Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4523108832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59e412252cba4dc01069ba6be8044c1812ba3a77166ce062d20ed46bd7da1196
|
| 3 |
size 4523108832
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2912179275
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:449b10dad01f930d7096bf20b319165b871e44924ab0c80a56ea019eb2b9855c
|
| 3 |
size 2912179275
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdc37bbd2e979f041dfbbb004a5c74bab6cdda159cb18116df728588515a9ef6
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a036b9529dfa34fa02854662d61c3e2cd7af540260222cbaee309d1e565d1f4
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1058,6 +1058,356 @@
|
|
| 1058 |
"learning_rate": 0.00017002,
|
| 1059 |
"loss": 1.1760727882385253,
|
| 1060 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1061 |
}
|
| 1062 |
],
|
| 1063 |
"logging_steps": 10,
|
|
@@ -1077,7 +1427,7 @@
|
|
| 1077 |
"attributes": {}
|
| 1078 |
}
|
| 1079 |
},
|
| 1080 |
-
"total_flos": 1.
|
| 1081 |
"train_batch_size": 1,
|
| 1082 |
"trial_name": null,
|
| 1083 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0064,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1058 |
"learning_rate": 0.00017002,
|
| 1059 |
"loss": 1.1760727882385253,
|
| 1060 |
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.0198,
|
| 1064 |
+
"grad_norm": 0.7265837788581848,
|
| 1065 |
+
"learning_rate": 0.00016982,
|
| 1066 |
+
"loss": 1.1267470359802245,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.0208,
|
| 1071 |
+
"grad_norm": 0.8042080998420715,
|
| 1072 |
+
"learning_rate": 0.00016962,
|
| 1073 |
+
"loss": 1.0916626930236817,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.0218,
|
| 1078 |
+
"grad_norm": 0.7643582224845886,
|
| 1079 |
+
"learning_rate": 0.00016942000000000001,
|
| 1080 |
+
"loss": 1.0545287132263184,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.0228,
|
| 1085 |
+
"grad_norm": 0.7249123454093933,
|
| 1086 |
+
"learning_rate": 0.00016922,
|
| 1087 |
+
"loss": 1.1005349159240723,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.0238,
|
| 1092 |
+
"grad_norm": 0.7539435625076294,
|
| 1093 |
+
"learning_rate": 0.00016902,
|
| 1094 |
+
"loss": 1.0422410011291503,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.0248,
|
| 1099 |
+
"grad_norm": 0.7162719964981079,
|
| 1100 |
+
"learning_rate": 0.00016882,
|
| 1101 |
+
"loss": 1.039008617401123,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.0258,
|
| 1106 |
+
"grad_norm": 0.7562013268470764,
|
| 1107 |
+
"learning_rate": 0.00016862,
|
| 1108 |
+
"loss": 1.0739432334899903,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.0268,
|
| 1113 |
+
"grad_norm": 0.7008998394012451,
|
| 1114 |
+
"learning_rate": 0.00016842,
|
| 1115 |
+
"loss": 1.0126309394836426,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.0278,
|
| 1120 |
+
"grad_norm": 0.7990198731422424,
|
| 1121 |
+
"learning_rate": 0.00016822,
|
| 1122 |
+
"loss": 0.9999658584594726,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.0288,
|
| 1127 |
+
"grad_norm": 0.7978523969650269,
|
| 1128 |
+
"learning_rate": 0.00016802,
|
| 1129 |
+
"loss": 1.0024938583374023,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.0298,
|
| 1134 |
+
"grad_norm": 0.7431021928787231,
|
| 1135 |
+
"learning_rate": 0.00016782,
|
| 1136 |
+
"loss": 1.009383487701416,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.0308,
|
| 1141 |
+
"grad_norm": 0.8124121427536011,
|
| 1142 |
+
"learning_rate": 0.00016762,
|
| 1143 |
+
"loss": 0.9954951286315918,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 3.0006,
|
| 1148 |
+
"grad_norm": 0.7478945255279541,
|
| 1149 |
+
"learning_rate": 0.00016742,
|
| 1150 |
+
"loss": 0.9498451232910157,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 3.0016,
|
| 1155 |
+
"grad_norm": 0.7504536509513855,
|
| 1156 |
+
"learning_rate": 0.00016722,
|
| 1157 |
+
"loss": 0.7260428428649902,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 3.0026,
|
| 1162 |
+
"grad_norm": 0.6449979543685913,
|
| 1163 |
+
"learning_rate": 0.00016702,
|
| 1164 |
+
"loss": 0.6750858783721924,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 3.0036,
|
| 1169 |
+
"grad_norm": 0.8800742030143738,
|
| 1170 |
+
"learning_rate": 0.00016682,
|
| 1171 |
+
"loss": 0.6494207859039307,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 3.0046,
|
| 1176 |
+
"grad_norm": 0.674615204334259,
|
| 1177 |
+
"learning_rate": 0.00016662,
|
| 1178 |
+
"loss": 0.6307613372802734,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 3.0056,
|
| 1183 |
+
"grad_norm": 0.780610978603363,
|
| 1184 |
+
"learning_rate": 0.00016642,
|
| 1185 |
+
"loss": 0.5745514392852783,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 3.0066,
|
| 1190 |
+
"grad_norm": 0.8345136642456055,
|
| 1191 |
+
"learning_rate": 0.00016622,
|
| 1192 |
+
"loss": 0.6355406284332276,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 3.0076,
|
| 1197 |
+
"grad_norm": 0.7923954725265503,
|
| 1198 |
+
"learning_rate": 0.00016601999999999999,
|
| 1199 |
+
"loss": 0.7923160076141358,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 3.0086,
|
| 1204 |
+
"grad_norm": 0.725975513458252,
|
| 1205 |
+
"learning_rate": 0.00016582,
|
| 1206 |
+
"loss": 0.756317138671875,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 3.0096,
|
| 1211 |
+
"grad_norm": 0.8168895840644836,
|
| 1212 |
+
"learning_rate": 0.00016562,
|
| 1213 |
+
"loss": 0.758098840713501,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 3.0106,
|
| 1218 |
+
"grad_norm": 0.7553869485855103,
|
| 1219 |
+
"learning_rate": 0.00016542,
|
| 1220 |
+
"loss": 0.7652549743652344,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 3.0116,
|
| 1225 |
+
"grad_norm": 0.8063785433769226,
|
| 1226 |
+
"learning_rate": 0.00016522,
|
| 1227 |
+
"loss": 0.7233606815338135,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 3.0126,
|
| 1232 |
+
"grad_norm": 0.7430322170257568,
|
| 1233 |
+
"learning_rate": 0.00016502,
|
| 1234 |
+
"loss": 0.7092338085174561,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 3.0136,
|
| 1239 |
+
"grad_norm": 0.7664160132408142,
|
| 1240 |
+
"learning_rate": 0.00016482,
|
| 1241 |
+
"loss": 0.7311967372894287,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 3.0146,
|
| 1246 |
+
"grad_norm": 0.7792779803276062,
|
| 1247 |
+
"learning_rate": 0.00016462,
|
| 1248 |
+
"loss": 0.7741461277008057,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 3.0156,
|
| 1253 |
+
"grad_norm": 0.7967932224273682,
|
| 1254 |
+
"learning_rate": 0.00016442000000000003,
|
| 1255 |
+
"loss": 0.7999020576477051,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 3.0166,
|
| 1260 |
+
"grad_norm": 0.7274350523948669,
|
| 1261 |
+
"learning_rate": 0.00016422000000000002,
|
| 1262 |
+
"loss": 0.7347360610961914,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.0176,
|
| 1267 |
+
"grad_norm": 0.8932685256004333,
|
| 1268 |
+
"learning_rate": 0.00016402000000000002,
|
| 1269 |
+
"loss": 0.776170301437378,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 3.0186,
|
| 1274 |
+
"grad_norm": 0.7732952833175659,
|
| 1275 |
+
"learning_rate": 0.00016382000000000001,
|
| 1276 |
+
"loss": 0.729710578918457,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 3.0196,
|
| 1281 |
+
"grad_norm": 0.8386185765266418,
|
| 1282 |
+
"learning_rate": 0.00016362,
|
| 1283 |
+
"loss": 0.6981480121612549,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 3.0206,
|
| 1288 |
+
"grad_norm": 0.8548919558525085,
|
| 1289 |
+
"learning_rate": 0.00016342,
|
| 1290 |
+
"loss": 0.6844400405883789,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 3.0216,
|
| 1295 |
+
"grad_norm": 0.7728302478790283,
|
| 1296 |
+
"learning_rate": 0.00016322000000000003,
|
| 1297 |
+
"loss": 0.6626255989074707,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.0226,
|
| 1302 |
+
"grad_norm": 0.815079391002655,
|
| 1303 |
+
"learning_rate": 0.00016302000000000002,
|
| 1304 |
+
"loss": 0.6900956153869628,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.0236,
|
| 1309 |
+
"grad_norm": 0.7471504807472229,
|
| 1310 |
+
"learning_rate": 0.00016282000000000002,
|
| 1311 |
+
"loss": 0.6368459224700928,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 3.0246,
|
| 1316 |
+
"grad_norm": 0.7270839214324951,
|
| 1317 |
+
"learning_rate": 0.00016262,
|
| 1318 |
+
"loss": 0.6348861217498779,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 3.0256,
|
| 1323 |
+
"grad_norm": 0.7989698648452759,
|
| 1324 |
+
"learning_rate": 0.00016242,
|
| 1325 |
+
"loss": 0.6348659038543701,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 3.0266,
|
| 1330 |
+
"grad_norm": 0.7626523375511169,
|
| 1331 |
+
"learning_rate": 0.00016222000000000003,
|
| 1332 |
+
"loss": 0.5972939968109131,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 3.0276,
|
| 1337 |
+
"grad_norm": 0.7608401775360107,
|
| 1338 |
+
"learning_rate": 0.00016202000000000002,
|
| 1339 |
+
"loss": 0.608570671081543,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.0286,
|
| 1344 |
+
"grad_norm": 0.8012869358062744,
|
| 1345 |
+
"learning_rate": 0.00016182000000000002,
|
| 1346 |
+
"loss": 0.5898276329040527,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.0296,
|
| 1351 |
+
"grad_norm": 0.7275280356407166,
|
| 1352 |
+
"learning_rate": 0.00016162000000000001,
|
| 1353 |
+
"loss": 0.6227708339691163,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 3.0306,
|
| 1358 |
+
"grad_norm": 1.054669737815857,
|
| 1359 |
+
"learning_rate": 0.00016142,
|
| 1360 |
+
"loss": 0.551525354385376,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 4.0004,
|
| 1365 |
+
"grad_norm": 0.6590172052383423,
|
| 1366 |
+
"learning_rate": 0.00016122,
|
| 1367 |
+
"loss": 0.6316772937774658,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 4.0014,
|
| 1372 |
+
"grad_norm": 0.7991273999214172,
|
| 1373 |
+
"learning_rate": 0.00016102000000000003,
|
| 1374 |
+
"loss": 0.46561732292175295,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 4.0024,
|
| 1379 |
+
"grad_norm": 0.6764177680015564,
|
| 1380 |
+
"learning_rate": 0.00016082000000000002,
|
| 1381 |
+
"loss": 0.4100037574768066,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 4.0034,
|
| 1386 |
+
"grad_norm": 0.7882692813873291,
|
| 1387 |
+
"learning_rate": 0.00016062000000000002,
|
| 1388 |
+
"loss": 0.38791024684906006,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 4.0044,
|
| 1393 |
+
"grad_norm": 0.6683878898620605,
|
| 1394 |
+
"learning_rate": 0.00016042,
|
| 1395 |
+
"loss": 0.39162867069244384,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 4.0054,
|
| 1400 |
+
"grad_norm": 0.6484203934669495,
|
| 1401 |
+
"learning_rate": 0.00016022,
|
| 1402 |
+
"loss": 0.34521486759185793,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 4.0064,
|
| 1407 |
+
"grad_norm": 0.6811336874961853,
|
| 1408 |
+
"learning_rate": 0.00016002,
|
| 1409 |
+
"loss": 0.35950288772583006,
|
| 1410 |
+
"step": 2000
|
| 1411 |
}
|
| 1412 |
],
|
| 1413 |
"logging_steps": 10,
|
|
|
|
| 1427 |
"attributes": {}
|
| 1428 |
}
|
| 1429 |
},
|
| 1430 |
+
"total_flos": 1.6931438178729984e+17,
|
| 1431 |
"train_batch_size": 1,
|
| 1432 |
"trial_name": null,
|
| 1433 |
"trial_params": null
|