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 78207176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:370f330eba363f87a49727e57e915a5ba62e244aa19b1cb4c4dd4cbff597da92
|
| 3 |
size 78207176
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40177764
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ec56cb46dbb6f866163627befa182c4b9b3afaa4d4beaf8e38ec89f30255e8
|
| 3 |
size 40177764
|
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 sha256:933f1102cf96a4acb2468267696dd282e1db9df7763fc44738a73f57f483334a
|
| 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:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 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,
|
|
@@ -1081,6 +1081,364 @@
|
|
| 1081 |
"eval_samples_per_second": 89.712,
|
| 1082 |
"eval_steps_per_second": 22.445,
|
| 1083 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1084 |
}
|
| 1085 |
],
|
| 1086 |
"logging_steps": 1,
|
|
@@ -1104,12 +1462,12 @@
|
|
| 1104 |
"should_evaluate": false,
|
| 1105 |
"should_log": false,
|
| 1106 |
"should_save": true,
|
| 1107 |
-
"should_training_stop":
|
| 1108 |
},
|
| 1109 |
"attributes": {}
|
| 1110 |
}
|
| 1111 |
},
|
| 1112 |
-
"total_flos":
|
| 1113 |
"train_batch_size": 8,
|
| 1114 |
"trial_name": null,
|
| 1115 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.9486095905303955,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.1310830738980829,
|
| 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,
|
|
|
|
| 1081 |
"eval_samples_per_second": 89.712,
|
| 1082 |
"eval_steps_per_second": 22.445,
|
| 1083 |
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.09896772079305259,
|
| 1087 |
+
"grad_norm": 0.2969697415828705,
|
| 1088 |
+
"learning_rate": 1.553232954407171e-05,
|
| 1089 |
+
"loss": 2.6574,
|
| 1090 |
+
"step": 151
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.09962313616254301,
|
| 1094 |
+
"grad_norm": 0.3212166428565979,
|
| 1095 |
+
"learning_rate": 1.4938160786375572e-05,
|
| 1096 |
+
"loss": 2.7024,
|
| 1097 |
+
"step": 152
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.10027855153203342,
|
| 1101 |
+
"grad_norm": 0.3293731212615967,
|
| 1102 |
+
"learning_rate": 1.435357758543015e-05,
|
| 1103 |
+
"loss": 2.7815,
|
| 1104 |
+
"step": 153
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.10093396690152384,
|
| 1108 |
+
"grad_norm": 0.33274203538894653,
|
| 1109 |
+
"learning_rate": 1.3778739760445552e-05,
|
| 1110 |
+
"loss": 2.9143,
|
| 1111 |
+
"step": 154
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.10158938227101426,
|
| 1115 |
+
"grad_norm": 0.346316933631897,
|
| 1116 |
+
"learning_rate": 1.3213804466343421e-05,
|
| 1117 |
+
"loss": 2.6944,
|
| 1118 |
+
"step": 155
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.10224479764050468,
|
| 1122 |
+
"grad_norm": 0.34352895617485046,
|
| 1123 |
+
"learning_rate": 1.2658926150792322e-05,
|
| 1124 |
+
"loss": 2.9016,
|
| 1125 |
+
"step": 156
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.10290021300999508,
|
| 1129 |
+
"grad_norm": 0.34370890259742737,
|
| 1130 |
+
"learning_rate": 1.2114256511983274e-05,
|
| 1131 |
+
"loss": 2.6517,
|
| 1132 |
+
"step": 157
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.1035556283794855,
|
| 1136 |
+
"grad_norm": 0.33687496185302734,
|
| 1137 |
+
"learning_rate": 1.157994445715706e-05,
|
| 1138 |
+
"loss": 2.7905,
|
| 1139 |
+
"step": 158
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.10421104374897591,
|
| 1143 |
+
"grad_norm": 0.3169892132282257,
|
| 1144 |
+
"learning_rate": 1.1056136061894384e-05,
|
| 1145 |
+
"loss": 2.8319,
|
| 1146 |
+
"step": 159
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.10486645911846633,
|
| 1150 |
+
"grad_norm": 0.3209782540798187,
|
| 1151 |
+
"learning_rate": 1.0542974530180327e-05,
|
| 1152 |
+
"loss": 2.838,
|
| 1153 |
+
"step": 160
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.10552187448795675,
|
| 1157 |
+
"grad_norm": 0.31733939051628113,
|
| 1158 |
+
"learning_rate": 1.0040600155253765e-05,
|
| 1159 |
+
"loss": 2.9153,
|
| 1160 |
+
"step": 161
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.10617728985744716,
|
| 1164 |
+
"grad_norm": 0.3245903551578522,
|
| 1165 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1166 |
+
"loss": 2.915,
|
| 1167 |
+
"step": 162
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.10683270522693757,
|
| 1171 |
+
"grad_norm": 0.3132364749908447,
|
| 1172 |
+
"learning_rate": 9.068759265665384e-06,
|
| 1173 |
+
"loss": 2.9082,
|
| 1174 |
+
"step": 163
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.10748812059642798,
|
| 1178 |
+
"grad_norm": 0.3096357583999634,
|
| 1179 |
+
"learning_rate": 8.599558442598998e-06,
|
| 1180 |
+
"loss": 2.8298,
|
| 1181 |
+
"step": 164
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.1081435359659184,
|
| 1185 |
+
"grad_norm": 0.3304586112499237,
|
| 1186 |
+
"learning_rate": 8.141676086873572e-06,
|
| 1187 |
+
"loss": 2.8318,
|
| 1188 |
+
"step": 165
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.10879895133540882,
|
| 1192 |
+
"grad_norm": 0.301999032497406,
|
| 1193 |
+
"learning_rate": 7.695237378953223e-06,
|
| 1194 |
+
"loss": 2.7103,
|
| 1195 |
+
"step": 166
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.10945436670489923,
|
| 1199 |
+
"grad_norm": 0.316394567489624,
|
| 1200 |
+
"learning_rate": 7.260364370723044e-06,
|
| 1201 |
+
"loss": 2.813,
|
| 1202 |
+
"step": 167
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.11010978207438965,
|
| 1206 |
+
"grad_norm": 0.3100992739200592,
|
| 1207 |
+
"learning_rate": 6.837175952121306e-06,
|
| 1208 |
+
"loss": 2.7979,
|
| 1209 |
+
"step": 168
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.11076519744388005,
|
| 1213 |
+
"grad_norm": 0.33947116136550903,
|
| 1214 |
+
"learning_rate": 6.425787818636131e-06,
|
| 1215 |
+
"loss": 3.044,
|
| 1216 |
+
"step": 169
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.11142061281337047,
|
| 1220 |
+
"grad_norm": 0.34802699089050293,
|
| 1221 |
+
"learning_rate": 6.026312439675552e-06,
|
| 1222 |
+
"loss": 2.949,
|
| 1223 |
+
"step": 170
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.11207602818286089,
|
| 1227 |
+
"grad_norm": 0.3301544487476349,
|
| 1228 |
+
"learning_rate": 5.6388590278194096e-06,
|
| 1229 |
+
"loss": 2.9406,
|
| 1230 |
+
"step": 171
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.1127314435523513,
|
| 1234 |
+
"grad_norm": 0.3329584002494812,
|
| 1235 |
+
"learning_rate": 5.263533508961827e-06,
|
| 1236 |
+
"loss": 2.889,
|
| 1237 |
+
"step": 172
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.11338685892184172,
|
| 1241 |
+
"grad_norm": 0.36334100365638733,
|
| 1242 |
+
"learning_rate": 4.900438493352055e-06,
|
| 1243 |
+
"loss": 2.7989,
|
| 1244 |
+
"step": 173
