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 1163996488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:447ca78f8c5ab228b6bf38d712344ab491d973f04af4ae6f9881c31a71d04779
|
| 3 |
size 1163996488
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca07c3cbf368dfd16d15ba02590dd65ede43337f2a900129d0e09d2c6ed4fb08
|
| 3 |
size 325339796
|
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 sha256:2ecd7846f36f8ca60b89a4fb437c6a3f7f7fc11db8da0a712174f8690e45188d
|
| 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:a032dcbe590e69725a7fa9cedb5934521429cb4c18983c09c5035cbcaaeebd93
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 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": 13.263,
|
| 1090 |
"eval_steps_per_second": 3.318,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -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": 2.
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.4315598011016846,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.07202016564638099,
|
| 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": 13.263,
|
| 1090 |
"eval_steps_per_second": 3.318,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.054375225063017646,
|
| 1095 |
+
"grad_norm": 0.17845895886421204,
|
| 1096 |
+
"learning_rate": 1.242586363525737e-05,
|
| 1097 |
+
"loss": 1.2068,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.05473532589124955,
|
| 1102 |
+
"grad_norm": 0.182268425822258,
|
| 1103 |
+
"learning_rate": 1.1950528629100457e-05,
|
| 1104 |
+
"loss": 0.9337,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.055095426719481456,
|
| 1109 |
+
"grad_norm": 0.2000552862882614,
|
| 1110 |
+
"learning_rate": 1.1482862068344121e-05,
|
| 1111 |
+
"loss": 1.063,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.05545552754771336,
|
| 1116 |
+
"grad_norm": 0.24774210155010223,
|
| 1117 |
+
"learning_rate": 1.1022991808356442e-05,
|
| 1118 |
+
"loss": 0.9987,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.05581562837594527,
|
| 1123 |
+
"grad_norm": 0.24467074871063232,
|
| 1124 |
+
"learning_rate": 1.0571043573074737e-05,
|
| 1125 |
+
"loss": 1.0237,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.05617572920417717,
|
| 1130 |
+
"grad_norm": 0.26388347148895264,
|
| 1131 |
+
"learning_rate": 1.0127140920633857e-05,
|
| 1132 |
+
"loss": 1.094,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.05653583003240908,
|
| 1137 |
+
"grad_norm": 0.26566648483276367,
|
| 1138 |
+
"learning_rate": 9.69140520958662e-06,
|
| 1139 |
+
"loss": 0.9359,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.05689593086064098,
|
| 1144 |
+
"grad_norm": 0.2803097665309906,
|
| 1145 |
+
"learning_rate": 9.263955565725648e-06,
|
| 1146 |
+
"loss": 0.9668,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.05725603168887288,
|
| 1151 |
+
"grad_norm": 0.3015349805355072,
|
| 1152 |
+
"learning_rate": 8.844908849515509e-06,
|
| 1153 |
+
"loss": 0.9699,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.05761613251710479,
|
| 1158 |
+
"grad_norm": 0.32080352306365967,
|
| 1159 |
+
"learning_rate": 8.434379624144261e-06,
|
| 1160 |
+
"loss": 1.0425,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.05797623334533669,
|
| 1165 |
+
"grad_norm": 0.3093397617340088,
|
| 1166 |
+
"learning_rate": 8.032480124203013e-06,
|
| 1167 |
+
"loss": 1.0277,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.0583363341735686,
|
| 1172 |
+
"grad_norm": 0.35267412662506104,
|
| 1173 |
+
"learning_rate": 7.639320225002106e-06,
|
| 1174 |
+
"loss": 1.0362,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.0586964350018005,
|
| 1179 |
+
"grad_norm": 0.3147299885749817,
|
| 1180 |
+
"learning_rate": 7.255007412532307e-06,
|
| 1181 |
+
"loss": 1.2137,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.05905653583003241,
|
| 1186 |
+
"grad_norm": 0.3240807354450226,
|
| 1187 |
+
"learning_rate": 6.8796467540791986e-06,
|
| 1188 |
+
"loss": 1.1423,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.05941663665826431,
|
| 1193 |
+
"grad_norm": 0.34494078159332275,
|
| 1194 |
+
"learning_rate": 6.513340869498859e-06,
|
| 1195 |
+
"loss": 1.0648,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.05977673748649622,
|
| 1200 |
+
"grad_norm": 0.344433456659317,
|
| 1201 |
+
"learning_rate": 6.1561899031625794e-06,
|
| 1202 |
+
"loss": 1.1728,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.060136838314728124,
|
| 1207 |
+
"grad_norm": 0.3598881959915161,
|
| 1208 |
+
"learning_rate": 5.808291496578435e-06,
|
| 1209 |
+
"loss": 1.243,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.06049693914296003,
|
| 1214 |
+
"grad_norm": 0.32712891697883606,
|
| 1215 |
+
"learning_rate": 5.469740761697044e-06,
|
| 1216 |
+
"loss": 1.1395,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.060857039971191934,
|
| 1221 |
+
"grad_norm": 0.3846420347690582,
|
| 1222 |
+
"learning_rate": 5.140630254908905e-06,
|
| 1223 |
+
"loss": 1.228,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.061217140799423836,
|
| 1228 |
+
"grad_norm": 0.38621753454208374,
|
| 1229 |
+
"learning_rate": 4.821049951740442e-06,
|
| 1230 |
+
"loss": 1.2447,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.061577241627655745,
|
| 1235 |
+
"grad_norm": 0.3678813874721527,
|
| 1236 |
+
"learning_rate": 4.511087222255528e-06,
|
| 1237 |
+
"loss": 1.4654,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.061937342455887646,
|
| 1242 |
+
"grad_norm": 0.42819997668266296,
|
| 1243 |
+
"learning_rate": 4.2108268071694616e-06,
|
| 1244 |
+
"loss": 1.346,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.062297443284119555,
|
| 1249 |
+
"grad_norm": 0.4565679430961609,
|
| 1250 |
+
"learning_rate": 3.9203507946816445e-06,
|
| 1251 |
+
"loss": 1.5151,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.06265754411235146,
|
| 1256 |
+
"grad_norm": 0.45869430899620056,
|
| 1257 |
+
"learning_rate": 3.6397385980335e-06,
|
| 1258 |
+
"loss": 1.5592,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.06301764494058336,
|
| 1263 |
+
"grad_norm": 0.4956825375556946,
|
| 1264 |
+
"learning_rate": 3.3690669337977e-06,
|
| 1265 |
+
"loss": 1.492,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.06337774576881527,
|
| 1270 |
+
"grad_norm": 0.485346257686615,
|
| 1271 |
+
"learning_rate": 3.1084098009046106e-06,
|
| 1272 |
+
"loss": 1.3435,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.06373784659704718,
|
| 1277 |
+
"grad_norm": 0.48392120003700256,
|
| 1278 |
+
"learning_rate": 2.8578384604117217e-06,
|
| 1279 |
+
"loss": 1.2057,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.06409794742527908,
|
| 1284 |
+
"grad_norm": 0.549443781375885,
|
| 1285 |
+
"learning_rate": 2.6174214160215704e-06,
|
| 1286 |
+
"loss": 1.5785,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.06445804825351098,
|
| 1291 |
+
"grad_norm": 0.6267411112785339,
|
| 1292 |
+
"learning_rate": 2.3872243953535535e-06,
|
| 1293 |
+
"loss": 1.4255,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.06481814908174288,
|
| 1298 |
+
"grad_norm": 0.6748881936073303,
|
| 1299 |
+
"learning_rate": 2.1673103319746146e-06,
|
| 1300 |
+
"loss": 1.5805,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.0651782499099748,
|
| 1305 |
+
"grad_norm": 0.5772015452384949,
|
| 1306 |
+
"learning_rate": 1.957739348193859e-06,
|
| 1307 |
+
"loss": 1.5119,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.0655383507382067,
|
| 1312 |
+
"grad_norm": 0.6203552484512329,
|
| 1313 |
+
"learning_rate": 1.7585687386256944e-06,
|
| 1314 |
+
"loss": 1.8784,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.0658984515664386,
|
| 1319 |
+
"grad_norm": 0.6191961169242859,
|
| 1320 |
+
"learning_rate": 1.5698529545260744e-06,
