Commit
•
5c20430
1
Parent(s):
adc9e4c
Upload 7 files
Browse files- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +460 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f14ff405d771a19d42c65e8960e32fae16533f3ac701ce86509191d6acf6eca1
|
| 3 |
+
size 26719
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7da4efa2107e419b748ba6e6d07908c82ba34a61bdda8d5462c547112c47956
|
| 3 |
+
size 498691883
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ee751c6679dfd93855bd123dd9491ae335784e145c0ba21cf46ffa7cf3d109
|
| 3 |
+
size 14439
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f71fc68a2307b7c9559c27b8b33ab647783de01c671949f94d9448a40a2355e
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17c3bf6ff131f71817ef4d9319384e7d13849ee245a4360dbf89ce1daaf630cc
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.177585244178772,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/Shareddrives/flipflow/Desarrollo/Projects/contrastive-product-matching/reports/contrastive-ft-siamese/all-xlarge-all-512-all-0.1-5e-05-frozen-roberta-base/0/checkpoint-25136",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"global_step": 28278,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.16,
|
| 12 |
+
"learning_rate": 7.829408020369192e-07,
|
| 13 |
+
"loss": 1.7523,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.32,
|
| 18 |
+
"learning_rate": 1.5786123488224062e-06,
|
| 19 |
+
"loss": 1.6241,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.48,
|
| 24 |
+
"learning_rate": 2.374283895607893e-06,
|
| 25 |
+
"loss": 1.4901,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.64,
|
| 30 |
+
"learning_rate": 3.1699554423933804e-06,
|
| 31 |
+
"loss": 1.3765,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.8,
|
| 36 |
+
"learning_rate": 3.965626989178867e-06,
|
| 37 |
+
"loss": 1.2813,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.95,
|
| 42 |
+
"learning_rate": 4.7612985359643546e-06,
|
| 43 |
+
"loss": 1.2277,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.822340580767547,
|
| 49 |
+
"eval_f1": 0.05583559519193486,
|
| 50 |
+
"eval_loss": 1.2101483345031738,
|
| 51 |
+
"eval_precision": 0.11464968152866242,
|
| 52 |
+
"eval_recall": 0.03690415171706817,
|
| 53 |
+
"eval_runtime": 113.1945,
|
| 54 |
+
"eval_samples_per_second": 121.084,
|
| 55 |
+
"eval_steps_per_second": 15.142,
|
| 56 |
+
"step": 3142
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.11,
|
| 60 |
+
"learning_rate": 5.556970082749841e-06,
|
| 61 |
+
"loss": 1.204,
|
| 62 |
+
"step": 3500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.27,
|
| 66 |
+
"learning_rate": 6.3526416295353275e-06,
|
| 67 |
+
"loss": 1.2103,
|
| 68 |
+
"step": 4000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.43,
|
| 72 |
+
"learning_rate": 7.148313176320815e-06,
|
| 73 |
+
"loss": 1.1915,
|
| 74 |
+
"step": 4500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.59,
|
| 78 |
+
"learning_rate": 7.942393380012732e-06,
|
| 79 |
+
"loss": 1.2112,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.75,
|
| 84 |
+
"learning_rate": 8.738064926798218e-06,
|
| 85 |
+
"loss": 1.1908,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.91,
|
| 90 |
+
"learning_rate": 9.533736473583705e-06,
|
| 91 |
+
"loss": 1.1902,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.0,
|
| 96 |
+
"eval_accuracy": 0.8191303078943528,
|
| 97 |
+
"eval_f1": 0.05561904761904763,
|
| 98 |
+
"eval_loss": 1.187880039215088,
|
| 99 |
+
"eval_precision": 0.1083086053412463,
|
| 100 |
+
"eval_recall": 0.03741670937980523,
|
| 101 |
+
"eval_runtime": 105.6854,
|
| 102 |
+
"eval_samples_per_second": 129.687,
|
| 103 |
+
"eval_steps_per_second": 16.218,
|
| 104 |
+
"step": 6284
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.07,
|
| 108 |
+
"learning_rate": 1.0329408020369192e-05,
|
| 109 |
+
"loss": 1.1958,
|
| 110 |
+
"step": 6500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.23,
|
| 114 |
+
"learning_rate": 1.112507956715468e-05,
|
| 115 |
+
"loss": 1.1903,
|
| 116 |
+
"step": 7000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.39,
|
| 120 |
+
"learning_rate": 1.1919159770846595e-05,
|
| 121 |
+
"loss": 1.1805,
|
| 122 |
+
"step": 7500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.55,
|
| 126 |
+
"learning_rate": 1.271483131763208e-05,
|
| 127 |
+
"loss": 1.1802,
|
| 128 |
+
"step": 8000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.71,
|
| 132 |
+
"learning_rate": 1.3510502864417568e-05,
|
| 133 |
+
"loss": 1.1926,
|
| 134 |
+
"step": 8500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.86,
|
| 138 |
+
"learning_rate": 1.4306174411203055e-05,
|
| 139 |
+
"loss": 1.1741,
|
| 140 |
+
"step": 9000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.0,
|
| 144 |
+
"eval_accuracy": 0.4888370056909383,
|
| 145 |
+
"eval_f1": 0.24259459459459462,
|
| 146 |
+
"eval_loss": 1.1829431056976318,
|
| 147 |
+
"eval_precision": 0.15371968762844226,
|
| 148 |
+
"eval_recall": 0.5750896975909789,
|
| 149 |
+
"eval_runtime": 105.5508,
|
| 150 |
+
"eval_samples_per_second": 129.852,
|
| 151 |
+
"eval_steps_per_second": 16.239,
|
| 152 |
+
"step": 9426
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.02,
|
| 156 |
+
"learning_rate": 1.5101845957988542e-05,
|
| 157 |
+
"loss": 1.1848,
|
| 158 |
+
"step": 9500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.18,
|
| 162 |
+
"learning_rate": 1.589751750477403e-05,
|
| 163 |
+
"loss": 1.1885,
|
| 164 |
+
"step": 10000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.34,
|
| 168 |
+
"learning_rate": 1.6693189051559517e-05,
|
| 169 |
+
"loss": 1.178,
|
| 170 |
+
"step": 10500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.5,
|
| 174 |
+
"learning_rate": 1.7488860598345004e-05,
|
| 175 |
+
"loss": 1.1823,
|
| 176 |
+
"step": 11000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.66,
|
| 180 |
+
"learning_rate": 1.828294080203692e-05,
|
| 181 |
+
"loss": 1.1783,
|
| 182 |
+
"step": 11500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.82,
|
| 186 |
+
"learning_rate": 1.9078612348822408e-05,
|
| 187 |
+
"loss": 1.1807,
|
| 188 |
+
"step": 12000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.98,
|
| 192 |
+
"learning_rate": 1.9874283895607895e-05,
|
| 193 |
+
"loss": 1.1737,
|
| 194 |
+
"step": 12500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.0,
|
| 198 |
+
"eval_accuracy": 0.4849700860936816,
|
| 199 |
+
"eval_f1": 0.26993484331368295,
|
| 200 |
+
"eval_loss": 1.1806172132492065,
|
| 201 |
+
"eval_precision": 0.16908525524747345,
|
| 202 |
+
"eval_recall": 0.6688877498718606,
|
| 203 |
+
"eval_runtime": 105.6153,
|
| 204 |
+
"eval_samples_per_second": 129.773,
|
| 205 |
+
"eval_steps_per_second": 16.229,
|
| 206 |
+
"step": 12568
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.14,
|
| 210 |
+
"learning_rate": 2.0669955442393383e-05,
|
| 211 |
+
"loss": 1.1733,
|
| 212 |
+
"step": 13000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.3,
|
| 216 |
+
"learning_rate": 2.14640356460853e-05,
|
| 217 |
+
"loss": 1.1763,
|
| 218 |
+
"step": 13500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.46,
|
| 222 |
+
"learning_rate": 2.2258115849777213e-05,
|
| 223 |
+
"loss": 1.1767,
|
| 224 |
+
