Training in progress, step 187, 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 478211024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ebefe4723f943b5f9e84b2b96441bdcb43beaad4e54fae3a539e81a2158591d
|
| 3 |
size 478211024
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 243337876
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5975e7d7fd4807ee1871401af774c097434e2a30eb961d17234332d46e112d71
|
| 3 |
size 243337876
|
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:e6cb43a5bd9c7e834b5537f6c3a927e687f296f232d0ca0ec88fd4df23196657
|
| 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 sha256:668ec8597c3f420a63a11711389ba814235340c6b18085fdcc8191e9cdf0a8c6
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.1385369300842285,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch":
|
| 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 +1089,265 @@
|
|
| 1089 |
"eval_samples_per_second": 20.423,
|
| 1090 |
"eval_steps_per_second": 5.252,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1371,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos": 1.
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.1385369300842285,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 3.004016064257028,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 187,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 20.423,
|
| 1090 |
"eval_steps_per_second": 5.252,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 2.42570281124498,
|
| 1095 |
+
"grad_norm": 5.148977279663086,
|
| 1096 |
+
"learning_rate": 9.864418103451828e-06,
|
| 1097 |
+
"loss": 2.2449,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.4417670682730925,
|
| 1102 |
+
"grad_norm": 4.7471466064453125,
|
| 1103 |
+
"learning_rate": 9.34151817719166e-06,
|
| 1104 |
+
"loss": 1.7333,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 2.4578313253012047,
|
| 1109 |
+
"grad_norm": 5.056032180786133,
|
| 1110 |
+
"learning_rate": 8.831426594527975e-06,
|
| 1111 |
+
"loss": 1.7489,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.4738955823293174,
|
| 1116 |
+
"grad_norm": 5.261003017425537,
|
| 1117 |
+
"learning_rate": 8.334304045874247e-06,
|
| 1118 |
+
"loss": 1.6044,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.4899598393574296,
|
| 1123 |
+
"grad_norm": 5.535795211791992,
|
| 1124 |
+
"learning_rate": 7.850307136104247e-06,
|
| 1125 |
+
"loss": 2.2367,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.5060240963855422,
|
| 1130 |
+
"grad_norm": 5.856411933898926,
|
| 1131 |
+
"learning_rate": 7.379588335217874e-06,
|
| 1132 |
+
"loss": 3.0989,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 2.522088353413655,
|
| 1137 |
+
"grad_norm": 5.084694862365723,
|
| 1138 |
+
"learning_rate": 6.922295930309691e-06,
|
| 1139 |
+
"loss": 2.7171,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.538152610441767,
|
| 1144 |
+
"grad_norm": 6.212282657623291,
|
| 1145 |
+
"learning_rate": 6.478573978855146e-06,
|
| 1146 |
+
"loss": 2.8528,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.5542168674698793,
|
| 1151 |
+
"grad_norm": 4.591296195983887,
|
| 1152 |
+
"learning_rate": 6.048562263329138e-06,
|
| 1153 |
+
"loss": 2.0066,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.570281124497992,
|
| 1158 |
+
"grad_norm": 5.471847057342529,
|
| 1159 |
+
"learning_rate": 5.6323962471714286e-06,
|
| 1160 |
+
"loss": 2.6712,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.5863453815261046,
|
| 1165 |
+
"grad_norm": 6.344399929046631,
|
| 1166 |
+
"learning_rate": 5.23020703211255e-06,
|
| 1167 |
+
"loss": 2.3738,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 2.602409638554217,
|
| 1172 |
+
"grad_norm": 4.858112335205078,
|
| 1173 |
+
"learning_rate": 4.842121316873821e-06,
|
| 1174 |
+
"loss": 2.2417,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.6184738955823295,
|
| 1179 |
+
"grad_norm": 5.603279113769531,
|
| 1180 |
+
"learning_rate": 4.468261357254339e-06,
|
| 1181 |
+
"loss": 2.6957,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.6345381526104417,
|
| 1186 |
+
"grad_norm": 5.545329570770264,
|
| 1187 |
+
"learning_rate": 4.108744927617669e-06,
|
| 1188 |
+
"loss": 2.2776,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.6506024096385543,
|
| 1193 |
+
"grad_norm": 4.7836222648620605,
|
| 1194 |
+
"learning_rate": 3.763685283790208e-06,
|
| 1195 |
+
"loss": 2.0821,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 2.6666666666666665,
|
| 1200 |
+
"grad_norm": 4.492027282714844,
|
| 1201 |
+
"learning_rate": 3.4331911273830784e-06,
|
| 1202 |
+
"loss": 2.031,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.682730923694779,
|
| 1207 |
+
"grad_norm": 6.321730136871338,
|
| 1208 |
+
"learning_rate": 3.117366571548608e-06,
|
| 1209 |
+
"loss": 2.5016,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.6987951807228914,
|
| 1214 |
+
"grad_norm": 8.664602279663086,
|
| 1215 |
+
"learning_rate": 2.816311108182368e-06,
|
| 1216 |
+
"loss": 2.1106,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 2.714859437751004,
|
| 1221 |
+
"grad_norm": 5.606003284454346,
|
| 1222 |
+
"learning_rate": 2.530119576580936e-06,
|
| 1223 |
+
"loss": 2.185,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.7309236947791167,
|
| 1228 |
+
"grad_norm": 5.336299896240234,
|
| 1229 |
+
"learning_rate": 2.258882133565404e-06,
|
| 1230 |
+
"loss": 2.0902,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.746987951807229,
|
| 1235 |
+
"grad_norm": 5.943612575531006,
|
| 1236 |
+
"learning_rate": 2.0026842250799038e-06,
|
| 1237 |
+
"loss": 3.1001,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 2.7630522088353415,
|
| 1242 |
+
"grad_norm": 5.235433101654053,
|
| 1243 |
+
"learning_rate": 1.7616065592742038e-06,
|
| 1244 |
+
"loss": 2.7069,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.7791164658634537,
|
| 1249 |
+
"grad_norm": 4.886165142059326,
|
| 1250 |
+
"learning_rate": 1.5357250810788314e-06,
|
| 1251 |
+
"loss": 2.3469,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 2.7951807228915664,
|
| 1256 |
+
"grad_norm": 5.185632228851318,
|
| 1257 |
+
"learning_rate": 1.3251109482806666e-06,
|
| 1258 |
+
"loss": 2.7937,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 2.8112449799196786,
|
| 1263 |
+
"grad_norm": 5.091357231140137,
|
| 1264 |
+
"learning_rate": 1.1298305091066664e-06,
|
| 1265 |
+
"loss": 2.5354,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.8273092369477912,
|
| 1270 |
+
"grad_norm": 4.6926774978637695,
|
| 1271 |
+
"learning_rate": 9.499452813226284e-07,
|
| 1272 |
+
"loss": 2.2616,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.8433734939759034,
|
| 1277 |
+
"grad_norm": 4.782034397125244,
|
| 1278 |
+
"learning_rate": 7.855119328537109e-07,
|
| 1279 |
+
"loss": 2.0711,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 2.859437751004016,
|
| 1284 |
+
"grad_norm": 5.071019172668457,
|
| 1285 |
+
"learning_rate": 6.365822639327723e-07,
|
| 1286 |
+
"loss": 2.1635,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 2.8755020080321287,
|
| 1291 |
+
"grad_norm": 4.6255974769592285,
|
| 1292 |
+
"learning_rate": 5.032031907821089e-07,
|
| 1293 |
+
"loss": 2.1709,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 2.891566265060241,
|
| 1298 |
+
"grad_norm": 5.228384494781494,
|
| 1299 |
+
"learning_rate": 3.854167308337708e-07,
|
| 1300 |
+
"loss": 2.1617,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.907630522088353,
|
| 1305 |
+
"grad_norm": 5.127053260803223,
|
| 1306 |
+
"learning_rate": 2.8325998949314536e-07,
|
| 1307 |
+
"loss": 2.1208,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.923694779116466,
|
| 1312 |
+
"grad_norm": 4.4402055740356445,
|
| 1313 |
+
"learning_rate": 1.9676514844987337e-07,
|
| 1314 |
+
"loss": 1.9813,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 2.9397590361445785,
|
| 1319 |
+
"grad_norm": 6.084360122680664,
|
| 1320 |
+
"learning_rate": 1.2595945553992573e-07,
|
| 1321 |
+
"loss": 2.1314,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 2.9558232931726907,
|
| 1326 |
+
"grad_norm": 4.875538349151611,
|
| 1327 |
+
"learning_rate": 7.086521616190279e-08,
|
| 1328 |
+
"loss": 1.9403,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.9718875502008033,
|
| 1333 |
+
"grad_norm": 4.680423736572266,
|
| 1334 |
+
"learning_rate": 3.149978625032191e-08,
|
| 1335 |
+
"loss": 1.7237,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.9879518072289155,
|
| 1340 |
+
"grad_norm": 5.582780838012695,
|
| 1341 |
+
"learning_rate": 7.875566808107637e-09,
|
| 1342 |
+
"loss": 2.8136,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 3.004016064257028,
|
| 1347 |
+
"grad_norm": 5.710657596588135,
|
| 1348 |
+
"learning_rate": 0.0,
|
| 1349 |
+
"loss": 1.9331,
|
| 1350 |
+
"step": 187
|
| 1351 |
}
|
| 1352 |
],
|
| 1353 |
"logging_steps": 1,
|
|
|
|
| 1371 |
"should_evaluate": false,
|
| 1372 |
"should_log": false,
|
| 1373 |
"should_save": true,
|
| 1374 |
+
"should_training_stop": true
|
| 1375 |
},
|
| 1376 |
"attributes": {}
|
| 1377 |
}
|
| 1378 |
},
|
| 1379 |
+
"total_flos": 1.4076236595304858e+17,
|
| 1380 |
"train_batch_size": 8,
|
| 1381 |
"trial_name": null,
|
| 1382 |
"trial_params": null
|