Checkpoint 2032
Browse files- config.json +1 -1
- model.safetensors +2 -2
- trainer_state.json +359 -2
config.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"bos_token_id": 0,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
"cls_token_id": 0,
|
| 10 |
-
"dtype": "
|
| 11 |
"eos_token_id": 1,
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
|
|
|
| 7 |
"bos_token_id": 0,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
"cls_token_id": 0,
|
| 10 |
+
"dtype": "float32",
|
| 11 |
"eos_token_id": 1,
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
model.safetensors
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:d962f5f2ab34269a713b2159215c844a6d7e6bb9da5a159e26d3a164845de2c2
|
| 3 |
+
size 1420398464
|
trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 1.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1072,6 +1072,363 @@
|
|
| 1072 |
"learning_rate": 2e-05,
|
| 1073 |
"loss": 1.8683,
|
| 1074 |
"step": 1520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1075 |
}
|
| 1076 |
],
|
| 1077 |
"logging_steps": 10,
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.9941118743866535,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2032,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1072 |
"learning_rate": 2e-05,
|
| 1073 |
"loss": 1.8683,
|
| 1074 |
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.5014720314033365,
|
| 1078 |
+
"grad_norm": 24.893234252929688,
|
| 1079 |
+
"learning_rate": 2e-05,
|
| 1080 |
+
"loss": 2.7447,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.5112855740922473,
|
| 1085 |
+
"grad_norm": 20.632429122924805,
|
| 1086 |
+
"learning_rate": 2e-05,
|
| 1087 |
+
"loss": 2.0633,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.521099116781158,
|
| 1092 |
+
"grad_norm": 11.803605079650879,
|
| 1093 |
+
"learning_rate": 2e-05,
|
| 1094 |
+
"loss": 1.4992,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.5309126594700686,
|
| 1099 |
+
"grad_norm": 11.409942626953125,
|
| 1100 |
+
"learning_rate": 2e-05,
|
| 1101 |
+
"loss": 1.9619,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.5407262021589794,
|
| 1106 |
+
"grad_norm": 19.285724639892578,
|
| 1107 |
+
"learning_rate": 2e-05,
|
| 1108 |
+
"loss": 2.4316,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.5505397448478901,
|
| 1113 |
+
"grad_norm": 3.482271909713745,
|
| 1114 |
+
"learning_rate": 2e-05,
|
| 1115 |
+
"loss": 1.8275,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.5603532875368007,
|
| 1120 |
+
"grad_norm": 8.602056503295898,
|
| 1121 |
+
"learning_rate": 2e-05,
|
| 1122 |
+
"loss": 1.8139,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.5701668302257115,
|
| 1127 |
+
"grad_norm": 6.880626201629639,
|
| 1128 |
+
"learning_rate": 2e-05,
|
| 1129 |
+
"loss": 1.162,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.5799803729146222,
|
| 1134 |
+
"grad_norm": 10.55600643157959,
|
| 1135 |
+
"learning_rate": 2e-05,
|
| 1136 |
+
"loss": 1.8477,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.5897939156035328,
|
| 1141 |
+
"grad_norm": 5.864988327026367,
|
| 1142 |
+
"learning_rate": 2e-05,
|
| 1143 |
+
"loss": 1.0593,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.5996074582924436,
|
| 1148 |
+
"grad_norm": 11.867835998535156,
|
| 1149 |
+
"learning_rate": 2e-05,
|
| 1150 |
+
"loss": 1.8334,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.6094210009813543,
|
| 1155 |
+
"grad_norm": 8.558449745178223,
|
| 1156 |
+
"learning_rate": 2e-05,
|
| 1157 |
+
"loss": 1.7685,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.6192345436702649,
