Training in progress, step 200, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f07faf6127d39169a72ebc1b375dd95836420665148e5c732581a23669ec2234
|
| 3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d93a52fad5d33875c072a85f36ce088d497e195ffd53e2e3592720d2337dce0b
|
| 3 |
size 335922386
|
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:fd8f18ccd06ecf2fa901c5d4b147731be385d926b5a1010e53cdee4a7e6e9e68
|
| 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:fe157715eb8e05b3bab2a7f2fafac33705dc4a1a9dd7f6d860c3a7f9597d78bb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1113,6 +1113,372 @@
|
|
| 1113 |
"eval_samples_per_second": 5.807,
|
| 1114 |
"eval_steps_per_second": 0.813,
|
| 1115 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
@@ -1136,12 +1502,12 @@
|
|
| 1136 |
"should_evaluate": false,
|
| 1137 |
"should_log": false,
|
| 1138 |
"should_save": true,
|
| 1139 |
-
"should_training_stop":
|
| 1140 |
},
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
-
"total_flos":
|
| 1145 |
"train_batch_size": 8,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.1996617466211319,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 1.7660044150110377,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1113 |
"eval_samples_per_second": 5.807,
|
| 1114 |
"eval_steps_per_second": 0.813,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.3333333333333333,
|
| 1119 |
+
"grad_norm": 0.22895404696464539,
|
| 1120 |
+
"learning_rate": 4.659698863221513e-05,
|
| 1121 |
+
"loss": 0.1954,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.3421633554083885,
|
| 1126 |
+
"grad_norm": 0.26738283038139343,
|
| 1127 |
+
"learning_rate": 4.481448235912671e-05,
|
| 1128 |
+
"loss": 0.1996,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.3509933774834437,
|
| 1133 |
+
"grad_norm": 0.23517753183841705,
|
| 1134 |
+
"learning_rate": 4.306073275629044e-05,
|
| 1135 |
+
"loss": 0.1866,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.359823399558499,
|
| 1140 |
+
"grad_norm": 0.24005506932735443,
|
| 1141 |
+
"learning_rate": 4.133621928133665e-05,
|
| 1142 |
+
"loss": 0.1938,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.368653421633554,
|
| 1147 |
+
"grad_norm": 0.2558877468109131,
|
| 1148 |
+
"learning_rate": 3.964141339903026e-05,
|
| 1149 |
+
"loss": 0.1885,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.3774834437086092,
|
| 1154 |
+
"grad_norm": 0.22536706924438477,
|
| 1155 |
+
"learning_rate": 3.797677845237696e-05,
|
| 1156 |
+
"loss": 0.1748,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.3863134657836644,
|
| 1161 |
+
"grad_norm": 0.24991802871227264,
|
| 1162 |
+
"learning_rate": 3.634276953594982e-05,
|
| 1163 |
+
"loss": 0.187,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.3951434878587197,
|
| 1168 |
+
"grad_norm": 0.22741112112998962,
|
| 1169 |
+
"learning_rate": 3.473983337147118e-05,
|
| 1170 |
+
"loss": 0.1728,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.403973509933775,
|
| 1175 |
+
"grad_norm": 0.247371643781662,
|
| 1176 |
+
"learning_rate": 3.316840818568315e-05,
|
| 1177 |
+
"loss": 0.1947,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.4128035320088301,
|
| 1182 |
+
"grad_norm": 0.2145814299583435,
|
| 1183 |
+
"learning_rate": 3.162892359054098e-05,
|
| 1184 |
+
"loss": 0.1477,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.4216335540838851,
|
| 1189 |
+
"grad_norm": 0.20137929916381836,
|
| 1190 |
+
"learning_rate": 3.0121800465761293e-05,
|
| 1191 |
+
"loss": 0.147,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.4304635761589404,
|
| 1196 |
+
"grad_norm": 0.22576574981212616,
|
| 1197 |
+
"learning_rate": 2.8647450843757897e-05,
|
| 1198 |
+
"loss": 0.1609,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.4392935982339956,
|
| 1203 |
+
"grad_norm": 0.20561394095420837,
|
| 1204 |
+
"learning_rate": 2.7206277796996144e-05,
|
| 1205 |
+
"loss": 0.1319,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.4481236203090508,
|
| 1210 |
+
"grad_norm": 0.22655843198299408,
|
| 1211 |
+
"learning_rate": 2.5798675327796993e-05,
|
| 1212 |
+
"loss": 0.1745,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.4569536423841059,
|
| 1217 |
+
"grad_norm": 0.24106654524803162,
|
| 1218 |
+
"learning_rate": 2.4425028260620715e-05,
|
| 1219 |
+
"loss": 0.1623,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.465783664459161,
|
| 1224 |
+
"grad_norm": 0.25789502263069153,
|
| 1225 |
+
"learning_rate": 2.3085712136859668e-05,
|
| 1226 |
+
"loss": 0.1694,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.4746136865342163,
|
| 1231 |
+
"grad_norm": 0.26895081996917725,
|
| 1232 |
+
"learning_rate": 2.178109311216913e-05,
|
| 1233 |
+
"loss": 0.1587,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.4834437086092715,
|
| 1238 |
+
"grad_norm": 0.30352866649627686,
|
| 1239 |
+
"learning_rate": 2.0511527856363912e-05,
|
| 1240 |
+
"loss": 0.1995,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.4922737306843268,
|
| 1245 |
+
"grad_norm": 0.5954450964927673,
|
| 1246 |
+
"learning_rate": 1.927736345590839e-05,
|
| 1247 |
+
"loss": 0.3586,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.501103752759382,
|
| 1252 |
+
"grad_norm": 0.21726396679878235,
|
| 1253 |
+
"learning_rate": 1.8078937319026654e-05,
|
| 1254 |
+
"loss": 0.2243,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.5099337748344372,
|
| 1259 |
+
"grad_norm": 0.22568368911743164,
|
| 1260 |
+
"learning_rate": 1.6916577083458228e-05,
|
| 1261 |
+
"loss": 0.2319,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.5187637969094923,
|
| 1266 |
+
"grad_norm": 0.23746433854103088,
|
| 1267 |
+
"learning_rate": 1.579060052688548e-05,
|
| 1268 |
+
"loss": 0.2414,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.5275938189845475,
|
| 1273 |
+
"grad_norm": 0.21537818014621735,
|
| 1274 |
+
"learning_rate": 1.4701315480056164e-05,
|
| 1275 |
+
"loss": 0.2029,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.5364238410596025,
|
| 1280 |
+
"grad_norm": 0.22447596490383148,
|
| 1281 |
+
"learning_rate": 1.3649019742625623e-05,
|
| 1282 |
+
"loss": 0.1825,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.5452538631346577,
|
| 1287 |
+
"grad_norm": 0.2091474086046219,
|
| 1288 |
+
"learning_rate": 1.2634001001741373e-05,
|
| 1289 |
+
"loss": 0.1776,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.5452538631346577,
|
| 1294 |
+
"eval_loss": 0.19788633286952972,
|
| 1295 |
+
"eval_runtime": 7.9222,
|
| 1296 |
+
"eval_samples_per_second": 6.311,
|
| 1297 |
+
"eval_steps_per_second": 0.884,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.554083885209713,
|
| 1302 |
+
"grad_norm": 0.22721268236637115,
|
| 1303 |
+
"learning_rate": 1.1656536753392287e-05,
|
| 1304 |
+
"loss": 0.2137,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.5629139072847682,
|
| 1309 |
+
"grad_norm": 0.20839567482471466,
|
| 1310 |
+
"learning_rate": 1.0716894226543953e-05,
|
| 1311 |
+
"loss": 0.1749,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.5717439293598234,
|
| 1316 |
+
"grad_norm": 0.21761561930179596,
|
| 1317 |
+
"learning_rate": 9.815330310080887e-06,
|
| 1318 |
+
"loss": 0.1772,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.5805739514348787,
|
| 1323 |
+
"grad_norm": 0.22803503274917603,
|
| 1324 |
+
"learning_rate": 8.952091482575824e-06,
|
| 1325 |
+
"loss": 0.1855,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.589403973509934,
|
| 1330 |
+
"grad_norm": 0.21269898116588593,
|
| 1331 |
+
"learning_rate": 8.127413744904804e-06,
|
| 1332 |
+
"loss": 0.1775,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.598233995584989,
|
| 1337 |
+
"grad_norm": 0.22217035293579102,
|
| 1338 |
+
"learning_rate": 7.34152255572697e-06,
|
| 1339 |
+
"loss": 0.2023,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.6070640176600441,
|
| 1344 |
+
"grad_norm": 0.21203316748142242,
|
| 1345 |
+
"learning_rate": 6.594632769846353e-06,
|
| 1346 |
+
"loss": 0.1833,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.6158940397350994,
|
| 1351 |
+
"grad_norm": 0.20570416748523712,
|
| 1352 |
+
"learning_rate": 5.886948579472778e-06,
|
| 1353 |
+
"loss": 0.1535,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.6247240618101544,
|
| 1358 |
+
"grad_norm": 0.22212745249271393,
|
| 1359 |
+
"learning_rate": 5.218663458397715e-06,
|
| 1360 |
+
"loss": 0.1816,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.6335540838852096,
|
| 1365 |
+
"grad_norm": 0.22477659583091736,
|
| 1366 |
+
"learning_rate": 4.589960109100444e-06,
|
| 1367 |
+
"loss": 0.1934,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.6423841059602649,
|
| 1372 |
+
"grad_norm": 0.21524512767791748,
|
| 1373 |
+
"learning_rate": 4.001010412799138e-06,
|
| 1374 |
+
"loss": 0.1755,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.65121412803532,
|
| 1379 |
+
"grad_norm": 0.2027374505996704,
|
| 1380 |
+
"learning_rate": 3.451975382460109e-06,
|
| 1381 |
+
"loss": 0.1684,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.6600441501103753,
|
| 1386 |
+
"grad_norm": 0.1885063648223877,
|
| 1387 |
+
"learning_rate": 2.9430051187785962e-06,
|
| 1388 |
+
"loss": 0.1393,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.6688741721854305,
|
| 1393 |
+
"grad_norm": 0.20242398977279663,
|
| 1394 |
+
"learning_rate": 2.4742387691426445e-06,
|
| 1395 |
+
"loss": 0.1542,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.6777041942604858,
|
| 1400 |
+
"grad_norm": 0.20245841145515442,
|
| 1401 |
+
"learning_rate": 2.0458044895916513e-06,
|
| 1402 |
+
"loss": 0.1246,
|
| 1403 |
+
"step": 190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.6865342163355408,
|
| 1407 |
+
"grad_norm": 0.19838440418243408,
|
| 1408 |
+
"learning_rate": 1.6578194097797258e-06,
|
| 1409 |
+
"loss": 0.15,
|
| 1410 |
+
"step": 191
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.695364238410596,
|
| 1414 |
+
"grad_norm": 0.19168749451637268,
|
| 1415 |
+
"learning_rate": 1.3103896009537207e-06,
|
| 1416 |
+
"loss": 0.1339,
|
| 1417 |
+
"step": 192
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.7041942604856513,
|
| 1421 |
+
"grad_norm": 0.21052022278308868,
|
| 1422 |
+
"learning_rate": 1.0036100469542786e-06,
|
| 1423 |
+
"loss": 0.1397,
|
| 1424 |
+
"step": 193
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.7130242825607063,
|
| 1428 |
+
"grad_norm": 0.24240228533744812,
|
| 1429 |
+
"learning_rate": 7.375646182482875e-07,
|
| 1430 |
+
"loss": 0.1545,
|
| 1431 |
+
"step": 194
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.7218543046357615,
|
| 1435 |
+
"grad_norm": 0.2707175314426422,
|
| 1436 |
+
"learning_rate": 5.123260489995229e-07,
|
| 1437 |
+
"loss": 0.1654,
|
| 1438 |
+
"step": 195
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.7306843267108167,
|
| 1442 |
+
"grad_norm": 0.3442803621292114,
|
| 1443 |
+
"learning_rate": 3.2795591718381975e-07,
|
| 1444 |
+
"loss": 0.2205,
|
| 1445 |
+
"step": 196
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.739514348785872,
|
| 1449 |
+
"grad_norm": 0.7022460103034973,
|
| 1450 |
+
"learning_rate": 1.8450462775428942e-07,
|
| 1451 |
+
"loss": 0.3136,
|
| 1452 |
+
"step": 197
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.7483443708609272,
|
| 1456 |
+
"grad_norm": 0.190536230802536,
|
| 1457 |
+
"learning_rate": 8.201139886109264e-08,
|
| 1458 |
+
"loss": 0.2159,
|
| 1459 |
+
"step": 198
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.7571743929359824,
|
| 1463 |
+
"grad_norm": 0.21792356669902802,
|
| 1464 |
+
"learning_rate": 2.0504251129649374e-08,
|
| 1465 |
+
"loss": 0.2479,
|
| 1466 |
+
"step": 199
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.7660044150110377,
|
| 1470 |
+
"grad_norm": 0.22573994100093842,
|
| 1471 |
+
"learning_rate": 0.0,
|
| 1472 |
+
"loss": 0.2372,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.7660044150110377,
|
| 1477 |
+
"eval_loss": 0.1996617466211319,
|
| 1478 |
+
"eval_runtime": 8.6103,
|
| 1479 |
+
"eval_samples_per_second": 5.807,
|
| 1480 |
+
"eval_steps_per_second": 0.813,
|
| 1481 |
+
"step": 200
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
|
|
| 1502 |
"should_evaluate": false,
|
| 1503 |
"should_log": false,
|
| 1504 |
"should_save": true,
|
| 1505 |
+
"should_training_stop": true
|
| 1506 |
},
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
+
"total_flos": 4.3349111537821286e+17,
|
| 1511 |
"train_batch_size": 8,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|