"step": 14000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.61,
|
| 228 |
+
"learning_rate": 2.30537873965627e-05,
|
| 229 |
+
"loss": 1.1891,
|
| 230 |
+
"step": 14500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.77,
|
| 234 |
+
"learning_rate": 2.3849458943348187e-05,
|
| 235 |
+
"loss": 1.182,
|
| 236 |
+
"step": 15000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.93,
|
| 240 |
+
"learning_rate": 2.4645130490133675e-05,
|
| 241 |
+
"loss": 1.1839,
|
| 242 |
+
"step": 15500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 5.0,
|
| 246 |
+
"eval_accuracy": 0.4106960455275062,
|
| 247 |
+
"eval_f1": 0.25550742003871324,
|
| 248 |
+
"eval_loss": 1.1798352003097534,
|
| 249 |
+
"eval_precision": 0.1557653405259609,
|
| 250 |
+
"eval_recall": 0.7104049205535623,
|
| 251 |
+
"eval_runtime": 105.6302,
|
| 252 |
+
"eval_samples_per_second": 129.755,
|
| 253 |
+
"eval_steps_per_second": 16.226,
|
| 254 |
+
"step": 15710
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.09,
|
| 258 |
+
"learning_rate": 2.544080203691916e-05,
|
| 259 |
+
"loss": 1.1756,
|
| 260 |
+
"step": 16000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.25,
|
| 264 |
+
"learning_rate": 2.6236473583704646e-05,
|
| 265 |
+
"loss": 1.1727,
|
| 266 |
+
"step": 16500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.41,
|
| 270 |
+
"learning_rate": 2.7032145130490133e-05,
|
| 271 |
+
"loss": 1.1892,
|
| 272 |
+
"step": 17000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.57,
|
| 276 |
+
"learning_rate": 2.782781667727562e-05,
|
| 277 |
+
"loss": 1.1792,
|
| 278 |
+
"step": 17500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.73,
|
| 282 |
+
"learning_rate": 2.8621896880967537e-05,
|
| 283 |
+
"loss": 1.1858,
|
| 284 |
+
"step": 18000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 5.89,
|
| 288 |
+
"learning_rate": 2.941597708465945e-05,
|
| 289 |
+
"loss": 1.1694,
|
| 290 |
+
"step": 18500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.0,
|
| 294 |
+
"eval_accuracy": 0.39085072231139645,
|
| 295 |
+
"eval_f1": 0.25315323374183735,
|
| 296 |
+
"eval_loss": 1.1799324750900269,
|
| 297 |
+
"eval_precision": 0.15333766796705678,
|
| 298 |
+
"eval_recall": 0.7252690927729369,
|
| 299 |
+
"eval_runtime": 105.6599,
|
| 300 |
+
"eval_samples_per_second": 129.718,
|
| 301 |
+
"eval_steps_per_second": 16.222,
|
| 302 |
+
"step": 18852
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.05,
|
| 306 |
+
"learning_rate": 3.0211648631444938e-05,
|
| 307 |
+
"loss": 1.1804,
|
| 308 |
+
"step": 19000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.21,
|
| 312 |
+
"learning_rate": 3.100732017823043e-05,
|
| 313 |
+
"loss": 1.1857,
|
| 314 |
+
"step": 19500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 6.37,
|
| 318 |
+
"learning_rate": 3.1802991725015916e-05,
|
| 319 |
+
"loss": 1.178,
|
| 320 |
+
"step": 20000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.52,
|
| 324 |
+
"learning_rate": 3.25986632718014e-05,
|
| 325 |
+
"loss": 1.1785,
|
| 326 |
+
"step": 20500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.68,
|
| 330 |
+
"learning_rate": 3.339433481858688e-05,
|
| 331 |
+
"loss": 1.1887,
|
| 332 |
+
"step": 21000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.84,
|
| 336 |
+
"learning_rate": 3.419000636537237e-05,
|
| 337 |
+
"loss": 1.1636,
|
| 338 |
+
"step": 21500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.0,
|
| 342 |
+
"eval_accuracy": 0.4095286735736174,
|
| 343 |
+
"eval_f1": 0.255816091954023,
|
| 344 |
+
"eval_loss": 1.1779592037200928,
|
| 345 |
+
"eval_precision": 0.1558718063648588,
