Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
15ba2e7
•
1 Parent(s): f8d8b6d

Training in progress, step 30000

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 sha256:5cd44a10da57f9a7af8a613cb110bfcdaa6091d9e966275f9be32c3cbac6e95c
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378ed0d882252599d9f0e1dbbfb4741624ca7fc860e052bffacf351f82c256a6
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:f7aa750c6022b392876b37347d88443a910853d6e20622071db2be72b7ec9575
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1cad91c57acc5a25fdaa0d1c404494f4afc5dccb8ac51fe43affbe951510a4
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 sha256:24b3e714d5a3f2b101b256c07d93d4450d1c230c05fa4c1e05e0f3e10df1f2c2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7ca791f8f9db92060a859292f379077f5f2920ee869b17f445578bbdc3289c
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:b362f451bff8d54f13f679d0f1b9fad8617c3c95e43c89334e57be01fac0b34c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11eaea0408dd00ff70ecd55ec7fae9712c0061ae9c7214db95373a15bdf97b99
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 sha256:164ecca6e8456a909e3fe2a2e9f70b6db787429b035490cc6f3f6f08e081b7da
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2bd03a91b6a4df48cbb243ab2ab35dc2040b54739e80d179d554b66720529e
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:a54c41b0555d65d685a008aaa2800bc89d4601df173762f7e6ce861a36c4f39c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435973bcd9622dae63c811dc1ad815c42fcdb664d86b5d860b69c19b8df3153b
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1024e3372e453a1172cc413011eb31a7486f07a890d066aa12a732864a83e17
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0162771ac68ca8935cfe08d9e5e0d29a7d9494edb15c1a2047d0fa67d983de0d
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78871b8b3dee3bb6764b90d839389fe2bb0b36b7cde4a95334fe9b5115f28b09
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bc4d73cd4293b508895cd41de6a8e84cecd0961300003d0f6eda5e166dfa47
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": 0.425531914893617,
5
- "global_step": 25000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -306,6 +306,66 @@
306
  "learning_rate": 0.00014913866539908636,
307
  "loss": 0.3794,
308
  "step": 25000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
309
  }
310
  ],
311
  "max_steps": 500000,
 
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,
 
306
  "learning_rate": 0.00014913866539908636,
307
  "loss": 0.3794,
308
  "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.43,
312
+ "learning_rate": 0.00014910393208783659,
313
+ "loss": 0.3788,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.44,
318
+ "learning_rate": 0.00014906851674867546,
319
+ "loss": 0.3784,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.45,
324
+ "learning_rate": 0.00014903249260525252,
325
+ "loss": 0.3777,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.46,
330
+ "learning_rate": 0.00014899571562788615,
331
+ "loss": 0.3776,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.47,
336
+ "learning_rate": 0.00014895833328588902,
337
+ "loss": 0.3768,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.48,
342
+ "learning_rate": 0.00014892019611930716,
343
+ "loss": 0.3762,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 0.49,
348
+ "learning_rate": 0.00014888137873821385,
349
+ "loss": 0.3761,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 0.49,
354
+ "learning_rate": 0.00014884188152572092,
355
+ "loss": 0.3755,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 0.5,
360
+ "learning_rate": 0.0001488017048716499,
361
+ "loss": 0.3752,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 0.51,
366
+ "learning_rate": 0.00014876084917252817,
367
+ "loss": 0.3748,
368
+ "step": 30000
369
  }
370
  ],
371
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7aa750c6022b392876b37347d88443a910853d6e20622071db2be72b7ec9575
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1cad91c57acc5a25fdaa0d1c404494f4afc5dccb8ac51fe43affbe951510a4
3
  size 201355195