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 sha256:0acefd8f8eeeb92767b2df043e9fb71de1151610e46f5d8dde30511839e1fc65
|
| 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 sha256:11258d350092e7c16ef3e4c534b804770e49e9ce873f5bccae10cd0a9e741915
|
| 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:f84aec7bda5c65eed2f4e3fdd64ac37661b2c414fea019ef35645df4307cf7a6
|
| 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": 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": 5.455,
|
| 1114 |
"eval_steps_per_second": 0.764,
|
| 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": 0.07271432131528854,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.03939528241493081,
|
| 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": 5.455,
|
| 1114 |
"eval_steps_per_second": 0.764,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.029743438223272762,
|
| 1119 |
+
"grad_norm": 0.9880196452140808,
|
| 1120 |
+
"learning_rate": 4.659698863221513e-05,
|
| 1121 |
+
"loss": 0.3546,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.029940414635347416,
|
| 1126 |
+
"grad_norm": 0.7226404547691345,
|
| 1127 |
+
"learning_rate": 4.481448235912671e-05,
|
| 1128 |
+
"loss": 0.2702,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.030137391047422073,
|
| 1133 |
+
"grad_norm": 0.8038386702537537,
|
| 1134 |
+
"learning_rate": 4.306073275629044e-05,
|
| 1135 |
+
"loss": 0.3077,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.030334367459496726,
|
| 1140 |
+
"grad_norm": 0.6242251396179199,
|
| 1141 |
+
"learning_rate": 4.133621928133665e-05,
|
| 1142 |
+
"loss": 0.2612,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.03053134387157138,
|
| 1147 |
+
"grad_norm": 0.6672581434249878,
|
| 1148 |
+
"learning_rate": 3.964141339903026e-05,
|
| 1149 |
+
"loss": 0.2917,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.030728320283646034,
|
| 1154 |
+
"grad_norm": 0.5822924375534058,
|
| 1155 |
+
"learning_rate": 3.797677845237696e-05,
|
| 1156 |
+
"loss": 0.3038,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.030925296695720687,
|
| 1161 |
+
"grad_norm": 0.5603398680686951,
|
| 1162 |
+
"learning_rate": 3.634276953594982e-05,
|
| 1163 |
+
"loss": 0.2806,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.03112227310779534,
|
| 1168 |
+
"grad_norm": 0.526652991771698,
|
| 1169 |
+
"learning_rate": 3.473983337147118e-05,
|
| 1170 |
+
"loss": 0.3352,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.031319249519869995,
|
| 1175 |
+
"grad_norm": 0.5369526147842407,
|
| 1176 |
+
"learning_rate": 3.316840818568315e-05,
|
| 1177 |
+
"loss": 0.2806,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.03151622593194465,
|
| 1182 |
+
"grad_norm": 0.4179346263408661,
|
| 1183 |
+
"learning_rate": 3.162892359054098e-05,
|
| 1184 |
+
"loss": 0.2744,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.0317132023440193,
|
| 1189 |
+
"grad_norm": 0.6778124570846558,
|
| 1190 |
+
"learning_rate": 3.0121800465761293e-05,
|
| 1191 |
+
"loss": 0.2826,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.031910178756093956,
|
| 1196 |
+
"grad_norm": 0.37569910287857056,
|
| 1197 |
+
"learning_rate": 2.8647450843757897e-05,
|
| 1198 |
+
"loss": 0.2533,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.03210715516816861,
|
| 1203 |
+
"grad_norm": 0.33460506796836853,
|
| 1204 |
+
"learning_rate": 2.7206277796996144e-05,
|
| 1205 |
+
"loss": 0.2703,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.03230413158024326,
|
| 1210 |
+
"grad_norm": 0.5205643177032471,
|
| 1211 |
+
"learning_rate": 2.5798675327796993e-05,
|
| 1212 |
+
"loss": 0.3269,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.03250110799231792,
|
| 1217 |
+
"grad_norm": 0.8476812243461609,
|
| 1218 |
+
"learning_rate": 2.4425028260620715e-05,
|
| 1219 |
+
"loss": 0.3097,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.03269808440439258,
|
| 1224 |
+
"grad_norm": 0.48694828152656555,
|
| 1225 |
+
"learning_rate": 2.3085712136859668e-05,
|
| 1226 |
+
"loss": 0.2699,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.03289506081646723,
|
| 1231 |
+
"grad_norm": 0.7992863655090332,
|
| 1232 |
+
"learning_rate": 2.178109311216913e-05,
|
| 1233 |
+
"loss": 0.2547,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.033092037228541885,
|
| 1238 |
+
"grad_norm": 0.489131361246109,
|
| 1239 |
+
"learning_rate": 2.0511527856363912e-05,
|
| 1240 |
+
"loss": 0.2847,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.03328901364061654,
|
| 1245 |
+
"grad_norm": 0.7267995476722717,
|
| 1246 |
+
"learning_rate": 1.927736345590839e-05,
|
| 1247 |
+
"loss": 0.1622,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.03348599005269119,
|
| 1252 |
+
"grad_norm": 0.4803732633590698,
|
| 1253 |
+
"learning_rate": 1.8078937319026654e-05,
|
| 1254 |
+
"loss": 0.2689,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.033682966464765846,
|
| 1259 |
+
"grad_norm": 0.4199903905391693,
|
| 1260 |
+
"learning_rate": 1.6916577083458228e-05,
|
| 1261 |
+
"loss": 0.299,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.0338799428768405,
|
| 1266 |
+
"grad_norm": 0.36284616589546204,
|
| 1267 |
+
"learning_rate": 1.579060052688548e-05,
|
| 1268 |
+
"loss": 0.262,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.03407691928891515,
|
| 1273 |
+
"grad_norm": 0.4913172423839569,
|
| 1274 |
+
"learning_rate": 1.4701315480056164e-05,
|
| 1275 |
+
"loss": 0.2382,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.03427389570098981,
|
| 1280 |
+
"grad_norm": 0.701080322265625,
|
| 1281 |
+
"learning_rate": 1.3649019742625623e-05,
|
| 1282 |
+
"loss": 0.2878,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.03447087211306446,
|
| 1287 |
+
"grad_norm": 0.4284681975841522,
|
| 1288 |
+
"learning_rate": 1.2634001001741373e-05,
|
| 1289 |
+
"loss": 0.2711,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.03447087211306446,
|
| 1294 |
+
"eval_loss": 0.07281436771154404,
|
| 1295 |
+
"eval_runtime": 11.8755,
|
| 1296 |
+
"eval_samples_per_second": 4.21,
|
| 1297 |
+
"eval_steps_per_second": 0.589,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.034667848525139114,
|
| 1302 |
+
"grad_norm": 0.5271365642547607,
|
| 1303 |
+
"learning_rate": 1.1656536753392287e-05,
|
| 1304 |
+
"loss": 0.2571,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.03486482493721377,
|
| 1309 |
+
"grad_norm": 0.4727443754673004,
|
| 1310 |
+
"learning_rate": 1.0716894226543953e-05,
|
| 1311 |
+
"loss": 0.2677,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.03506180134928842,
|
| 1316 |
+
"grad_norm": 0.37858378887176514,
|
| 1317 |
+
"learning_rate": 9.815330310080887e-06,
|
| 1318 |
+
"loss": 0.2534,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.035258777761363075,
|
| 1323 |
+
"grad_norm": 0.4432028830051422,
|
| 1324 |
+
"learning_rate": 8.952091482575824e-06,
|
| 1325 |
+
"loss": 0.3306,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.03545575417343773,
|
| 1330 |
+
"grad_norm": 0.4843367636203766,
|
| 1331 |
+
"learning_rate": 8.127413744904804e-06,
|
| 1332 |
+
"loss": 0.2407,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.03565273058551238,
|
| 1337 |
+
"grad_norm": 0.5236724615097046,
|
| 1338 |
+
"learning_rate": 7.34152255572697e-06,
|
| 1339 |
+
"loss": 0.2688,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.035849706997587036,
|
| 1344 |
+
"grad_norm": 0.688205897808075,
|
| 1345 |
+
"learning_rate": 6.594632769846353e-06,
|
| 1346 |
+
"loss": 0.3668,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.036046683409661696,
|
| 1351 |
+
"grad_norm": 0.4552861452102661,
|
| 1352 |
+
"learning_rate": 5.886948579472778e-06,
|
| 1353 |
+
"loss": 0.275,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.03624365982173635,
|
| 1358 |
+
"grad_norm": 0.5080707669258118,
|
| 1359 |
+
"learning_rate": 5.218663458397715e-06,
|
| 1360 |
+
"loss": 0.2851,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.036440636233811004,
|
| 1365 |
+
"grad_norm": 0.43050211668014526,
|
| 1366 |
+
"learning_rate": 4.589960109100444e-06,
|
| 1367 |
+
"loss": 0.2722,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.03663761264588566,
|
| 1372 |
+
"grad_norm": 0.548950731754303,
|
| 1373 |
+
"learning_rate": 4.001010412799138e-06,
|
| 1374 |
+
"loss": 0.2045,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.03683458905796031,
|
| 1379 |
+
"grad_norm": 0.42442962527275085,
|
| 1380 |
+
"learning_rate": 3.451975382460109e-06,
|
| 1381 |
+
"loss": 0.3006,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.037031565470034965,
|
| 1386 |
+
"grad_norm": 0.5989577174186707,
|
| 1387 |
+
"learning_rate": 2.9430051187785962e-06,
|
| 1388 |
+
"loss": 0.1922,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.03722854188210962,
|
| 1393 |
+
"grad_norm": 0.528300404548645,
|
| 1394 |
+
"learning_rate": 2.4742387691426445e-06,
|
| 1395 |
+
"loss": 0.2248,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.03742551829418427,
|
| 1400 |
+
"grad_norm": 0.5548564195632935,
|
| 1401 |
+
"learning_rate": 2.0458044895916513e-06,
|
| 1402 |
+
"loss": 0.2838,
|
| 1403 |
+
"step": 190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.037622494706258926,
|
| 1407 |
+
"grad_norm": 0.6061025857925415,
|
| 1408 |
+
"learning_rate": 1.6578194097797258e-06,
|
| 1409 |
+
"loss": 0.2634,
|
| 1410 |
+
"step": 191
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.03781947111833358,
|
| 1414 |
+
"grad_norm": 0.6724241971969604,
|
| 1415 |
+
"learning_rate": 1.3103896009537207e-06,
|
| 1416 |
+
"loss": 0.3241,
|
| 1417 |
+
"step": 192
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.03801644753040823,
|
| 1421 |
+
"grad_norm": 0.629009485244751,
|
| 1422 |
+
"learning_rate": 1.0036100469542786e-06,
|
| 1423 |
+
"loss": 0.2181,
|
| 1424 |
+
"step": 193
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.03821342394248289,
|
| 1428 |
+
"grad_norm": 0.6329449415206909,
|
| 1429 |
+
"learning_rate": 7.375646182482875e-07,
|
| 1430 |
+
"loss": 0.1653,
|
| 1431 |
+
"step": 194
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.03841040035455754,
|
| 1435 |
+
"grad_norm": 0.5899990200996399,
|
| 1436 |
+
"learning_rate": 5.123260489995229e-07,
|
| 1437 |
+
"loss": 0.2021,
|
| 1438 |
+
"step": 195
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.038607376766632194,
|
| 1442 |
+
"grad_norm": 0.6992418169975281,
|
| 1443 |
+
"learning_rate": 3.2795591718381975e-07,
|
| 1444 |
+
"loss": 0.1811,
|
| 1445 |
+
"step": 196
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.03880435317870685,
|
| 1449 |
+
"grad_norm": 0.7541390657424927,
|
| 1450 |
+
"learning_rate": 1.8450462775428942e-07,
|
| 1451 |
+
"loss": 0.1525,
|
| 1452 |
+
"step": 197
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.0390013295907815,
|
| 1456 |
+
"grad_norm": 0.5883744955062866,
|
| 1457 |
+
"learning_rate": 8.201139886109264e-08,
|
| 1458 |
+
"loss": 0.143,
|
| 1459 |
+
"step": 198
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.039198306002856155,
|
| 1463 |
+
"grad_norm": 0.8709452748298645,
|
| 1464 |
+
"learning_rate": 2.0504251129649374e-08,
|
| 1465 |
+
"loss": 0.1841,
|
| 1466 |
+
"step": 199
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.03939528241493081,
|
| 1470 |
+
"grad_norm": 0.9281623363494873,
|
| 1471 |
+
"learning_rate": 0.0,
|
| 1472 |
+
"loss": 0.2595,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.03939528241493081,
|
| 1477 |
+
"eval_loss": 0.07271432131528854,
|
| 1478 |
+
"eval_runtime": 12.7749,
|
| 1479 |
+
"eval_samples_per_second": 3.914,
|
| 1480 |
+
"eval_steps_per_second": 0.548,
|
| 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": 3.47763455488426e+17,
|
| 1511 |
"train_batch_size": 8,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|