| { | |
| "best_metric": 0.7659574468085106, | |
| "best_model_checkpoint": "resnet-50-finetuned-omars6/checkpoint-185", | |
| "epoch": 2.983783783783784, | |
| "global_step": 276, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00017857142857142857, | |
| "loss": 1.3812, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00035714285714285714, | |
| "loss": 1.3333, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0004959677419354839, | |
| "loss": 1.3696, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0004758064516129033, | |
| "loss": 1.24, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0004556451612903226, | |
| "loss": 1.3542, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00043548387096774196, | |
| "loss": 1.252, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0004153225806451613, | |
| "loss": 1.1834, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00039516129032258064, | |
| "loss": 0.9832, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.000375, | |
| "loss": 1.1032, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.7507598784194529, | |
| "eval_loss": 0.9538100957870483, | |
| "eval_runtime": 7.329, | |
| "eval_samples_per_second": 44.89, | |
| "eval_steps_per_second": 5.731, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0003548387096774194, | |
| "loss": 0.8926, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0003346774193548387, | |
| "loss": 0.9348, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00031451612903225806, | |
| "loss": 0.8059, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00029435483870967743, | |
| "loss": 1.0991, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00027419354838709674, | |
| "loss": 0.9479, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0002540322580645161, | |
| "loss": 0.8192, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00023387096774193548, | |
| "loss": 0.9356, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00021370967741935485, | |
| "loss": 0.9438, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001935483870967742, | |
| "loss": 0.8227, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7659574468085106, | |
| "eval_loss": 0.8379674553871155, | |
| "eval_runtime": 7.139, | |
| "eval_samples_per_second": 46.085, | |
| "eval_steps_per_second": 5.883, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00017338709677419356, | |
| "loss": 0.919, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0001532258064516129, | |
| "loss": 0.837, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00013306451612903227, | |
| "loss": 0.7367, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00011290322580645161, | |
| "loss": 0.7793, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.274193548387098e-05, | |
| "loss": 0.7871, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.258064516129033e-05, | |
| "loss": 0.7907, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.241935483870968e-05, | |
| "loss": 0.9355, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.8561, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.2096774193548387e-05, | |
| "loss": 0.8362, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.7355623100303952, | |
| "eval_loss": 0.7410567998886108, | |
| "eval_runtime": 7.2705, | |
| "eval_samples_per_second": 45.252, | |
| "eval_steps_per_second": 5.777, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "step": 276, | |
| "total_flos": 1.874563372905431e+17, | |
| "train_loss": 0.9914917963138525, | |
| "train_runtime": 385.9636, | |
| "train_samples_per_second": 22.984, | |
| "train_steps_per_second": 0.715 | |
| } | |
| ], | |
| "max_steps": 276, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.874563372905431e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |