| { | |
| "best_metric": 0.8727272727272727, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-350", | |
| "epoch": 45.16129032258065, | |
| "eval_steps": 500, | |
| "global_step": 350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9032258064516129, | |
| "eval_accuracy": 0.2, | |
| "eval_loss": 2.3726940155029297, | |
| "eval_runtime": 2.5133, | |
| "eval_samples_per_second": 43.767, | |
| "eval_steps_per_second": 1.592, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 6.954860687255859, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.3966, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "eval_accuracy": 0.3181818181818182, | |
| "eval_loss": 2.2909836769104004, | |
| "eval_runtime": 2.5816, | |
| "eval_samples_per_second": 42.609, | |
| "eval_steps_per_second": 1.549, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": 5.919530391693115, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 2.3131, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.967741935483871, | |
| "eval_accuracy": 0.4090909090909091, | |
| "eval_loss": 2.1218321323394775, | |
| "eval_runtime": 2.4729, | |
| "eval_samples_per_second": 44.483, | |
| "eval_steps_per_second": 1.618, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 3.870967741935484, | |
| "grad_norm": 8.89976692199707, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 2.072, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.45454545454545453, | |
| "eval_loss": 1.8349428176879883, | |
| "eval_runtime": 2.5693, | |
| "eval_samples_per_second": 42.813, | |
| "eval_steps_per_second": 1.557, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 4.903225806451613, | |
| "eval_accuracy": 0.5363636363636364, | |
| "eval_loss": 1.463451862335205, | |
| "eval_runtime": 2.638, | |
| "eval_samples_per_second": 41.698, | |
| "eval_steps_per_second": 1.516, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 5.161290322580645, | |
| "grad_norm": 12.236054420471191, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 1.5528, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.935483870967742, | |
| "eval_accuracy": 0.6636363636363637, | |
| "eval_loss": 1.103641390800476, | |
| "eval_runtime": 2.4384, | |
| "eval_samples_per_second": 45.111, | |
| "eval_steps_per_second": 1.64, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 6.451612903225806, | |
| "grad_norm": 10.842184066772461, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 1.0472, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 6.967741935483871, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9272710680961609, | |
| "eval_runtime": 3.0352, | |
| "eval_samples_per_second": 36.241, | |
| "eval_steps_per_second": 1.318, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 7.741935483870968, | |
| "grad_norm": 10.389890670776367, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 0.7989, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7909090909090909, | |
| "eval_loss": 0.8008114695549011, | |
| "eval_runtime": 2.4733, | |
| "eval_samples_per_second": 44.475, | |
| "eval_steps_per_second": 1.617, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 8.903225806451612, | |
| "eval_accuracy": 0.7818181818181819, | |
| "eval_loss": 0.7358732223510742, | |
| "eval_runtime": 2.439, | |
| "eval_samples_per_second": 45.101, | |
| "eval_steps_per_second": 1.64, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 9.03225806451613, | |
| "grad_norm": 8.742050170898438, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.604, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 9.935483870967742, | |
| "eval_accuracy": 0.7909090909090909, | |
| "eval_loss": 0.7282811403274536, | |
| "eval_runtime": 3.311, | |
| "eval_samples_per_second": 33.223, | |
| "eval_steps_per_second": 1.208, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 10.32258064516129, | |
| "grad_norm": 11.235774993896484, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.5228, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 10.967741935483872, | |
| "eval_accuracy": 0.8363636363636363, | |
| "eval_loss": 0.5896822214126587, | |
| "eval_runtime": 2.4309, | |
| "eval_samples_per_second": 45.251, | |
| "eval_steps_per_second": 1.646, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 11.612903225806452, | |
| "grad_norm": 10.12472915649414, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 0.4734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 0.6503061652183533, | |
| "eval_runtime": 2.482, | |
| "eval_samples_per_second": 44.32, | |
| "eval_steps_per_second": 1.612, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 12.903225806451612, | |
| "grad_norm": 5.467583179473877, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.3987, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 12.903225806451612, | |
| "eval_accuracy": 0.8272727272727273, | |
| "eval_loss": 0.5785130858421326, | |
| "eval_runtime": 2.5549, | |
| "eval_samples_per_second": 43.054, | |
| "eval_steps_per_second": 1.566, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 13.935483870967742, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 0.6091312766075134, | |
| "eval_runtime": 2.4459, | |
| "eval_samples_per_second": 44.973, | |
| "eval_steps_per_second": 1.635, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 14.193548387096774, | |
| "grad_norm": 8.375397682189941, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.3742, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 14.967741935483872, | |
| "eval_accuracy": 0.8454545454545455, | |
| "eval_loss": 0.5278283953666687, | |
| "eval_runtime": 3.0723, | |
| "eval_samples_per_second": 35.804, | |
| "eval_steps_per_second": 1.302, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 15.483870967741936, | |
| "grad_norm": 9.191360473632812, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 0.3588, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.5279448628425598, | |
| "eval_runtime": 2.7269, | |
| "eval_samples_per_second": 40.339, | |
| "eval_steps_per_second": 1.467, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 16.774193548387096, | |
| "grad_norm": 10.030477523803711, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 0.3536, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 16.903225806451612, | |
| "eval_accuracy": 0.8363636363636363, | |
| "eval_loss": 0.5189336538314819, | |
| "eval_runtime": 2.4748, | |
| "eval_samples_per_second": 44.447, | |
| "eval_steps_per_second": 1.616, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 17.93548387096774, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.5036130547523499, | |
| "eval_runtime": 3.2666, | |
| "eval_samples_per_second": 33.674, | |
| "eval_steps_per_second": 1.225, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 18.06451612903226, | |
| "grad_norm": 5.293987274169922, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.331, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 18.967741935483872, | |
| "eval_accuracy": 0.8363636363636363, | |
| "eval_loss": 0.5327084064483643, | |
| "eval_runtime": 2.49, | |
| "eval_samples_per_second": 44.178, | |
| "eval_steps_per_second": 1.606, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 19.35483870967742, | |
| "grad_norm": 4.783825397491455, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.2836, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.47167953848838806, | |
| "eval_runtime": 2.4734, | |
| "eval_samples_per_second": 44.474, | |
| "eval_steps_per_second": 1.617, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 20.64516129032258, | |
| "grad_norm": 6.62587308883667, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 0.2785, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 20.903225806451612, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4598047435283661, | |
| "eval_runtime": 2.8824, | |
| "eval_samples_per_second": 38.162, | |
| "eval_steps_per_second": 1.388, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 21.93548387096774, | |
| "grad_norm": 8.891733169555664, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.2439, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 21.93548387096774, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4782707691192627, | |
| "eval_runtime": 2.4502, | |
| "eval_samples_per_second": 44.894, | |
| "eval_steps_per_second": 1.632, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 22.967741935483872, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4948057234287262, | |
| "eval_runtime": 2.6324, | |
| "eval_samples_per_second": 41.787, | |
| "eval_steps_per_second": 1.52, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 23.225806451612904, | |
| "grad_norm": 8.404036521911621, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 0.2779, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8454545454545455, | |
| "eval_loss": 0.48835644125938416, | |
| "eval_runtime": 2.483, | |
| "eval_samples_per_second": 44.301, | |
| "eval_steps_per_second": 1.611, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 24.516129032258064, | |
| "grad_norm": 3.865527629852295, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 0.2167, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 24.903225806451612, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.5084207057952881, | |
| "eval_runtime": 2.4768, | |
| "eval_samples_per_second": 44.413, | |
| "eval_steps_per_second": 1.615, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 25.806451612903224, | |
| "grad_norm": 4.576181888580322, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.2164, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 25.93548387096774, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.471531480550766, | |
| "eval_runtime": 3.2991, | |
| "eval_samples_per_second": 33.342, | |
| "eval_steps_per_second": 1.212, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 26.967741935483872, | |
| "eval_accuracy": 0.8272727272727273, | |
| "eval_loss": 0.5503013730049133, | |
| "eval_runtime": 2.5348, | |
| "eval_samples_per_second": 43.396, | |
| "eval_steps_per_second": 1.578, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 27.096774193548388, | |
| "grad_norm": 9.690849304199219, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.2342, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8272727272727273, | |
| "eval_loss": 0.49801039695739746, | |
| "eval_runtime": 2.4694, | |
| "eval_samples_per_second": 44.545, | |
| "eval_steps_per_second": 1.62, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 28.387096774193548, | |
| "grad_norm": 6.414791107177734, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 0.216, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 28.903225806451612, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4240585267543793, | |
| "eval_runtime": 2.5761, | |
| "eval_samples_per_second": 42.7, | |
| "eval_steps_per_second": 1.553, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 29.677419354838708, | |
| "grad_norm": 7.521275043487549, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.1986, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 29.93548387096774, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4466007649898529, | |
| "eval_runtime": 2.468, | |
| "eval_samples_per_second": 44.571, | |
| "eval_steps_per_second": 1.621, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 30.967741935483872, | |
| "grad_norm": 4.934516429901123, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 0.1919, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 30.967741935483872, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.4557681381702423, | |
| "eval_runtime": 2.9585, | |
| "eval_samples_per_second": 37.181, | |
