| { | |
| "best_metric": 0.7882830626450116, | |
| "best_model_checkpoint": "vit-base-patch16-224-finetuned-cedar/checkpoint-108", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 216, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.7007, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.6193, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.793814432989691e-05, | |
| "loss": 0.5897, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.536082474226804e-05, | |
| "loss": 0.5124, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.2783505154639175e-05, | |
| "loss": 0.5419, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.765661252900232, | |
| "eval_loss": 0.5085464119911194, | |
| "eval_runtime": 27.8034, | |
| "eval_samples_per_second": 62.007, | |
| "eval_steps_per_second": 1.942, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.020618556701031e-05, | |
| "loss": 0.4913, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.7628865979381445e-05, | |
| "loss": 0.4795, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.5051546391752576e-05, | |
| "loss": 0.4856, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.2474226804123714e-05, | |
| "loss": 0.4715, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.9896907216494846e-05, | |
| "loss": 0.4541, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7882830626450116, | |
| "eval_loss": 0.46672987937927246, | |
| "eval_runtime": 27.8433, | |
| "eval_samples_per_second": 61.918, | |
| "eval_steps_per_second": 1.939, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.7319587628865977e-05, | |
| "loss": 0.4464, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.4742268041237116e-05, | |
| "loss": 0.4412, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.2164948453608247e-05, | |
| "loss": 0.4327, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1.9587628865979382e-05, | |
| "loss": 0.4301, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.7010309278350517e-05, | |
| "loss": 0.4184, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 1.4432989690721649e-05, | |
| "loss": 0.3847, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7320185614849188, | |
| "eval_loss": 0.5602948069572449, | |
| "eval_runtime": 27.4724, | |
| "eval_samples_per_second": 62.754, | |
| "eval_steps_per_second": 1.966, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.1855670103092783e-05, | |
| "loss": 0.4003, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 9.278350515463918e-06, | |
| "loss": 0.4209, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 6.701030927835052e-06, | |
| "loss": 0.405, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 4.123711340206186e-06, | |
| "loss": 0.4026, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.5463917525773197e-06, | |
| "loss": 0.3669, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7749419953596288, | |
| "eval_loss": 0.4869101941585541, | |
| "eval_runtime": 27.2972, | |
| "eval_samples_per_second": 63.157, | |
| "eval_steps_per_second": 1.978, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 216, | |
| "total_flos": 2.1362991696950723e+18, | |
| "train_loss": 0.4688039951854282, | |
| "train_runtime": 1140.3926, | |
| "train_samples_per_second": 24.174, | |
| "train_steps_per_second": 0.189 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 216, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 2.1362991696950723e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |