Hugging Face's logo

dima806
/
medium-article-titles-engagement

Text Classification
Transformers
PyTorch
Safetensors
English
distilbert
medium
Inference Endpoints
Model card Files Community
1
dima806 commited on
Commit
076fcf4
•
1 Parent(s): e597bfe

Upload . with huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-10645/config.json +30 -0
  2. checkpoint-10645/optimizer.pt +3 -0
  3. checkpoint-10645/pytorch_model.bin +3 -0
  4. checkpoint-10645/rng_state.pth +3 -0
  5. checkpoint-10645/scheduler.pt +3 -0
  6. checkpoint-10645/trainer_state.json +0 -0
  7. checkpoint-10645/training_args.bin +3 -0
  8. checkpoint-12774/config.json +30 -0
  9. checkpoint-12774/optimizer.pt +3 -0
  10. checkpoint-12774/pytorch_model.bin +3 -0
  11. checkpoint-12774/rng_state.pth +3 -0
  12. checkpoint-12774/scheduler.pt +3 -0
  13. checkpoint-12774/trainer_state.json +0 -0
  14. checkpoint-12774/training_args.bin +3 -0
  15. checkpoint-14903/config.json +30 -0
  16. checkpoint-14903/optimizer.pt +3 -0
  17. checkpoint-14903/pytorch_model.bin +3 -0
  18. checkpoint-14903/rng_state.pth +3 -0
  19. checkpoint-14903/scheduler.pt +3 -0
  20. checkpoint-14903/trainer_state.json +0 -0
  21. checkpoint-14903/training_args.bin +3 -0
  22. checkpoint-17032/config.json +30 -0
  23. checkpoint-17032/optimizer.pt +3 -0
  24. checkpoint-17032/pytorch_model.bin +3 -0
  25. checkpoint-17032/rng_state.pth +3 -0
  26. checkpoint-17032/scheduler.pt +3 -0
  27. checkpoint-17032/trainer_state.json +0 -0
  28. checkpoint-17032/training_args.bin +3 -0
  29. checkpoint-19161/config.json +30 -0
  30. checkpoint-19161/optimizer.pt +3 -0
  31. checkpoint-19161/pytorch_model.bin +3 -0
  32. checkpoint-19161/rng_state.pth +3 -0
  33. checkpoint-19161/scheduler.pt +3 -0
  34. checkpoint-19161/trainer_state.json +0 -0
  35. checkpoint-19161/training_args.bin +3 -0
  36. checkpoint-2129/optimizer.pt +1 -1
  37. checkpoint-2129/pytorch_model.bin +1 -1
  38. checkpoint-2129/rng_state.pth +1 -1
  39. checkpoint-2129/scheduler.pt +1 -1
  40. checkpoint-2129/trainer_state.json +0 -0
  41. checkpoint-2129/training_args.bin +1 -1
  42. checkpoint-21290/config.json +30 -0
  43. checkpoint-21290/optimizer.pt +3 -0
  44. checkpoint-21290/pytorch_model.bin +3 -0
  45. checkpoint-21290/rng_state.pth +3 -0
  46. checkpoint-21290/scheduler.pt +3 -0
  47. checkpoint-21290/trainer_state.json +0 -0
  48. checkpoint-21290/training_args.bin +3 -0
  49. checkpoint-4258/config.json +30 -0
  50. checkpoint-4258/optimizer.pt +3 -0
checkpoint-10645/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NOT ENGAGING TITLE",
13
+ "1": "ENGAGING TITLE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "distilbert",
18
+ "n_heads": 12,
19
+ "n_layers": 6,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "problem_type": "single_label_classification",
23
+ "qa_dropout": 0.1,
24
+ "seq_classif_dropout": 0.2,
25
+ "sinusoidal_pos_embds": false,
26
+ "tie_weights_": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "vocab_size": 28996
30
+ }
checkpoint-10645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1425570a105f40dfeff020fb14d8d13cffcfbe8d9e08ec377a1ad341f4a1c14
3
+ size 526325317
checkpoint-10645/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46106cfa5c7a725c549eaa5ebdc45a22a281f25d150f1f5f8d58249615f61e37
3
+ size 263167661
checkpoint-10645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31471d8cd77efaa2d3760b3195e0f2d8bab98c6e7f31827a7a341af52e98f77a
3
+ size 14575
checkpoint-10645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f04f907500fbdfd6200fb3fd41953cfb47270695409f1e8fd7e6fabfd70b47
3
+ size 627
checkpoint-10645/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e3143372676e416a3afc8577502b2fd1d7e0d0a66edcca2d99681e9727436b
3
+ size 3579
checkpoint-12774/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NOT ENGAGING TITLE",
13
+ "1": "ENGAGING TITLE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "distilbert",
18
+ "n_heads": 12,
19
+ "n_layers": 6,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "problem_type": "single_label_classification",
23
+ "qa_dropout": 0.1,
24
+ "seq_classif_dropout": 0.2,
25
+ "sinusoidal_pos_embds": false,
26
+ "tie_weights_": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "vocab_size": 28996
30
+ }
checkpoint-12774/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ad2f5e37771aeccdc41cc99352511652d1f61d8c7997a4c0515dc72770650c
3
+ size 526325317
checkpoint-12774/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd618b0245e5dececd3fb701054a1183acd18f1206261619826eae04116ee3e8
3
+ size 263167661
checkpoint-12774/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:667cc8f21c94ecf2d05ea5226a535af602f76f07aae4d3dec5db5d0951103a26
3
+ size 14575
checkpoint-12774/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392ea28646700739b40b2a339d7e6d69a3b130bfc945017f8bf989187c04af94
3
+ size 627
checkpoint-12774/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12774/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e3143372676e416a3afc8577502b2fd1d7e0d0a66edcca2d99681e9727436b
3
+ size 3579
checkpoint-14903/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NOT ENGAGING TITLE",
13
+ "1": "ENGAGING TITLE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "distilbert",
18
+ "n_heads": 12,
19
+ "n_layers": 6,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "problem_type": "single_label_classification",
23
+ "qa_dropout": 0.1,
24
+ "seq_classif_dropout": 0.2,
25
+ "sinusoidal_pos_embds": false,
26
+ "tie_weights_": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "vocab_size": 28996
30
+ }
checkpoint-14903/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:158434a3a0fcc007bb1a35346a62ea1920c067686fa4a590a9472c0581f4dd72
3
+ size 526325317
checkpoint-14903/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b189b713ac4a74ab654539934990729444c70a82191f21267e085e2a6cc8257
3
+ size 263167661
checkpoint-14903/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75632b8cdfeee9e83ec4ae75a471f718e5e7dcf3a8e441cec4ba391adc93ee48
3
+ size 14575
checkpoint-14903/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc38e61ede4622e2167a19f664d6364d4f92f4ad39e576232d8e28fd1246446
3
+ size 627
checkpoint-14903/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14903/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e3143372676e416a3afc8577502b2fd1d7e0d0a66edcca2d99681e9727436b
3
+ size 3579
checkpoint-17032/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NOT ENGAGING TITLE",
13
+ "1": "ENGAGING TITLE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "distilbert",
18
+ "n_heads": 12,
19
+ "n_layers": 6,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "problem_type": "single_label_classification",
23
+ "qa_dropout": 0.1,
24
+ "seq_classif_dropout": 0.2,
25
+ "sinusoidal_pos_embds": false,
26
+ "tie_weights_": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "vocab_size": 28996
30
+ }
checkpoint-17032/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5021c098486b66e2400c54fe98ddb92060e4e953363ee569e455b5d9817a247f
3
+ size 526325317
checkpoint-17032/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6fa279eb98c88de80016d5d364a43b9037343b00c844e8e755b00fc1d663b0d
3
+ size 263167661
checkpoint-17032/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a90ddb84d7bf7f93d471562a6d2a3bdb841a5a0d2348b4b0f421c7a8b93509f
3
+ size 14575
checkpoint-17032/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6471695657b01525e4b157b66d70b2fe4e649377f4cf5b5763655d66b9e87330
3
+ size 627
checkpoint-17032/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17032/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e3143372676e416a3afc8577502b2fd1d7e0d0a66edcca2d99681e9727436b
3
+ size 3579
checkpoint-19161/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NOT ENGAGING TITLE",
13
+ "1": "ENGAGING TITLE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "distilbert",
18
+ "n_heads": 12,
19
+ "n_layers": 6,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "problem_type": "single_label_classification",
23
+ "qa_dropout": 0.1,
24
+ "seq_classif_dropout": 0.2,
25
+ "sinusoidal_pos_embds": false,
26
+ "tie_weights_": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "vocab_size": 28996
30
+ }
checkpoint-19161/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:829bbb9b42aec156b96048ac75597d74d0188ff99676082597ed63f5775a1de9
3
+ size 526325317
checkpoint-19161/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c50d03b387a2f1c2070da5fd6e483a031032728319b09cee8af08edd99aaa7
3
+ size 263167661
checkpoint-19161/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45eb052df2be170a7fcc7e1e76c632eb33b25cbd941677d04e063956900c65d0
3
+ size 14575
checkpoint-19161/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ed562f2be4d1f7d5aa011e0c77d5371d6f13aba53ceb5987512dee0eba3ddf
3
+ size 627
checkpoint-19161/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-19161/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e3143372676e416a3afc8577502b2fd1d7e0d0a66edcca2d99681e9727436b
3
+ size 3579
checkpoint-2129/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12661c1b807a71f76496315e6c8c2418a04937bb4977a83f7fe257954e4624c4
3
  size 526325317
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241bc2b084e66263adc5f41f2ae9d4175f520ad82c1fd69b94f7451195440d78
3
  size 526325317
checkpoint-2129/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4620318968f84e74e73d471a46d932c4ca087e46e6d28a3420b8b61ec7b0729
3
  size 263167661
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c31574ad11240ad00d779b4eaa94eb2921f6734af764ecbb85235a8ef082339d
3
  size 263167661
checkpoint-2129/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5adb7e529eb113cdd52ec4ee8c4d96b2d8ff061fadcb01323dab8b224cefc3f4
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a63e050a8414ce451e4ba35638366c61742c15066fccb09fbb46555f765fb608
3
  size 14575
checkpoint-2129/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:923a8812e6482c25919577d51110e470174396622d73814cd19f46a83bb83da1
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec34ba0a33b98e6f32193df10489a04b72b949a712fb4cd79d08bbeb193b644
3
  size 627
checkpoint-2129/trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
checkpoint-2129/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61144ad5a14db849074143ef18b12aaa5ca89078c4d68f0089580887e1baf58c
3
  size 3579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e3143372676e416a3afc8577502b2fd1d7e0d0a66edcca2d99681e9727436b
3
  size 3579
checkpoint-21290/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NOT ENGAGING TITLE",
13
+ "1": "ENGAGING TITLE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "distilbert",
18
+ "n_heads": 12,
19
+ "n_layers": 6,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "problem_type": "single_label_classification",
23
+ "qa_dropout": 0.1,
24
+ "seq_classif_dropout": 0.2,
25
+ "sinusoidal_pos_embds": false,
26
+ "tie_weights_": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "vocab_size": 28996
30
+ }
checkpoint-21290/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c00bc5a964cba022cb061fa69f636ede4d0cdfd8bd84fba8f93f0cb9b9a6cae7
3
+ size 526325317
checkpoint-21290/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:242d43e60334dbc732e13b6868194be0e1b4c6cc0c2efceb42c4e968e80abceb
3
+ size 263167661
checkpoint-21290/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d0a660e9bca20697cc0148aada63fd0877114c9f82a43f40fce3d4abb5f436
3
+ size 14575
checkpoint-21290/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27be73079d76e1a8ad4cb47ec05669e86b04ff3cfaa75d6cf3c473396580af36
3
+ size 627
checkpoint-21290/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-21290/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e3143372676e416a3afc8577502b2fd1d7e0d0a66edcca2d99681e9727436b
3
+ size 3579
checkpoint-4258/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NOT ENGAGING TITLE",
13
+ "1": "ENGAGING TITLE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "distilbert",
18
+ "n_heads": 12,
19
+ "n_layers": 6,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "problem_type": "single_label_classification",
23
+ "qa_dropout": 0.1,
24
+ "seq_classif_dropout": 0.2,
25
+ "sinusoidal_pos_embds": false,
26
+ "tie_weights_": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "vocab_size": 28996
30
+ }
checkpoint-4258/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6e4022913e3b574d0f456aa242a0e1271e369a791b26b22f1125cdc7872a33
3
+ size 526325317