Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
743896b
•
1 Parent(s): 60fb041

Training in progress, step 195000

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:baaab21925e93460d24e02cac40a21109c4d19dc3a9c2c641547d7a31b0e2e34
3
  size 402588883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca983718479681e579d29cd9094be0c7c9c2a4a9090254a55f24bd5c0619bafd
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:b2f77d6be3df78a76dc41f7ace05e7c297fca237b33e8a1a52bc11437ea6ea34
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f18242f447e921e3c8bfe10bda44a88ac3483800711c4db8029aa3771b7661c
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:ca591252c1ef13b4a89d0485dc650e04b8acd26b162d76f5d6e7715cb8ec1d9a
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fb741f87d6e444e3062ae01fc450b73af26d189ed2f5a5abb171d910b8fe45
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 sha256:14d7cea85b5746ba7ba206fef3febbbcb3fada188d2b42064507d0774d655bdf
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0edbf78736e07267e57673c105d194cdb5dde95e5d6a6879711dce6a32790ef
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 sha256:3e728e7b4508f9b187d0b866da280fc06ff39068ea40e4f441c4315272f00f50
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63c81ff2901346612a920a1b930f509255b3e2b1bba838237c2171af2ad17ea
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:e960b9fbdf27b87b2539486d0e91a8e405b6cc30b052f608dcadd5f555f9606b
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a6414262619b04b7d12a4bdb56ffe57c47a1c283a51b70837ae86f6c001b06
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:434679b868ab4977ed91cda292df1daebee137047ea8180e875efa6af98860b3
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe830494e25bc662e72bff02d200828ca96c54c81f269e958f76ab22dcc869f
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:692456d5c45157319246b6580538cab100d84ec4a09da8043159c331a645e1a5
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6524f23bfd8a035d4353c716f97c0fce59590fa21b8588d26b54c67e3b7e43ab
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": 3.2340425531914896,
5
- "global_step": 190000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -2286,6 +2286,66 @@
2286
  "learning_rate": 0.00010579775065387587,
2287
  "loss": 0.3347,
2288
  "step": 190000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2289
  }
2290
  ],
2291
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.3191489361702127,
5
+ "global_step": 195000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
2286
  "learning_rate": 0.00010579775065387587,
2287
  "loss": 0.3347,
2288
  "step": 190000
2289
+ },
2290
+ {
2291
+ "epoch": 3.24,
2292
+ "learning_rate": 0.00010559401003179132,
2293
+ "loss": 0.3352,
2294
+ "step": 190500
2295
+ },
2296
+ {
2297
+ "epoch": 3.25,
2298
+ "learning_rate": 0.00010538919907962285,
2299
+ "loss": 0.3344,
2300
+ "step": 191000
2301
+ },
2302
+ {
2303
+ "epoch": 3.26,
2304
+ "learning_rate": 0.00010518413754630952,
2305
+ "loss": 0.3342,
2306
+ "step": 191500
2307
+ },
2308
+ {
2309
+ "epoch": 3.27,
2310
+ "learning_rate": 0.00010497882745572583,
2311
+ "loss": 0.3338,
2312
+ "step": 192000
2313
+ },
2314
+ {
2315
+ "epoch": 3.28,
2316
+ "learning_rate": 0.00010477327083419952,
2317
+ "loss": 0.3344,
2318
+ "step": 192500
2319
+ },
2320
+ {
2321
+ "epoch": 3.29,
2322
+ "learning_rate": 0.00010456746971049145,
2323
+ "loss": 0.3344,
2324
+ "step": 193000
2325
+ },
2326
+ {
2327
+ "epoch": 3.29,
2328
+ "learning_rate": 0.0001043614261157756,
2329
+ "loss": 0.3341,
2330
+ "step": 193500
2331
+ },
2332
+ {
2333
+ "epoch": 3.3,
2334
+ "learning_rate": 0.00010415514208361913,
2335
+ "loss": 0.3336,
2336
+ "step": 194000
2337
+ },
2338
+ {
2339
+ "epoch": 3.31,
2340
+ "learning_rate": 0.0001039486196499621,
2341
+ "loss": 0.3336,
2342
+ "step": 194500
2343
+ },
2344
+ {
2345
+ "epoch": 3.32,
2346
+ "learning_rate": 0.00010374186085309757,
2347
+ "loss": 0.3337,
2348
+ "step": 195000
2349
  }
2350
  ],
2351
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2f77d6be3df78a76dc41f7ace05e7c297fca237b33e8a1a52bc11437ea6ea34
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f18242f447e921e3c8bfe10bda44a88ac3483800711c4db8029aa3771b7661c
3
  size 201355195