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 578859568
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:452543d07fdb291d5cff953230d5055c3c2f07f9ace1a5a08eb8c03ff8024649
|
| 3 |
size 578859568
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 294324372
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:577b6226186110858f099544da2576c9d028b63194affe90b3d117f6d328a1d0
|
| 3 |
size 294324372
|
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 sha256:9aad1d594dee184a7652a540da097599d5a876408e16a28fe7bd53aa7da90dd5
|
| 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 sha256:3ccd6c733a208e149811e7f1cec59782806cc39c64e33a8b91e1933bc027c5e4
|
| 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": 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": 11.538,
|
| 1090 |
"eval_steps_per_second": 5.779,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1117,7 +1475,7 @@
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 2,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7939153909683228,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.0055593776276745815,
|
| 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": 11.538,
|
| 1090 |
"eval_steps_per_second": 5.779,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.004197330108894309,
|
| 1095 |
+
"grad_norm": 0.4086618423461914,
|
| 1096 |
+
"learning_rate": 0.0016184643766056315,
|
| 1097 |
+
"loss": 1.0707,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.004225126997032682,
|
| 1102 |
+
"grad_norm": 0.2321600317955017,
|
| 1103 |
+
"learning_rate": 0.0016134135287043667,
|
| 1104 |
+
"loss": 1.0719,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.004252923885171055,
|
| 1109 |
+
"grad_norm": 0.09448766708374023,
|
| 1110 |
+
"learning_rate": 0.0016083374657755133,
|
| 1111 |
+
"loss": 1.035,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.004280720773309428,
|
| 1116 |
+
"grad_norm": 0.0990653857588768,
|
| 1117 |
+
"learning_rate": 0.0016032363964761363,
|
| 1118 |
+
"loss": 0.9306,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.004308517661447801,
|
| 1123 |
+
"grad_norm": 0.09489451348781586,
|
| 1124 |
+
"learning_rate": 0.001598110530491216,
|
| 1125 |
+
"loss": 0.8499,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.004336314549586173,
|
| 1130 |
+
"grad_norm": 0.09735696017742157,
|
| 1131 |
+
"learning_rate": 0.0015929600785250257,
|
| 1132 |
+
"loss": 0.8704,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.004364111437724547,
|
| 1137 |
+
"grad_norm": 0.1042320653796196,
|
| 1138 |
+
"learning_rate": 0.0015877852522924731,
|
| 1139 |
+
"loss": 0.8512,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.00439190832586292,
|
| 1144 |
+
"grad_norm": 0.12351106107234955,
|
| 1145 |
+
"learning_rate": 0.0015825862645103962,
|
| 1146 |
+
"loss": 0.9413,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.004419705214001293,
|
| 1151 |
+
"grad_norm": 0.09481119364500046,
|
| 1152 |
+
"learning_rate": 0.0015773633288888196,
|
| 1153 |
+
"loss": 0.8296,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.0044475021021396655,
|
| 1158 |
+
"grad_norm": 0.105812206864357,
|
| 1159 |
+
"learning_rate": 0.0015721166601221697,
|
| 1160 |
+
"loss": 0.7714,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.004475298990278038,
|
| 1165 |
+
"grad_norm": 0.11305416375398636,
|
| 1166 |
+
"learning_rate": 0.00156684647388045,
|
| 1167 |
+
"loss": 0.9412,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.004503095878416411,
|
| 1172 |
+
"grad_norm": 0.10926243662834167,
|
| 1173 |
+
"learning_rate": 0.0015615529868003748,
|
| 1174 |
+
"loss": 0.8682,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.004530892766554784,
|
| 1179 |
+
"grad_norm": 0.10087363421916962,
|
| 1180 |
+
"learning_rate": 0.0015562364164764648,
|
| 1181 |
+
"loss": 0.8325,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.004558689654693157,
|
| 1186 |
+
"grad_norm": 0.09206137806177139,
|
| 1187 |
+
"learning_rate": 0.0015508969814521025,
|
| 1188 |
+
"loss": 0.7958,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.00458648654283153,
|
| 1193 |
+
"grad_norm": 0.11067818850278854,
|
| 1194 |
+
"learning_rate": 0.0015455349012105486,
|
| 1195 |
+
"loss": 1.0522,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.004614283430969903,
|
| 1200 |
+
"grad_norm": 0.11335323750972748,
|
| 1201 |
+
"learning_rate": 0.0015401503961659203,
|
| 1202 |
+
"loss": 0.9374,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.004642080319108276,
|
| 1207 |
+
"grad_norm": 0.1060660108923912,
|
| 1208 |
+
"learning_rate": 0.0015347436876541297,
|
| 1209 |
+
"loss": 0.9861,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.004669877207246649,
|
| 1214 |
+
"grad_norm": 0.12663975358009338,
|
| 1215 |
+
"learning_rate": 0.0015293149979237874,
|
| 1216 |
+
"loss": 0.7834,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.004697674095385022,
|
| 1221 |
+
"grad_norm": 0.1315016895532608,
|
| 1222 |
+
"learning_rate": 0.0015238645501270654,
|
| 1223 |
+
"loss": 0.9251,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0047254709835233945,
|
| 1228 |
+
"grad_norm": 0.16219031810760498,
|
| 1229 |
+
"learning_rate": 0.0015183925683105253,
|
| 1230 |
+
"loss": 0.8951,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.004753267871661767,
|
| 1235 |
+
"grad_norm": 0.1081567108631134,
|
| 1236 |
+
"learning_rate": 0.0015128992774059062,
|
| 1237 |
+
"loss": 0.9457,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.00478106475980014,
|
| 1242 |
+
"grad_norm": 0.1203177273273468,
|
| 1243 |
+
"learning_rate": 0.0015073849032208823,
|
| 1244 |
+
"loss": 0.9307,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.004808861647938513,
|
| 1249 |
+
"grad_norm": 0.11848781257867813,
|
| 1250 |
+
"learning_rate": 0.0015018496724297776,
|
| 1251 |
+
"loss": 0.8301,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.004836658536076886,
|
| 1256 |
+
"grad_norm": 0.13573849201202393,
|
| 1257 |
+
"learning_rate": 0.0014962938125642501,
|
| 1258 |
+
"loss": 0.723,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.0048644554242152594,
|
| 1263 |
+
"grad_norm": 0.10743360966444016,
|
| 1264 |
+
"learning_rate": 0.001490717552003938,
|
| 1265 |
+
"loss": 0.7861,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.004892252312353632,
|
| 1270 |
+
"grad_norm": 0.10989518463611603,
|
| 1271 |
+
"learning_rate": 0.001485121119967072,
|
| 1272 |
+
"loss": 0.7905,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.004920049200492005,
|
| 1277 |
+
"grad_norm": 0.10301119089126587,
|
| 1278 |
+
"learning_rate": 0.001479504746501054,
|
| 1279 |
+
"loss": 0.6952,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.004947846088630378,
|
| 1284 |
+
"grad_norm": 0.12021514773368835,
|
| 1285 |
+
"learning_rate": 0.0014738686624729987,
|
| 1286 |
+
"loss": 0.782,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.004975642976768751,
|
| 1291 |
+
"grad_norm": 0.11153309047222137,
|
| 1292 |
+
"learning_rate": 0.0014682130995602458,
|
| 1293 |
+
"loss": 0.8065,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.0050034398649071235,
|
| 1298 |
+
"grad_norm": 0.11229830235242844,
|
| 1299 |
+
"learning_rate": 0.0014625382902408355,
|
| 1300 |
+
"loss": 0.7113,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.005031236753045496,
|
| 1305 |
+
"grad_norm": 0.11783714592456818,
|
| 1306 |
+
"learning_rate": 0.0014568444677839517,
|
| 1307 |
+
"loss": 0.6218,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.005059033641183869,
|
| 1312 |
+
"grad_norm": 0.12635229527950287,
|
| 1313 |
+
"learning_rate": 0.0014511318662403345,
|
| 1314 |
+
"loss": 0.6719,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.005086830529322243,
|
| 1319 |
+
"grad_norm": 0.12254615128040314,
|
| 1320 |
+
