| { | |
| "best_metric": 0.6870071488415761, | |
| "best_model_checkpoint": "opt-2.7b-realtime-chat-v2/checkpoint-204", | |
| "epoch": 2.9874151475859962, | |
| "global_step": 306, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.935483870967742e-06, | |
| "loss": 2.6432, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.870967741935484e-06, | |
| "loss": 2.6152, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.8064516129032256e-06, | |
| "loss": 2.5393, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.741935483870968e-06, | |
| "loss": 2.4402, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 2.3797, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.1612903225806451e-05, | |
| "loss": 2.3533, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.3548387096774194e-05, | |
| "loss": 2.307, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.5483870967741936e-05, | |
| "loss": 2.266, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.741935483870968e-05, | |
| "loss": 2.2859, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.935483870967742e-05, | |
| "loss": 2.2434, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.1290322580645163e-05, | |
| "loss": 2.2224, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.3225806451612902e-05, | |
| "loss": 2.2518, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.5161290322580648e-05, | |
| "loss": 2.232, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.7096774193548387e-05, | |
| "loss": 2.2121, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.903225806451613e-05, | |
| "loss": 2.2042, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.9890909090909092e-05, | |
| "loss": 2.1655, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.9672727272727274e-05, | |
| "loss": 2.197, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.9454545454545456e-05, | |
| "loss": 2.2383, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.9236363636363635e-05, | |
| "loss": 2.1827, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.901818181818182e-05, | |
| "loss": 2.1667, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.88e-05, | |
| "loss": 2.1688, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8581818181818184e-05, | |
| "loss": 2.1722, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.8363636363636363e-05, | |
| "loss": 2.1771, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.8145454545454548e-05, | |
| "loss": 2.1681, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.7927272727272727e-05, | |
| "loss": 2.0974, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.6825691202041083, | |
| "eval_loss": 2.1267497539520264, | |
| "eval_runtime": 510.4375, | |
| "eval_samples_per_second": 3.519, | |
| "eval_steps_per_second": 3.519, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.770909090909091e-05, | |
| "loss": 2.1322, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.749090909090909e-05, | |
| "loss": 2.1157, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 2.1325, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.7054545454545455e-05, | |
| "loss": 2.1346, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.6836363636363637e-05, | |
| "loss": 2.143, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.661818181818182e-05, | |
| "loss": 2.143, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.64e-05, | |
| "loss": 2.1353, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.618181818181818e-05, | |
| "loss": 2.1296, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.5963636363636365e-05, | |
| "loss": 2.117, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.5745454545454544e-05, | |
| "loss": 2.1093, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.552727272727273e-05, | |
| "loss": 2.1206, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.5309090909090908e-05, | |
| "loss": 2.1308, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.509090909090909e-05, | |
| "loss": 2.1258, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.4872727272727272e-05, | |
| "loss": 2.1113, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.4654545454545454e-05, | |
| "loss": 2.0913, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.4436363636363636e-05, | |
| "loss": 2.1067, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.421818181818182e-05, | |
| "loss": 2.1034, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.4e-05, | |
| "loss": 2.0804, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.3781818181818183e-05, | |
| "loss": 2.1228, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.356363636363636e-05, | |
| "loss": 2.1044, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.3345454545454547e-05, | |
| "loss": 2.1045, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.3127272727272725e-05, | |
| "loss": 2.0758, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.290909090909091e-05, | |
| "loss": 2.1185, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.269090909090909e-05, | |
| "loss": 2.0844, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.2472727272727275e-05, | |
| "loss": 2.0817, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.2254545454545454e-05, | |
| "loss": 2.0842, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6858646182863831, | |
| "eval_loss": 2.096801519393921, | |
| "eval_runtime": 510.9612, | |
| "eval_samples_per_second": 3.515, | |
| "eval_steps_per_second": 3.515, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.2036363636363636e-05, | |
| "loss": 2.0166, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 1.9987, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.16e-05, | |
| "loss": 1.9678, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.1381818181818182e-05, | |
| "loss": 2.0026, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.1163636363636364e-05, | |
| "loss": 1.9867, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.0945454545454546e-05, | |
| "loss": 2.0086, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.0727272727272728e-05, | |
| "loss": 1.9611, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.0509090909090907e-05, | |
| "loss": 1.9681, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.0290909090909092e-05, | |
| "loss": 1.9623, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.0072727272727274e-05, | |
| "loss": 1.9776, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.9854545454545456e-05, | |
| "loss": 1.999, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.963636363636364e-05, | |
| "loss": 1.9827, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.9418181818181817e-05, | |
| "loss": 1.9945, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.9692, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.898181818181818e-05, | |
| "loss": 1.9519, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.8763636363636367e-05, | |
| "loss": 1.9432, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.8545454545454545e-05, | |
| "loss": 1.9454, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.832727272727273e-05, | |
| "loss": 1.9759, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.810909090909091e-05, | |
| "loss": 1.9672, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.789090909090909e-05, | |
| "loss": 1.9527, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.7672727272727274e-05, | |
| "loss": 1.9465, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.7454545454545456e-05, | |
| "loss": 1.9948, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.7236363636363638e-05, | |
| "loss": 1.9685, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.701818181818182e-05, | |
| "loss": 1.9518, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 1.9624, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_accuracy": 0.6862566888822462, | |
| "eval_loss": 2.0935797691345215, | |
| "eval_runtime": 510.8965, | |
| "eval_samples_per_second": 3.515, | |
| "eval_steps_per_second": 3.515, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.6581818181818184e-05, | |
| "loss": 1.9587, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.6363636363636363e-05, | |
