Training in progress, step 375000
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 sha256:01baad12886859fe661dc2c57b9551bee36b3953bfb73c88674787afb1b0d4f1
|
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:bd981b2367b8f646d8a64ee2a06cb78ea5c57392438a6ecb841b7b90f8bc9262
|
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 sha256:901a27103a0b4211a4cb7a615613c314ba9ba27cf41267b98b7ba2249414cd9b
|
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 sha256:91f2501e96098cce18ed377f2b39bc56addb66460445a4b4b497a44f3ffc8dec
|
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:dcb9d53d5ff6d1d8aebbf1aee526cc63f3a9dde3f1806b1d8b9b050a109501bb
|
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 sha256:33faa00288becf57e2f9d3147b6546682afc43e2c183d9d5c3bb0b18c48d7d88
|
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:aecfd8f3c31fe2329f8e851fcd0e456175517d9817546d182dadca4d30b38d2a
|
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:c25dbfef0114645bbf748b2cdd5378d772f339989f50b561bc114ec7915e61ce
|
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": 6.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -4446,6 +4446,66 @@
|
|
4446 |
"learning_rate": 3.212789106152626e-05,
|
4447 |
"loss": 0.3215,
|
4448 |
"step": 370000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4449 |
}
|
4450 |
],
|
4451 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.382975464038604,
|
5 |
+
"global_step": 375000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
4446 |
"learning_rate": 3.212789106152626e-05,
|
4447 |
"loss": 0.3215,
|
4448 |
"step": 370000
|
4449 |
+
},
|
4450 |
+
{
|
4451 |
+
"epoch": 6.31,
|
4452 |
+
"learning_rate": 3.1967682851177825e-05,
|
4453 |
+
"loss": 0.3212,
|
4454 |
+
"step": 370500
|
4455 |
+
},
|
4456 |
+
{
|
4457 |
+
"epoch": 6.31,
|
4458 |
+
"learning_rate": 3.180794870040819e-05,
|
4459 |
+
"loss": 0.3216,
|
4460 |
+
"step": 371000
|
4461 |
+
},
|
4462 |
+
{
|
4463 |
+
"epoch": 6.32,
|
4464 |
+
"learning_rate": 3.1649008227028015e-05,
|
4465 |
+
"loss": 0.3214,
|
4466 |
+
"step": 371500
|
4467 |
+
},
|
4468 |
+
{
|
4469 |
+
"epoch": 6.33,
|
4470 |
+
"learning_rate": 3.149022596427511e-05,
|
4471 |
+
"loss": 0.3211,
|
4472 |
+
"step": 372000
|
4473 |
+
},
|
4474 |
+
{
|
4475 |
+
"epoch": 6.34,
|
4476 |
+
"learning_rate": 3.133223860153585e-05,
|
4477 |
+
"loss": 0.3214,
|
4478 |
+
"step": 372500
|
4479 |
+
},
|
4480 |
+
{
|
4481 |
+
"epoch": 6.35,
|
4482 |
+
"learning_rate": 3.117441448272091e-05,
|
4483 |
+
"loss": 0.3214,
|
4484 |
+
"step": 373000
|
4485 |
+
},
|
4486 |
+
{
|
4487 |
+
"epoch": 6.36,
|
4488 |
+
"learning_rate": 3.1017072252723306e-05,
|
4489 |
+
"loss": 0.3214,
|
4490 |
+
"step": 373500
|
4491 |
+
},
|
4492 |
+
{
|
4493 |
+
"epoch": 6.37,
|
4494 |
+
"learning_rate": 3.086021346444738e-05,
|
4495 |
+
"loss": 0.3212,
|
4496 |
+
"step": 374000
|
4497 |
+
},
|
4498 |
+
{
|
4499 |
+
"epoch": 6.37,
|
4500 |
+
"learning_rate": 3.070415192857639e-05,
|
4501 |
+
"loss": 0.3212,
|
4502 |
+
"step": 374500
|
4503 |
+
},
|
4504 |
+
{
|
4505 |
+
"epoch": 6.38,
|
4506 |
+
"learning_rate": 3.054826368875238e-05,
|
4507 |
+
"loss": 0.3212,
|
4508 |
+
"step": 375000
|
4509 |
}
|
4510 |
],
|
4511 |
"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:bd981b2367b8f646d8a64ee2a06cb78ea5c57392438a6ecb841b7b90f8bc9262
|
3 |
size 201355195
|