| { | |
| "best_metric": 0.5768261964735516, | |
| "best_model_checkpoint": "resnet-50-finetuned-omar/checkpoint-333", | |
| "epoch": 2.986547085201794, | |
| "global_step": 333, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 1.0992, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 1.0937, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 1.089, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.8996655518394655e-05, | |
| "loss": 1.0776, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.7324414715719065e-05, | |
| "loss": 1.0506, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.565217391304348e-05, | |
| "loss": 1.0407, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.397993311036789e-05, | |
| "loss": 1.0425, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.230769230769231e-05, | |
| "loss": 1.0591, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.0635451505016724e-05, | |
| "loss": 1.0361, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.896321070234114e-05, | |
| "loss": 1.0337, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.729096989966555e-05, | |
| "loss": 0.9977, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5214105793450882, | |
| "eval_loss": 0.993331253528595, | |
| "eval_runtime": 9.0682, | |
| "eval_samples_per_second": 43.779, | |
| "eval_steps_per_second": 5.514, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.5618729096989966e-05, | |
| "loss": 1.0008, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.394648829431438e-05, | |
| "loss": 0.9833, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.22742474916388e-05, | |
| "loss": 0.9977, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.0602006688963215e-05, | |
| "loss": 1.0122, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.8929765886287625e-05, | |
| "loss": 0.9786, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.725752508361204e-05, | |
| "loss": 0.9888, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.5585284280936454e-05, | |
| "loss": 0.9688, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.391304347826087e-05, | |
| "loss": 0.9591, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.2240802675585284e-05, | |
| "loss": 0.9611, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.05685618729097e-05, | |
| "loss": 0.9273, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.8896321070234117e-05, | |
| "loss": 0.9814, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5340050377833753, | |
| "eval_loss": 0.9008849263191223, | |
| "eval_runtime": 8.9706, | |
| "eval_samples_per_second": 44.256, | |
| "eval_steps_per_second": 5.574, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.722408026755853e-05, | |
| "loss": 0.9379, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.5551839464882946e-05, | |
| "loss": 0.9327, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.3879598662207358e-05, | |
| "loss": 0.9464, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2207357859531774e-05, | |
| "loss": 0.8991, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0535117056856187e-05, | |
| "loss": 0.9211, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.862876254180602e-06, | |
| "loss": 0.9617, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.1906354515050165e-06, | |
| "loss": 0.9298, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.518394648829431e-06, | |
| "loss": 0.9174, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.9123, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.173913043478261e-06, | |
| "loss": 0.9272, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.016722408026756e-07, | |
| "loss": 0.9463, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.5768261964735516, | |
| "eval_loss": 0.8737264275550842, | |
| "eval_runtime": 8.7069, | |
| "eval_samples_per_second": 45.596, | |
| "eval_steps_per_second": 5.743, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 333, | |
| "total_flos": 2.262617043191931e+17, | |
| "train_loss": 0.9869003245780418, | |
| "train_runtime": 506.9873, | |
| "train_samples_per_second": 21.107, | |
| "train_steps_per_second": 0.657 | |
| } | |
| ], | |
| "max_steps": 333, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.262617043191931e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |