Training in progress, step 445000
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 sha256:6ddd3c37bd4200e08826b0a91d5f24c4ff7218397da5c07f384461ccffb9cb9a
|
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 sha256:03b07a4229a48459c79e80fe855bce597db6900e72bddc707e70f6fbfdf9dfe9
|
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:f36ebe1c0a4a168a3c7f0b3e3add08a4eb2922192e4272ca5261870371aafca2
|
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 sha256:253da2fe3f872eb2bc3b8f0a902fed4630b5393d1b6eb6c17b44eefb61bc3cd7
|
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 sha256:8d999a91a6cc7ee3d02856a88c102af0111baa8c1942338c39f2ea2e1a438591
|
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:f88aa60029ff1bb0064fa8b9fff446d83665a7596e171fd5c753540b5ef66f9a
|
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 sha256:7330c5c7638e093c49e8abfe8223573d14775e88899da3795fd13f4a889cdc79
|
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 sha256:32389c0ec049ef4b8ced7f61f25d86b3dbbfb5bec67ce1197c94aeae299a5a2e
|
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": 7.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -5286,6 +5286,66 @@
|
|
5286 |
"learning_rate": 1.4943207748699148e-05,
|
5287 |
"loss": 0.3192,
|
5288 |
"step": 440000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5289 |
}
|
5290 |
],
|
5291 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.574463196057906,
|
5 |
+
"global_step": 445000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5286 |
"learning_rate": 1.4943207748699148e-05,
|
5287 |
"loss": 0.3192,
|
5288 |
"step": 440000
|
5289 |
+
},
|
5290 |
+
{
|
5291 |
+
"epoch": 7.5,
|
5292 |
+
"learning_rate": 1.4862516814602821e-05,
|
5293 |
+
"loss": 0.3191,
|
5294 |
+
"step": 440500
|
5295 |
+
},
|
5296 |
+
{
|
5297 |
+
"epoch": 7.51,
|
5298 |
+
"learning_rate": 1.478230641353945e-05,
|
5299 |
+
"loss": 0.3189,
|
5300 |
+
"step": 441000
|
5301 |
+
},
|
5302 |
+
{
|
5303 |
+
"epoch": 7.51,
|
5304 |
+
"learning_rate": 1.4702739684782337e-05,
|
5305 |
+
"loss": 0.319,
|
5306 |
+
"step": 441500
|
5307 |
+
},
|
5308 |
+
{
|
5309 |
+
"epoch": 7.52,
|
5310 |
+
"learning_rate": 1.4623817413622956e-05,
|
5311 |
+
"loss": 0.319,
|
5312 |
+
"step": 442000
|
5313 |
+
},
|
5314 |
+
{
|
5315 |
+
"epoch": 7.53,
|
5316 |
+
"learning_rate": 1.4545696288600928e-05,
|
5317 |
+
"loss": 0.3193,
|
5318 |
+
"step": 442500
|
5319 |
+
},
|
5320 |
+
{
|
5321 |
+
"epoch": 7.54,
|
5322 |
+
"learning_rate": 1.4468063970276709e-05,
|
5323 |
+
"loss": 0.3191,
|
5324 |
+
"step": 443000
|
5325 |
+
},
|
5326 |
+
{
|
5327 |
+
"epoch": 7.55,
|
5328 |
+
"learning_rate": 1.4391078425704797e-05,
|
5329 |
+
"loss": 0.319,
|
5330 |
+
"step": 443500
|
5331 |
+
},
|
5332 |
+
{
|
5333 |
+
"epoch": 7.56,
|
5334 |
+
"learning_rate": 1.4314740414701418e-05,
|
5335 |
+
"loss": 0.319,
|
5336 |
+
"step": 444000
|
5337 |
+
},
|
5338 |
+
{
|
5339 |
+
"epoch": 7.57,
|
5340 |
+
"learning_rate": 1.423905069069194e-05,
|
5341 |
+
"loss": 0.3191,
|
5342 |
+
"step": 444500
|
5343 |
+
},
|
5344 |
+
{
|
5345 |
+
"epoch": 7.57,
|
5346 |
+
"learning_rate": 1.4164010000703365e-05,
|
5347 |
+
"loss": 0.319,
|
5348 |
+
"step": 445000
|
5349 |
}
|
5350 |
],
|
5351 |
"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 sha256:03b07a4229a48459c79e80fe855bce597db6900e72bddc707e70f6fbfdf9dfe9
|
3 |
size 201355195
|