Training in progress, step 200, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 463916180
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a1b5d04dc1b71c86c326d07d5ed5f1303d95568ea7b0cbfd36a537b4b4a84b0
|
| 3 |
size 463916180
|
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 sha256:0a00b970987a27a219c5ca484196bc632c7dd1f9beb4a5919852010591a598fb
|
| 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 sha256:7df65c8f4b426598b0abc4173b1983dcf7411aee63ea4061d980eae7a1af2363
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 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 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 2.687,
|
| 1090 |
"eval_steps_per_second": 0.672,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1103,7 +1461,7 @@
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
-
"early_stopping_patience_counter":
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
@@ -1112,12 +1470,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 2.4024024024024024,
|
| 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": 2.687,
|
| 1090 |
"eval_steps_per_second": 0.672,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.8138138138138138,
|
| 1095 |
+
"grad_norm": NaN,
|
| 1096 |
+
"learning_rate": 1.7085562498478883e-05,
|
| 1097 |
+
"loss": 0.0,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.825825825825826,
|
| 1102 |
+
"grad_norm": NaN,
|
| 1103 |
+
"learning_rate": 1.6431976865013128e-05,
|
| 1104 |
+
"loss": 0.0,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.8378378378378377,
|
| 1109 |
+
"grad_norm": NaN,
|
| 1110 |
+
"learning_rate": 1.5788935343973164e-05,
|
| 1111 |
+
"loss": 0.0,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.84984984984985,
|
| 1116 |
+
"grad_norm": NaN,
|
| 1117 |
+
"learning_rate": 1.5156613736490108e-05,
|
| 1118 |
+
"loss": 0.0,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.8618618618618619,
|
| 1123 |
+
"grad_norm": NaN,
|
| 1124 |
+
"learning_rate": 1.4535184912977763e-05,
|
| 1125 |
+
"loss": 0.0,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.8738738738738738,
|
| 1130 |
+
"grad_norm": NaN,
|
| 1131 |
+
"learning_rate": 1.3924818765871553e-05,
|
| 1132 |
+
"loss": 0.0,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.885885885885886,
|
| 1137 |
+
"grad_norm": NaN,
|
| 1138 |
+
"learning_rate": 1.3325682163181601e-05,
|
| 1139 |
+
"loss": 0.0,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.8978978978978978,
|
| 1144 |
+
"grad_norm": NaN,
|
| 1145 |
+
"learning_rate": 1.2737938902872767e-05,
|
| 1146 |
+
"loss": 0.0,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.90990990990991,
|
| 1151 |
+
"grad_norm": NaN,
|
| 1152 |
+
"learning_rate": 1.2161749668083823e-05,
|
| 1153 |
+
"loss": 0.0,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.921921921921922,
|
| 1158 |
+
"grad_norm": NaN,
|
| 1159 |
+
"learning_rate": 1.159727198319836e-05,
|
| 1160 |
+
"loss": 0.0,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.9339339339339339,
|
| 1165 |
+
"grad_norm": NaN,
|
| 1166 |
+
"learning_rate": 1.1044660170779142e-05,
|
| 1167 |
+
"loss": 0.0,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.945945945945946,
|
| 1172 |
+
"grad_norm": NaN,
|
| 1173 |
+
"learning_rate": 1.0504065309377897e-05,
|
| 1174 |
+
"loss": 0.0,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.9579579579579578,
|
| 1179 |
+
"grad_norm": NaN,
|
| 1180 |
+
"learning_rate": 9.97563519223192e-06,
|
| 1181 |
+
"loss": 0.0,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.96996996996997,
|
| 1186 |
+
"grad_norm": NaN,
|
| 1187 |
+
"learning_rate": 9.459514286858898e-06,
|
| 1188 |
+
"loss": 0.0,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.981981981981982,
|
| 1193 |
+
"grad_norm": NaN,
|
| 1194 |
+
"learning_rate": 8.95584369556093e-06,
|
| 1195 |
+
"loss": 0.0,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.993993993993994,
|
| 1200 |
+
"grad_norm": NaN,
|
| 1201 |
+
"learning_rate": 8.464761116848546e-06,
|
| 1202 |
+
"loss": 0.0,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.006006006006006,
|
| 1207 |
+
"grad_norm": NaN,
|
| 1208 |
+
"learning_rate": 7.986400807795349e-06,
|
| 1209 |
+
"loss": 0.0,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.018018018018018,
|
| 1214 |
+
"grad_norm": NaN,
|
| 1215 |
+
"learning_rate": 7.520893547333436e-06,
|
| 1216 |
+
"loss": 1.519,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 2.03003003003003,
|
| 1221 |
+
"grad_norm": NaN,
|
| 1222 |
+
"learning_rate": 7.068366600499744e-06,
|
| 1223 |
+
"loss": 8.7522,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.042042042042042,
|
| 1228 |
+
"grad_norm": NaN,
|
| 1229 |
+
"learning_rate": 6.6289436836431076e-06,
|
| 1230 |
+
"loss": 0.0,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.054054054054054,
|
| 1235 |
+
"grad_norm": NaN,
|
| 1236 |
+
"learning_rate": 6.20274493060135e-06,
|
| 1237 |
+
"loss": 0.0,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 2.066066066066066,
|
| 1242 |
+
"grad_norm": NaN,
|
| 1243 |
+
"learning_rate": 5.789886859858009e-06,
|
| 1244 |
+
"loss": 0.0,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.078078078078078,
|
| 1249 |
+
"grad_norm": NaN,
|
| 1250 |
+
"learning_rate": 5.3904823426872605e-06,
|
| 1251 |
+
"loss": 0.0,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 2.09009009009009,
|
| 1256 |
+
"grad_norm": NaN,
|
| 1257 |
+
"learning_rate": 5.004640572296062e-06,
|
| 1258 |
+
"loss": 0.0,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 2.1021021021021022,
|
| 1263 |
+
"grad_norm": NaN,
|
| 1264 |
+
"learning_rate": 4.632467033971838e-06,
|
| 1265 |
+
"loss": 0.0,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.114114114114114,
|
| 1270 |
+
"grad_norm": NaN,
|
| 1271 |
+
"learning_rate": 4.274063476243839e-06,
|
| 1272 |
+
"loss": 0.0,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.126126126126126,
|
| 1277 |
+
"grad_norm": NaN,
|
| 1278 |
+
"learning_rate": 3.929527883066117e-06,
|
| 1279 |
+
"loss": 0.0,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 2.138138138138138,
|
| 1284 |
+
"grad_norm": NaN,
|
| 1285 |
+
"learning_rate": 3.5989544470296595e-06,
|
| 1286 |
+
"loss": 0.0,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 2.15015015015015,
|
| 1291 |
+
"grad_norm": NaN,
|
| 1292 |
+
"learning_rate": 3.282433543611136e-06,
|
| 1293 |
+
"loss": 0.0,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 2.1621621621621623,
|
| 1298 |
+
"grad_norm": NaN,
|
| 1299 |
+
"learning_rate": 2.980051706465095e-06,
|
| 1300 |
+
"loss": 0.0,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.174174174174174,
|
| 1305 |
+
"grad_norm": NaN,
|
| 1306 |
+
"learning_rate": 2.691891603766556e-06,
|
| 1307 |
+
"loss": 0.0,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.186186186186186,
|
| 1312 |
+
"grad_norm": NaN,
|
| 1313 |
+
"learning_rate": 2.4180320156103298e-06,
|
| 1314 |
+
"loss": 0.0,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 2.1981981981981984,
|
| 1319 |
+
"grad_norm": NaN,
|
| 1320 |
+
"learning_rate": 2.158547812473352e-06,
|
| 1321 |
+
"loss": 0.0,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 2.21021021021021,
|
| 1326 |
+
"grad_norm": NaN,
|
| 1327 |
+
"learning_rate": 1.9135099347458293e-06,
|
| 1328 |
+