| "eval_steps_per_second": 1.352, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.43898770213127136, | |
| "eval_runtime": 2.4694, | |
| "eval_samples_per_second": 44.544, | |
| "eval_steps_per_second": 1.62, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 32.25806451612903, | |
| "grad_norm": 8.577577590942383, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.1958, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 32.903225806451616, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.43786120414733887, | |
| "eval_runtime": 2.4873, | |
| "eval_samples_per_second": 44.224, | |
| "eval_steps_per_second": 1.608, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 33.54838709677419, | |
| "grad_norm": 6.008741855621338, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.1693, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 33.935483870967744, | |
| "eval_accuracy": 0.8454545454545455, | |
| "eval_loss": 0.442380428314209, | |
| "eval_runtime": 3.2712, | |
| "eval_samples_per_second": 33.627, | |
| "eval_steps_per_second": 1.223, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 34.83870967741935, | |
| "grad_norm": 7.021655559539795, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.2158, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 34.96774193548387, | |
| "eval_accuracy": 0.8363636363636363, | |
| "eval_loss": 0.45243895053863525, | |
| "eval_runtime": 2.4917, | |
| "eval_samples_per_second": 44.146, | |
| "eval_steps_per_second": 1.605, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4387998878955841, | |
| "eval_runtime": 2.6925, | |
| "eval_samples_per_second": 40.854, | |
| "eval_steps_per_second": 1.486, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 36.12903225806452, | |
| "grad_norm": 7.29483699798584, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.1578, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 36.903225806451616, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4327390491962433, | |
| "eval_runtime": 2.5946, | |
| "eval_samples_per_second": 42.395, | |
| "eval_steps_per_second": 1.542, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 37.41935483870968, | |
| "grad_norm": 4.809728622436523, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.1866, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 37.935483870967744, | |
| "eval_accuracy": 0.8454545454545455, | |
| "eval_loss": 0.4527719020843506, | |
| "eval_runtime": 2.884, | |
| "eval_samples_per_second": 38.141, | |
| "eval_steps_per_second": 1.387, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 38.70967741935484, | |
| "grad_norm": 5.220081329345703, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.1664, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 38.96774193548387, | |
| "eval_accuracy": 0.8454545454545455, | |
| "eval_loss": 0.45329469442367554, | |
| "eval_runtime": 3.0675, | |
| "eval_samples_per_second": 35.86, | |
| "eval_steps_per_second": 1.304, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 6.373405933380127, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 0.1757, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4492085576057434, | |
| "eval_runtime": 2.5073, | |
| "eval_samples_per_second": 43.872, | |
| "eval_steps_per_second": 1.595, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 40.903225806451616, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.44178226590156555, | |
| "eval_runtime": 2.4731, | |
| "eval_samples_per_second": 44.479, | |
| "eval_steps_per_second": 1.617, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 41.29032258064516, | |
| "grad_norm": 6.021412372589111, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 0.1542, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 41.935483870967744, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.4412206709384918, | |
| "eval_runtime": 3.2551, | |
| "eval_samples_per_second": 33.793, | |
| "eval_steps_per_second": 1.229, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 42.58064516129032, | |
| "grad_norm": 6.342203617095947, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.144, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 42.96774193548387, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.44375744462013245, | |
| "eval_runtime": 2.4771, | |
| "eval_samples_per_second": 44.406, | |
| "eval_steps_per_second": 1.615, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 43.87096774193548, | |
| "grad_norm": 4.18281888961792, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 0.1647, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.441061407327652, | |
| "eval_runtime": 2.4882, | |
| "eval_samples_per_second": 44.209, | |
| "eval_steps_per_second": 1.608, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 44.903225806451616, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.43833261728286743, | |
| "eval_runtime": 3.0681, | |
| "eval_samples_per_second": 35.853, | |
| "eval_steps_per_second": 1.304, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 45.16129032258065, | |
| "grad_norm": 5.460458278656006, | |
| "learning_rate": 0.0, | |
| "loss": 0.1418, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 45.16129032258065, | |
| "eval_accuracy": 0.8727272727272727, | |
| "eval_loss": 0.4381871521472931, | |
| "eval_runtime": 2.8317, | |
| "eval_samples_per_second": 38.846, | |
| "eval_steps_per_second": 1.413, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 45.16129032258065, | |
| "step": 350, | |
| "total_flos": 1.1015215348522291e+18, | |
| "train_loss": 0.5093351830754961, | |
| "train_runtime": 1677.4202, | |
| "train_samples_per_second": 29.241, | |
| "train_steps_per_second": 0.209 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 350, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1015215348522291e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |