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 2269195160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ec90b1bef3fae36ee2e6f3e35f4d0633e742835c484b7b53c25b2fb33e55b97
|
| 3 |
size 2269195160
|
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 sha256:19b76775cb19aff3bbb8b74cab7e572f060c28279af09a0e2609759aba90d1e1
|
| 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 sha256:391c32b5504b892c155845f383b09ba76c17c7429f8d75818faf9576ee7599e8
|
| 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": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 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": 10.28,
|
| 1114 |
"eval_steps_per_second": 1.439,
|
| 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": 1.273140788078308,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.17357344326318072,
|
| 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": 10.28,
|
| 1114 |
"eval_steps_per_second": 1.439,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.13104794966370145,
|
| 1119 |
+
"grad_norm": 1.435655117034912,
|
| 1120 |
+
"learning_rate": 4.659698863221513e-05,
|
| 1121 |
+
"loss": 1.3466,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.13191581688001736,
|
| 1126 |
+
"grad_norm": 1.3139824867248535,
|
| 1127 |
+
"learning_rate": 4.481448235912671e-05,
|
| 1128 |
+
"loss": 1.3012,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.13278368409633326,
|
| 1133 |
+
"grad_norm": 1.475575566291809,
|
| 1134 |
+
"learning_rate": 4.306073275629044e-05,
|
| 1135 |
+
"loss": 1.341,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.13365155131264916,
|
| 1140 |
+
"grad_norm": 1.266109824180603,
|
| 1141 |
+
"learning_rate": 4.133621928133665e-05,
|
| 1142 |
+
"loss": 1.2559,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.13451941852896507,
|
| 1147 |
+
"grad_norm": 1.6535367965698242,
|
| 1148 |
+
"learning_rate": 3.964141339903026e-05,
|
| 1149 |
+
"loss": 1.2211,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.13538728574528097,
|
| 1154 |
+
"grad_norm": 1.2901335954666138,
|
| 1155 |
+
"learning_rate": 3.797677845237696e-05,
|
| 1156 |
+
"loss": 1.265,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.13625515296159688,
|
| 1161 |
+
"grad_norm": 1.4438883066177368,
|
| 1162 |
+
"learning_rate": 3.634276953594982e-05,
|
| 1163 |
+
"loss": 1.4203,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.13712302017791278,
|
| 1168 |
+
"grad_norm": 1.3088321685791016,
|
| 1169 |
+
"learning_rate": 3.473983337147118e-05,
|
| 1170 |
+
"loss": 1.5061,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.13799088739422868,
|
| 1175 |
+
"grad_norm": 1.4172899723052979,
|
| 1176 |
+
"learning_rate": 3.316840818568315e-05,
|
| 1177 |
+
"loss": 1.3196,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.1388587546105446,
|
| 1182 |
+
"grad_norm": 1.0322235822677612,
|
| 1183 |
+
"learning_rate": 3.162892359054098e-05,
|
| 1184 |
+
"loss": 1.1525,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.1397266218268605,
|
| 1189 |
+
"grad_norm": 1.4172779321670532,
|
| 1190 |
+
"learning_rate": 3.0121800465761293e-05,
|
| 1191 |
+
"loss": 1.1612,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.1405944890431764,
|
| 1196 |
+
"grad_norm": 1.2472504377365112,
|
| 1197 |
+
"learning_rate": 2.8647450843757897e-05,
|
| 1198 |
+
"loss": 1.1889,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.1414623562594923,
|
| 1203 |
+
"grad_norm": 1.3722219467163086,
|
| 1204 |
+
"learning_rate": 2.7206277796996144e-05,
|
| 1205 |
+
"loss": 1.3959,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.1423302234758082,
|
| 1210 |
+
"grad_norm": 1.0866336822509766,
|
| 1211 |
+
"learning_rate": 2.5798675327796993e-05,
|
| 1212 |
+
"loss": 1.1537,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.1431980906921241,
|
| 1217 |
+
"grad_norm": 1.1457860469818115,
|
| 1218 |
+
"learning_rate": 2.4425028260620715e-05,
|
| 1219 |
+
"loss": 1.1059,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.14406595790844,
|
| 1224 |
+
"grad_norm": 1.2376954555511475,
|
| 1225 |
+
"learning_rate": 2.3085712136859668e-05,
|
| 1226 |
+
"loss": 1.2862,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.14493382512475592,
|
| 1231 |
+
"grad_norm": 1.3723816871643066,
|
| 1232 |
+
"learning_rate": 2.178109311216913e-05,
|
| 1233 |
+
"loss": 1.3396,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.14580169234107182,
|
| 1238 |
+
"grad_norm": 1.3971730470657349,
|
| 1239 |
+
"learning_rate": 2.0511527856363912e-05,
|
| 1240 |
+
"loss": 0.991,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.14666955955738772,
|
| 1245 |
+
"grad_norm": 1.1824660301208496,
|
| 1246 |
+
"learning_rate": 1.927736345590839e-05,
|
| 1247 |
+
"loss": 1.2045,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.14753742677370363,
|
| 1252 |
+
"grad_norm": 1.5620667934417725,
|
| 1253 |
+
"learning_rate": 1.8078937319026654e-05,
|
| 1254 |
+
"loss": 1.4492,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.14840529399001953,
|
| 1259 |
+
"grad_norm": 1.6076619625091553,
|
| 1260 |
+
"learning_rate": 1.6916577083458228e-05,
|
| 1261 |
+
"loss": 1.1662,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.14927316120633544,
|
| 1266 |
+
"grad_norm": 1.2753527164459229,
|
| 1267 |
+
"learning_rate": 1.579060052688548e-05,
|
| 1268 |
+
"loss": 1.0975,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.15014102842265134,
|
| 1273 |
+
"grad_norm": 1.6548813581466675,
|
| 1274 |
+
"learning_rate": 1.4701315480056164e-05,
|
| 1275 |
+
"loss": 1.3443,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.15100889563896724,
|
| 1280 |
+
"grad_norm": 1.3361274003982544,
|
| 1281 |
+
"learning_rate": 1.3649019742625623e-05,
|
| 1282 |
+
"loss": 1.1309,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.15187676285528315,
|
| 1287 |
+
"grad_norm": 1.3236322402954102,
|
| 1288 |
+
"learning_rate": 1.2634001001741373e-05,
|
| 1289 |
+
"loss": 1.3047,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.15187676285528315,
|
| 1294 |
+
"eval_loss": 1.2790803909301758,
|
| 1295 |
+
"eval_runtime": 4.8651,
|
| 1296 |
+
"eval_samples_per_second": 10.277,
|
| 1297 |
+
"eval_steps_per_second": 1.439,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.15274463007159905,
|
| 1302 |
+
"grad_norm": 1.4842597246170044,
|
| 1303 |
+
"learning_rate": 1.1656536753392287e-05,
|
| 1304 |
+
"loss": 1.0864,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.15361249728791496,
|
| 1309 |
+
"grad_norm": 1.5153896808624268,
|
| 1310 |
+
"learning_rate": 1.0716894226543953e-05,
|
| 1311 |
+
"loss": 1.1642,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.15448036450423086,
|
| 1316 |
+
"grad_norm": 1.2488980293273926,
|
| 1317 |
+
"learning_rate": 9.815330310080887e-06,
|
| 1318 |
+
"loss": 1.323,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.15534823172054676,
|
| 1323 |
+
"grad_norm": 1.6930081844329834,
|
| 1324 |
+
"learning_rate": 8.952091482575824e-06,
|
| 1325 |
+
"loss": 1.2604,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.15621609893686267,
|
| 1330 |
+
"grad_norm": 1.3704711198806763,
|
| 1331 |
+
"learning_rate": 8.127413744904804e-06,
|
| 1332 |
+
"loss": 1.2578,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.15708396615317857,
|
| 1337 |
+
"grad_norm": 1.291325330734253,
|
| 1338 |
+
"learning_rate": 7.34152255572697e-06,
|
| 1339 |
+
"loss": 1.2179,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.15795183336949448,
|
| 1344 |
+
"grad_norm": 1.5434905290603638,
|
| 1345 |
+
"learning_rate": 6.594632769846353e-06,
|
| 1346 |
+
"loss": 1.305,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.15881970058581038,
|
| 1351 |
+
"grad_norm": 1.337917447090149,
|
| 1352 |
+
"learning_rate": 5.886948579472778e-06,
|
| 1353 |
+
"loss": 1.0775,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.15968756780212628,
|
| 1358 |
+
"grad_norm": 1.2450789213180542,
|
| 1359 |
+
"learning_rate": 5.218663458397715e-06,
|
| 1360 |
+
"loss": 1.2888,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.1605554350184422,
|
| 1365 |
+
"grad_norm": 1.8470358848571777,
|
| 1366 |
+
"learning_rate": 4.589960109100444e-06,
|
| 1367 |
+
"loss": 1.3356,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.1614233022347581,
|
| 1372 |
+
"grad_norm": 1.937638282775879,
|
| 1373 |
+
"learning_rate": 4.001010412799138e-06,
|
| 1374 |
+
"loss": 1.6163,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.162291169451074,
|
| 1379 |
+
"grad_norm": 1.4495834112167358,
|
| 1380 |
+
"learning_rate": 3.451975382460109e-06,
|
| 1381 |
+
"loss": 1.284,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.1631590366673899,
|
| 1386 |
+
"grad_norm": 1.6046760082244873,
|
| 1387 |
+
"learning_rate": 2.9430051187785962e-06,
|
| 1388 |
+
"loss": 1.2811,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.1640269038837058,
|
| 1393 |
+
"grad_norm": 1.4449301958084106,
|
| 1394 |
+
"learning_rate": 2.4742387691426445e-06,
|
| 1395 |
+
"loss": 1.3251,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.1648947711000217,
|
| 1400 |
+
"grad_norm": 1.6170849800109863,
|
| 1401 |
+
"learning_rate": 2.0458044895916513e-06,
|
| 1402 |
+
"loss": 1.0835,
|
| 1403 |
+
"step": 190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.1657626383163376,
|
| 1407 |
+
"grad_norm": 1.2608143091201782,
|
| 1408 |
+
"learning_rate": 1.6578194097797258e-06,
|
| 1409 |
+
"loss": 1.1025,
|
| 1410 |
+
"step": 191
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.16663050553265352,
|
| 1414 |
+
"grad_norm": 1.7908244132995605,
|
| 1415 |
+
"learning_rate": 1.3103896009537207e-06,
|
| 1416 |
+
"loss": 1.5649,
|
| 1417 |
+
"step": 192
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.16749837274896942,
|
| 1421 |
+
"grad_norm": 1.5216867923736572,
|
| 1422 |
+
"learning_rate": 1.0036100469542786e-06,
|
| 1423 |
+
"loss": 0.9956,
|
| 1424 |
+
"step": 193
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.16836623996528532,
|
| 1428 |
+
"grad_norm": 1.6887457370758057,
|
| 1429 |
+
"learning_rate": 7.375646182482875e-07,
|
| 1430 |
+
"loss": 1.2089,
|
| 1431 |
+
"step": 194
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.16923410718160123,
|
| 1435 |
+
"grad_norm": 2.0695362091064453,
|
| 1436 |
+
"learning_rate": 5.123260489995229e-07,
|
| 1437 |
+
"loss": 1.495,
|
| 1438 |
+
"step": 195
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.1701019743979171,
|
| 1442 |
+
"grad_norm": 1.8778845071792603,
|
| 1443 |
+
"learning_rate": 3.2795591718381975e-07,
|
| 1444 |
+
"loss": 1.4961,
|
| 1445 |
+
"step": 196
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.170969841614233,
|
| 1449 |
+
"grad_norm": 2.050307273864746,
|
| 1450 |
+
"learning_rate": 1.8450462775428942e-07,
|
| 1451 |
+
"loss": 1.5306,
|
| 1452 |
+
"step": 197
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.1718377088305489,
|
| 1456 |
+
"grad_norm": 1.506821632385254,
|
| 1457 |
+
"learning_rate": 8.201139886109264e-08,
|
| 1458 |
+
"loss": 1.18,
|
| 1459 |
+
"step": 198
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.17270557604686482,
|
| 1463 |
+
"grad_norm": 1.6801998615264893,
|
| 1464 |
+
"learning_rate": 2.0504251129649374e-08,
|
| 1465 |
+
"loss": 1.2565,
|
| 1466 |
+
"step": 199
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.17357344326318072,
|
| 1470 |
+
"grad_norm": 1.8449974060058594,
|
| 1471 |
+
"learning_rate": 0.0,
|
| 1472 |
+
"loss": 1.4853,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.17357344326318072,
|
| 1477 |
+
"eval_loss": 1.273140788078308,
|
| 1478 |
+
"eval_runtime": 4.8567,
|
| 1479 |
+
"eval_samples_per_second": 10.295,
|
| 1480 |
+
"eval_steps_per_second": 1.441,
|
| 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": 3.153022666407936e+17,
|
| 1511 |
"train_batch_size": 8,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|