Uploaded checkpoint-2000
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +361 -3
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2836579040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6de7026ac70336a1e4f551d99a58a8514e4bd50583f739c7893192c7a65816a1
|
| 3 |
size 2836579040
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5673376169
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:134bc8892a2731bc1e2f8484e566ed4e144adf4f48185fbbdea1cfb162ccab36
|
| 3 |
size 5673376169
|
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:ab013867373e136d27f7d01b3dabf2d49ddfdadab46a1f92a068804ac704272a
|
| 3 |
size 14244
|
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 sha256:57607646084b17d566404fe68cd6273a1c70907c03ac525780a2134b72276444
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1081,6 +1081,364 @@
|
|
| 1081 |
"eval_samples_per_second": 15.353,
|
| 1082 |
"eval_steps_per_second": 15.353,
|
| 1083 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1084 |
}
|
| 1085 |
],
|
| 1086 |
"logging_steps": 10,
|
|
@@ -1088,7 +1446,7 @@
|
|
| 1088 |
"num_input_tokens_seen": 0,
|
| 1089 |
"num_train_epochs": 1,
|
| 1090 |
"save_steps": 500,
|
| 1091 |
-
"total_flos":
|
| 1092 |
"train_batch_size": 1,
|
| 1093 |
"trial_name": null,
|
| 1094 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1081 |
"eval_samples_per_second": 15.353,
|
| 1082 |
"eval_steps_per_second": 15.353,
|
| 1083 |
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.08,
|
| 1087 |
+
"grad_norm": 56.25,
|
| 1088 |
+
"learning_rate": 3.5933333333333335e-07,
|
| 1089 |
+
"loss": 0.9445,
|
| 1090 |
+
"step": 1510
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.08,
|
| 1094 |
+
"grad_norm": 57.0,
|
| 1095 |
+
"learning_rate": 3.5200000000000003e-07,
|
| 1096 |
+
"loss": 0.9411,
|
| 1097 |
+
"step": 1520
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.08,
|
| 1101 |
+
"grad_norm": 55.25,
|
| 1102 |
+
"learning_rate": 3.446666666666667e-07,
|
| 1103 |
+
"loss": 0.9502,
|
| 1104 |
+
"step": 1530
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.08,
|
| 1108 |
+
"grad_norm": 55.5,
|
| 1109 |
+
"learning_rate": 3.3733333333333334e-07,
|
| 1110 |
+
"loss": 0.9696,
|
| 1111 |
+
"step": 1540
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.08,
|
| 1115 |
+
"grad_norm": 53.25,
|
| 1116 |
+
"learning_rate": 3.3e-07,
|
| 1117 |
+
"loss": 0.9587,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.08,
|
| 1122 |
+
"grad_norm": 55.5,
|
| 1123 |
+
"learning_rate": 3.226666666666667e-07,
|
| 1124 |
+
"loss": 1.0107,
|
| 1125 |
+
"step": 1560
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.08,
|
| 1129 |
+
"grad_norm": 56.75,
|
| 1130 |
+
"learning_rate": 3.153333333333334e-07,
|
| 1131 |
+
"loss": 0.9738,
|
| 1132 |
+
"step": 1570
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.08,
|
| 1136 |
+
"grad_norm": 54.0,
|
| 1137 |
+
"learning_rate": 3.0800000000000006e-07,
|
| 1138 |
+
"loss": 0.9859,
|
| 1139 |
+
"step": 1580
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.08,
|
| 1143 |
+
"grad_norm": 57.25,
|
| 1144 |
+
"learning_rate": 3.006666666666667e-07,
|
| 1145 |
+
"loss": 0.9419,
|
| 1146 |
+
"step": 1590
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.08,
|
| 1150 |
+
"grad_norm": 54.75,
|
| 1151 |
+
"learning_rate": 2.9333333333333337e-07,
|
| 1152 |
+
"loss": 0.9493,
|
| 1153 |
+
"step": 1600
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.08,
|
| 1157 |
+
"grad_norm": 54.75,
|
| 1158 |
+
"learning_rate": 2.8600000000000005e-07,
|
| 1159 |
+
"loss": 0.9896,
|
| 1160 |
+
"step": 1610
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.08,
|
| 1164 |
+
"grad_norm": 56.0,
|
| 1165 |
+
"learning_rate": 2.7866666666666673e-07,
|
| 1166 |
+
"loss": 0.9342,
|
| 1167 |
+
"step": 1620
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.08,
|
| 1171 |
+
"grad_norm": 56.5,
|
| 1172 |
+
"learning_rate": 2.7133333333333335e-07,
|
| 1173 |
+
"loss": 0.9641,
|
| 1174 |
+
"step": 1630
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.08,
|
| 1178 |
+
"grad_norm": 56.25,
|
| 1179 |
+
"learning_rate": 2.64e-07,
|
| 1180 |
+
"loss": 0.9459,
|
| 1181 |
+
"step": 1640
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.08,
|
| 1185 |
+
"grad_norm": 55.5,
|
| 1186 |
+
"learning_rate": 2.5666666666666666e-07,
|
| 1187 |
+
"loss": 0.9835,
|
| 1188 |
+
"step": 1650
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.08,
|
| 1192 |
+
"grad_norm": 54.0,
|
| 1193 |
+
"learning_rate": 2.4933333333333334e-07,
|
| 1194 |
+
"loss": 0.9505,
|
| 1195 |
+
"step": 1660
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.08,
|
| 1199 |
+
"grad_norm": 57.5,
|
| 1200 |
+
"learning_rate": 2.42e-07,
|
| 1201 |
+
"loss": 0.9574,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.08,
|
| 1206 |
+
"grad_norm": 52.5,
|
| 1207 |
+
"learning_rate": 2.346666666666667e-07,
|
| 1208 |
+
"loss": 0.9476,
|
| 1209 |
+
"step": 1680
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.08,
|
| 1213 |
+
"grad_norm": 56.0,
|
| 1214 |
+
"learning_rate": 2.2733333333333333e-07,
|
| 1215 |
+
"loss": 0.9757,
|
| 1216 |
+
"step": 1690
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.09,
|
| 1220 |
+
"grad_norm": 57.75,
|
| 1221 |
+
"learning_rate": 2.2e-07,
|
| 1222 |
+
"loss": 1.0152,
|
| 1223 |
+
"step": 1700
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.09,
|
| 1227 |
+
"grad_norm": 55.5,
|
| 1228 |
+
"learning_rate": 2.1266666666666667e-07,
|
| 1229 |
+
"loss": 0.9584,
|
| 1230 |
+
"step": 1710
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.09,
|
| 1234 |
+
"grad_norm": 56.25,
|
| 1235 |
+
"learning_rate": 2.0533333333333335e-07,
|
| 1236 |
+
"loss": 0.9793,
|
| 1237 |
+
"step": 1720
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.09,
|
| 1241 |
+
"grad_norm": 57.0,
|
| 1242 |
+
"learning_rate": 1.98e-07,
|
| 1243 |
+
"loss": 0.9512,
|
| 1244 |
+
"step": 1730
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.09,
|
| 1248 |
+
"grad_norm": 54.75,
|
| 1249 |
+
"learning_rate": 1.9066666666666668e-07,
|
| 1250 |
+
"loss": 0.9505,
|
| 1251 |
+
"step": 1740
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.09,
|
| 1255 |
+
"grad_norm": 56.5,
|
| 1256 |
+
"learning_rate": 1.8333333333333333e-07,
|
| 1257 |
+
"loss": 0.9632,
|
| 1258 |
+
"step": 1750
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.09,
|
| 1262 |
+
"grad_norm": 53.5,
|
| 1263 |
+
"learning_rate": 1.7600000000000001e-07,
|
| 1264 |
+
"loss": 0.9366,
|
| 1265 |
+
"step": 1760
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.09,
|
| 1269 |
+
"grad_norm": 57.5,
|
| 1270 |
+
"learning_rate": 1.6866666666666667e-07,
|
| 1271 |
+
"loss": 0.9409,
|
| 1272 |
+
"step": 1770
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.09,
|
| 1276 |
+
"grad_norm": 59.5,
|
| 1277 |
+
"learning_rate": 1.6133333333333335e-07,
|
| 1278 |
+
"loss": 1.0027,
|
| 1279 |
+
"step": 1780
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.09,
|
| 1283 |
+
"grad_norm": 56.25,
|
| 1284 |
+
"learning_rate": 1.5400000000000003e-07,
|
| 1285 |
+
"loss": 0.9519,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.09,
|
| 1290 |
+
"grad_norm": 57.25,
|
| 1291 |
+
"learning_rate": 1.4666666666666668e-07,
|
| 1292 |
+
"loss": 0.9499,
|
| 1293 |
+
"step": 1800
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.09,
|
| 1297 |
+
"grad_norm": 55.5,
|
| 1298 |
+
"learning_rate": 1.3933333333333336e-07,
|
| 1299 |
+
"loss": 0.9739,
|
| 1300 |
+
"step": 1810
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.09,
|
| 1304 |
+
"grad_norm": 56.0,
|
| 1305 |
+
"learning_rate": 1.32e-07,
|
| 1306 |
+
"loss": 0.9899,
|
| 1307 |
+
"step": 1820
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.09,
|
| 1311 |
+
"grad_norm": 61.25,
|
| 1312 |
+
"learning_rate": 1.2466666666666667e-07,
|
| 1313 |
+
"loss": 0.9731,
|
| 1314 |
+
"step": 1830
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.09,
|
| 1318 |
+
"grad_norm": 56.0,
|
| 1319 |
+
"learning_rate": 1.1733333333333335e-07,
|
| 1320 |
+
"loss": 0.9449,
|
| 1321 |
+
"step": 1840
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.09,
|
| 1325 |
+
"grad_norm": 57.25,
|
| 1326 |
+
"learning_rate": 1.1e-07,
|
| 1327 |
+
"loss": 1.0051,
|
| 1328 |
+
"step": 1850
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.09,
|
| 1332 |
+
"grad_norm": 54.75,
|
| 1333 |
+
"learning_rate": 1.0266666666666667e-07,
|
| 1334 |
+
"loss": 0.9907,
|
| 1335 |
+
"step": 1860
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.09,
|
| 1339 |
+
"grad_norm": 56.0,
|
| 1340 |
+
"learning_rate": 9.533333333333334e-08,
|
| 1341 |
+
"loss": 0.9608,
|
| 1342 |
+
"step": 1870
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.09,
|
| 1346 |
+
"grad_norm": 57.5,
|
| 1347 |
+
"learning_rate": 8.800000000000001e-08,
|
| 1348 |
+
"loss": 0.9558,
|
| 1349 |
+
"step": 1880
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.09,
|
| 1353 |
+
"grad_norm": 59.0,
|
| 1354 |
+
"learning_rate": 8.066666666666667e-08,
|
| 1355 |
+
"loss": 0.9928,
|
| 1356 |
+
"step": 1890
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.1,
|
| 1360 |
+
"grad_norm": 57.25,
|
| 1361 |
+
"learning_rate": 7.333333333333334e-08,
|
| 1362 |
+
"loss": 0.9629,
|
| 1363 |
+
"step": 1900
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.1,
|
| 1367 |
+
"grad_norm": 56.75,
|
| 1368 |
+
"learning_rate": 6.6e-08,
|
| 1369 |
+
"loss": 0.9358,
|
| 1370 |
+
"step": 1910
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.1,
|
| 1374 |
+
"grad_norm": 57.25,
|
| 1375 |
+
"learning_rate": 5.8666666666666676e-08,
|
| 1376 |
+
"loss": 0.9602,
|
| 1377 |
+
"step": 1920
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.1,
|
| 1381 |
+
"grad_norm": 59.25,
|
| 1382 |
+
"learning_rate": 5.1333333333333336e-08,
|
| 1383 |
+
"loss": 0.9639,
|
| 1384 |
+
"step": 1930
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.1,
|
| 1388 |
+
"grad_norm": 58.5,
|
| 1389 |
+
"learning_rate": 4.4000000000000004e-08,
|
| 1390 |
+
"loss": 0.9643,
|
| 1391 |
+
"step": 1940
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.1,
|
| 1395 |
+
"grad_norm": 59.25,
|
| 1396 |
+
"learning_rate": 3.666666666666667e-08,
|
| 1397 |
+
"loss": 0.9413,
|
| 1398 |
+
"step": 1950
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.1,
|
| 1402 |
+
"grad_norm": 55.25,
|
| 1403 |
+
"learning_rate": 2.9333333333333338e-08,
|
| 1404 |
+
"loss": 0.9927,
|
| 1405 |
+
"step": 1960
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.1,
|
| 1409 |
+
"grad_norm": 56.75,
|
| 1410 |
+
"learning_rate": 2.2000000000000002e-08,
|
| 1411 |
+
"loss": 0.987,
|
| 1412 |
+
"step": 1970
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.1,
|
| 1416 |
+
"grad_norm": 53.75,
|
| 1417 |
+
"learning_rate": 1.4666666666666669e-08,
|
| 1418 |
+
"loss": 0.9517,
|
| 1419 |
+
"step": 1980
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.1,
|
| 1423 |
+
"grad_norm": 56.25,
|
| 1424 |
+
"learning_rate": 7.3333333333333345e-09,
|
| 1425 |
+
"loss": 0.9575,
|
| 1426 |
+
"step": 1990
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.1,
|
| 1430 |
+
"grad_norm": 55.75,
|
| 1431 |
+
"learning_rate": 0.0,
|
| 1432 |
+
"loss": 0.9746,
|
| 1433 |
+
"step": 2000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.1,
|
| 1437 |
+
"eval_loss": 0.9655321836471558,
|
| 1438 |
+
"eval_runtime": 64.9317,
|
| 1439 |
+
"eval_samples_per_second": 15.401,
|
| 1440 |
+
"eval_steps_per_second": 15.401,
|
| 1441 |
+
"step": 2000
|
| 1442 |
}
|
| 1443 |
],
|
| 1444 |
"logging_steps": 10,
|
|
|
|
| 1446 |
"num_input_tokens_seen": 0,
|
| 1447 |
"num_train_epochs": 1,
|
| 1448 |
"save_steps": 500,
|
| 1449 |
+
"total_flos": 3.227844083712e+16,
|
| 1450 |
"train_batch_size": 1,
|
| 1451 |
"trial_name": null,
|
| 1452 |
"trial_params": null
|