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 224224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54633b045fa3875795f5e3b282e7622e8d6fc1887620d7137e21adf0bdedcff9
|
| 3 |
size 224224
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 458278
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:578416452e14be514a99d9286e95a5f5428c38a515851f529186ae1cfc1d81ef
|
| 3 |
size 458278
|
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 sha256:73ed1b5bb9723457092efbac7b1cf8e5382350824de5a4a887b2d3e65f0865fc
|
| 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 sha256:9abccd3ade815397c3a4e9cae178fd4a326a690915052661d8621974d592484a
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 10.
|
| 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": 329.202,
|
| 1090 |
"eval_steps_per_second": 82.706,
|
| 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": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 10.320320129394531,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.4166666666666667,
|
| 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": 329.202,
|
| 1090 |
"eval_steps_per_second": 82.706,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.3145833333333333,
|
| 1095 |
+
"grad_norm": 0.37281185388565063,
|
| 1096 |
+
"learning_rate": 2.583589473684211e-05,
|
| 1097 |
+
"loss": 20.6498,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.31666666666666665,
|
| 1102 |
+
"grad_norm": 0.48406609892845154,
|
| 1103 |
+
"learning_rate": 2.530863157894737e-05,
|
| 1104 |
+
"loss": 20.6228,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.31875,
|
| 1109 |
+
"grad_norm": 0.39599233865737915,
|
| 1110 |
+
"learning_rate": 2.4781368421052633e-05,
|
| 1111 |
+
"loss": 20.638,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.32083333333333336,
|
| 1116 |
+
"grad_norm": 0.3863723874092102,
|
| 1117 |
+
"learning_rate": 2.4254105263157896e-05,
|
| 1118 |
+
"loss": 20.6314,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.3229166666666667,
|
| 1123 |
+
"grad_norm": 0.45764878392219543,
|
| 1124 |
+
"learning_rate": 2.372684210526316e-05,
|
| 1125 |
+
"loss": 20.6385,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.325,
|
| 1130 |
+
"grad_norm": 0.2955838441848755,
|
| 1131 |
+
"learning_rate": 2.3199578947368422e-05,
|
| 1132 |
+
"loss": 20.6307,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.32708333333333334,
|
| 1137 |
+
"grad_norm": 0.29116860032081604,
|
| 1138 |
+
"learning_rate": 2.2672315789473688e-05,
|
| 1139 |
+
"loss": 20.6354,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.32916666666666666,
|
| 1144 |
+
"grad_norm": 0.5557569861412048,
|
| 1145 |
+
"learning_rate": 2.2145052631578948e-05,
|
| 1146 |
+
"loss": 20.6324,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.33125,
|
| 1151 |
+
"grad_norm": 0.4483456313610077,
|
| 1152 |
+
"learning_rate": 2.1617789473684214e-05,
|
| 1153 |
+
"loss": 20.6235,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.3333333333333333,
|
| 1158 |
+
"grad_norm": 0.36201009154319763,
|
| 1159 |
+
"learning_rate": 2.1090526315789473e-05,
|
| 1160 |
+
"loss": 20.6236,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.33541666666666664,
|
| 1165 |
+
"grad_norm": 0.5224501490592957,
|
| 1166 |
+
"learning_rate": 2.056326315789474e-05,
|
| 1167 |
+
"loss": 20.6368,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.3375,
|
| 1172 |
+
"grad_norm": 0.4168667495250702,
|
| 1173 |
+
"learning_rate": 2.0036000000000003e-05,
|
| 1174 |
+
"loss": 20.6212,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.33958333333333335,
|
| 1179 |
+
"grad_norm": 0.422823041677475,
|
| 1180 |
+
"learning_rate": 1.9508736842105266e-05,
|
| 1181 |
+
"loss": 20.6554,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.3416666666666667,
|
| 1186 |
+
"grad_norm": 0.4180959165096283,
|
| 1187 |
+
"learning_rate": 1.898147368421053e-05,
|
| 1188 |
+
"loss": 20.632,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.34375,
|
| 1193 |
+
"grad_norm": 0.527528703212738,
|
| 1194 |
+
"learning_rate": 1.8454210526315788e-05,
|
| 1195 |
+
"loss": 20.6571,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.3458333333333333,
|
| 1200 |
+
"grad_norm": 0.6775944828987122,
|
| 1201 |
+
"learning_rate": 1.7926947368421054e-05,
|
| 1202 |
+
"loss": 20.6503,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.34791666666666665,
|
| 1207 |
+
"grad_norm": 0.45938971638679504,
|
| 1208 |
+
"learning_rate": 1.7399684210526317e-05,
|
| 1209 |
+
"loss": 20.6307,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.35,
|
| 1214 |
+
"grad_norm": 0.581780731678009,
|
| 1215 |
+
"learning_rate": 1.687242105263158e-05,
|
| 1216 |
+
"loss": 20.5861,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.35208333333333336,
|
| 1221 |
+
"grad_norm": 0.46029457449913025,
|
| 1222 |
+
"learning_rate": 1.6345157894736843e-05,
|
| 1223 |
+
"loss": 20.6182,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.3541666666666667,
|
| 1228 |
+
"grad_norm": 0.4315298795700073,
|
| 1229 |
+
"learning_rate": 1.5817894736842106e-05,
|
| 1230 |
+
"loss": 20.617,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.35625,
|
| 1235 |
+
"grad_norm": 0.5391767621040344,
|
| 1236 |
+
"learning_rate": 1.529063157894737e-05,
|
| 1237 |
+
"loss": 20.6657,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.35833333333333334,
|
| 1242 |
+
"grad_norm": 0.7053831815719604,
|
| 1243 |
+
"learning_rate": 1.4763368421052632e-05,
|
| 1244 |
+
"loss": 20.6452,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.36041666666666666,
|
| 1249 |
+
"grad_norm": 0.3821829557418823,
|
| 1250 |
+
"learning_rate": 1.4236105263157895e-05,
|
| 1251 |
+
"loss": 20.6239,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.3625,
|
| 1256 |
+
"grad_norm": 0.41374513506889343,
|
| 1257 |
+
"learning_rate": 1.370884210526316e-05,
|
| 1258 |
+
"loss": 20.6571,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.3645833333333333,
|
| 1263 |
+
"grad_norm": 0.4170868694782257,
|
| 1264 |
+
"learning_rate": 1.318157894736842e-05,
|
| 1265 |
+
"loss": 20.6462,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.36666666666666664,
|
| 1270 |
+
"grad_norm": 0.338599294424057,
|
| 1271 |
+
"learning_rate": 1.2654315789473685e-05,
|
| 1272 |
+
"loss": 20.6363,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.36875,
|
| 1277 |
+
"grad_norm": 0.5105868577957153,
|
| 1278 |
+
"learning_rate": 1.2127052631578948e-05,
|
| 1279 |
+
"loss": 20.6538,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.37083333333333335,
|
| 1284 |
+
"grad_norm": 0.4912939965724945,
|
| 1285 |
+
"learning_rate": 1.1599789473684211e-05,
|
| 1286 |
+
"loss": 20.6367,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.3729166666666667,
|
| 1291 |
+
"grad_norm": 0.4326838552951813,
|
| 1292 |
+
"learning_rate": 1.1072526315789474e-05,
|
| 1293 |
+
"loss": 20.6502,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.375,
|
| 1298 |
+
"grad_norm": 0.4481593668460846,
|
| 1299 |
+
"learning_rate": 1.0545263157894737e-05,
|
| 1300 |
+
"loss": 20.6533,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.3770833333333333,
|
| 1305 |
+
"grad_norm": 0.5464130640029907,
|
| 1306 |
+
"learning_rate": 1.0018000000000001e-05,
|
| 1307 |
+
"loss": 20.6477,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.37916666666666665,
|
| 1312 |
+
"grad_norm": 0.42457976937294006,
|
| 1313 |
+
"learning_rate": 9.490736842105264e-06,
|
| 1314 |
+
"loss": 20.6598,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.38125,
|
| 1319 |
+
"grad_norm": 0.4240236282348633,
|
