Training in progress, step 200, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 64219860
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f8009fdc806005f5a11dfe3d501909749d95aec61cb68fbf25b5adf49c5f6f1
|
| 3 |
size 64219860
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8779be528e2ba9d45d281b632c7cda2125c1a7d2be8d038725dbddeb1c305ce9
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 11.704,
|
| 1090 |
"eval_steps_per_second": 5.852,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1103,12 +1461,12 @@
|
|
| 1103 |
"should_evaluate": false,
|
| 1104 |
"should_log": false,
|
| 1105 |
"should_save": true,
|
| 1106 |
-
"should_training_stop":
|
| 1107 |
},
|
| 1108 |
"attributes": {}
|
| 1109 |
}
|
| 1110 |
},
|
| 1111 |
-
"total_flos":
|
| 1112 |
"train_batch_size": 2,
|
| 1113 |
"trial_name": null,
|
| 1114 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.008441668073611346,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 11.704,
|
| 1090 |
"eval_steps_per_second": 5.852,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.006373459395576566,
|
| 1095 |
+
"grad_norm": NaN,
|
| 1096 |
+
"learning_rate": 3.106465908814342e-05,
|
| 1097 |
+
"loss": 0.0,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.006415667735944623,
|
| 1102 |
+
"grad_norm": NaN,
|
| 1103 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 1104 |
+
"loss": 0.0,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.00645787607631268,
|
| 1109 |
+
"grad_norm": NaN,
|
| 1110 |
+
"learning_rate": 2.87071551708603e-05,
|
| 1111 |
+
"loss": 0.0,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.0065000844166807365,
|
| 1116 |
+
"grad_norm": NaN,
|
| 1117 |
+
"learning_rate": 2.7557479520891104e-05,
|
| 1118 |
+
"loss": 0.0,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0065422927570487925,
|
| 1123 |
+
"grad_norm": NaN,
|
| 1124 |
+
"learning_rate": 2.6427608932686843e-05,
|
| 1125 |
+
"loss": 0.0,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.006584501097416849,
|
| 1130 |
+
"grad_norm": NaN,
|
| 1131 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 1132 |
+
"loss": 0.0,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.006626709437784906,
|
| 1137 |
+
"grad_norm": NaN,
|
| 1138 |
+
"learning_rate": 2.422851302396655e-05,
|
| 1139 |
+
"loss": 0.0,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.006668917778152963,
|
| 1144 |
+
"grad_norm": NaN,
|
| 1145 |
+
"learning_rate": 2.315988891431412e-05,
|
| 1146 |
+
"loss": 0.0,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.00671112611852102,
|
| 1151 |
+
"grad_norm": NaN,
|
| 1152 |
+
"learning_rate": 2.2112272123788768e-05,
|
| 1153 |
+
"loss": 0.0,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.006753334458889077,
|
| 1158 |
+
"grad_norm": NaN,
|
| 1159 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 1160 |
+
"loss": 0.0,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0067955427992571335,
|
| 1165 |
+
"grad_norm": NaN,
|
| 1166 |
+
"learning_rate": 2.008120031050753e-05,
|
| 1167 |
+
"loss": 0.0,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.00683775113962519,
|
| 1172 |
+
"grad_norm": NaN,
|
| 1173 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 1174 |
+
"loss": 0.0,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.006879959479993246,
|
| 1179 |
+
"grad_norm": NaN,
|
| 1180 |
+
"learning_rate": 1.8137518531330767e-05,
|
| 1181 |
+
"loss": 0.0,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.006922167820361303,
|
| 1186 |
+
"grad_norm": NaN,
|
| 1187 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 1188 |
+
"loss": 0.0,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.00696437616072936,
|
| 1193 |
+
"grad_norm": NaN,
|
| 1194 |
+
"learning_rate": 1.6283352173747145e-05,
|
| 1195 |
+
"loss": 0.0,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.007006584501097417,
|
| 1200 |
+
"grad_norm": NaN,
|
| 1201 |
+
"learning_rate": 1.5390474757906446e-05,
|
| 1202 |
+
"loss": 0.0,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.007048792841465474,
|
| 1207 |
+
"grad_norm": NaN,
|
| 1208 |
+
"learning_rate": 1.4520728741446089e-05,
|
| 1209 |
+
"loss": 0.0,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.00709100118183353,
|
| 1214 |
+
"grad_norm": NaN,
|
| 1215 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 1216 |
+
"loss": 0.0,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.007133209522201587,
|
| 1221 |
+
"grad_norm": NaN,
|
| 1222 |
+
"learning_rate": 1.2851575637272262e-05,
|
| 1223 |
+
"loss": 1.5238,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.007175417862569644,
|
| 1228 |
+
"grad_norm": NaN,
|
| 1229 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 1230 |
+
"loss": 0.0,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.007217626202937701,
|
| 1235 |
+
"grad_norm": NaN,
|
| 1236 |
+
"learning_rate": 1.1277718055638819e-05,
|
| 1237 |
+
"loss": 0.0,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.007259834543305757,
|
| 1242 |
+
"grad_norm": NaN,
|
| 1243 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 1244 |
+
"loss": 0.0,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.007302042883673814,
|
| 1249 |
+
"grad_norm": NaN,
|
| 1250 |
+
"learning_rate": 9.80087698670411e-06,
|
| 1251 |
+
"loss": 0.0,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0073442512240418706,
|
| 1256 |
+
"grad_norm": NaN,
|
| 1257 |
+
"learning_rate": 9.09934649508375e-06,
|
| 1258 |
+
"loss": 0.0,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.007386459564409927,
|
| 1263 |
+
"grad_norm": NaN,
|
| 1264 |
+
"learning_rate": 8.422667334494249e-06,
|
| 1265 |
+
"loss": 0.0,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.007428667904777984,
|
| 1270 |
+
"grad_norm": NaN,
|
| 1271 |
+
"learning_rate": 7.771024502261526e-06,
|
| 1272 |
+
"loss": 0.0,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.007470876245146041,
|
| 1277 |
+
"grad_norm": NaN,
|
| 1278 |
+
"learning_rate": 7.144596151029303e-06,
|
| 1279 |
+
"loss": 0.0,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.007513084585514098,
|
| 1284 |
+
"grad_norm": NaN,
|
| 1285 |
+
"learning_rate": 6.543553540053926e-06,
|
| 1286 |
+
"loss": 1.9954,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.007555292925882155,
|
| 1291 |
+
"grad_norm": NaN,
|
| 1292 |
+
"learning_rate": 5.968060988383883e-06,
|
| 1293 |
+
"loss": 0.0,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.007597501266250211,
|
| 1298 |
+
"grad_norm": NaN,
|
| 1299 |
+
"learning_rate": 5.418275829936537e-06,
|
| 1300 |
+
"loss": 0.0,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.0076397096066182675,
|
| 1305 |
+
"grad_norm": NaN,
|
| 1306 |
+
"learning_rate": 4.8943483704846475e-06,
|
| 1307 |
+
"loss": 0.0,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.007681917946986324,
|
| 1312 |
+
"grad_norm": NaN,
|
| 1313 |
+
"learning_rate": 4.3964218465642355e-06,
|
| 1314 |
+
"loss": 0.0,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.007724126287354381,
|
| 1319 |
+
"grad_norm": NaN,
|
| 1320 |
+
"learning_rate": 3.924632386315186e-06,
|
| 1321 |
+
"loss": 0.0,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.007766334627722438,
|
| 1326 |
+
"grad_norm": NaN,
|
| 1327 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 1328 |
+
"loss": 0.0,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.007808542968090495,
|
| 1333 |
+
"grad_norm": NaN,
|
| 1334 |
+
"learning_rate": 3.059973406066963e-06,
|
| 1335 |
+
"loss": 0.0,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.007850751308458552,
|
| 1340 |
+
"grad_norm": NaN,
|
| 1341 |
+
"learning_rate": 2.667340275199426e-06,
|
| 1342 |
+
"loss": 0.0,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.007892959648826608,
|
| 1347 |
+
"grad_norm": NaN,
|
| 1348 |
+
"learning_rate": 2.3013169216400733e-06,
|
| 1349 |
+
"loss": 0.0,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.007935167989194665,
|
| 1354 |
+
"grad_norm": NaN,
|
| 1355 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 1356 |
+
"loss": 0.0,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.007977376329562722,
|
| 1361 |
+
"grad_norm": NaN,
|
| 1362 |
+
"learning_rate": 1.6494925127617634e-06,
|
| 1363 |
+
"loss": 0.0,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.008019584669930779,
|
| 1368 |
+
"grad_norm": NaN,
|
| 1369 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 1370 |
+
"loss": 0.0,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.008061793010298836,
|
| 1375 |
+
"grad_norm": NaN,
|
| 1376 |
+
"learning_rate": 1.1052129398531507e-06,
|
| 1377 |
+
"loss": 0.0,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.008104001350666891,
|
| 1382 |
+
"grad_norm": NaN,
|
| 1383 |
+
"learning_rate": 8.735930673024806e-07,
|
| 1384 |
+
"loss": 0.0,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.008146209691034948,
|
| 1389 |
+
"grad_norm": NaN,
|
| 1390 |
+
"learning_rate": 6.690733646361857e-07,
|
| 1391 |
+
"loss": 0.0,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.008188418031403005,
|
| 1396 |
+
"grad_norm": NaN,
|
| 1397 |
+
"learning_rate": 4.917097454988584e-07,
|
| 1398 |
+
"loss": 0.0,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.008230626371771061,
|
| 1403 |
+
"grad_norm": NaN,
|
| 1404 |
+
"learning_rate": 3.415506993330153e-07,
|
| 1405 |
+
"loss": 2.0765,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.008272834712139118,
|
| 1410 |
+
"grad_norm": NaN,
|
| 1411 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 1412 |
+
"loss": 0.0,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.008315043052507175,
|
| 1417 |
+
"grad_norm": NaN,
|
| 1418 |
+
"learning_rate": 1.230030851695263e-07,
|
| 1419 |
+
"loss": 0.0,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.008357251392875232,
|
| 1424 |
+
"grad_norm": NaN,
|
| 1425 |
+
"learning_rate": 5.467426590739511e-08,
|
| 1426 |
+
"loss": 0.0,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.008399459733243289,
|
| 1431 |
+
"grad_norm": NaN,
|
| 1432 |
+
"learning_rate": 1.3669500753099585e-08,
|
| 1433 |
+
"loss": 0.0,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.008441668073611346,
|
| 1438 |
+
"grad_norm": NaN,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.0,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.008441668073611346,
|
| 1445 |
+
"eval_loss": NaN,
|
| 1446 |
+
"eval_runtime": 851.7167,
|
| 1447 |
+
"eval_samples_per_second": 11.713,
|
| 1448 |
+
"eval_steps_per_second": 5.856,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1461 |
"should_evaluate": false,
|
| 1462 |
"should_log": false,
|
| 1463 |
"should_save": true,
|
| 1464 |
+
"should_training_stop": true
|
| 1465 |
},
|
| 1466 |
"attributes": {}
|
| 1467 |
}
|
| 1468 |
},
|
| 1469 |
+
"total_flos": 1.203470561968128e+17,
|
| 1470 |
"train_batch_size": 2,
|
| 1471 |
"trial_name": null,
|
| 1472 |
"trial_params": null
|