|
| 346 |
+
"eval_recall": 0.7129677088672476,
|
| 347 |
+
"eval_runtime": 105.6851,
|
| 348 |
+
"eval_samples_per_second": 129.687,
|
| 349 |
+
"eval_steps_per_second": 16.218,
|
| 350 |
+
"step": 21994
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 7.0,
|
| 354 |
+
"learning_rate": 3.498567791215786e-05,
|
| 355 |
+
"loss": 1.1821,
|
| 356 |
+
"step": 22000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 7.16,
|
| 360 |
+
"learning_rate": 3.5778166772756204e-05,
|
| 361 |
+
"loss": 1.1688,
|
| 362 |
+
"step": 22500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 7.32,
|
| 366 |
+
"learning_rate": 3.657383831954169e-05,
|
| 367 |
+
"loss": 1.1845,
|
| 368 |
+
"step": 23000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 7.48,
|
| 372 |
+
"learning_rate": 3.736950986632718e-05,
|
| 373 |
+
"loss": 1.1655,
|
| 374 |
+
"step": 23500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 7.64,
|
| 378 |
+
"learning_rate": 3.8165181413112666e-05,
|
| 379 |
+
"loss": 1.19,
|
| 380 |
+
"step": 24000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.8,
|
| 384 |
+
"learning_rate": 3.896085295989816e-05,
|
| 385 |
+
"loss": 1.184,
|
| 386 |
+
"step": 24500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 7.96,
|
| 390 |
+
"learning_rate": 3.975652450668365e-05,
|
| 391 |
+
"loss": 1.1808,
|
| 392 |
+
"step": 25000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 8.0,
|
| 396 |
+
"eval_accuracy": 0.4719830731066686,
|
| 397 |
+
"eval_f1": 0.26994855240593163,
|
| 398 |
+
"eval_loss": 1.177585244178772,
|
| 399 |
+
"eval_precision": 0.1680482290881688,
|
| 400 |
+
"eval_recall": 0.6858021527421835,
|
| 401 |
+
"eval_runtime": 105.6107,
|
| 402 |
+
"eval_samples_per_second": 129.779,
|
| 403 |
+
"eval_steps_per_second": 16.229,
|
| 404 |
+
"step": 25136
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 8.12,
|
| 408 |
+
"learning_rate": 4.0552196053469135e-05,
|
| 409 |
+
"loss": 1.1774,
|
| 410 |
+
"step": 25500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 8.27,
|
| 414 |
+
"learning_rate": 4.134786760025462e-05,
|
| 415 |
+
"loss": 1.1627,
|
| 416 |
+
"step": 26000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 8.43,
|
| 420 |
+
"learning_rate": 4.2141947803946535e-05,
|
| 421 |
+
"loss": 1.1773,
|
| 422 |
+
"step": 26500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 8.59,
|
| 426 |
+
"learning_rate": 4.293761935073202e-05,
|
| 427 |
+
"loss": 1.1902,
|
| 428 |
+
"step": 27000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 8.75,
|
| 432 |
+
"learning_rate": 4.373329089751751e-05,
|
| 433 |
+
"loss": 1.1792,
|
| 434 |
+
"step": 27500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 8.91,
|
| 438 |
+
"learning_rate": 4.4528962444303e-05,
|
| 439 |
+
"loss": 1.171,
|
| 440 |
+
"step": 28000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.0,
|
| 444 |
+
"eval_accuracy": 0.40989347730920767,
|
| 445 |
+
"eval_f1": 0.2570273746095903,
|
| 446 |
+
"eval_loss": 1.1790105104446411,
|
| 447 |
+
"eval_precision": 0.1565752658086178,
|
| 448 |
+
"eval_recall": 0.717068170169144,
|
| 449 |
+
"eval_runtime": 105.7455,
|
| 450 |
+
"eval_samples_per_second": 129.613,
|
| 451 |
+
"eval_steps_per_second": 16.209,
|
| 452 |
+
"step": 28278
|
| 453 |
+
}
|
| 454 |
+
],
|
| 455 |
+
"max_steps": 628400,
|
| 456 |
+
"num_train_epochs": 200,
|
| 457 |
+
"total_flos": 0.0,
|
| 458 |
+
"trial_name": null,
|
| 459 |
+
"trial_params": null
|
| 460 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebfee223d2fca02206e0537a3354f7e3524985d065f4f3059aec69c1a68011c6
|
| 3 |
+
size 3311
|