"loss": 0.0,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.2222222222222223,
|
| 1333 |
+
"grad_norm": NaN,
|
| 1334 |
+
"learning_rate": 1.6829853733368294e-06,
|
| 1335 |
+
"loss": 0.0,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.234234234234234,
|
| 1340 |
+
"grad_norm": NaN,
|
| 1341 |
+
"learning_rate": 1.4670371513596842e-06,
|
| 1342 |
+
"loss": 0.0,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 2.2462462462462462,
|
| 1347 |
+
"grad_norm": NaN,
|
| 1348 |
+
"learning_rate": 1.2657243069020402e-06,
|
| 1349 |
+
"loss": 0.0,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.2582582582582584,
|
| 1354 |
+
"grad_norm": NaN,
|
| 1355 |
+
"learning_rate": 1.0791018768854855e-06,
|
| 1356 |
+
"loss": 1.5516,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 2.27027027027027,
|
| 1361 |
+
"grad_norm": NaN,
|
| 1362 |
+
"learning_rate": 9.072208820189698e-07,
|
| 1363 |
+
"loss": 12.3966,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 2.2822822822822824,
|
| 1368 |
+
"grad_norm": NaN,
|
| 1369 |
+
"learning_rate": 7.501283128502722e-07,
|
| 1370 |
+
"loss": 0.0,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 2.294294294294294,
|
| 1375 |
+
"grad_norm": NaN,
|
| 1376 |
+
"learning_rate": 6.07867116919233e-07,
|
| 1377 |
+
"loss": 0.0,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 2.3063063063063063,
|
| 1382 |
+
"grad_norm": NaN,
|
| 1383 |
+
"learning_rate": 4.804761870163643e-07,
|
| 1384 |
+
"loss": 0.0,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.3183183183183185,
|
| 1389 |
+
"grad_norm": NaN,
|
| 1390 |
+
"learning_rate": 3.6799035054990215e-07,
|
| 1391 |
+
"loss": 0.0,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.33033033033033,
|
| 1396 |
+
"grad_norm": NaN,
|
| 1397 |
+
"learning_rate": 2.704403600243721e-07,
|
| 1398 |
+
"loss": 0.0,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.3423423423423424,
|
| 1403 |
+
"grad_norm": NaN,
|
| 1404 |
+
"learning_rate": 1.878528846331584e-07,
|
| 1405 |
+
"loss": 0.0,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.3543543543543546,
|
| 1410 |
+
"grad_norm": NaN,
|
| 1411 |
+
"learning_rate": 1.202505029674006e-07,
|
| 1412 |
+
"loss": 0.0,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.3663663663663663,
|
| 1417 |
+
"grad_norm": NaN,
|
| 1418 |
+
"learning_rate": 6.765169684323947e-08,
|
| 1419 |
+
"loss": 0.0,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.3783783783783785,
|
| 1424 |
+
"grad_norm": NaN,
|
| 1425 |
+
"learning_rate": 3.007084624906731e-08,
|
| 1426 |
+
"loss": 0.0,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 2.3903903903903903,
|
| 1431 |
+
"grad_norm": NaN,
|
| 1432 |
+
"learning_rate": 7.518225414204771e-09,
|
| 1433 |
+
"loss": 0.0,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.4024024024024024,
|
| 1438 |
+
"grad_norm": NaN,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.0,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.4024024024024024,
|
| 1445 |
+
"eval_loss": NaN,
|
| 1446 |
+
"eval_runtime": 47.7586,
|
| 1447 |
+
"eval_samples_per_second": 2.931,
|
| 1448 |
+
"eval_steps_per_second": 0.733,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1461 |
"early_stopping_threshold": 0.0
|
| 1462 |
},
|
| 1463 |
"attributes": {
|
| 1464 |
+
"early_stopping_patience_counter": 3
|
| 1465 |
}
|
| 1466 |
},
|
| 1467 |
"TrainerControl": {
|
|
|
|
| 1470 |
"should_evaluate": false,
|
| 1471 |
"should_log": false,
|
| 1472 |
"should_save": true,
|
| 1473 |
+
"should_training_stop": true
|
| 1474 |
},
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 4.93193388883968e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|