|
| 1321 |
+
"loss": 1.6006,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.0662585523946705,
|
| 1326 |
+
"grad_norm": 0.6806838512420654,
|
| 1327 |
+
"learning_rate": 1.3916435889060575e-06,
|
| 1328 |
+
"loss": 1.8019,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.06661865322290242,
|
| 1333 |
+
"grad_norm": 0.6513646841049194,
|
| 1334 |
+
"learning_rate": 1.2239893624267852e-06,
|
| 1335 |
+
"loss": 1.7764,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.06697875405113432,
|
| 1340 |
+
"grad_norm": 0.7780475616455078,
|
| 1341 |
+
"learning_rate": 1.0669361100797704e-06,
|
| 1342 |
+
"loss": 1.6974,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.06733885487936622,
|
| 1347 |
+
"grad_norm": 0.7961820363998413,
|
| 1348 |
+
"learning_rate": 9.205267686560293e-07,
|
| 1349 |
+
"loss": 1.7828,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.06769895570759812,
|
| 1354 |
+
"grad_norm": 0.8191195726394653,
|
| 1355 |
+
"learning_rate": 7.848013650076258e-07,
|
| 1356 |
+
"loss": 1.6961,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.06805905653583003,
|
| 1361 |
+
"grad_norm": 0.751133143901825,
|
| 1362 |
+
"learning_rate": 6.597970051047053e-07,
|
| 1363 |
+
"loss": 1.7882,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.06841915736406194,
|
| 1368 |
+
"grad_norm": 1.0630866289138794,
|
| 1369 |
+
"learning_rate": 5.455478638911071e-07,
|
| 1370 |
+
"loss": 1.9139,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.06877925819229384,
|
| 1375 |
+
"grad_norm": 0.9345506429672241,
|
| 1376 |
+
"learning_rate": 4.420851759412603e-07,
|
| 1377 |
+
"loss": 2.0675,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.06913935902052575,
|
| 1382 |
+
"grad_norm": 1.0234652757644653,
|
| 1383 |
+
"learning_rate": 3.4943722692099224e-07,
|
| 1384 |
+
"loss": 1.7824,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.06949945984875765,
|
| 1389 |
+
"grad_norm": 1.1317789554595947,
|
| 1390 |
+
"learning_rate": 2.676293458544743e-07,
|
| 1391 |
+
"loss": 2.1633,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.06985956067698956,
|
| 1396 |
+
"grad_norm": 1.1043999195098877,
|
| 1397 |
+
"learning_rate": 1.9668389819954338e-07,
|
| 1398 |
+
"loss": 1.6105,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.07021966150522146,
|
| 1403 |
+
"grad_norm": 0.9714563488960266,
|
| 1404 |
+
"learning_rate": 1.3662027973320614e-07,
|
| 1405 |
+
"loss": 1.9675,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.07057976233345337,
|
| 1410 |
+
"grad_norm": 1.1052969694137573,
|
| 1411 |
+
"learning_rate": 8.745491124901861e-08,
|
| 1412 |
+
"loss": 1.7856,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.07093986316168527,
|
| 1417 |
+
"grad_norm": 1.3346896171569824,
|
| 1418 |
+
"learning_rate": 4.920123406781052e-08,
|
| 1419 |
+
"loss": 2.0093,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.07129996398991717,
|
| 1424 |
+
"grad_norm": 1.2368483543395996,
|
| 1425 |
+
"learning_rate": 2.1869706362958044e-08,
|
| 1426 |
+
"loss": 1.7745,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.07166006481814909,
|
| 1431 |
+
"grad_norm": 1.3380067348480225,
|
| 1432 |
+
"learning_rate": 5.467800301239834e-09,
|
| 1433 |
+
"loss": 1.7581,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.07202016564638099,
|
| 1438 |
+
"grad_norm": 1.7450910806655884,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.7731,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.07202016564638099,
|
| 1445 |
+
"eval_loss": 1.4315598011016846,
|
| 1446 |
+
"eval_runtime": 352.6531,
|
| 1447 |
+
"eval_samples_per_second": 13.262,
|
| 1448 |
+
"eval_steps_per_second": 3.318,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 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": 2.7075605394200986e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|