| 1320 |
+
"learning_rate": 8.963473684210527e-06,
|
| 1321 |
+
"loss": 20.6248,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.38333333333333336,
|
| 1326 |
+
"grad_norm": 0.5708866715431213,
|
| 1327 |
+
"learning_rate": 8.43621052631579e-06,
|
| 1328 |
+
"loss": 20.6368,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.3854166666666667,
|
| 1333 |
+
"grad_norm": 0.5419739484786987,
|
| 1334 |
+
"learning_rate": 7.908947368421053e-06,
|
| 1335 |
+
"loss": 20.6538,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.3875,
|
| 1340 |
+
"grad_norm": 0.5176281332969666,
|
| 1341 |
+
"learning_rate": 7.381684210526316e-06,
|
| 1342 |
+
"loss": 20.6526,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.38958333333333334,
|
| 1347 |
+
"grad_norm": 0.5326713919639587,
|
| 1348 |
+
"learning_rate": 6.85442105263158e-06,
|
| 1349 |
+
"loss": 20.6238,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.39166666666666666,
|
| 1354 |
+
"grad_norm": 0.7119190096855164,
|
| 1355 |
+
"learning_rate": 6.3271578947368425e-06,
|
| 1356 |
+
"loss": 20.6531,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.39375,
|
| 1361 |
+
"grad_norm": 0.5899550318717957,
|
| 1362 |
+
"learning_rate": 5.7998947368421054e-06,
|
| 1363 |
+
"loss": 20.6368,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.3958333333333333,
|
| 1368 |
+
"grad_norm": 0.5252934694290161,
|
| 1369 |
+
"learning_rate": 5.272631578947368e-06,
|
| 1370 |
+
"loss": 20.6664,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.39791666666666664,
|
| 1375 |
+
"grad_norm": 0.358653724193573,
|
| 1376 |
+
"learning_rate": 4.745368421052632e-06,
|
| 1377 |
+
"loss": 20.6579,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.4,
|
| 1382 |
+
"grad_norm": 0.43110373616218567,
|
| 1383 |
+
"learning_rate": 4.218105263157895e-06,
|
| 1384 |
+
"loss": 20.6374,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.40208333333333335,
|
| 1389 |
+
"grad_norm": 0.45655491948127747,
|
| 1390 |
+
"learning_rate": 3.690842105263158e-06,
|
| 1391 |
+
"loss": 20.6361,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.4041666666666667,
|
| 1396 |
+
"grad_norm": 0.30297571420669556,
|
| 1397 |
+
"learning_rate": 3.1635789473684213e-06,
|
| 1398 |
+
"loss": 20.6386,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.40625,
|
| 1403 |
+
"grad_norm": 0.3377545177936554,
|
| 1404 |
+
"learning_rate": 2.636315789473684e-06,
|
| 1405 |
+
"loss": 20.6289,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.4083333333333333,
|
| 1410 |
+
"grad_norm": 0.5056354999542236,
|
| 1411 |
+
"learning_rate": 2.1090526315789475e-06,
|
| 1412 |
+
"loss": 20.6388,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.41041666666666665,
|
| 1417 |
+
"grad_norm": 0.6402460932731628,
|
| 1418 |
+
"learning_rate": 1.5817894736842106e-06,
|
| 1419 |
+
"loss": 20.6102,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.4125,
|
| 1424 |
+
"grad_norm": 0.6596386432647705,
|
| 1425 |
+
"learning_rate": 1.0545263157894738e-06,
|
| 1426 |
+
"loss": 20.6331,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.41458333333333336,
|
| 1431 |
+
"grad_norm": 0.6789427399635315,
|
| 1432 |
+
"learning_rate": 5.272631578947369e-07,
|
| 1433 |
+
"loss": 20.6559,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.4166666666666667,
|
| 1438 |
+
"grad_norm": 0.6088905334472656,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 20.6439,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.4166666666666667,
|
| 1445 |
+
"eval_loss": 10.320320129394531,
|
| 1446 |
+
"eval_runtime": 0.6112,
|
| 1447 |
+
"eval_samples_per_second": 332.15,
|
| 1448 |
+
"eval_steps_per_second": 83.447,
|
| 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": 14821833572352.0,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|