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 313820248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:568c159742a82bc37251cce6fcce5f3ed43525533a9fca34f3c3d6327c777aea
|
| 3 |
size 313820248
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 159641092
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6661e2531d6c5d8ce9e2c76da80a8643e07761ee47eeb1485c2e3152baacc3f6
|
| 3 |
size 159641092
|
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:ce0ca8776dabaca3ce8f6ec774c4429f12612cf640ff619ab028c3a4bdf2e851
|
| 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:b60d6f1383abda4776549360effee800fe6cfe2c0604503e9e3fbaa79347f790
|
| 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": 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": 25.776,
|
| 1090 |
"eval_steps_per_second": 6.444,
|
| 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": 0.9832578301429749,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.015401794309037002,
|
| 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": 25.776,
|
| 1090 |
"eval_steps_per_second": 6.444,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.011628354703322937,
|
| 1095 |
+
"grad_norm": 0.49048227071762085,
|
| 1096 |
+
"learning_rate": 1.0872630680850196e-05,
|
| 1097 |
+
"loss": 0.5683,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.011705363674868121,
|
| 1102 |
+
"grad_norm": 0.6810614466667175,
|
| 1103 |
+
"learning_rate": 1.0456712550462898e-05,
|
| 1104 |
+
"loss": 0.7572,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.011782372646413308,
|
| 1109 |
+
"grad_norm": 0.7518895268440247,
|
| 1110 |
+
"learning_rate": 1.0047504309801104e-05,
|
| 1111 |
+
"loss": 0.7942,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.011859381617958492,
|
| 1116 |
+
"grad_norm": 0.8100650310516357,
|
| 1117 |
+
"learning_rate": 9.645117832311886e-06,
|
| 1118 |
+
"loss": 0.8327,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.011936390589503677,
|
| 1123 |
+
"grad_norm": 0.8092503547668457,
|
| 1124 |
+
"learning_rate": 9.249663126440394e-06,
|
| 1125 |
+
"loss": 0.829,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.012013399561048863,
|
| 1130 |
+
"grad_norm": 0.6432150602340698,
|
| 1131 |
+
"learning_rate": 8.861248305554624e-06,
|
| 1132 |
+
"loss": 0.6496,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.012090408532594047,
|
| 1137 |
+
"grad_norm": 0.5999425649642944,
|
| 1138 |
+
"learning_rate": 8.47997955838829e-06,
|
| 1139 |
+
"loss": 0.5903,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.012167417504139232,
|
| 1144 |
+
"grad_norm": 0.7111806869506836,
|
| 1145 |
+
"learning_rate": 8.10596112000994e-06,
|
| 1146 |
+
"loss": 0.7107,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.012244426475684416,
|
| 1151 |
+
"grad_norm": 0.7115854620933533,
|
| 1152 |
+
"learning_rate": 7.739295243326067e-06,
|
| 1153 |
+
"loss": 0.7083,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.012321435447229603,
|
| 1158 |
+
"grad_norm": 0.6803847551345825,
|
| 1159 |
+
"learning_rate": 7.380082171126228e-06,
|
| 1160 |
+
"loss": 0.7334,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.012398444418774787,
|
| 1165 |
+
"grad_norm": 0.7553372979164124,
|
| 1166 |
+
"learning_rate": 7.028420108677635e-06,
|
| 1167 |
+
"loss": 0.7847,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.012475453390319972,
|
| 1172 |
+
"grad_norm": 0.7494491934776306,
|
| 1173 |
+
"learning_rate": 6.684405196876842e-06,
|
| 1174 |
+
"loss": 0.8008,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.012552462361865158,
|
| 1179 |
+
"grad_norm": 0.8308342695236206,
|
| 1180 |
+
"learning_rate": 6.3481314859657675e-06,
|
| 1181 |
+
"loss": 0.8929,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.012629471333410342,
|
| 1186 |
+
"grad_norm": 0.7959633469581604,
|
| 1187 |
+
"learning_rate": 6.019690909819298e-06,
|
| 1188 |
+
"loss": 0.9435,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.012706480304955527,
|
| 1193 |
+
"grad_norm": 0.7931632995605469,
|
| 1194 |
+
"learning_rate": 5.6991732608115e-06,
|
| 1195 |
+
"loss": 0.8936,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.012783489276500712,
|
| 1200 |
+
"grad_norm": 0.8373035192489624,
|
| 1201 |
+
"learning_rate": 5.386666165267256e-06,
|
| 1202 |
+
"loss": 0.8984,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.012860498248045898,
|
| 1207 |
+
"grad_norm": 0.8174297213554382,
|
| 1208 |
+
"learning_rate": 5.08225505950613e-06,
|
| 1209 |
+
"loss": 0.9191,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.012937507219591082,
|
| 1214 |
+
"grad_norm": 0.8664717078208923,
|
| 1215 |
+
"learning_rate": 4.786023166484913e-06,
|
| 1216 |
+
"loss": 0.9423,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.013014516191136267,
|
| 1221 |
+
"grad_norm": 0.8544601798057556,
|
| 1222 |
+
"learning_rate": 4.498051473045291e-06,
|
| 1223 |
+
"loss": 0.8387,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.013091525162681453,
|
| 1228 |
+
"grad_norm": 0.8214935660362244,
|
| 1229 |
+
"learning_rate": 4.218418707772886e-06,
|
| 1230 |
+
"loss": 0.8581,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.013168534134226638,
|
| 1235 |
+
"grad_norm": 0.8594068288803101,
|
| 1236 |
+
"learning_rate": 3.947201319473587e-06,
|
| 1237 |
+
"loss": 0.8652,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.013245543105771822,
|
| 1242 |
+
"grad_norm": 0.883743405342102,
|
| 1243 |
+
"learning_rate": 3.684473456273278e-06,
|
| 1244 |
+
"loss": 0.9762,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.013322552077317007,
|
| 1249 |
+
"grad_norm": 0.8632309436798096,
|
| 1250 |
+
"learning_rate": 3.4303069453464383e-06,
|
| 1251 |
+
"loss": 0.9785,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.013399561048862193,
|
| 1256 |
+
"grad_norm": 0.9207712411880493,
|
| 1257 |
+
"learning_rate": 3.184771273279312e-06,
|
| 1258 |
+
"loss": 0.9446,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.013476570020407377,
|
| 1263 |
+
"grad_norm": 1.1362985372543335,
|
| 1264 |
+
"learning_rate": 2.947933567072987e-06,
|
| 1265 |
+
"loss": 1.0367,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.013553578991952562,
|
| 1270 |
+
"grad_norm": 1.0557373762130737,
|
| 1271 |
+
"learning_rate": 2.719858575791534e-06,
|
| 1272 |
+
"loss": 1.0773,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.013630587963497748,
|
| 1277 |
+
"grad_norm": 1.030173420906067,
|
| 1278 |
+
"learning_rate": 2.500608652860256e-06,
|
| 1279 |
+
"loss": 1.0026,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.013707596935042933,
|
| 1284 |
+
"grad_norm": 1.1021617650985718,
|
| 1285 |
+
"learning_rate": 2.2902437390188737e-06,
|
| 1286 |
+
"loss": 1.0793,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.013784605906588117,
|
| 1291 |
+
"grad_norm": 1.0124552249908447,
|
| 1292 |
+
"learning_rate": 2.0888213459343587e-06,
|
| 1293 |
+
"loss": 1.1299,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.013861614878133302,
|
| 1298 |
+
"grad_norm": 1.2554916143417358,
|
| 1299 |
+
"learning_rate": 1.8963965404777875e-06,
|
| 1300 |
+
"loss": 1.1183,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.013938623849678488,
|
| 1305 |
+
"grad_norm": 1.148569107055664,
|
| 1306 |
+
"learning_rate": 1.7130219296696263e-06,
|
| 1307 |
+
"loss": 1.229,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.014015632821223672,
|
| 1312 |
+
"grad_norm": 1.1936874389648438,
|
| 1313 |
+
"learning_rate": 1.5387476462974824e-06,
|
| 1314 |
+
"loss": 1.2108,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.014092641792768857,
|
| 1319 |
+
"grad_norm": 1.2075494527816772,
|
| 1320 |
+
"learning_rate": 1.3736213352103147e-06,
|
| 1321 |
+
"loss": 1.2433,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.014169650764314043,
|
| 1326 |
+
"grad_norm": 1.2774829864501953,
|
| 1327 |
+
"learning_rate": 1.2176881402928002e-06,
|
| 1328 |
+
"loss": 1.2738,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.014246659735859228,
|
| 1333 |
+
"grad_norm": 1.2447525262832642,
|
| 1334 |
+
"learning_rate": 1.0709906921234367e-06,
|
| 1335 |
+
"loss": 1.1435,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.014323668707404412,
|
| 1340 |
+
"grad_norm": 1.3485177755355835,
|
| 1341 |
+
"learning_rate": 9.33569096319799e-07,
|
| 1342 |
+
"loss": 1.1858,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.014400677678949597,
|
| 1347 |
+
"grad_norm": 1.4245103597640991,
|
| 1348 |
+
"learning_rate": 8.054609225740255e-07,
|
| 1349 |
+
"loss": 1.1984,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.014477686650494783,
|
| 1354 |
+
"grad_norm": 1.3392527103424072,
|
| 1355 |
+
"learning_rate": 6.867011943816724e-07,
|
| 1356 |
+
"loss": 1.1286,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.014554695622039968,
|
| 1361 |
+
"grad_norm": 1.5184451341629028,
|
| 1362 |
+
"learning_rate": 5.77322379466617e-07,
|
| 1363 |
+
"loss": 1.1872,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.014631704593585152,
|
| 1368 |
+
"grad_norm": 1.5353091955184937,
|
| 1369 |
+
"learning_rate": 4.773543809047186e-07,
|
| 1370 |
+
"loss": 1.2407,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.014708713565130338,
|
| 1375 |
+
"grad_norm": 1.5289061069488525,
|
| 1376 |
+
"learning_rate": 3.868245289486027e-07,
|
| 1377 |
+
"loss": 1.149,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.014785722536675523,
|
| 1382 |
+
"grad_norm": 1.5167860984802246,
|
| 1383 |
+
"learning_rate": 3.0575757355586817e-07,
|
| 1384 |
+
"loss": 1.0424,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.014862731508220707,
|
| 1389 |
+
"grad_norm": 1.6470500230789185,
|
| 1390 |
+
"learning_rate": 2.3417567762266497e-07,
|
| 1391 |
+
"loss": 1.1479,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.014939740479765892,
|
| 1396 |
+
"grad_norm": 1.915789246559143,
|
| 1397 |
+
"learning_rate": 1.7209841092460043e-07,
|
| 1398 |
+
"loss": 1.1813,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.015016749451311078,
|
| 1403 |
+
"grad_norm": 1.8250898122787476,
|
| 1404 |
+
"learning_rate": 1.1954274476655534e-07,
|
| 1405 |
+
"loss": 1.2852,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.015093758422856263,
|
| 1410 |
+
"grad_norm": 1.7232822179794312,
|
| 1411 |
+
"learning_rate": 7.652304734289127e-08,
|
| 1412 |
+
"loss": 1.012,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.015170767394401447,
|
| 1417 |
+
"grad_norm": 1.8250606060028076,
|
| 1418 |
+
"learning_rate": 4.30510798093342e-08,
|
| 1419 |
+
"loss": 1.1473,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.015247776365946633,
|
| 1424 |
+
"grad_norm": 2.0770554542541504,
|
| 1425 |
+
"learning_rate": 1.9135993067588284e-08,
|
| 1426 |
+
"loss": 1.09,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.015324785337491818,
|
| 1431 |
+
"grad_norm": 2.2757625579833984,
|
| 1432 |
+
"learning_rate": 4.784325263584854e-09,
|
| 1433 |
+
"loss": 1.1364,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.015401794309037002,
|
| 1438 |
+
"grad_norm": 2.7049641609191895,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.8939,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.015401794309037002,
|
| 1445 |
+
"eval_loss": 0.9832578301429749,
|
| 1446 |
+
"eval_runtime": 848.8014,
|
| 1447 |
+
"eval_samples_per_second": 25.767,
|
| 1448 |
+
"eval_steps_per_second": 6.442,
|
| 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": 8.972467927882138e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|