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 226532664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4984e74a0cc26a254713214d97e4c847629bfdc2b9702c5daa9f55570d2fc6f6
|
| 3 |
size 226532664
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 115354708
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e0437f713dcecc650ad1528fac17844d3596241df7b9ec5106bc4c670ccf3b8
|
| 3 |
size 115354708
|
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:baee50c7c9340c9ae776684b5d59694bacb36d0b83a32a06550a2a14f1285125
|
| 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,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 51.136,
|
| 1090 |
"eval_steps_per_second": 12.784,
|
| 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":
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.160458564758301,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.15710919088766692,
|
| 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": 51.136,
|
| 1090 |
"eval_steps_per_second": 12.784,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.11861743912018853,
|
| 1095 |
+
"grad_norm": 10.751768112182617,
|
| 1096 |
+
"learning_rate": 1.553232954407171e-05,
|
| 1097 |
+
"loss": 10.848,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.11940298507462686,
|
| 1102 |
+
"grad_norm": 10.703509330749512,
|
| 1103 |
+
"learning_rate": 1.4938160786375572e-05,
|
| 1104 |
+
"loss": 10.1631,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.1201885310290652,
|
| 1109 |
+
"grad_norm": 10.520252227783203,
|
| 1110 |
+
"learning_rate": 1.435357758543015e-05,
|
| 1111 |
+
"loss": 9.6222,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.12097407698350353,
|
| 1116 |
+
"grad_norm": 10.443438529968262,
|
| 1117 |
+
"learning_rate": 1.3778739760445552e-05,
|
| 1118 |
+
"loss": 10.0078,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.12175962293794187,
|
| 1123 |
+
"grad_norm": 9.865094184875488,
|
| 1124 |
+
"learning_rate": 1.3213804466343421e-05,
|
| 1125 |
+
"loss": 9.1698,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.12254516889238021,
|
| 1130 |
+
"grad_norm": 10.785650253295898,
|
| 1131 |
+
"learning_rate": 1.2658926150792322e-05,
|
| 1132 |
+
"loss": 10.5674,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.12333071484681854,
|
| 1137 |
+
"grad_norm": 9.981478691101074,
|
| 1138 |
+
"learning_rate": 1.2114256511983274e-05,
|
| 1139 |
+
"loss": 9.6051,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.12411626080125687,
|
| 1144 |
+
"grad_norm": 9.448806762695312,
|
| 1145 |
+
"learning_rate": 1.157994445715706e-05,
|
| 1146 |
+
"loss": 8.974,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.1249018067556952,
|
| 1151 |
+
"grad_norm": 9.241495132446289,
|
| 1152 |
+
"learning_rate": 1.1056136061894384e-05,
|
| 1153 |
+
"loss": 9.2556,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.12568735271013354,
|
| 1158 |
+
"grad_norm": 8.831537246704102,
|
| 1159 |
+
"learning_rate": 1.0542974530180327e-05,
|
| 1160 |
+
"loss": 8.6257,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.12647289866457187,
|
| 1165 |
+
"grad_norm": 8.385761260986328,
|
| 1166 |
+
"learning_rate": 1.0040600155253765e-05,
|
| 1167 |
+
"loss": 8.857,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.1272584446190102,
|
| 1172 |
+
"grad_norm": 8.78468132019043,
|
| 1173 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1174 |
+
"loss": 8.9289,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.12804399057344854,
|
| 1179 |
+
"grad_norm": 8.653111457824707,
|
| 1180 |
+
"learning_rate": 9.068759265665384e-06,
|
| 1181 |
+
"loss": 8.5998,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.12882953652788687,
|
| 1186 |
+
"grad_norm": 8.265691757202148,
|
| 1187 |
+
"learning_rate": 8.599558442598998e-06,
|
| 1188 |
+
"loss": 9.7063,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.12961508248232523,
|
| 1193 |
+
"grad_norm": 8.031036376953125,
|
| 1194 |
+
"learning_rate": 8.141676086873572e-06,
|
| 1195 |
+
"loss": 8.2274,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.13040062843676356,
|
| 1200 |
+
"grad_norm": 7.343542098999023,
|
| 1201 |
+
"learning_rate": 7.695237378953223e-06,
|
| 1202 |
+
"loss": 8.336,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.1311861743912019,
|
| 1207 |
+
"grad_norm": 7.548643112182617,
|
| 1208 |
+
"learning_rate": 7.260364370723044e-06,
|
| 1209 |
+
"loss": 7.6068,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.13197172034564023,
|
| 1214 |
+
"grad_norm": 8.050704956054688,
|
| 1215 |
+
"learning_rate": 6.837175952121306e-06,
|
| 1216 |
+
"loss": 8.6397,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.13275726630007856,
|
| 1221 |
+
"grad_norm": 7.44391393661499,
|
| 1222 |
+
"learning_rate": 6.425787818636131e-06,
|
| 1223 |
+
"loss": 8.0332,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.1335428122545169,
|
| 1228 |
+
"grad_norm": 8.91024398803711,
|
| 1229 |
+
"learning_rate": 6.026312439675552e-06,
|
| 1230 |
+
"loss": 8.402,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.13432835820895522,
|
| 1235 |
+
"grad_norm": 8.633265495300293,
|
| 1236 |
+
"learning_rate": 5.6388590278194096e-06,
|
| 1237 |
+
"loss": 8.961,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.13511390416339356,
|
| 1242 |
+
"grad_norm": 8.588522911071777,
|
| 1243 |
+
"learning_rate": 5.263533508961827e-06,
|
| 1244 |
+
"loss": 8.6485,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.1358994501178319,
|
| 1249 |
+
"grad_norm": 7.742713928222656,
|
| 1250 |
+
"learning_rate": 4.900438493352055e-06,
|
| 1251 |
+
"loss": 8.5585,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.13668499607227022,
|
| 1256 |
+
"grad_norm": 11.482580184936523,
|
| 1257 |
+
"learning_rate": 4.549673247541875e-06,
|
| 1258 |
+
"loss": 8.1041,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.13747054202670855,
|
| 1263 |
+
"grad_norm": 8.185383796691895,
|
| 1264 |
+
"learning_rate": 4.2113336672471245e-06,
|
| 1265 |
+
"loss": 8.2961,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.13825608798114689,
|
| 1270 |
+
"grad_norm": 8.976303100585938,
|
| 1271 |
+
"learning_rate": 3.885512251130763e-06,
|
| 1272 |
+
"loss": 9.0425,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.13904163393558522,
|
| 1277 |
+
"grad_norm": 8.094759941101074,
|
| 1278 |
+
"learning_rate": 3.5722980755146517e-06,
|
| 1279 |
+
"loss": 8.116,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.13982717989002358,
|
| 1284 |
+
"grad_norm": 8.698500633239746,
|
| 1285 |
+
"learning_rate": 3.271776770026963e-06,
|
| 1286 |
+
"loss": 7.8347,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1406127258444619,
|
| 1291 |
+
"grad_norm": 8.874629974365234,
|
| 1292 |
+
"learning_rate": 2.9840304941919415e-06,
|
| 1293 |
+
"loss": 9.2932,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.14139827179890024,
|
| 1298 |
+
"grad_norm": 7.529841899871826,
|
| 1299 |
+
"learning_rate": 2.7091379149682685e-06,
|
| 1300 |
+
"loss": 8.2836,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.14218381775333858,
|
| 1305 |
+
"grad_norm": 7.4498138427734375,
|
| 1306 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1307 |
+
"loss": 8.0029,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.1429693637077769,
|
| 1312 |
+
"grad_norm": 8.121156692504883,
|
| 1313 |
+
"learning_rate": 2.1982109232821178e-06,
|
| 1314 |
+
"loss": 9.0914,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.14375490966221524,
|
| 1319 |
+
"grad_norm": 8.470314025878906,
|
| 1320 |
+
"learning_rate": 1.962316193157593e-06,
|
| 1321 |
+
"loss": 8.6966,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.14454045561665357,
|
| 1326 |
+
"grad_norm": 10.73297119140625,
|
| 1327 |
+
"learning_rate": 1.7395544861325718e-06,
|
| 1328 |
+
"loss": 8.6064,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.1453260015710919,
|
| 1333 |
+
"grad_norm": 9.106901168823242,
|
| 1334 |
+
"learning_rate": 1.5299867030334814e-06,
|
| 1335 |
+
"loss": 8.9369,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.14611154752553024,
|
| 1340 |
+
"grad_norm": 8.249195098876953,
|
| 1341 |
+
"learning_rate": 1.333670137599713e-06,
|
| 1342 |
+
"loss": 8.2996,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.14689709347996857,
|
| 1347 |
+
"grad_norm": 9.387349128723145,
|
| 1348 |
+
"learning_rate": 1.1506584608200367e-06,
|
| 1349 |
+
"loss": 8.281,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.1476826394344069,
|
| 1354 |
+
"grad_norm": 9.602078437805176,
|
| 1355 |
+
"learning_rate": 9.810017062595322e-07,
|
| 1356 |
+
"loss": 9.1248,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.14846818538884524,
|
| 1361 |
+
"grad_norm": 8.565011024475098,
|
| 1362 |
+
"learning_rate": 8.247462563808817e-07,
|
| 1363 |
+
"loss": 8.3959,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.14925373134328357,
|
| 1368 |
+
"grad_norm": 9.041011810302734,
|
| 1369 |
+
"learning_rate": 6.819348298638839e-07,
|
| 1370 |
+
"loss": 9.2478,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.15003927729772193,
|
| 1375 |
+
"grad_norm": 9.530031204223633,
|
| 1376 |
+
"learning_rate": 5.526064699265753e-07,
|
| 1377 |
+
"loss": 8.1651,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.15082482325216026,
|
| 1382 |
+
"grad_norm": 10.153264999389648,
|
| 1383 |
+
"learning_rate": 4.367965336512403e-07,
|
| 1384 |
+
"loss": 9.5332,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.1516103692065986,
|
| 1389 |
+
"grad_norm": 9.929384231567383,
|
| 1390 |
+
"learning_rate": 3.3453668231809286e-07,
|
| 1391 |
+
"loss": 9.1516,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.15239591516103693,
|
| 1396 |
+
"grad_norm": 10.931221961975098,
|
| 1397 |
+
"learning_rate": 2.458548727494292e-07,
|
| 1398 |
+
"loss": 10.1943,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.15318146111547526,
|
| 1403 |
+
"grad_norm": 11.9827299118042,
|
| 1404 |
+
"learning_rate": 1.7077534966650766e-07,
|
| 1405 |
+
"loss": 8.6382,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.1539670070699136,
|
| 1410 |
+
"grad_norm": 10.247384071350098,
|
| 1411 |
+
"learning_rate": 1.0931863906127327e-07,
|
| 1412 |
+
"loss": 8.8943,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.15475255302435192,
|
| 1417 |
+
"grad_norm": 13.635087966918945,
|
| 1418 |
+
"learning_rate": 6.150154258476315e-08,
|
| 1419 |
+
"loss": 10.0398,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.15553809897879026,
|
| 1424 |
+
"grad_norm": 13.633051872253418,
|
| 1425 |
+
"learning_rate": 2.7337132953697554e-08,
|
| 1426 |
+
"loss": 9.5399,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.1563236449332286,
|
| 1431 |
+
"grad_norm": 12.43005657196045,
|
| 1432 |
+
"learning_rate": 6.834750376549792e-09,
|
| 1433 |
+
"loss": 8.9625,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.15710919088766692,
|
| 1438 |
+
"grad_norm": 17.10336685180664,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 10.3047,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.15710919088766692,
|
| 1445 |
+
"eval_loss": 2.160458564758301,
|
| 1446 |
+
"eval_runtime": 41.7337,
|
| 1447 |
+
"eval_samples_per_second": 51.373,
|
| 1448 |
+
"eval_steps_per_second": 12.843,
|
| 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": 4.97506999861248e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|