval_accuracy": 0.5864864864864865, |
| "eval_loss": 1.218226432800293, |
| "eval_runtime": 6.5264, |
| "eval_samples_per_second": 56.692, |
| "eval_steps_per_second": 7.201, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00015918367346938776, |
| "loss": 1.0635, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.0001510204081632653, |
| "loss": 0.7321, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.00014285714285714287, |
| "loss": 0.6528, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.0001346938775510204, |
| "loss": 0.7303, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.63, |
| "eval_accuracy": 0.7378378378378379, |
| "eval_loss": 0.8550543785095215, |
| "eval_runtime": 6.3277, |
| "eval_samples_per_second": 58.473, |
| "eval_steps_per_second": 7.428, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.00012653061224489798, |
| "loss": 0.5354, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 0.00011836734693877552, |
| "loss": 0.4344, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 0.00011020408163265306, |
| "loss": 0.2725, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 0.00010204081632653062, |
| "loss": 0.2245, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.45, |
| "eval_accuracy": 0.7648648648648648, |
| "eval_loss": 0.7530784606933594, |
| "eval_runtime": 6.2236, |
| "eval_samples_per_second": 59.452, |
| "eval_steps_per_second": 7.552, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 9.387755102040817e-05, |
| "loss": 0.2367, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 8.571428571428571e-05, |
| "loss": 0.2139, |
| "step": 140 |
| }, |
| { |
| "epoch": 3.06, |
| "learning_rate": 7.755102040816327e-05, |
| "loss": 0.1734, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.27, |
| "learning_rate": 6.938775510204082e-05, |
| "loss": 0.1038, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.27, |
| "eval_accuracy": 0.7783783783783784, |
| "eval_loss": 0.7436022758483887, |
| "eval_runtime": 6.8074, |
| "eval_samples_per_second": 54.352, |
| "eval_steps_per_second": 6.904, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.47, |
| "learning_rate": 6.122448979591838e-05, |
| "loss": 0.0875, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.67, |
| "learning_rate": 5.3061224489795926e-05, |
| "loss": 0.0858, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 4.4897959183673474e-05, |
| "loss": 0.1078, |
| "step": 190 |
| }, |
| { |
| "epoch": 4.08, |
| "learning_rate": 3.673469387755102e-05, |
| "loss": 0.0703, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.08, |
| "eval_accuracy": 0.7891891891891892, |
| "eval_loss": 0.7128137350082397, |
| "eval_runtime": 6.0759, |
| "eval_samples_per_second": 60.896, |
| "eval_steps_per_second": 7.735, |
| "step": 200 |
| } |
| ], |
| "max_steps": 245, |
| "num_train_epochs": 5, |
| "total_flos": 2.467477633522729e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
