Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
f8d8b6d
•
1 Parent(s): a3e0fef

Training in progress, step 25000

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 sha256:13f8d440dee0bab83268031d3ca51cab7f723eefc2ce80fc493ac3c6717c71e7
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cd44a10da57f9a7af8a613cb110bfcdaa6091d9e966275f9be32c3cbac6e95c
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ad0dc798bf3ab8bc86e8ca945a4782e43cd0d5a1828253e63883880781b3cdf
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7aa750c6022b392876b37347d88443a910853d6e20622071db2be72b7ec9575
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:aa36bb0d4cec624b08cc83d638858ce248a094ffa647685bae58b915dff037e9
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b3e714d5a3f2b101b256c07d93d4450d1c230c05fa4c1e05e0f3e10df1f2c2
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 sha256:74a9401956a29de2159a5b1a96f5c8acb3c2df03434a7575562e5bff46d935cf
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b362f451bff8d54f13f679d0f1b9fad8617c3c95e43c89334e57be01fac0b34c
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:a76dc75ea1a15c659d60f8d677cdda9bb534c90320b07847d866dce5eee22958
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:164ecca6e8456a909e3fe2a2e9f70b6db787429b035490cc6f3f6f08e081b7da
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 sha256:3fda5933a166c0774efdde4c472d56f927648e883235c5867dc882b3657f0455
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54c41b0555d65d685a008aaa2800bc89d4601df173762f7e6ce861a36c4f39c
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e171ab488f2f0f70ef9238e83eeacee5c282c69323a08adb507167abf9a3ee7
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1024e3372e453a1172cc413011eb31a7486f07a890d066aa12a732864a83e17
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c641ad045fc2fcec80756b378b25cace7a7d7436b423b673949d42813805e426
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78871b8b3dee3bb6764b90d839389fe2bb0b36b7cde4a95334fe9b5115f28b09
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": 0.3404255319148936,
5
- "global_step": 20000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -246,6 +246,66 @@
246
  "learning_rate": 0.00014944830467991823,
247
  "loss": 0.3855,
248
  "step": 20000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
249
  }
250
  ],
251
  "max_steps": 500000,
 
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,
 
246
  "learning_rate": 0.00014944830467991823,
247
  "loss": 0.3855,
248
  "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.35,
252
+ "learning_rate": 0.00014942040664853227,
253
+ "loss": 0.3843,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.36,
258
+ "learning_rate": 0.00014939182346575884,
259
+ "loss": 0.3841,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.37,
264
+ "learning_rate": 0.0001493625554137024,
265
+ "loss": 0.3833,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.37,
270
+ "learning_rate": 0.00014933266336950772,
271
+ "loss": 0.3825,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.38,
276
+ "learning_rate": 0.0001493020278205035,
277
+ "loss": 0.3822,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.39,
282
+ "learning_rate": 0.00014927070828846305,
283
+ "loss": 0.3814,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.4,
288
+ "learning_rate": 0.00014923870508249748,
289
+ "loss": 0.3809,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.41,
294
+ "learning_rate": 0.00014920601851846558,
295
+ "loss": 0.3806,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.42,
300
+ "learning_rate": 0.0001491727163396211,
301
+ "loss": 0.3797,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.43,
306
+ "learning_rate": 0.00014913866539908636,
307
+ "loss": 0.3794,
308
+ "step": 25000
309
  }
310
  ],
311
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ad0dc798bf3ab8bc86e8ca945a4782e43cd0d5a1828253e63883880781b3cdf
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7aa750c6022b392876b37347d88443a910853d6e20622071db2be72b7ec9575
3
  size 201355195