Commit
•
5c972c9
1
Parent(s):
c7b0544
Training in progress, step 2000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +363 -3
- pytorch_model.bin +1 -1
- runs/Feb08_07-03-50_74bc69b4becb/events.out.tfevents.1675839843.74bc69b4becb.290.8 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4115013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f3a3e48a26a2d622517197ff24d94300acf16b986c0e194767a2c3e5fb70890
|
| 3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e4b616d5ea5f92c203d471e43b622d1302d66f27b9105c5655030fdf5c7e986
|
| 3 |
size 2329702453
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e491699f12f10fb03cc72b55406e2697d49735bc8f126f7938c3aea820b10f54
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:705762f34c23f694831c26f3540c14aaf4399a434031642b13285a5bcfd2e85c
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1086,11 +1086,371 @@
|
|
| 1086 |
"eval_samples_per_second": 0.23,
|
| 1087 |
"eval_steps_per_second": 0.23,
|
| 1088 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1089 |
}
|
| 1090 |
],
|
| 1091 |
"max_steps": 3542,
|
| 1092 |
"num_train_epochs": 7,
|
| 1093 |
-
"total_flos":
|
| 1094 |
"trial_name": null,
|
| 1095 |
"trial_params": null
|
| 1096 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.95080754530884,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1086 |
"eval_samples_per_second": 0.23,
|
| 1087 |
"eval_steps_per_second": 0.23,
|
| 1088 |
"step": 1500
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.98,
|
| 1092 |
+
"learning_rate": 0.0002943221320973349,
|
| 1093 |
+
"loss": 0.1245,
|
| 1094 |
+
"step": 1510
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.0,
|
| 1098 |
+
"learning_rate": 0.00029287369640787947,
|
| 1099 |
+
"loss": 0.1917,
|
| 1100 |
+
"step": 1520
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 3.02,
|
| 1104 |
+
"learning_rate": 0.0002914252607184241,
|
| 1105 |
+
"loss": 0.205,
|
| 1106 |
+
"step": 1530
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.04,
|
| 1110 |
+
"learning_rate": 0.0002899768250289687,
|
| 1111 |
+
"loss": 0.1493,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 3.06,
|
| 1116 |
+
"learning_rate": 0.0002885283893395133,
|
| 1117 |
+
"loss": 0.1596,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 3.08,
|
| 1122 |
+
"learning_rate": 0.00028707995365005794,
|
| 1123 |
+
"loss": 0.1689,
|
| 1124 |
+
"step": 1560
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 3.1,
|
| 1128 |
+
"learning_rate": 0.0002856315179606025,
|
| 1129 |
+
"loss": 0.1371,
|
| 1130 |
+
"step": 1570
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.12,
|
| 1134 |
+
"learning_rate": 0.0002841830822711471,
|
| 1135 |
+
"loss": 0.1676,
|
| 1136 |
+
"step": 1580
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.14,
|
| 1140 |
+
"learning_rate": 0.0002827346465816918,
|
| 1141 |
+
"loss": 0.1441,
|
| 1142 |
+
"step": 1590
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 3.16,
|
| 1146 |
+
"learning_rate": 0.0002812862108922364,
|
| 1147 |
+
"loss": 0.1436,
|
| 1148 |
+
"step": 1600
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.16,
|
| 1152 |
+
"eval_loss": 0.8872199058532715,
|
| 1153 |
+
"eval_rouge1": 0.16825396825396824,
|
| 1154 |
+
"eval_rouge2": 0.05833333333333333,
|
| 1155 |
+
"eval_rougeL": 0.1650793650793651,
|
| 1156 |
+
"eval_rougeLsum": 0.17285714285714288,
|
| 1157 |
+
"eval_runtime": 83.5131,
|
| 1158 |
+
"eval_samples_per_second": 0.239,
|
| 1159 |
+
"eval_steps_per_second": 0.239,
|
| 1160 |
+
"step": 1600
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.18,
|
| 1164 |
+
"learning_rate": 0.000279837775202781,
|
| 1165 |
+
"loss": 0.2173,
|
| 1166 |
+
"step": 1610
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 3.2,
|
| 1170 |
+
"learning_rate": 0.00027838933951332564,
|
| 1171 |
+
"loss": 0.1457,
|
| 1172 |
+
"step": 1620
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 3.22,
|
| 1176 |
+
"learning_rate": 0.0002769409038238702,
|
| 1177 |
+
"loss": 0.1503,
|
| 1178 |
+
"step": 1630
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.24,
|
| 1182 |
+
"learning_rate": 0.00027549246813441487,
|
| 1183 |
+
"loss": 0.1371,
|
| 1184 |
+
"step": 1640
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 3.26,
|
| 1188 |
+
"learning_rate": 0.00027404403244495946,
|
| 1189 |
+
"loss": 0.1331,
|
| 1190 |
+
"step": 1650
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 3.28,
|
| 1194 |
+
"learning_rate": 0.00027259559675550405,
|
| 1195 |
+
"loss": 0.2068,
|
| 1196 |
+
"step": 1660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 3.3,
|
| 1200 |
+
"learning_rate": 0.0002711471610660487,
|
| 1201 |
+
"loss": 0.2001,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 3.32,
|
| 1206 |
+
"learning_rate": 0.0002696987253765933,
|
| 1207 |
+
"loss": 0.177,
|
| 1208 |
+
"step": 1680
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 3.34,
|
| 1212 |
+
"learning_rate": 0.00026825028968713787,
|
| 1213 |
+
"loss": 0.1772,
|
| 1214 |
+
"step": 1690
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 3.36,
|
| 1218 |
+
"learning_rate": 0.0002668018539976825,
|
| 1219 |
+
"loss": 0.138,
|
| 1220 |
+
"step": 1700
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.36,
|
| 1224 |
+
"eval_loss": 0.8929020762443542,
|
| 1225 |
+
"eval_rouge1": 0.22999999999999998,
|
| 1226 |
+
"eval_rouge2": 0.12491883116883117,
|
| 1227 |
+
"eval_rougeL": 0.22615384615384615,
|
| 1228 |
+
"eval_rougeLsum": 0.23115384615384618,
|
| 1229 |
+
"eval_runtime": 86.6494,
|
| 1230 |
+
"eval_samples_per_second": 0.231,
|
| 1231 |
+
"eval_steps_per_second": 0.231,
|
| 1232 |
+
"step": 1700
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 3.38,
|
| 1236 |
+
"learning_rate": 0.0002653534183082271,
|
| 1237 |
+
"loss": 0.164,
|
| 1238 |
+
"step": 1710
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 3.4,
|
| 1242 |
+
"learning_rate": 0.0002639049826187717,
|
| 1243 |
+
"loss": 0.1249,
|
| 1244 |
+
"step": 1720
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 3.42,
|
| 1248 |
+
"learning_rate": 0.00026245654692931634,
|
| 1249 |
+
"loss": 0.1356,
|
| 1250 |
+
"step": 1730
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 3.44,
|
| 1254 |
+
"learning_rate": 0.000261008111239861,
|
| 1255 |
+
"loss": 0.1374,
|
| 1256 |
+
"step": 1740
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 3.46,
|
| 1260 |
+
"learning_rate": 0.00025955967555040557,
|
| 1261 |
+
"loss": 0.2013,
|
| 1262 |
+
"step": 1750
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.48,
|
| 1266 |
+
"learning_rate": 0.0002581112398609502,
|
| 1267 |
+
"loss": 0.1337,
|
| 1268 |
+
"step": 1760
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 3.5,
|
| 1272 |
+
"learning_rate": 0.0002566628041714948,
|
| 1273 |
+
"loss": 0.1226,
|
| 1274 |
+
"step": 1770
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 3.52,
|
| 1278 |
+
"learning_rate": 0.0002552143684820394,
|
| 1279 |
+
"loss": 0.1166,
|
| 1280 |
+
"step": 1780
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 3.54,
|
| 1284 |
+
"learning_rate": 0.00025376593279258404,
|
| 1285 |
+
"loss": 0.2308,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 3.56,
|
| 1290 |
+
"learning_rate": 0.00025231749710312863,
|
| 1291 |
+
"loss": 0.1265,
|
| 1292 |
+
"step": 1800
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 3.56,
|
| 1296 |
+
"eval_loss": 0.9203845858573914,
|
| 1297 |
+
"eval_rouge1": 0.17454545454545453,
|
| 1298 |
+
"eval_rouge2": 0.07291666666666667,
|
| 1299 |
+
"eval_rougeL": 0.16999999999999998,
|
| 1300 |
+
"eval_rougeLsum": 0.17727272727272728,
|
| 1301 |
+
"eval_runtime": 87.9704,
|
| 1302 |
+
"eval_samples_per_second": 0.227,
|
| 1303 |
+
"eval_steps_per_second": 0.227,
|
| 1304 |
+
"step": 1800
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.58,
|
| 1308 |
+
"learning_rate": 0.0002508690614136732,
|
| 1309 |
+
"loss": 0.1526,
|
| 1310 |
+
"step": 1810
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 3.6,
|
| 1314 |
+
"learning_rate": 0.00024942062572421786,
|
| 1315 |
+
"loss": 0.2201,
|
| 1316 |
+
"step": 1820
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 3.62,
|
| 1320 |
+
"learning_rate": 0.00024797219003476245,
|
| 1321 |
+
"loss": 0.1271,
|
| 1322 |
+
"step": 1830
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 3.64,
|
| 1326 |
+
"learning_rate": 0.0002465237543453071,
|
| 1327 |
+
