Training in progress, step 198, 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 47724600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78caa2ecb707469c3b9436373b3cfd3d25d6860d81dfdd1fcff1dd3975613d82
|
| 3 |
size 47724600
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 25331516
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1cd66b51dd9ce1e23fb67cd242e2eb29e6b5e6b2e592166f989f3c2e9e97255
|
| 3 |
size 25331516
|
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 sha256:63afe6b53664eea8898016edb2f2324259424202f671640bd9eb38d5de37a2a7
|
| 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 sha256:588b963689e2bc6a644ef6e066b36a07667462b36247fb966e7188944b9c91f2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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,
|
|
@@ -1081,6 +1081,342 @@
|
|
| 1081 |
"eval_samples_per_second": 6.856,
|
| 1082 |
"eval_steps_per_second": 3.428,
|
| 1083 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1084 |
}
|
| 1085 |
],
|
| 1086 |
"logging_steps": 1,
|
|
@@ -1095,12 +1431,12 @@
|
|
| 1095 |
"should_evaluate": false,
|
| 1096 |
"should_log": false,
|
| 1097 |
"should_save": true,
|
| 1098 |
-
"should_training_stop":
|
| 1099 |
},
|
| 1100 |
"attributes": {}
|
| 1101 |
}
|
| 1102 |
},
|
| 1103 |
-
"total_flos": 2.
|
| 1104 |
"train_batch_size": 2,
|
| 1105 |
"trial_name": null,
|
| 1106 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 198,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1081 |
"eval_samples_per_second": 6.856,
|
| 1082 |
"eval_steps_per_second": 3.428,
|
| 1083 |
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.7626262626262627,
|
| 1087 |
+
"grad_norm": 9.82388687133789,
|
| 1088 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 1089 |
+
"loss": 0.302,
|
| 1090 |
+
"step": 151
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.7676767676767676,
|
| 1094 |
+
"grad_norm": 12.946221351623535,
|
| 1095 |
+
"learning_rate": 2.8117631612207084e-05,
|
| 1096 |
+
"loss": 0.4361,
|
| 1097 |
+
"step": 152
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.7727272727272727,
|
| 1101 |
+
"grad_norm": 9.764445304870605,
|
| 1102 |
+
"learning_rate": 2.6966013605133088e-05,
|
| 1103 |
+
"loss": 0.3317,
|
| 1104 |
+
"step": 153
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.7777777777777778,
|
| 1108 |
+
"grad_norm": 14.5607271194458,
|
| 1109 |
+
"learning_rate": 2.5834789435204243e-05,
|
| 1110 |
+
"loss": 0.3403,
|
| 1111 |
+
"step": 154
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.7828282828282829,
|
| 1115 |
+
"grad_norm": 11.619050979614258,
|
| 1116 |
+
"learning_rate": 2.4724274982774865e-05,
|
| 1117 |
+
"loss": 0.4053,
|
| 1118 |
+
"step": 155
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.7878787878787878,
|
| 1122 |
+
"grad_norm": 14.43159008026123,
|
| 1123 |
+
"learning_rate": 2.3634780345266806e-05,
|
| 1124 |
+
"loss": 0.3843,
|
| 1125 |
+
"step": 156
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.7929292929292929,
|
| 1129 |
+
"grad_norm": 15.145977020263672,
|
| 1130 |
+
"learning_rate": 2.2566609750578673e-05,
|
| 1131 |
+
"loss": 0.4364,
|
| 1132 |
+
"step": 157
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.797979797979798,
|
| 1136 |
+
"grad_norm": 11.833556175231934,
|
| 1137 |
+
"learning_rate": 2.1520061472133902e-05,
|
| 1138 |
+
"loss": 0.3154,
|
| 1139 |
+
"step": 158
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.803030303030303,
|
| 1143 |
+
"grad_norm": 12.835911750793457,
|
| 1144 |
+
"learning_rate": 2.04954277455917e-05,
|
| 1145 |
+
"loss": 0.3429,
|
| 1146 |
+
"step": 159
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.8080808080808081,
|
| 1150 |
+
"grad_norm": 11.492507934570312,
|
| 1151 |
+
"learning_rate": 1.9492994687243714e-05,
|
| 1152 |
+
"loss": 0.3757,
|
| 1153 |
+
"step": 160
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.8131313131313131,
|
| 1157 |
+
"grad_norm": 13.120503425598145,
|
| 1158 |
+
"learning_rate": 1.851304221411967e-05,
|
| 1159 |
+
"loss": 0.4127,
|
| 1160 |
+
"step": 161
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.8181818181818182,
|
| 1164 |
+
"grad_norm": 20.865995407104492,
|
| 1165 |
+
"learning_rate": 1.7555843965823992e-05,
|
| 1166 |
+
"loss": 0.4,
|
| 1167 |
+
"step": 162
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.8232323232323232,
|
| 1171 |
+
"grad_norm": 11.817997932434082,
|
| 1172 |
+
"learning_rate": 1.6621667228125302e-05,
|
| 1173 |
+
"loss": 0.4647,
|
| 1174 |
+
"step": 163
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.8282828282828283,
|
| 1178 |
+
"grad_norm": 10.320054054260254,
|
| 1179 |
+
"learning_rate": 1.57107728583203e-05,
|
| 1180 |
+
"loss": 0.3413,
|
| 1181 |
+
"step": 164
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.8333333333333334,
|
| 1185 |
+
"grad_norm": 11.233556747436523,
|
| 1186 |
+
"learning_rate": 1.4823415212392377e-05,
|
| 1187 |
+
"loss": 0.2859,
|
| 1188 |
+
"step": 165
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.8383838383838383,
|
| 1192 |
+
"grad_norm": 10.825108528137207,
|
| 1193 |
+
"learning_rate": 1.3959842073986085e-05,
|
| 1194 |
+
"loss": 0.2771,
|
| 1195 |
+
"step": 166
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.8434343434343434,
|
| 1199 |
+
"grad_norm": 11.109395027160645,
|
| 1200 |
+
"learning_rate": 1.3120294585216353e-05,
|
| 1201 |
+
"loss": 0.3611,
|
| 1202 |
+
"step": 167
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.8484848484848485,
|
| 1206 |
+
"grad_norm": 10.571539878845215,
|
| 1207 |
+
"learning_rate": 1.230500717933285e-05,
|
| 1208 |
+
"loss": 0.3888,
|
| 1209 |
+
"step": 168
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.8535353535353535,
|
| 1213 |
+
"grad_norm": 11.521129608154297,
|
| 1214 |
+
"learning_rate": 1.1514207515257147e-05,
|
| 1215 |
+
"loss": 0.3247,
|
| 1216 |
+
"step": 169
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.8585858585858586,
|
| 1220 |
+
"grad_norm": 11.530449867248535,
|
| 1221 |
+
"learning_rate": 1.0748116414011888e-05,
|
| 1222 |
+
"loss": 0.2623,
|
| 1223 |
+
"step": 170
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.8636363636363636,
|
| 1227 |
+
"grad_norm": 10.529777526855469,
|
| 1228 |
+
"learning_rate": 1.0006947797059219e-05,
|
| 1229 |
+
"loss": 0.3313,
|
| 1230 |
+
"step": 171
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.8686868686868687,
|
| 1234 |
+
"grad_norm": 9.755709648132324,
|
| 1235 |
+
"learning_rate": 9.29090862656593e-06,
|
| 1236 |
+
"loss": 0.3945,
|
| 1237 |
+
"step": 172
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.8737373737373737,
|
| 1241 |
+
"grad_norm": 10.26276969909668,
|
| 1242 |
+
"learning_rate": 8.600198847611729e-06,
|
| 1243 |
+
"loss": 0.2629,
|
| 1244 |
+
"step": 173
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.8787878787878788,
|
| 1248 |
+
"grad_norm": 18.38811492919922,
|
| 1249 |
+
"learning_rate": 7.935011332357112e-06,
|
| 1250 |
+
"loss": 0.408,
|
| 1251 |
+
"step": 174
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.8838383838383839,
|
| 1255 |
+
"grad_norm": 11.992220878601074,
|
| 1256 |
+
"learning_rate": 7.295531826186264e-06,
|
| 1257 |
+
"loss": 0.4615,
|
| 1258 |
+
"step": 175
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.8888888888888888,
|
| 1262 |
+
"grad_norm": 14.000274658203125,
|
| 1263 |
+
"learning_rate": 6.681938895839746e-06,
|
| 1264 |
+
"loss": 0.3583,
|
| 1265 |
+
"step": 176
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.8939393939393939,
|
| 1269 |
+
"grad_norm": 11.123028755187988,
|
| 1270 |
+
"learning_rate": 6.094403879552213e-06,
|
| 1271 |
+
"loss": 0.2686,
|
| 1272 |
+
"step": 177
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.898989898989899,
|
| 1276 |
+
"grad_norm": 11.463796615600586,
|
| 1277 |
+
"learning_rate": 5.533090839208133e-06,
|
| 1278 |
+
"loss": 0.3694,
|
| 1279 |
+
"step": 178
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.9040404040404041,
|
| 1283 |
+
"grad_norm": 14.426941871643066,
|
| 1284 |
+
"learning_rate": 4.998156514529595e-06,
|
| 1285 |
+
"loss": 0.4453,
|
| 1286 |
+
"step": 179
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.9090909090909091,
|
| 1290 |
+
"grad_norm": 11.056812286376953,
|
| 1291 |
+
"learning_rate": 4.489750279308757e-06,
|
| 1292 |
+
"loss": 0.3627,
|
| 1293 |
+
"step": 180
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.9141414141414141,
|
| 1297 |
+
"grad_norm": 15.307928085327148,
|
| 1298 |
+
"learning_rate": 4.008014099696922e-06,
|
| 1299 |
+
"loss": 0.5187,
|
| 1300 |
+
"step": 181
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.9191919191919192,
|
| 1304 |
+
"grad_norm": 16.49620246887207,
|
| 1305 |
+
"learning_rate": 3.5530824945623542e-06,
|
| 1306 |
+
"loss": 0.4363,
|
| 1307 |
+
"step": 182
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.9242424242424242,
|
| 1311 |
+
"grad_norm": 14.4350004196167,
|
| 1312 |
+
"learning_rate": 3.1250824979274675e-06,
|
| 1313 |
+
"loss": 0.422,
|
| 1314 |
+
"step": 183
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.9292929292929293,
|
| 1318 |
+
"grad_norm": 8.324783325195312,
|
| 1319 |
+
"learning_rate": 2.7241336234962944e-06,
|
| 1320 |
+
"loss": 0.3985,
|
| 1321 |
+
"step": 184
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.9343434343434344,
|
| 1325 |
+
"grad_norm": 11.766496658325195,
|
| 1326 |
+
"learning_rate": 2.3503478312815298e-06,
|
| 1327 |
+
"loss": 0.3377,
|
| 1328 |
+
"step": 185
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.9393939393939394,
|
| 1332 |
+
"grad_norm": 15.193984031677246,
|
| 1333 |
+
"learning_rate": 2.003829496341325e-06,
|
| 1334 |
+
"loss": 0.3802,
|
| 1335 |
+
"step": 186
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.9444444444444444,
|
| 1339 |
+
"grad_norm": 20.59272003173828,
|
| 1340 |
+
"learning_rate": 1.684675379633649e-06,
|
| 1341 |
+
"loss": 0.4727,
|
| 1342 |
+
"step": 187
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.9494949494949495,
|
| 1346 |
+
"grad_norm": 10.777263641357422,
|
| 1347 |
+
"learning_rate": 1.3929746009971433e-06,
|
| 1348 |
+
"loss": 0.3044,
|
| 1349 |
+
"step": 188
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.9545454545454546,
|
| 1353 |
+
"grad_norm": 20.804996490478516,
|
| 1354 |
+
"learning_rate": 1.1288086142653864e-06,
|
| 1355 |
+
"loss": 0.3692,
|
| 1356 |
+
"step": 189
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.9595959595959596,
|
| 1360 |
+
"grad_norm": 19.473365783691406,
|
| 1361 |
+
"learning_rate": 8.922511845219971e-07,
|
| 1362 |
+
"loss": 0.321,
|
| 1363 |
+
"step": 190
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.9646464646464646,
|
| 1367 |
+
"grad_norm": 10.078756332397461,
|
| 1368 |
+
"learning_rate": 6.833683675025904e-07,
|
| 1369 |
+
"loss": 0.3689,
|
| 1370 |
+
"step": 191
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.9696969696969697,
|
| 1374 |
+
"grad_norm": 10.66713809967041,
|
| 1375 |
+
"learning_rate": 5.022184911495864e-07,
|
| 1376 |
+
"loss": 0.2831,
|
| 1377 |
+
"step": 192
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.9747474747474747,
|
| 1381 |
+
"grad_norm": 13.519158363342285,
|
| 1382 |
+
"learning_rate": 3.488521393248401e-07,
|
| 1383 |
+
"loss": 0.3693,
|
| 1384 |
+
"step": 193
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.9797979797979798,
|
| 1388 |
+
"grad_norm": 18.351518630981445,
|
| 1389 |
+
"learning_rate": 2.2331213768468363e-07,
|
| 1390 |
+
"loss": 0.5692,
|
| 1391 |
+
"step": 194
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.9848484848484849,
|
| 1395 |
+
"grad_norm": 20.144264221191406,
|
| 1396 |
+
"learning_rate": 1.2563354172142606e-07,
|
| 1397 |
+
"loss": 0.4896,
|
| 1398 |
+
"step": 195
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.98989898989899,
|
| 1402 |
+
"grad_norm": 21.47068977355957,
|
| 1403 |
+
"learning_rate": 5.584362697453882e-08,
|
| 1404 |
+
"loss": 0.4884,
|
| 1405 |
+
"step": 196
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.9949494949494949,
|
| 1409 |
+
"grad_norm": 14.894364356994629,
|
| 1410 |
+
"learning_rate": 1.3961881414292778e-08,
|
| 1411 |
+
"loss": 0.4101,
|
| 1412 |
+
"step": 197
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 1.0,
|
| 1416 |
+
"grad_norm": 20.294527053833008,
|
| 1417 |
+
"learning_rate": 0.0,
|
| 1418 |
+
"loss": 0.5037,
|
| 1419 |
+
"step": 198
|
| 1420 |
}
|
| 1421 |
],
|
| 1422 |
"logging_steps": 1,
|
|
|
|
| 1431 |
"should_evaluate": false,
|
| 1432 |
"should_log": false,
|
| 1433 |
"should_save": true,
|
| 1434 |
+
"should_training_stop": true
|
| 1435 |
},
|
| 1436 |
"attributes": {}
|
| 1437 |
}
|
| 1438 |
},
|
| 1439 |
+
"total_flos": 2.812060362394829e+16,
|
| 1440 |
"train_batch_size": 2,
|
| 1441 |
"trial_name": null,
|
| 1442 |
"trial_params": null
|