Training in progress, step 190, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +292 -4
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 201361312
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:580fc52310b83ed38dd8230dae36c94bbb8bb8af222f06f36f4c914cd8499695
|
| 3 |
size 201361312
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 402868986
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06d4d10fec4c9ba03adecebd0634448511f1cc75385d1aef731b7bbe6b155f3a
|
| 3 |
size 402868986
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0af2eed038a2210043dbdee050b112df7fa6a86e2bbb3bb3f1645c647dda3059
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d904a910e9136c36800b8d8907ff26678dba030f6a37072d3ab3bebb97d959b
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d45b235a1cd2029de7b2e2b7938b1edb7dc6bde3cf47712ca38f0e6eb4488756
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:510e006b0434d52de82d4e4e36666ffab9697bda9405632e00e10ca71c33a5b8
|
| 3 |
size 15024
|
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 sha256:4b0717fa852ff14c4fb6ef3d8fb6e7d6c5b1e6b17d5f3ada276b0ae8e8648b64
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.11555452644824982,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 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 +1113,294 @@
|
|
| 1113 |
"eval_samples_per_second": 25.37,
|
| 1114 |
"eval_steps_per_second": 3.552,
|
| 1115 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
@@ -1136,12 +1424,12 @@
|
|
| 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": 2,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.11555452644824982,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.12331656660717183,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 190,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1113 |
"eval_samples_per_second": 25.37,
|
| 1114 |
"eval_steps_per_second": 3.552,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.09800421872464708,
|
| 1119 |
+
"grad_norm": 0.4107028543949127,
|
| 1120 |
+
"learning_rate": 1.9922179741796086e-05,
|
| 1121 |
+
"loss": 1.0317,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.09865325328573747,
|
| 1126 |
+
"grad_norm": 0.5017074346542358,
|
| 1127 |
+
"learning_rate": 1.9438237813334586e-05,
|
| 1128 |
+
"loss": 1.2946,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.09930228784682785,
|
| 1133 |
+
"grad_norm": 0.5874817371368408,
|
| 1134 |
+
"learning_rate": 1.8965008980117037e-05,
|
| 1135 |
+
"loss": 1.3075,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.09995132240791822,
|
| 1140 |
+
"grad_norm": 0.7980416417121887,
|
| 1141 |
+
"learning_rate": 1.850263580385163e-05,
|
| 1142 |
+
"loss": 1.7944,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.1006003569690086,
|
| 1147 |
+
"grad_norm": 0.8562352657318115,
|
| 1148 |
+
"learning_rate": 1.8051257575944925e-05,
|
| 1149 |
+
"loss": 1.5412,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.10124939153009897,
|
| 1154 |
+
"grad_norm": 0.9079697728157043,
|
| 1155 |
+
"learning_rate": 1.7611010275539962e-05,
|
| 1156 |
+
"loss": 2.1056,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.10189842609118936,
|
| 1161 |
+
"grad_norm": 1.362610101699829,
|
| 1162 |
+
"learning_rate": 1.718202652855205e-05,
|
| 1163 |
+
"loss": 2.8629,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.10254746065227974,
|
| 1168 |
+
"grad_norm": 1.0792609453201294,
|
| 1169 |
+
"learning_rate": 1.6764435567714794e-05,
|
| 1170 |
+
"loss": 2.2353,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.10319649521337011,