|
| 1162 |
+
"grad_norm": 7.745001792907715,
|
| 1163 |
+
"learning_rate": 2e-05,
|
| 1164 |
+
"loss": 1.1716,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.6290480863591756,
|
| 1169 |
+
"grad_norm": 25.266897201538086,
|
| 1170 |
+
"learning_rate": 2e-05,
|
| 1171 |
+
"loss": 1.1115,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.6388616290480864,
|
| 1176 |
+
"grad_norm": 2.910959243774414,
|
| 1177 |
+
"learning_rate": 2e-05,
|
| 1178 |
+
"loss": 1.5551,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.648675171736997,
|
| 1183 |
+
"grad_norm": 3.1996586322784424,
|
| 1184 |
+
"learning_rate": 2e-05,
|
| 1185 |
+
"loss": 2.0908,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.6584887144259077,
|
| 1190 |
+
"grad_norm": 7.940663814544678,
|
| 1191 |
+
"learning_rate": 2e-05,
|
| 1192 |
+
"loss": 2.1272,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.6683022571148185,
|
| 1197 |
+
"grad_norm": 10.518881797790527,
|
| 1198 |
+
"learning_rate": 2e-05,
|
| 1199 |
+
"loss": 2.2504,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.678115799803729,
|
| 1204 |
+
"grad_norm": 13.522726058959961,
|
| 1205 |
+
"learning_rate": 2e-05,
|
| 1206 |
+
"loss": 3.0516,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.6879293424926398,
|
| 1211 |
+
"grad_norm": 72.19231414794922,
|
| 1212 |
+
"learning_rate": 2e-05,
|
| 1213 |
+
"loss": 1.6259,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.6977428851815506,
|
| 1218 |
+
"grad_norm": 16.836326599121094,
|
| 1219 |
+
"learning_rate": 2e-05,
|
| 1220 |
+
"loss": 1.5319,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.7075564278704611,
|
| 1225 |
+
"grad_norm": 5.992958068847656,
|
| 1226 |
+
"learning_rate": 2e-05,
|
| 1227 |
+
"loss": 1.9591,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.717369970559372,
|
| 1232 |
+
"grad_norm": 16.606359481811523,
|
| 1233 |
+
"learning_rate": 2e-05,
|
| 1234 |
+
"loss": 2.8002,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.7271835132482827,
|
| 1239 |
+
"grad_norm": 13.355613708496094,
|
| 1240 |
+
"learning_rate": 2e-05,
|
| 1241 |
+
"loss": 1.202,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.7369970559371932,
|
| 1246 |
+
"grad_norm": 22.692291259765625,
|
| 1247 |
+
"learning_rate": 2e-05,
|
| 1248 |
+
"loss": 1.5828,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.746810598626104,
|
| 1253 |
+
"grad_norm": 4.382213592529297,
|
| 1254 |
+
"learning_rate": 2e-05,
|
| 1255 |
+
"loss": 1.3851,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.7566241413150148,
|
| 1260 |
+
"grad_norm": 18.94695281982422,
|
| 1261 |
+
"learning_rate": 2e-05,
|
| 1262 |
+
"loss": 1.6604,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.7664376840039253,
|
| 1267 |
+
"grad_norm": 4.105762958526611,
|
| 1268 |
+
"learning_rate": 2e-05,
|
| 1269 |
+
"loss": 2.3467,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.776251226692836,
|
| 1274 |
+
"grad_norm": 17.720151901245117,
|
| 1275 |
+
"learning_rate": 2e-05,
|
| 1276 |
+
"loss": 1.0744,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.7860647693817469,
|
| 1281 |
+
"grad_norm": 23.243711471557617,
|
| 1282 |
+
"learning_rate": 2e-05,
|
| 1283 |
+
"loss": 1.5227,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.7958783120706574,
|
| 1288 |
+
"grad_norm": 9.93882942199707,
|
| 1289 |
+
"learning_rate": 2e-05,
|
| 1290 |
+
"loss": 2.278,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.8056918547595682,
|
| 1295 |
+
"grad_norm": 47.31532287597656,
|
| 1296 |
+
"learning_rate": 2e-05,
|
| 1297 |
