Training in progress, step 105000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +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/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08cf004a4167c9c7ae98c0231796d5b6a6bc11daf59c4891672b277a9fd3bf86
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2a92a2775a46aae98e480e957880a6d45fafbcded21ecfd79f87949dd62e541
|
3 |
size 201355195
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f84fb568b8e69e561cc9cf6aa6190bb9d4f6b5d257ce3edb1419c48e56f1321e
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bdb5f6c4f4e400291361664219d55340fe3bffcd033ac78310d09a92dc46450
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e2f90b03495fbf9d29e752d4b2148bd36b7456142ea58c54e92ff9b258d8f86
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85230c331f18f7ad054aa1a1d01219c994a4ccc484a9883c6b0d9b462f1d2e60
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da2b5ae7b682150cce1149dffb67fc49550406e268bcb94590fe321a3945861a
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c8c556903f1149af3f9e946ff6989ad0dd63928353dcb7c818c8a8eba116279
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1206,6 +1206,66 @@
|
|
1206 |
"learning_rate": 0.00013664101180730875,
|
1207 |
"loss": 0.3498,
|
1208 |
"step": 100000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1209 |
}
|
1210 |
],
|
1211 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7872340425531914,
|
5 |
+
"global_step": 105000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1206 |
"learning_rate": 0.00013664101180730875,
|
1207 |
"loss": 0.3498,
|
1208 |
"step": 100000
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 1.71,
|
1212 |
+
"learning_rate": 0.00013651151426193926,
|
1213 |
+
"loss": 0.3494,
|
1214 |
+
"step": 100500
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 1.72,
|
1218 |
+
"learning_rate": 0.00013638145897073862,
|
1219 |
+
"loss": 0.3497,
|
1220 |
+
"step": 101000
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.73,
|
1224 |
+
"learning_rate": 0.00013625084721730006,
|
1225 |
+
"loss": 0.3493,
|
1226 |
+
"step": 101500
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 1.74,
|
1230 |
+
"learning_rate": 0.0001361199431777653,
|
1231 |
+
"loss": 0.3498,
|
1232 |
+
"step": 102000
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 1.74,
|
1236 |
+
"learning_rate": 0.00013598822347904763,
|
1237 |
+
"loss": 0.3495,
|
1238 |
+
"step": 102500
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 1.75,
|
1242 |
+
"learning_rate": 0.00013585595119916755,
|
1243 |
+
"loss": 0.3497,
|
1244 |
+
"step": 103000
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 1.76,
|
1248 |
+
"learning_rate": 0.00013572312764359914,
|
1249 |
+
"loss": 0.3493,
|
1250 |
+
"step": 103500
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 1.77,
|
1254 |
+
"learning_rate": 0.00013558975412325717,
|
1255 |
+
"loss": 0.3489,
|
1256 |
+
"step": 104000
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 1.78,
|
1260 |
+
"learning_rate": 0.00013545583195448453,
|
1261 |
+
"loss": 0.3486,
|
1262 |
+
"step": 104500
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 1.79,
|
1266 |
+
"learning_rate": 0.00013532136245903893,
|
1267 |
+
"loss": 0.3492,
|
1268 |
+
"step": 105000
|
1269 |
}
|
1270 |
],
|
1271 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2a92a2775a46aae98e480e957880a6d45fafbcded21ecfd79f87949dd62e541
|
3 |
size 201355195
|