| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetunedt/checkpoint-25", | |
| "epoch": 10.0, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7791, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4714, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01467892061918974, | |
| "eval_runtime": 6.0168, | |
| "eval_samples_per_second": 59.167, | |
| "eval_steps_per_second": 1.994, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.044, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.0126, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0089, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007656927919015288, | |
| "eval_runtime": 5.0843, | |
| "eval_samples_per_second": 70.02, | |
| "eval_steps_per_second": 2.36, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.0071, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0101, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00026955531211569905, | |
| "eval_runtime": 4.9485, | |
| "eval_samples_per_second": 71.941, | |
| "eval_steps_per_second": 2.425, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.005, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.0057, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0021, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00016395412967540324, | |
| "eval_runtime": 4.9361, | |
| "eval_samples_per_second": 72.121, | |
| "eval_steps_per_second": 2.431, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.002, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.0028, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00011135207751067355, | |
| "eval_runtime": 5.1657, | |
| "eval_samples_per_second": 68.917, | |
| "eval_steps_per_second": 2.323, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0012, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.0013, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0016, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00014620741421822459, | |
| "eval_runtime": 4.9247, | |
| "eval_samples_per_second": 72.289, | |
| "eval_steps_per_second": 2.437, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0007, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0044, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 9.979216702049598e-05, | |
| "eval_runtime": 4.9812, | |
| "eval_samples_per_second": 71.469, | |
| "eval_steps_per_second": 2.409, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.0003, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0023, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0007, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 8.071383490459993e-05, | |
| "eval_runtime": 5.0468, | |
| "eval_samples_per_second": 70.539, | |
| "eval_steps_per_second": 2.378, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.0003, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0013, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 8.012407488422468e-05, | |
| "eval_runtime": 5.1177, | |
| "eval_samples_per_second": 69.563, | |
| "eval_steps_per_second": 2.345, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0021, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.0019, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0004, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 7.809004455339164e-05, | |
| "eval_runtime": 4.9442, | |
| "eval_samples_per_second": 72.004, | |
| "eval_steps_per_second": 2.427, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 250, | |
| "total_flos": 2.4764710519574323e+18, | |
| "train_loss": 0.09477622657828033, | |
| "train_runtime": 1542.5779, | |
| "train_samples_per_second": 20.725, | |
| "train_steps_per_second": 0.162 | |
| } | |
| ], | |
| "max_steps": 250, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.4764710519574323e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |