Training in progress, step 200, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 78480072
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db4c502a33de28f2f4e5fb81654fe2891a2ec3dee351c28b48bcea7d3d93c07f
|
| 3 |
size 78480072
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 157104826
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60973ee914e44e0877bcbcc67a46f3aacffeccab287d87041b5c9af60d5bd52e
|
| 3 |
size 157104826
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd521acb05725e4af1abcedc4db1dff0cd02deb0eb665fd07b46de0c36ddf855
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f79cd37a71602ee3453d865ba27de10ecc8b80e4e141ea841dd118ec67931783
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee565522fc66381f4018eda676a684cdaf33134b7012615202a96fe9dc2dbe12
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58c98eae267ed133853583e845b35fd8852bbef2e18652180fea04483992c255
|
| 3 |
size 15024
|
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 sha256:22e2023c6402f9316009a8f28e4762eb4b8de513322ef266c713a2e6a744c1ce
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1113,6 +1113,372 @@
|
|
| 1113 |
"eval_samples_per_second": 71.812,
|
| 1114 |
"eval_steps_per_second": 18.671,
|
| 1115 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
@@ -1141,7 +1507,7 @@
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
-
"total_flos":
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.357637882232666,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 1.9659038550145906,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1113 |
"eval_samples_per_second": 71.812,
|
| 1114 |
"eval_steps_per_second": 18.671,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.484257410536016,
|
| 1119 |
+
"grad_norm": 1.773645281791687,
|
| 1120 |
+
"learning_rate": 0.00011768432908660658,
|
| 1121 |
+
"loss": 2.3309,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.4940869298110888,
|
| 1126 |
+
"grad_norm": 2.4841768741607666,
|
| 1127 |
+
"learning_rate": 0.0001167257084227782,
|
| 1128 |
+
"loss": 2.4843,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.5039164490861618,
|
| 1133 |
+
"grad_norm": 0.9996944665908813,
|
| 1134 |
+
"learning_rate": 0.00011576631979826418,
|
| 1135 |
+
"loss": 1.9544,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.5137459683612349,
|
| 1140 |
+
"grad_norm": 1.0130380392074585,
|
| 1141 |
+
"learning_rate": 0.00011480627275881042,
|
| 1142 |
+
"loss": 2.0417,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.523575487636308,
|
| 1147 |
+
"grad_norm": 0.939575731754303,
|
| 1148 |
+
"learning_rate": 0.00011384567692534251,
|
| 1149 |
+
"loss": 2.0705,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.5334050069113807,
|
| 1154 |
+
"grad_norm": 0.929763913154602,
|
| 1155 |
+
"learning_rate": 0.000112884641981449,
|
| 1156 |
+
"loss": 2.0803,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.5432345261864537,
|
| 1161 |
+
"grad_norm": 0.9794033765792847,
|
| 1162 |
+
"learning_rate": 0.00011192327766085715,
|
| 1163 |
+
"loss": 1.9835,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.5530640454615265,
|
| 1168 |
+
"grad_norm": 1.0879063606262207,
|
| 1169 |
+
"learning_rate": 0.00011096169373490361,
|
| 1170 |
+
"loss": 2.0013,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.5628935647365996,
|
| 1175 |
+
"grad_norm": 1.06622314453125,
|
| 1176 |
+
"learning_rate": 0.00011000000000000002,
|
| 1177 |
+
"loss": 2.0374,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.5727230840116726,
|
| 1182 |
+
"grad_norm": 1.0707110166549683,
|
| 1183 |
+
"learning_rate": 0.00010903830626509644,
|
| 1184 |
+
"loss": 2.0073,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.5825526032867456,
|
| 1189 |
+
"grad_norm": 1.1493885517120361,
|
| 1190 |
+
"learning_rate": 0.00010807672233914287,
|
| 1191 |
+
"loss": 2.0256,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.5923821225618184,
|
| 1196 |
+
"grad_norm": 1.2368179559707642,
|
| 1197 |
+
"learning_rate": 0.00010711535801855104,
|
| 1198 |
+
"loss": 2.0373,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.6022116418368915,
|
| 1203 |
+
"grad_norm": 1.444209337234497,
|
| 1204 |
+
"learning_rate": 0.00010615432307465751,
|
| 1205 |
+
"loss": 2.2538,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.6120411611119643,
|
| 1210 |
+
"grad_norm": 1.398610234260559,
|
| 1211 |
+
"learning_rate": 0.00010519372724118961,
|
| 1212 |
+
"loss": 1.7089,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.6218706803870373,
|
| 1217 |
+
"grad_norm": 1.2919524908065796,
|
| 1218 |
+
"learning_rate": 0.00010423368020173585,
|
| 1219 |
+
"loss": 2.4992,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.6317001996621103,
|
| 1224 |
+
"grad_norm": 1.1141935586929321,
|
| 1225 |
+
"learning_rate": 0.00010327429157722181,
|
| 1226 |
+
"loss": 1.9982,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.6415297189371834,
|
| 1231 |
+
"grad_norm": 0.9911397099494934,
|
| 1232 |
+
"learning_rate": 0.00010231567091339343,
|
| 1233 |
+
"loss": 2.0274,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.6513592382122562,
|
| 1238 |
+
"grad_norm": 0.9675605893135071,
|
| 1239 |
+
"learning_rate": 0.00010135792766830865,
|
| 1240 |
+
"loss": 1.9756,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.661188757487329,
|
| 1245 |
+
"grad_norm": 0.9353333711624146,
|
| 1246 |
+
"learning_rate": 0.00010040117119983918,
|
| 1247 |
+
"loss": 1.934,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.671018276762402,
|
| 1252 |
+
"grad_norm": 1.0085963010787964,
|
| 1253 |
+
"learning_rate": 9.944551075318384e-05,
|
| 1254 |
+
"loss": 2.0595,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.680847796037475,
|
| 1259 |
+
"grad_norm": 1.0311287641525269,
|
| 1260 |
+
"learning_rate": 9.849105544839445e-05,
|
| 1261 |
+
"loss": 1.9757,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.690677315312548,
|
| 1266 |
+
"grad_norm": 1.0677305459976196,
|
| 1267 |
+
"learning_rate": 9.753791426791632e-05,
|
| 1268 |
+
"loss": 1.9551,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.700506834587621,
|
| 1273 |
+
"grad_norm": 1.1577661037445068,
|
| 1274 |
+
"learning_rate": 9.65861960441443e-05,
|
| 1275 |
+
"loss": 2.0813,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.710336353862694,
|
| 1280 |
+
"grad_norm": 1.2702162265777588,
|
| 1281 |
+
"learning_rate": 9.563600944699588e-05,
|
| 1282 |
+
"loss": 2.0461,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.7201658731377667,
|
| 1287 |
+
"grad_norm": 1.3127394914627075,
|
| 1288 |
+
"learning_rate": 9.468746297150308e-05,
|
| 1289 |
+
"loss": 1.9524,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.7201658731377667,
|
| 1294 |
+
"eval_loss": 2.385427951812744,
|
| 1295 |
+
"eval_runtime": 0.6961,
|
| 1296 |
+
"eval_samples_per_second": 71.824,
|
| 1297 |
+
"eval_steps_per_second": 18.674,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.7299953924128397,
|
| 1302 |
+
"grad_norm": 1.6161891222000122,
|
| 1303 |
+
"learning_rate": 9.374066492542412e-05,
|
| 1304 |
+
"loss": 2.2694,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.7398249116879128,
|
| 1309 |
+
"grad_norm": 2.1535022258758545,
|
| 1310 |
+
"learning_rate": 9.279572341687653e-05,
|
| 1311 |
+
"loss": 2.2855,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.7496544309629858,
|
| 1316 |
+
"grad_norm": 1.000197410583496,
|
| 1317 |
+
"learning_rate": 9.185274634199304e-05,
|
| 1318 |
+
"loss": 1.9217,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.7594839502380588,
|
| 1323 |
+
"grad_norm": 1.2574663162231445,
|
| 1324 |
+
"learning_rate": 9.091184137260171e-05,
|
| 1325 |
+
"loss": 2.0003,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.7693134695131316,
|
| 1330 |
+
"grad_norm": 1.0235072374343872,
|
| 1331 |
+
"learning_rate": 8.997311594393172e-05,
|
| 1332 |
+
"loss": 2.0596,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.7791429887882044,
|
| 1337 |
+
"grad_norm": 0.9374403357505798,
|
| 1338 |
+
"learning_rate": 8.903667724234595e-05,
|
| 1339 |
+
"loss": 2.0426,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.7889725080632775,
|
| 1344 |
+
"grad_norm": 0.9672537446022034,
|
| 1345 |
+
"learning_rate": 8.810263219310225e-05,
|
| 1346 |
+
"loss": 1.9895,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.7988020273383505,
|
| 1351 |
+
"grad_norm": 1.1401046514511108,
|
| 1352 |
+
"learning_rate": 8.717108744814436e-05,
|
| 1353 |
+
"loss": 1.9909,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.8086315466134235,
|
| 1358 |
+
"grad_norm": 1.2541248798370361,
|
| 1359 |
+
"learning_rate": 8.624214937392412e-05,
|
| 1360 |
+
"loss": 1.988,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.8184610658884965,
|
| 1365 |
+
"grad_norm": 1.156072735786438,
|
| 1366 |
+
"learning_rate": 8.53159240392563e-05,
|
| 1367 |
+
"loss": 1.9679,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.8282905851635693,
|
| 1372 |
+
"grad_norm": 1.271194577217102,
|
| 1373 |
+
"learning_rate": 8.439251720320709e-05,
|
| 1374 |
+
"loss": 2.0339,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.8381201044386422,
|
| 1379 |
+
"grad_norm": 1.315255880355835,
|
| 1380 |
+
"learning_rate": 8.347203430301863e-05,
|
| 1381 |
+
"loss": 2.0626,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.8479496237137152,
|
| 1386 |
+
"grad_norm": 1.4638818502426147,
|
| 1387 |
+
"learning_rate": 8.255458044206957e-05,
|
| 1388 |
+
"loss": 2.1827,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.8577791429887882,
|
| 1393 |
+
"grad_norm": 1.450156569480896,
|
| 1394 |
+
"learning_rate": 8.164026037787415e-05,
|
| 1395 |
+
"loss": 1.6739,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.8676086622638612,
|
| 1400 |
+
"grad_norm": 1.2157936096191406,
|
| 1401 |
+
"learning_rate": 8.072917851012078e-05,
|
| 1402 |
+
"loss": 2.45,
|
| 1403 |
+
"step": 190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.8774381815389343,
|
| 1407 |
+
"grad_norm": 1.1207431554794312,
|
| 1408 |
+
"learning_rate": 7.982143886875122e-05,
|
| 1409 |
+
"loss": 2.0453,
|
| 1410 |
+
"step": 191
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.887267700814007,
|
| 1414 |
+
"grad_norm": 1.12586510181427,
|
| 1415 |
+
"learning_rate": 7.891714510208232e-05,
|
| 1416 |
+
"loss": 1.9761,
|
| 1417 |
+
"step": 192
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.8970972200890799,
|
| 1421 |
+
"grad_norm": 1.021728754043579,
|
| 1422 |
+
"learning_rate": 7.801640046497103e-05,
|
| 1423 |
+
"loss": 2.0234,
|
| 1424 |
+
"step": 193
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.906926739364153,
|
| 1428 |
+
"grad_norm": 1.0452762842178345,
|
| 1429 |
+
"learning_rate": 7.711930780702445e-05,
|
| 1430 |
+
"loss": 1.9967,
|
| 1431 |
+
"step": 194
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.916756258639226,
|
| 1435 |
+
"grad_norm": 0.9748082756996155,
|
| 1436 |
+
"learning_rate": 7.622596956085635e-05,
|
| 1437 |
+
"loss": 1.9948,
|
| 1438 |
+
"step": 195
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.926585777914299,
|
| 1442 |
+
"grad_norm": 1.0299899578094482,
|
| 1443 |
+
"learning_rate": 7.533648773039084e-05,
|
| 1444 |
+
"loss": 2.0412,
|
| 1445 |
+
"step": 196
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.936415297189372,
|
| 1449 |
+
"grad_norm": 1.0700615644454956,
|
| 1450 |
+
"learning_rate": 7.445096387921553e-05,
|
| 1451 |
+
"loss": 1.9714,
|
| 1452 |
+
"step": 197
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.9462448164644448,
|
| 1456 |
+
"grad_norm": 1.1362632513046265,
|
| 1457 |
+
"learning_rate": 7.356949911898456e-05,
|
| 1458 |
+
"loss": 1.94,
|
| 1459 |
+
"step": 198
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.9560743357395176,
|
| 1463 |
+
"grad_norm": 1.336560845375061,
|
| 1464 |
+
"learning_rate": 7.269219409787342e-05,
|
| 1465 |
+
"loss": 1.9919,
|
| 1466 |
+
"step": 199
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.9659038550145906,
|
| 1470 |
+
"grad_norm": 1.305739402770996,
|
| 1471 |
+
"learning_rate": 7.181914898908661e-05,
|
| 1472 |
+
"loss": 2.0634,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.9659038550145906,
|
| 1477 |
+
"eval_loss": 2.357637882232666,
|
| 1478 |
+
"eval_runtime": 0.6963,
|
| 1479 |
+
"eval_samples_per_second": 71.809,
|
| 1480 |
+
"eval_steps_per_second": 18.67,
|
| 1481 |
+
"step": 200
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
|
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
+
"total_flos": 1.2592324420829184e+18,
|
| 1511 |
"train_batch_size": 1,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|