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 912336848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34e475139366fe8c4ce9d497f537c9ad99c79a8d135801aa020668afda91566b
|
| 3 |
size 912336848
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1824995682
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9f4e6d014d8c1fdacbb6bdcfa7d32fbfc9b23e0afd4d77e241a8d70bea38c5
|
| 3 |
size 1824995682
|
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:f505ab1f8a0a2f1cda1c6724b68f7cb71fd34793193d1b8e05301022820e751f
|
| 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": 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": 8.539,
|
| 1090 |
"eval_steps_per_second": 4.27,
|
| 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": 0.29387402534484863,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.03343503155431103,
|
| 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": 8.539,
|
| 1090 |
"eval_steps_per_second": 4.27,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.02524344882350483,
|
| 1095 |
+
"grad_norm": 13.698927879333496,
|
| 1096 |
+
"learning_rate": 1.7197048550474643e-05,
|
| 1097 |
+
"loss": 2.0011,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.025410623981276383,
|
| 1102 |
+
"grad_norm": 4.57670259475708,
|
| 1103 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 1104 |
+
"loss": 0.7285,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.025577799139047938,
|
| 1109 |
+
"grad_norm": 5.332927227020264,
|
| 1110 |
+
"learning_rate": 1.5900081996875083e-05,
|
| 1111 |
+
"loss": 1.6553,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.025744974296819493,
|
| 1116 |
+
"grad_norm": 4.747281074523926,
|
| 1117 |
+
"learning_rate": 1.526708147705013e-05,
|
| 1118 |
+
"loss": 1.5828,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.025912149454591048,
|
| 1123 |
+
"grad_norm": 6.941982746124268,
|
| 1124 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 1125 |
+
"loss": 1.6333,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.026079324612362603,
|
| 1130 |
+
"grad_norm": 4.2286906242370605,
|
| 1131 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 1132 |
+
"loss": 1.3459,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.026246499770134157,
|
| 1137 |
+
"grad_norm": 5.367886543273926,
|
| 1138 |
+
"learning_rate": 1.3432314919041478e-05,
|
| 1139 |
+
"loss": 2.187,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.026413674927905712,
|
| 1144 |
+
"grad_norm": 4.209599494934082,
|
| 1145 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 1146 |
+
"loss": 1.4172,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.026580850085677267,
|
| 1151 |
+
"grad_norm": 4.512683868408203,
|
| 1152 |
+
"learning_rate": 1.22645209888614e-05,
|
| 1153 |
+
"loss": 1.4754,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.026748025243448822,
|
| 1158 |
+
"grad_norm": 4.081887245178223,
|
| 1159 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 1160 |
+
"loss": 1.3108,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.02691520040122038,
|
| 1165 |
+
"grad_norm": 5.3542704582214355,
|
| 1166 |
+
"learning_rate": 1.1142701927151456e-05,
|
| 1167 |
+
"loss": 1.4906,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.027082375558991935,
|
| 1172 |
+
"grad_norm": 4.081936359405518,
|
| 1173 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 1174 |
+
"loss": 1.2706,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.02724955071676349,
|
| 1179 |
+
"grad_norm": 4.231374263763428,
|
| 1180 |
+
"learning_rate": 1.006822449763537e-05,
|
| 1181 |
+
"loss": 1.2147,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.027416725874535045,
|
| 1186 |
+
"grad_norm": 4.8198065757751465,
|
| 1187 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1188 |
+
"loss": 1.2229,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.0275839010323066,
|
| 1193 |
+
"grad_norm": 2.8951492309570312,
|
| 1194 |
+
"learning_rate": 9.042397785550405e-06,
|
| 1195 |
+
"loss": 1.0801,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.027751076190078154,
|
| 1200 |
+
"grad_norm": 3.751887083053589,
|
| 1201 |
+
"learning_rate": 8.548121372247918e-06,
|
| 1202 |
+
"loss": 1.1734,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.02791825134784971,
|
| 1207 |
+
"grad_norm": 3.6009128093719482,
|
| 1208 |
+
"learning_rate": 8.066471602728803e-06,
|
| 1209 |
+
"loss": 1.0859,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.028085426505621264,
|
| 1214 |
+
"grad_norm": 4.206813335418701,
|
| 1215 |
+
"learning_rate": 7.597595192178702e-06,
|
| 1216 |
+
"loss": 1.3385,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.02825260166339282,
|
| 1221 |
+
"grad_norm": 3.1863796710968018,
|
| 1222 |
+
"learning_rate": 7.1416349648943894e-06,
|
| 1223 |
+
"loss": 1.0789,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.028419776821164373,
|
| 1228 |
+
"grad_norm": 3.8083925247192383,
|
| 1229 |
+
"learning_rate": 6.698729810778065e-06,
|
| 1230 |
+
"loss": 1.3231,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.02858695197893593,
|
| 1235 |
+
"grad_norm": 3.731236696243286,
|
| 1236 |
+
"learning_rate": 6.269014643030213e-06,
|
| 1237 |
+
"loss": 1.2615,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.028754127136707486,
|
| 1242 |
+
"grad_norm": 3.2406563758850098,
|
| 1243 |
+
"learning_rate": 5.852620357053651e-06,
|
| 1244 |
+
"loss": 1.0247,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.02892130229447904,
|
| 1249 |
+
"grad_norm": 3.137932062149048,
|
| 1250 |
+
"learning_rate": 5.449673790581611e-06,
|
| 1251 |
+
"loss": 1.0584,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.029088477452250596,
|
| 1256 |
+
"grad_norm": 3.4075889587402344,
|
| 1257 |
+
"learning_rate": 5.060297685041659e-06,
|
| 1258 |
+
"loss": 0.9526,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.02925565261002215,
|
| 1263 |
+
"grad_norm": 2.9246928691864014,
|
| 1264 |
+
"learning_rate": 4.684610648167503e-06,
|
| 1265 |
+
"loss": 1.0782,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.029422827767793706,
|
| 1270 |
+
"grad_norm": 2.98100209236145,
|
| 1271 |
+
"learning_rate": 4.322727117869951e-06,
|
| 1272 |
+
"loss": 0.8377,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.02959000292556526,
|
| 1277 |
+
"grad_norm": 2.983445405960083,
|
| 1278 |
+
"learning_rate": 3.974757327377981e-06,
|
| 1279 |
+
"loss": 0.9029,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.029757178083336815,
|
| 1284 |
+
"grad_norm": 4.628471374511719,
|
| 1285 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 1286 |
+
"loss": 1.1078,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.02992435324110837,
|
| 1291 |
+
"grad_norm": 3.004387617111206,
|
| 1292 |
+
"learning_rate": 3.3209786751399187e-06,
|
| 1293 |
+
"loss": 0.8434,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.030091528398879925,
|
| 1298 |
+
"grad_norm": 3.0182106494903564,
|
| 1299 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 1300 |
+
"loss": 0.8544,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.030258703556651483,
|
| 1305 |
+
"grad_norm": 2.594118356704712,
|
| 1306 |
+
"learning_rate": 2.724071220034158e-06,
|
| 1307 |
+
"loss": 0.8118,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.030425878714423038,
|
| 1312 |
+
"grad_norm": 2.563934803009033,
|
| 1313 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1314 |
+
"loss": 0.8901,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.030593053872194593,
|
| 1319 |
+
"grad_norm": 2.9740052223205566,
|
| 1320 |
+
"learning_rate": 2.1847622018482283e-06,
|
| 1321 |
+
"loss": 0.7041,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.030760229029966148,
|
| 1326 |
+
"grad_norm": 3.805539608001709,
|
| 1327 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 1328 |
+
"loss": 1.3973,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.030927404187737702,
|
| 1333 |
+
"grad_norm": 3.97375750541687,
|
| 1334 |
+
"learning_rate": 1.70370868554659e-06,
|
| 1335 |
+
"loss": 1.302,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.031094579345509257,
|
| 1340 |
+
"grad_norm": 3.071467876434326,
|
| 1341 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 1342 |
+
"loss": 1.1345,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.031261754503280816,
|
| 1347 |
+
"grad_norm": 3.0634610652923584,
|
| 1348 |
+
"learning_rate": 1.2814967607382432e-06,
|
| 1349 |
+
"loss": 0.7903,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.03142892966105237,
|
| 1354 |
+
"grad_norm": 4.494502544403076,
|
| 1355 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 1356 |
+
"loss": 1.2488,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.031596104818823925,
|
| 1361 |
+
"grad_norm": 4.34606409072876,
|
| 1362 |
+
"learning_rate": 9.186408276168013e-07,
|
| 1363 |
+
"loss": 1.0173,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.031763279976595477,
|
| 1368 |
+
"grad_norm": 2.888704299926758,
|
| 1369 |
+
"learning_rate": 7.596123493895991e-07,
|
| 1370 |
+
"loss": 0.8213,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.031930455134367035,
|
| 1375 |
+
"grad_norm": 4.194661617279053,
|
| 1376 |
+
"learning_rate": 6.15582970243117e-07,
|
| 1377 |
+
"loss": 1.1698,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.032097630292138586,
|
| 1382 |
+
"grad_norm": 5.82328987121582,
|
| 1383 |
+
"learning_rate": 4.865965629214819e-07,
|
| 1384 |
+
"loss": 1.7499,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.032264805449910144,
|
| 1389 |
+
"grad_norm": 3.347778558731079,
|
| 1390 |
+
"learning_rate": 3.7269241793390085e-07,
|
| 1391 |
+
"loss": 1.3349,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.032431980607681696,
|
| 1396 |
+
"grad_norm": 4.213897705078125,
|
| 1397 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 1398 |
+
"loss": 1.4678,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.032599155765453254,
|
| 1403 |
+
"grad_norm": 4.0061235427856445,
|
| 1404 |
+
"learning_rate": 1.9026509541272275e-07,
|
| 1405 |
+
"loss": 1.2671,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.032766330923224805,
|
| 1410 |
+
"grad_norm": 4.156453609466553,
|
| 1411 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 1412 |
+
"loss": 1.3958,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.032933506080996364,
|
| 1417 |
+
"grad_norm": 4.175441741943359,
|
| 1418 |
+
"learning_rate": 6.852326227130834e-08,
|
| 1419 |
+
"loss": 1.3736,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.03310068123876792,
|
| 1424 |
+
"grad_norm": 4.913483142852783,
|
| 1425 |
+
"learning_rate": 3.04586490452119e-08,
|
| 1426 |
+
"loss": 1.8471,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.03326785639653947,
|
| 1431 |
+
"grad_norm": 5.498208999633789,
|
| 1432 |
+
"learning_rate": 7.615242180436522e-09,
|
| 1433 |
+
"loss": 1.8498,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.03343503155431103,
|
| 1438 |
+
"grad_norm": 4.281605243682861,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.6879,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.03343503155431103,
|
| 1445 |
+
"eval_loss": 0.29387402534484863,
|
| 1446 |
+
"eval_runtime": 1180.8398,
|
| 1447 |
+
"eval_samples_per_second": 8.532,
|
| 1448 |
+
"eval_steps_per_second": 4.266,
|
| 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": 4.6534246809993216e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|