"loss": 0.1749,
|
| 1328 |
+
"step": 1840
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 3.65,
|
| 1332 |
+
"learning_rate": 0.0002450753186558517,
|
| 1333 |
+
"loss": 0.133,
|
| 1334 |
+
"step": 1850
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 3.67,
|
| 1338 |
+
"learning_rate": 0.0002436268829663963,
|
| 1339 |
+
"loss": 0.2259,
|
| 1340 |
+
"step": 1860
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.69,
|
| 1344 |
+
"learning_rate": 0.00024217844727694092,
|
| 1345 |
+
"loss": 0.1549,
|
| 1346 |
+
"step": 1870
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 3.71,
|
| 1350 |
+
"learning_rate": 0.00024073001158748554,
|
| 1351 |
+
"loss": 0.1173,
|
| 1352 |
+
"step": 1880
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 3.73,
|
| 1356 |
+
"learning_rate": 0.00023928157589803013,
|
| 1357 |
+
"loss": 0.1337,
|
| 1358 |
+
"step": 1890
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 3.75,
|
| 1362 |
+
"learning_rate": 0.00023783314020857474,
|
| 1363 |
+
"loss": 0.1828,
|
| 1364 |
+
"step": 1900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 3.75,
|
| 1368 |
+
"eval_loss": 0.9094276428222656,
|
| 1369 |
+
"eval_rouge1": 0.18,
|
| 1370 |
+
"eval_rouge2": 0.14886363636363636,
|
| 1371 |
+
"eval_rougeL": 0.18,
|
| 1372 |
+
"eval_rougeLsum": 0.18615384615384614,
|
| 1373 |
+
"eval_runtime": 84.5106,
|
| 1374 |
+
"eval_samples_per_second": 0.237,
|
| 1375 |
+
"eval_steps_per_second": 0.237,
|
| 1376 |
+
"step": 1900
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 3.77,
|
| 1380 |
+
"learning_rate": 0.00023638470451911936,
|
| 1381 |
+
"loss": 0.1821,
|
| 1382 |
+
"step": 1910
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 3.79,
|
| 1386 |
+
"learning_rate": 0.00023493626882966395,
|
| 1387 |
+
"loss": 0.1257,
|
| 1388 |
+
"step": 1920
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 3.81,
|
| 1392 |
+
"learning_rate": 0.00023348783314020857,
|
| 1393 |
+
"loss": 0.172,
|
| 1394 |
+
"step": 1930
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 3.83,
|
| 1398 |
+
"learning_rate": 0.0002320393974507532,
|
| 1399 |
+
"loss": 0.1833,
|
| 1400 |
+
"step": 1940
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 3.85,
|
| 1404 |
+
"learning_rate": 0.0002305909617612978,
|
| 1405 |
+
"loss": 0.1334,
|
| 1406 |
+
"step": 1950
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 3.87,
|
| 1410 |
+
"learning_rate": 0.00022914252607184242,
|
| 1411 |
+
"loss": 0.1736,
|
| 1412 |
+
"step": 1960
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 3.89,
|
| 1416 |
+
"learning_rate": 0.00022769409038238703,
|
| 1417 |
+
"loss": 0.1163,
|
| 1418 |
+
"step": 1970
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 3.91,
|
| 1422 |
+
"learning_rate": 0.00022624565469293165,
|
| 1423 |
+
"loss": 0.1844,
|
| 1424 |
+
"step": 1980
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.93,
|
| 1428 |
+
"learning_rate": 0.00022479721900347624,
|
| 1429 |
+
"loss": 0.1358,
|
| 1430 |
+
"step": 1990
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 3.95,
|
| 1434 |
+
"learning_rate": 0.00022334878331402086,
|
| 1435 |
+
"loss": 0.1447,
|
| 1436 |
+
"step": 2000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 3.95,
|
| 1440 |
+
"eval_loss": 0.89415442943573,
|
| 1441 |
+
"eval_rouge1": 0.19,
|
| 1442 |
+
"eval_rouge2": 0.09886363636363635,
|
| 1443 |
+
"eval_rougeL": 0.18615384615384617,
|
| 1444 |
+
"eval_rougeLsum": 0.19615384615384615,
|
| 1445 |
+
"eval_runtime": 84.0506,
|
| 1446 |
+
"eval_samples_per_second": 0.238,
|
| 1447 |
+
"eval_steps_per_second": 0.238,
|
| 1448 |
+
"step": 2000
|
| 1449 |
}
|
| 1450 |
],
|
| 1451 |
"max_steps": 3542,
|
| 1452 |
"num_train_epochs": 7,
|
| 1453 |
+
"total_flos": 4.862361100638413e+16,
|
| 1454 |
"trial_name": null,
|
| 1455 |
"trial_params": null
|
| 1456 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e4b616d5ea5f92c203d471e43b622d1302d66f27b9105c5655030fdf5c7e986
|
| 3 |
size 2329702453
|
runs/Feb08_07-03-50_74bc69b4becb/events.out.tfevents.1675839843.74bc69b4becb.290.8
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89707d0ed5076499409b04d8894868bee0b330defbf8965e5c00268b2a46dfb4
|
| 3 |
+
size 34894
|