+
"loss": 2.4806,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.815505397448479,
|
| 1302 |
+
"grad_norm": 18.85761260986328,
|
| 1303 |
+
"learning_rate": 2e-05,
|
| 1304 |
+
"loss": 1.2861,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.8253189401373895,
|
| 1309 |
+
"grad_norm": 12.545721054077148,
|
| 1310 |
+
"learning_rate": 2e-05,
|
| 1311 |
+
"loss": 1.8076,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.8351324828263003,
|
| 1316 |
+
"grad_norm": 3.5376434326171875,
|
| 1317 |
+
"learning_rate": 2e-05,
|
| 1318 |
+
"loss": 1.8752,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.844946025515211,
|
| 1323 |
+
"grad_norm": 7.608773708343506,
|
| 1324 |
+
"learning_rate": 2e-05,
|
| 1325 |
+
"loss": 1.2668,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.8547595682041216,
|
| 1330 |
+
"grad_norm": 15.594606399536133,
|
| 1331 |
+
"learning_rate": 2e-05,
|
| 1332 |
+
"loss": 2.4341,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.8645731108930323,
|
| 1337 |
+
"grad_norm": 10.585665702819824,
|
| 1338 |
+
"learning_rate": 2e-05,
|
| 1339 |
+
"loss": 1.6737,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.8743866535819431,
|
| 1344 |
+
"grad_norm": 3.565300703048706,
|
| 1345 |
+
"learning_rate": 2e-05,
|
| 1346 |
+
"loss": 1.1942,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.8842001962708537,
|
| 1351 |
+
"grad_norm": 3.813704490661621,
|
| 1352 |
+
"learning_rate": 2e-05,
|
| 1353 |
+
"loss": 1.5228,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.8940137389597644,
|
| 1358 |
+
"grad_norm": 11.792035102844238,
|
| 1359 |
+
"learning_rate": 2e-05,
|
| 1360 |
+
"loss": 1.3769,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.9038272816486752,
|
| 1365 |
+
"grad_norm": 6.388332366943359,
|
| 1366 |
+
"learning_rate": 2e-05,
|
| 1367 |
+
"loss": 2.39,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.9136408243375858,
|
| 1372 |
+
"grad_norm": 6.338537216186523,
|
| 1373 |
+
"learning_rate": 2e-05,
|
| 1374 |
+
"loss": 1.3043,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.9234543670264965,
|
| 1379 |
+
"grad_norm": 6.711911201477051,
|
| 1380 |
+
"learning_rate": 2e-05,
|
| 1381 |
+
"loss": 1.2017,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.9332679097154073,
|
| 1386 |
+
"grad_norm": 8.049627304077148,
|
| 1387 |
+
"learning_rate": 2e-05,
|
| 1388 |
+
"loss": 0.9924,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.9430814524043178,
|
| 1393 |
+
"grad_norm": 15.855047225952148,
|
| 1394 |
+
"learning_rate": 2e-05,
|
| 1395 |
+
"loss": 1.5458,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.9528949950932286,
|
| 1400 |
+
"grad_norm": 27.410795211791992,
|
| 1401 |
+
"learning_rate": 2e-05,
|
| 1402 |
+
"loss": 1.5845,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.9627085377821394,
|
| 1407 |
+
"grad_norm": 10.094039916992188,
|
| 1408 |
+
"learning_rate": 2e-05,
|
| 1409 |
+
"loss": 2.6201,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.97252208047105,
|
| 1414 |
+
"grad_norm": 7.608443260192871,
|
| 1415 |
+
"learning_rate": 2e-05,
|
| 1416 |
+
"loss": 2.2552,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.9823356231599607,
|
| 1421 |
+
"grad_norm": 6.73370885848999,
|
| 1422 |
+
"learning_rate": 2e-05,
|
| 1423 |
+
"loss": 1.299,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.9921491658488715,
|
| 1428 |
+
"grad_norm": 13.77723217010498,
|
| 1429 |
+
"learning_rate": 2e-05,
|
| 1430 |
+
"loss": 1.3727,
|
| 1431 |
+
"step": 2030
|
| 1432 |
}
|
| 1433 |
],
|
| 1434 |
"logging_steps": 10,
|