"learning_rate": 0.0014454007204326592,
|
| 1321 |
+
"loss": 0.7263,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.005114627417460616,
|
| 1326 |
+
"grad_norm": 0.11896725744009018,
|
| 1327 |
+
"learning_rate": 0.0014396512659458822,
|
| 1328 |
+
"loss": 0.8887,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.005142424305598988,
|
| 1333 |
+
"grad_norm": 0.10813646763563156,
|
| 1334 |
+
"learning_rate": 0.0014338837391175581,
|
| 1335 |
+
"loss": 0.6242,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.005170221193737361,
|
| 1340 |
+
"grad_norm": 0.10913447290658951,
|
| 1341 |
+
"learning_rate": 0.0014280983770281258,
|
| 1342 |
+
"loss": 0.5932,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.005198018081875734,
|
| 1347 |
+
"grad_norm": 0.11929253488779068,
|
| 1348 |
+
"learning_rate": 0.00142229541749116,
|
| 1349 |
+
"loss": 0.7183,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.005225814970014107,
|
| 1354 |
+
"grad_norm": 0.1152404397726059,
|
| 1355 |
+
"learning_rate": 0.001416475099043599,
|
| 1356 |
+
"loss": 0.7041,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.00525361185815248,
|
| 1361 |
+
"grad_norm": 0.11904522776603699,
|
| 1362 |
+
"learning_rate": 0.001410637660935938,
|
| 1363 |
+
"loss": 0.7405,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.0052814087462908525,
|
| 1368 |
+
"grad_norm": 0.10983660072088242,
|
| 1369 |
+
"learning_rate": 0.0014047833431223937,
|
| 1370 |
+
"loss": 0.7169,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.005309205634429225,
|
| 1375 |
+
"grad_norm": 0.1285189539194107,
|
| 1376 |
+
"learning_rate": 0.0013989123862510418,
|
| 1377 |
+
"loss": 0.7584,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.005337002522567599,
|
| 1382 |
+
"grad_norm": 0.13100877404212952,
|
| 1383 |
+
"learning_rate": 0.0013930250316539236,
|
| 1384 |
+
"loss": 0.7606,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.005364799410705972,
|
| 1389 |
+
"grad_norm": 0.14966635406017303,
|
| 1390 |
+
"learning_rate": 0.0013871215213371283,
|
| 1391 |
+
"loss": 0.5972,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.005392596298844345,
|
| 1396 |
+
"grad_norm": 0.13933199644088745,
|
| 1397 |
+
"learning_rate": 0.0013812020979708417,
|
| 1398 |
+
"loss": 0.5656,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.005420393186982717,
|
| 1403 |
+
"grad_norm": 0.13888134062290192,
|
| 1404 |
+
"learning_rate": 0.0013752670048793744,
|
| 1405 |
+
"loss": 0.7759,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.00544819007512109,
|
| 1410 |
+
"grad_norm": 0.14111551642417908,
|
| 1411 |
+
"learning_rate": 0.0013693164860311565,
|
| 1412 |
+
"loss": 0.7513,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.005475986963259463,
|
| 1417 |
+
"grad_norm": 0.16336259245872498,
|
| 1418 |
+
"learning_rate": 0.0013633507860287115,
|
| 1419 |
+
"loss": 0.7926,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.005503783851397836,
|
| 1424 |
+
"grad_norm": 0.1474616378545761,
|
| 1425 |
+
"learning_rate": 0.0013573701500986012,
|
| 1426 |
+
"loss": 0.5559,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.005531580739536209,
|
| 1431 |
+
"grad_norm": 0.18535536527633667,
|
| 1432 |
+
"learning_rate": 0.001351374824081343,
|
| 1433 |
+
"loss": 0.7313,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.0055593776276745815,
|
| 1438 |
+
"grad_norm": 0.1758536696434021,
|
| 1439 |
+
"learning_rate": 0.0013453650544213076,
|
| 1440 |
+
"loss": 0.606,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.0055593776276745815,
|
| 1445 |
+
"eval_loss": 0.7939153909683228,
|
| 1446 |
+
"eval_runtime": 50.0064,
|
| 1447 |
+
"eval_samples_per_second": 11.539,
|
| 1448 |
+
"eval_steps_per_second": 5.779,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 1.2931550052089856e+16,
|
| 1479 |
"train_batch_size": 2,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|