Training in progress, step 110000
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 sha256:4dcb80e1de6b4a3d63d20ec36d78c6daad3d2e7994b649e270265e451fe08e4d
|
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 sha256:9cfeb2e1472a90b1e89d0d9ac65aac1da4d7a25897da27fea33fee0fe1ed5fc7
|
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:e5b444daf6e77e13c858f62cf2cbb4730fa88f6975667f35b26086c220a5cc09
|
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:bd1c6e403c950e34887c233798630c48f5058b7dea46ec59735a35a4d39740fc
|
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 sha256:59d4860a57730a2e87c7fa46862a0b5e82b9b90ebf0cff2bda0d37884c223ea5
|
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 sha256:6015660024571a25f8ad41a62d61c67c24aa070fe05769074305728cc104f178
|
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 sha256:7306503ba7fec325dea91cfb0eca3f63091abbfbc264378e7ac28cf1597f0c62
|
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 sha256:49f5c3aae30b2453bb0c9854b34a4f3aa5f820992d9962f329ede74d1d0cca2d
|
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,
|
@@ -1266,6 +1266,66 @@
|
|
1266 |
"learning_rate": 0.00013532136245903893,
|
1267 |
"loss": 0.3492,
|
1268 |
"step": 105000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1269 |
}
|
1270 |
],
|
1271 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.872340425531915,
|
5 |
+
"global_step": 110000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1266 |
"learning_rate": 0.00013532136245903893,
|
1267 |
"loss": 0.3492,
|
1268 |
"step": 105000
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 1.8,
|
1272 |
+
"learning_rate": 0.00013518634696408,
|
1273 |
+
"loss": 0.3484,
|
1274 |
+
"step": 105500
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 1.8,
|
1278 |
+
"learning_rate": 0.00013505078680215615,
|
1279 |
+
"loss": 0.3485,
|
1280 |
+
"step": 106000
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 1.81,
|
1284 |
+
"learning_rate": 0.0001349149560595238,
|
1285 |
+
"loss": 0.3482,
|
1286 |
+
"step": 106500
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 1.82,
|
1290 |
+
"learning_rate": 0.00013477831166543215,
|
1291 |
+
"loss": 0.3486,
|
1292 |
+
"step": 107000
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 1.83,
|
1296 |
+
"learning_rate": 0.00013464112663151925,
|
1297 |
+
"loss": 0.3483,
|
1298 |
+
"step": 107500
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 1.84,
|
1302 |
+
"learning_rate": 0.000134503402311746,
|
1303 |
+
"loss": 0.3479,
|
1304 |
+
"step": 108000
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 1.85,
|
1308 |
+
"learning_rate": 0.00013436514006539586,
|
1309 |
+
"loss": 0.3479,
|
1310 |
+
"step": 108500
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 1.86,
|
1314 |
+
"learning_rate": 0.00013422634125706136,
|
1315 |
+
"loss": 0.3477,
|
1316 |
+
"step": 109000
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 1.86,
|
1320 |
+
"learning_rate": 0.00013408700725663073,
|
1321 |
+
"loss": 0.3478,
|
1322 |
+
"step": 109500
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 1.87,
|
1326 |
+
"learning_rate": 0.00013394713943927426,
|
1327 |
+
"loss": 0.3475,
|
1328 |
+
"step": 110000
|
1329 |
}
|
1330 |
],
|
1331 |
"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 sha256:9cfeb2e1472a90b1e89d0d9ac65aac1da4d7a25897da27fea33fee0fe1ed5fc7
|
3 |
size 201355195
|