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.11404227429133214,
|
| 1248 |
+
"grad_norm": 0.3871985971927643,
|
| 1249 |
+
"learning_rate": 4.549673247541875e-06,
|
| 1250 |
+
"loss": 3.0005,
|
| 1251 |
+
"step": 174
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.11469768966082254,
|
| 1255 |
+
"grad_norm": 0.39044347405433655,
|
| 1256 |
+
"learning_rate": 4.2113336672471245e-06,
|
| 1257 |
+
"loss": 2.9216,
|
| 1258 |
+
"step": 175
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.11535310503031296,
|
| 1262 |
+
"grad_norm": 0.42362478375434875,
|
| 1263 |
+
"learning_rate": 3.885512251130763e-06,
|
| 1264 |
+
"loss": 2.8774,
|
| 1265 |
+
"step": 176
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.11600852039980337,
|
| 1269 |
+
"grad_norm": 0.41563165187835693,
|
| 1270 |
+
"learning_rate": 3.5722980755146517e-06,
|
| 1271 |
+
"loss": 2.8858,
|
| 1272 |
+
"step": 177
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.11666393576929379,
|
| 1276 |
+
"grad_norm": 0.40200382471084595,
|
| 1277 |
+
"learning_rate": 3.271776770026963e-06,
|
| 1278 |
+
"loss": 3.0528,
|
| 1279 |
+
"step": 178
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.11731935113878421,
|
| 1283 |
+
"grad_norm": 0.41342130303382874,
|
| 1284 |
+
"learning_rate": 2.9840304941919415e-06,
|
| 1285 |
+
"loss": 2.7216,
|
| 1286 |
+
"step": 179
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.11797476650827463,
|
| 1290 |
+
"grad_norm": 0.4515306055545807,
|
| 1291 |
+
"learning_rate": 2.7091379149682685e-06,
|
| 1292 |
+
"loss": 2.7365,
|
| 1293 |
+
"step": 180
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.11863018187776503,
|
| 1297 |
+
"grad_norm": 0.4612429738044739,
|
| 1298 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1299 |
+
"loss": 3.0391,
|
| 1300 |
+
"step": 181
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.11928559724725545,
|
| 1304 |
+
"grad_norm": 0.5291233658790588,
|
| 1305 |
+
"learning_rate": 2.1982109232821178e-06,
|
| 1306 |
+
"loss": 3.1772,
|
| 1307 |
+
"step": 182
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.11994101261674586,
|
| 1311 |
+
"grad_norm": 0.535449206829071,
|
| 1312 |
+
"learning_rate": 1.962316193157593e-06,
|
| 1313 |
+
"loss": 2.9083,
|
| 1314 |
+
"step": 183
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.12059642798623628,
|
| 1318 |
+
"grad_norm": 0.5292407274246216,
|
| 1319 |
+
"learning_rate": 1.7395544861325718e-06,
|
| 1320 |
+
"loss": 2.808,
|
| 1321 |
+
"step": 184
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.1212518433557267,
|
| 1325 |
+
"grad_norm": 0.5661318302154541,
|
| 1326 |
+
"learning_rate": 1.5299867030334814e-06,
|
| 1327 |
+
"loss": 2.7694,
|
| 1328 |
+
"step": 185
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.12190725872521711,
|
| 1332 |
+
"grad_norm": 0.643547534942627,
|
| 1333 |
+
"learning_rate": 1.333670137599713e-06,
|
| 1334 |
+
"loss": 2.8914,
|
| 1335 |
+
"step": 186
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.12256267409470752,
|
| 1339 |
+
"grad_norm": 0.6568232774734497,
|
| 1340 |
+
"learning_rate": 1.1506584608200367e-06,
|
| 1341 |
+
"loss": 3.3191,
|
| 1342 |
+
"step": 187
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.12321808946419793,
|
| 1346 |
+
"grad_norm": 0.6222873330116272,
|
| 1347 |
+
"learning_rate": 9.810017062595322e-07,
|
| 1348 |
+
"loss": 2.891,
|
| 1349 |
+