|
| 1175 |
+
"grad_norm": 1.1943668127059937,
|
| 1176 |
+
"learning_rate": 1.6358363193648352e-05,
|
| 1177 |
+
"loss": 1.8588,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.10384552977446049,
|
| 1182 |
+
"grad_norm": 1.8506977558135986,
|
| 1183 |
+
"learning_rate": 1.5963931736961547e-05,
|
| 1184 |
+
"loss": 2.0918,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.10449456433555086,
|
| 1189 |
+
"grad_norm": 1.4415589570999146,
|
| 1190 |
+
"learning_rate": 1.5581260021399396e-05,
|
| 1191 |
+
"loss": 2.2585,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.10514359889664125,
|
| 1196 |
+
"grad_norm": 2.1754801273345947,
|
| 1197 |
+
"learning_rate": 1.5210463328047095e-05,
|
| 1198 |
+
"loss": 3.5595,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.10579263345773163,
|
| 1203 |
+
"grad_norm": 1.5889264345169067,
|
| 1204 |
+
"learning_rate": 1.4851653360601179e-05,
|
| 1205 |
+
"loss": 2.6063,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.106441668018822,
|
| 1210 |
+
"grad_norm": 0.42740046977996826,
|
| 1211 |
+
"learning_rate": 1.4504938211718489e-05,
|
| 1212 |
+
"loss": 1.0057,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.10709070257991238,
|
| 1217 |
+
"grad_norm": 0.6118475198745728,
|
| 1218 |
+
"learning_rate": 1.4170422330452816e-05,
|
| 1219 |
+
"loss": 1.6187,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.10773973714100275,
|
| 1224 |
+
"grad_norm": 0.5750280618667603,
|
| 1225 |
+
"learning_rate": 1.384820649078939e-05,
|
| 1226 |
+
"loss": 1.5088,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.10838877170209314,
|
| 1231 |
+
"grad_norm": 0.8314217329025269,
|
| 1232 |
+
"learning_rate": 1.3538387761286303e-05,
|
| 1233 |
+
"loss": 1.4836,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.10903780626318352,
|
| 1238 |
+
"grad_norm": 0.9137848019599915,
|
| 1239 |
+
"learning_rate": 1.3241059475832373e-05,
|
| 1240 |
+
"loss": 2.4207,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.10968684082427389,
|
| 1245 |
+
"grad_norm": 0.8464080095291138,
|
| 1246 |
+
"learning_rate": 1.2956311205529943e-05,
|
| 1247 |
+
"loss": 1.6731,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.11033587538536427,
|
| 1252 |
+
"grad_norm": 1.062997817993164,
|
| 1253 |
+
"learning_rate": 1.268422873171136e-05,
|
| 1254 |
+
"loss": 1.8915,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.11098490994645464,
|
| 1259 |
+
"grad_norm": 1.1377428770065308,
|
| 1260 |
+
"learning_rate": 1.2424894020096997e-05,
|
| 1261 |
+
"loss": 1.7875,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.11163394450754503,
|
| 1266 |
+
"grad_norm": 1.1429808139801025,
|
| 1267 |
+
"learning_rate": 1.217838519610291e-05,
|
| 1268 |
+
"loss": 2.037,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.11228297906863541,
|
| 1273 |
+
"grad_norm": 1.6295369863510132,
|
| 1274 |
+
"learning_rate": 1.1944776521305213e-05,
|
| 1275 |
+
"loss": 3.373,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.11293201362972578,
|
| 1280 |
+
"grad_norm": 1.7956379652023315,
|
| 1281 |
+
"learning_rate": 1.1724138371068603e-05,
|
| 1282 |
+
"loss": 2.3656,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.11358104819081616,
|
| 1287 |
+
"grad_norm": 2.154815912246704,
|
| 1288 |
+
"learning_rate": 1.1516537213345519e-05,
|
| 1289 |
+
"loss": 3.9224,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.11358104819081616,
|
| 1294 |
+
"eval_loss": 0.11255475133657455,
|
| 1295 |
+
"eval_runtime": 1.9712,
|
| 1296 |
+
"eval_samples_per_second": 25.365,
|
| 1297 |
+
"eval_steps_per_second": 3.551,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.11423008275190653,
|
| 1302 |
+
"grad_norm": 0.4329838156700134,
|
| 1303 |
+
"learning_rate": 1.1322035588652484e-05,
|
| 1304 |
+
"loss": 1.0267,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.11487911731299692,
|
| 1309 |
+
"grad_norm": 0.4971684217453003,
|
| 1310 |
+
"learning_rate": 1.1140692091229556e-05,
|
| 1311 |
+
"loss": 1.5005,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.1155281518740873,
|
| 1316 |
+
"grad_norm": 0.6539115309715271,
|
| 1317 |
+
"learning_rate": 1.0972561351388622e-05,
|
| 1318 |
+
"loss": 1.5548,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.11617718643517767,
|
| 1323 |
+
"grad_norm": 0.6794347167015076,
|
| 1324 |
+
"learning_rate": 1.0817694019055866e-05,
|
| 1325 |
+
"loss": 1.3433,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.11682622099626805,
|
| 1330 |
+
"grad_norm": 0.6794097423553467,
|
| 1331 |
+
"learning_rate": 1.0676136748513286e-05,
|
| 1332 |
+
"loss": 1.4972,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.11747525555735842,
|
| 1337 |
+
"grad_norm": 0.8298191428184509,
|
| 1338 |
+
"learning_rate": 1.0547932184343948e-05,
|
| 1339 |
+
"loss": 1.89,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.11812429011844881,
|
| 1344 |
+
"grad_norm": 1.0593596696853638,
|
| 1345 |
+
"learning_rate": 1.043311894858519e-05,
|
| 1346 |
+
"loss": 1.5608,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.11877332467953919,
|
| 1351 |
+
"grad_norm": 1.1649240255355835,
|
| 1352 |
+
"learning_rate": 1.033173162909358e-05,
|
| 1353 |
+
"loss": 1.5776,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.11942235924062956,
|
| 1358 |
+
"grad_norm": 1.1592937707901,
|
| 1359 |
+
"learning_rate": 1.0243800769125222e-05,
|
| 1360 |
+
"loss": 2.2227,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.12007139380171994,
|
| 1365 |
+
"grad_norm": 1.402487874031067,
|
| 1366 |
+
"learning_rate": 1.0169352858134525e-05,
|
| 1367 |
+
"loss": 2.775,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.12072042836281031,
|
| 1372 |
+
"grad_norm": 1.5199470520019531,
|
| 1373 |
+
"learning_rate": 1.0108410323794131e-05,
|
| 1374 |
+
"loss": 2.5718,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.1213694629239007,
|
| 1379 |
+
"grad_norm": 4.227544784545898,
|
| 1380 |
+
"learning_rate": 1.0060991525238538e-05,
|
| 1381 |
+
"loss": 2.4256,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.12201849748499108,
|
| 1386 |
+
"grad_norm": 1.57233464717865,
|
| 1387 |
+
"learning_rate": 1.0027110747533332e-05,
|
| 1388 |
+
"loss": 2.703,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.12266753204608145,
|
| 1393 |
+
"grad_norm": 0.41703668236732483,
|
| 1394 |
+
"learning_rate": 1.0006778197371774e-05,
|
| 1395 |
+
"loss": 1.0445,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.12331656660717183,
|
| 1400 |
+
"grad_norm": 0.5908713340759277,
|
| 1401 |
+
"learning_rate": 1e-05,
|
| 1402 |
+
"loss": 1.4907,
|
| 1403 |
+
"step": 190
|
| 1404 |
}
|
| 1405 |
],
|
| 1406 |
"logging_steps": 1,
|
|
|
|
| 1424 |
"should_evaluate": false,
|
| 1425 |
"should_log": false,
|
| 1426 |
"should_save": true,
|
| 1427 |
+
"should_training_stop": true
|
| 1428 |
},
|
| 1429 |
"attributes": {}
|
| 1430 |
}
|
| 1431 |
},
|
| 1432 |
+
"total_flos": 1.1309430552941036e+18,
|
| 1433 |
"train_batch_size": 2,
|
| 1434 |
"trial_name": null,
|
| 1435 |
"trial_params": null
|