Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
8870036
•
1 Parent(s): 15ba2e7

Training in progress, step 35000

Browse files
Files changed (10) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scaler.pt +1 -1
  8. last-checkpoint/scheduler.pt +1 -1
  9. last-checkpoint/trainer_state.json +62 -2
  10. 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 sha256:378ed0d882252599d9f0e1dbbfb4741624ca7fc860e052bffacf351f82c256a6
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bf1dc3561fe5473043716a81ef1fda7e3ad979fa83ad8904b85db04d4a1ba1
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c1cad91c57acc5a25fdaa0d1c404494f4afc5dccb8ac51fe43affbe951510a4
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6bd1ad4ff009725546d85caa42fbbaf813b940bc95566c03ac7a2cb855aa80
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:dd7ca791f8f9db92060a859292f379077f5f2920ee869b17f445578bbdc3289c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:169057bd87435a758f008034e80ea7c37d721d81a0c05cf3cae3bcfcbe0bffa4
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 sha256:11eaea0408dd00ff70ecd55ec7fae9712c0061ae9c7214db95373a15bdf97b99
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b3cf51b6dbe776fb3c90a7e2d5175f7a1e4c776613a19dd490c15dc0138761a
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 sha256:7e2bd03a91b6a4df48cbb243ab2ab35dc2040b54739e80d179d554b66720529e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac3e395238c16bb6295a2b6cbcbd4943a2a577838a6f6330b6045a36e89c247
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 sha256:435973bcd9622dae63c811dc1ad815c42fcdb664d86b5d860b69c19b8df3153b
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1775af093be7b370439c4b9d31066b3a594dc600eb46ed4eecd8f94166c11b
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0162771ac68ca8935cfe08d9e5e0d29a7d9494edb15c1a2047d0fa67d983de0d
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b6574b57c2570000c9af4e77bbf53b450e6d4b62d98188361ee6a5f2aaa995
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4bc4d73cd4293b508895cd41de6a8e84cecd0961300003d0f6eda5e166dfa47
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513e5e5540abaa12c8c2e2fb504afe3a959d94df6eae36b19fc22d3feb620fc6
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": 0.5106382978723404,
5
- "global_step": 30000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -366,6 +366,66 @@
366
  "learning_rate": 0.00014876084917252817,
367
  "loss": 0.3748,
368
  "step": 30000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
369
  }
370
  ],
371
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5957446808510638,
5
+ "global_step": 35000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
366
  "learning_rate": 0.00014876084917252817,
367
  "loss": 0.3748,
368
  "step": 30000
369
+ },
370
+ {
371
+ "epoch": 0.52,
372
+ "learning_rate": 0.00014871931483158502,
373
+ "loss": 0.3747,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 0.53,
378
+ "learning_rate": 0.00014867718736049287,
379
+ "loss": 0.374,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 0.54,
384
+ "learning_rate": 0.0001486342983275925,
385
+ "loss": 0.3735,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 0.54,
390
+ "learning_rate": 0.00014859073190187644,
391
+ "loss": 0.3731,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 0.55,
396
+ "learning_rate": 0.0001485464885133277,
397
+ "loss": 0.3735,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 0.56,
402
+ "learning_rate": 0.00014850156859861065,
403
+ "loss": 0.3725,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 0.57,
408
+ "learning_rate": 0.00014845597260106674,
409
+ "loss": 0.3721,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 0.58,
414
+ "learning_rate": 0.00014840970097071006,
415
+ "loss": 0.3719,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 0.59,
420
+ "learning_rate": 0.00014836284873135484,
421
+ "loss": 0.3717,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 0.6,
426
+ "learning_rate": 0.00014831522856104197,
427
+ "loss": 0.371,
428
+ "step": 35000
429
  }
430
  ],
431
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c1cad91c57acc5a25fdaa0d1c404494f4afc5dccb8ac51fe43affbe951510a4
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6bd1ad4ff009725546d85caa42fbbaf813b940bc95566c03ac7a2cb855aa80
3
  size 201355195