"step": 188
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.12387350483368835,
|
| 1353 |
+
"grad_norm": 0.6692857146263123,
|
| 1354 |
+
"learning_rate": 8.247462563808817e-07,
|
| 1355 |
+
"loss": 3.2878,
|
| 1356 |
+
"step": 189
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.12452892020317877,
|
| 1360 |
+
"grad_norm": 0.68501877784729,
|
| 1361 |
+
"learning_rate": 6.819348298638839e-07,
|
| 1362 |
+
"loss": 3.0949,
|
| 1363 |
+
"step": 190
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.12518433557266917,
|
| 1367 |
+
"grad_norm": 0.7736201286315918,
|
| 1368 |
+
"learning_rate": 5.526064699265753e-07,
|
| 1369 |
+
"loss": 3.3124,
|
| 1370 |
+
"step": 191
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.1258397509421596,
|
| 1374 |
+
"grad_norm": 0.8811625242233276,
|
| 1375 |
+
"learning_rate": 4.367965336512403e-07,
|
| 1376 |
+
"loss": 3.5033,
|
| 1377 |
+
"step": 192
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.12649516631165,
|
| 1381 |
+
"grad_norm": 0.8846380114555359,
|
| 1382 |
+
"learning_rate": 3.3453668231809286e-07,
|
| 1383 |
+
"loss": 3.1777,
|
| 1384 |
+
"step": 193
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.12715058168114043,
|
| 1388 |
+
"grad_norm": 0.9585743546485901,
|
| 1389 |
+
"learning_rate": 2.458548727494292e-07,
|
| 1390 |
+
"loss": 2.9489,
|
| 1391 |
+
"step": 194
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.12780599705063084,
|
| 1395 |
+
"grad_norm": 0.9785580039024353,
|
| 1396 |
+
"learning_rate": 1.7077534966650766e-07,
|
| 1397 |
+
"loss": 3.3586,
|
| 1398 |
+
"step": 195
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.12846141242012124,
|
| 1402 |
+
"grad_norm": 1.106945276260376,
|
| 1403 |
+
"learning_rate": 1.0931863906127327e-07,
|
| 1404 |
+
"loss": 3.5678,
|
| 1405 |
+
"step": 196
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.12911682778961167,
|
| 1409 |
+
"grad_norm": 0.9721198678016663,
|
| 1410 |
+
"learning_rate": 6.150154258476315e-08,
|
| 1411 |
+
"loss": 3.1025,
|
| 1412 |
+
"step": 197
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.12977224315910207,
|
| 1416 |
+
"grad_norm": 1.1778976917266846,
|
| 1417 |
+
"learning_rate": 2.7337132953697554e-08,
|
| 1418 |
+
"loss": 3.3442,
|
| 1419 |
+
"step": 198
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.1304276585285925,
|
| 1423 |
+
"grad_norm": 1.3782392740249634,
|
| 1424 |
+
"learning_rate": 6.834750376549792e-09,
|
| 1425 |
+
"loss": 3.5686,
|
| 1426 |
+
"step": 199
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.1310830738980829,
|
| 1430 |
+
"grad_norm": 1.6824958324432373,
|
| 1431 |
+
"learning_rate": 0.0,
|
| 1432 |
+
"loss": 3.5027,
|
| 1433 |
+
"step": 200
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.1310830738980829,
|
| 1437 |
+
"eval_loss": 2.9486095905303955,
|
| 1438 |
+
"eval_runtime": 29.0953,
|
| 1439 |
+
"eval_samples_per_second": 88.33,
|
| 1440 |
+
"eval_steps_per_second": 22.1,
|
| 1441 |
+
"step": 200
|
| 1442 |
}
|
| 1443 |
],
|
| 1444 |
"logging_steps": 1,
|
|
|
|
| 1462 |
"should_evaluate": false,
|
| 1463 |
"should_log": false,
|
| 1464 |
"should_save": true,
|
| 1465 |
+
"should_training_stop": true
|
| 1466 |
},
|
| 1467 |
"attributes": {}
|
| 1468 |
}
|
| 1469 |
},
|
| 1470 |
+
"total_flos": 4975254291087360.0,
|
| 1471 |
"train_batch_size": 8,
|
| 1472 |
"trial_name": null,
|
| 1473 |
"trial_params": null
|