| "loss": 1.9752, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.6145454545454548e-05, | |
| "loss": 1.9559, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.5927272727272727e-05, | |
| "loss": 1.9707, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.5709090909090912e-05, | |
| "loss": 1.9844, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.549090909090909e-05, | |
| "loss": 1.9884, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.5272727272727273e-05, | |
| "loss": 1.9799, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 1.5054545454545455e-05, | |
| "loss": 1.9582, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.4836363636363637e-05, | |
| "loss": 1.9677, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 1.4618181818181817e-05, | |
| "loss": 1.9804, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.44e-05, | |
| "loss": 1.9816, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.4181818181818181e-05, | |
| "loss": 1.969, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.3963636363636363e-05, | |
| "loss": 1.9602, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.3745454545454546e-05, | |
| "loss": 1.9926, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.3527272727272728e-05, | |
| "loss": 1.9378, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.330909090909091e-05, | |
| "loss": 1.9567, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.309090909090909e-05, | |
| "loss": 1.9849, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.2872727272727272e-05, | |
| "loss": 1.9622, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.2654545454545454e-05, | |
| "loss": 1.9447, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.2436363636363636e-05, | |
| "loss": 1.958, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.2218181818181818e-05, | |
| "loss": 1.9729, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.9402, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.178181818181818e-05, | |
| "loss": 1.977, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.1563636363636363e-05, | |
| "loss": 1.9561, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.1345454545454545e-05, | |
| "loss": 1.9576, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.1127272727272727e-05, | |
| "loss": 1.9476, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.6870071488415761, | |
| "eval_loss": 2.0888001918792725, | |
| "eval_runtime": 510.9696, | |
| "eval_samples_per_second": 3.515, | |
| "eval_steps_per_second": 3.515, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 1.9169, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.0690909090909091e-05, | |
| "loss": 1.8484, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.0472727272727273e-05, | |
| "loss": 1.8525, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.0254545454545453e-05, | |
| "loss": 1.8692, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.0036363636363637e-05, | |
| "loss": 1.8738, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.81818181818182e-06, | |
| "loss": 1.8889, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.8661, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.381818181818183e-06, | |
| "loss": 1.8699, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.163636363636365e-06, | |
| "loss": 1.8902, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.945454545454546e-06, | |
| "loss": 1.8766, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.727272727272728e-06, | |
| "loss": 1.8634, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.50909090909091e-06, | |
| "loss": 1.8549, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 8.290909090909092e-06, | |
| "loss": 1.8592, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.072727272727274e-06, | |
| "loss": 1.8695, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.854545454545456e-06, | |
| "loss": 1.8753, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.636363636363636e-06, | |
| "loss": 1.8599, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 7.4181818181818185e-06, | |
| "loss": 1.8847, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 7.2e-06, | |
| "loss": 1.8712, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.981818181818182e-06, | |
| "loss": 1.8673, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.763636363636364e-06, | |
| "loss": 1.8617, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.545454545454545e-06, | |
| "loss": 1.8297, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 6.327272727272727e-06, | |
| "loss": 1.8624, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 6.109090909090909e-06, | |
| "loss": 1.8753, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.89090909090909e-06, | |
| "loss": 1.8789, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.672727272727272e-06, | |
| "loss": 1.888, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_accuracy": 0.6863803621574514, | |
| "eval_loss": 2.0992937088012695, | |
| "eval_runtime": 511.1737, | |
| "eval_samples_per_second": 3.513, | |
| "eval_steps_per_second": 3.513, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 1.8462, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 5.2363636363636365e-06, | |
| "loss": 1.8716, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.0181818181818186e-06, | |
| "loss": 1.8823, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.8718, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.581818181818183e-06, | |
| "loss": 1.8745, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.363636363636364e-06, | |
| "loss": 1.908, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.145454545454546e-06, | |
| "loss": 1.8412, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.927272727272728e-06, | |
| "loss": 1.8462, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.7090909090909092e-06, | |
| "loss": 1.8683, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.490909090909091e-06, | |
| "loss": 1.872, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.2727272727272725e-06, | |
| "loss": 1.852, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.0545454545454546e-06, | |
| "loss": 1.8619, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.836363636363636e-06, | |
| "loss": 1.8542, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.6181818181818183e-06, | |
| "loss": 1.8953, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.8341, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.181818181818182e-06, | |
| "loss": 1.8484, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.963636363636364e-06, | |
| "loss": 1.8473, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.7454545454545454e-06, | |
| "loss": 1.8827, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5272727272727273e-06, | |
| "loss": 1.8572, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.3090909090909091e-06, | |
| "loss": 1.8721, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.090909090909091e-06, | |
| "loss": 1.8363, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.727272727272727e-07, | |
| "loss": 1.8762, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 6.545454545454546e-07, | |
| "loss": 1.8749, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.3636363636363636e-07, | |
| "loss": 1.8522, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.1818181818181818e-07, | |
| "loss": 1.8716, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0, | |
| "loss": 1.8687, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.6864508822377811, | |
| "eval_loss": 2.0993993282318115, | |
| "eval_runtime": 511.0772, | |
| "eval_samples_per_second": 3.514, | |
| "eval_steps_per_second": 3.514, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 306, | |
| "total_flos": 4.2741192183760896e+17, | |
| "train_loss": 2.010221361334807, | |
| "train_runtime": 46544.0603, | |
| "train_samples_per_second": 0.845, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "max_steps": 306, | |
| "num_train_epochs": 3, | |
| "total_flos": 4.2741192183760896e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |