Hugging Face's logo

Nadav
/
Pixel-real-scans-v2

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
Nadav commited on
Commit
f5cdf0e
•
1 Parent(s): 14b16a5

Training in progress, step 25000

Browse files
Files changed (11) hide show
  1. config.json +1 -1
  2. last-checkpoint/config.json +1 -1
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/pytorch_model.bin +1 -1
  5. last-checkpoint/rng_state.pth +1 -1
  6. last-checkpoint/scaler.pt +1 -1
  7. last-checkpoint/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +71 -3
  9. last-checkpoint/training_args.bin +1 -1
  10. pytorch_model.bin +1 -1
  11. training_args.bin +1 -1
config.json CHANGED
@@ -18,7 +18,7 @@
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "layer_norm_eps": 1e-12,
21
- "mask_ratio": 0.25,
22
  "model_type": "pixel",
23
  "norm_pix_loss": true,
24
  "num_attention_heads": 12,
 
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "layer_norm_eps": 1e-12,
21
+ "mask_ratio": 0.29,
22
  "model_type": "pixel",
23
  "norm_pix_loss": true,
24
  "num_attention_heads": 12,
last-checkpoint/config.json CHANGED
@@ -18,7 +18,7 @@
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "layer_norm_eps": 1e-12,
21
- "mask_ratio": 0.25,
22
  "model_type": "pixel",
23
  "norm_pix_loss": true,
24
  "num_attention_heads": 12,
 
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "layer_norm_eps": 1e-12,
21
+ "mask_ratio": 0.29,
22
  "model_type": "pixel",
23
  "norm_pix_loss": true,
24
  "num_attention_heads": 12,
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:227bb459455ca9395e8701d0b76fa538ae5551af488261f8a6c040d98a6dded3
3
  size 893438545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54511fdc5c5a7b0e9e913352b7c70eeb4be98b664939b4420d74be15aa007937
3
  size 893438545
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ee7451dd5ec81a01259d5968e23ec645d0c3962b135c90aa707004f25bc4403
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef06c37b1b2de2e7bc399a7b91f0e41a8e27ec304f4ab7843f18254e5ab425e3
3
  size 449471589
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc90007b132e8f26a3d447fb1e8dee59d5ce3dfd07c853ec26d9c159e851307d
3
  size 15459
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7b0cc71c51ef5f7a78f816541ca99e7efff8df2315723a0c94e1b16e8f0771
3
  size 15459
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56d7925c4d371c4e7cd499e68da31588c0a08bf1a905f213b26db017a95291f6
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb6982c29cd162f49aeb531674acf574eccd46a8f556bec596040d7c3b95200a
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6464ca3b88e496d5d945a7955ac6cabd3c94f9611fe337e2e8a9af945aa679a
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66cad2ac81d79f6484466213369fcababfbacc00f3cf3a8946126f6ba258bade
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": 0.8705493166187864,
5
- "global_step": 20000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -278,11 +278,79 @@
278
  "eval_samples_per_second": 52.619,
279
  "eval_steps_per_second": 0.831,
280
  "step": 20000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
281
  }
282
  ],
283
  "max_steps": 100000,
284
  "num_train_epochs": 9,
285
- "total_flos": 9.419722694590464e+20,
286
  "trial_name": null,
287
  "trial_params": null
288
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.4352746583093932,
5
+ "global_step": 25000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
278
  "eval_samples_per_second": 52.619,
279
  "eval_steps_per_second": 0.831,
280
  "step": 20000
281
+ },
282
+ {
283
+ "epoch": 1.04,
284
+ "learning_rate": 9.169394796092694e-05,
285
+ "loss": 0.4465,
286
+ "step": 20500
287
+ },
288
+ {
289
+ "epoch": 1.09,
290
+ "learning_rate": 9.126149821203012e-05,
291
+ "loss": 0.444,
292
+ "step": 21000
293
+ },
294
+ {
295
+ "epoch": 1.13,
296
+ "learning_rate": 9.082019786191564e-05,
297
+ "loss": 0.4435,
298
+ "step": 21500
299
+ },
300
+ {
301
+ "epoch": 1.17,
302
+ "learning_rate": 9.037106452976014e-05,
303
+ "loss": 0.4422,
304
+ "step": 22000
305
+ },
306
+ {
307
+ "epoch": 1.22,
308
+ "learning_rate": 8.991240893598493e-05,
309
+ "loss": 0.4446,
310
+ "step": 22500
311
+ },
312
+ {
313
+ "epoch": 1.26,
314
+ "learning_rate": 8.944523560858406e-05,
315
+ "loss": 0.4418,
316
+ "step": 23000
317
+ },
318
+ {
319
+ "epoch": 1.3,
320
+ "learning_rate": 8.89696598155856e-05,
321
+ "loss": 0.4412,
322
+ "step": 23500
323
+ },
324
+ {
325
+ "epoch": 1.35,
326
+ "learning_rate": 8.848579889820028e-05,
327
+ "loss": 0.4414,
328
+ "step": 24000
329
+ },
330
+ {
331
+ "epoch": 1.39,
332
+ "learning_rate": 8.799377224186928e-05,
333
+ "loss": 0.4407,
334
+ "step": 24500
335
+ },
336
+ {
337
+ "epoch": 1.44,
338
+ "learning_rate": 8.749470933536528e-05,
339
+ "loss": 0.4402,
340
+ "step": 25000
341
+ },
342
+ {
343
+ "epoch": 1.44,
344
+ "eval_loss": 0.42174017429351807,
345
+ "eval_runtime": 91.5901,
346
+ "eval_samples_per_second": 54.591,
347
+ "eval_steps_per_second": 0.863,
348
+ "step": 25000
349
  }
350
  ],
351
  "max_steps": 100000,
352
  "num_train_epochs": 9,
353
+ "total_flos": 1.177465336823808e+21,
354
  "trial_name": null,
355
  "trial_params": null
356
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb90956c2fc47703463b50fd267631dda0878fd140ff91c80ab2b7c4fc6e5708
3
  size 5615
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da26d9c8c1c726588ec3b1e697e00057dd4bc580fad19e58afb508d1a16ec382
3
  size 5615
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ee7451dd5ec81a01259d5968e23ec645d0c3962b135c90aa707004f25bc4403
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef06c37b1b2de2e7bc399a7b91f0e41a8e27ec304f4ab7843f18254e5ab425e3
3
  size 449471589
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb90956c2fc47703463b50fd267631dda0878fd140ff91c80ab2b7c4fc6e5708
3
  size 5615
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da26d9c8c1c726588ec3b1e697e00057dd4bc580fad19e58afb508d1a16ec382
3
  size 5615