Hugging Face's logo

aravindhank
/
tiny-bart-sst2-distilled

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
aravindhank commited on
Commit
b25dadd
•
1 Parent(s): 9d7342b

End of training

Browse files
Files changed (27) hide show
  1. README.md +52 -0
  2. config.json +45 -0
  3. generation_config.json +9 -0
  4. logs/events.out.tfevents.1714306730.3c3bfa3584e6.237.0 +3 -0
  5. logs/events.out.tfevents.1714306945.3c3bfa3584e6.3085.0 +3 -0
  6. logs/events.out.tfevents.1714307091.3c3bfa3584e6.3967.0 +3 -0
  7. logs/events.out.tfevents.1714307222.3c3bfa3584e6.4719.0 +3 -0
  8. logs/events.out.tfevents.1714307630.3c3bfa3584e6.6592.0 +3 -0
  9. logs/events.out.tfevents.1714308659.3c3bfa3584e6.6592.1 +3 -0
  10. logs/events.out.tfevents.1714308727.3c3bfa3584e6.6592.2 +3 -0
  11. logs/events.out.tfevents.1714308943.3c3bfa3584e6.6592.3 +3 -0
  12. logs/events.out.tfevents.1714309121.3c3bfa3584e6.6592.4 +3 -0
  13. logs/events.out.tfevents.1714309726.3c3bfa3584e6.6592.5 +3 -0
  14. logs/events.out.tfevents.1714309846.3c3bfa3584e6.6592.6 +3 -0
  15. logs/events.out.tfevents.1714309906.3c3bfa3584e6.6592.7 +3 -0
  16. logs/events.out.tfevents.1714310436.3c3bfa3584e6.6592.8 +3 -0
  17. logs/events.out.tfevents.1714310716.3c3bfa3584e6.6592.9 +3 -0
  18. logs/events.out.tfevents.1714311103.3c3bfa3584e6.21342.0 +3 -0
  19. logs/events.out.tfevents.1714311190.3c3bfa3584e6.21342.1 +3 -0
  20. logs/events.out.tfevents.1714313431.3c3bfa3584e6.21342.2 +3 -0
  21. logs/events.out.tfevents.1714313474.3c3bfa3584e6.21342.3 +3 -0
  22. merges.txt +0 -0
  23. model.safetensors +3 -0
  24. special_tokens_map.json +51 -0
  25. tokenizer_config.json +59 -0
  26. training_args.bin +3 -0
  27. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: aravindhank/valuenet-bart-base
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: tiny-bart-sst2-distilled
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # tiny-bart-sst2-distilled
14
+
15
+ This model is a fine-tuned version of [aravindhank/valuenet-bart-base](https://huggingface.co/aravindhank/valuenet-bart-base) on the None dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 6e-05
35
+ - train_batch_size: 8
36
+ - eval_batch_size: 8
37
+ - seed: 33
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 1
41
+ - mixed_precision_training: Native AMP
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.40.1
50
+ - Pytorch 2.2.1+cu121
51
+ - Datasets 2.19.0
52
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aravindhank/valuenet-bart-base",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "BartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 768,
12
+ "decoder_attention_heads": 16,
13
+ "decoder_ffn_dim": 3072,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 3,
16
+ "decoder_start_token_id": 2,
17
+ "dropout": 0.1,
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 3072,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 3,
22
+ "eos_token_id": 2,
23
+ "forced_eos_token_id": 2,
24
+ "id2label": {
25
+ "0": "LABEL_0",
26
+ "1": "LABEL_1",
27
+ "2": "LABEL_2"
28
+ },
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1,
34
+ "LABEL_2": 2
35
+ },
36
+ "max_position_embeddings": 1024,
37
+ "model_type": "bart",
38
+ "num_hidden_layers": 3,
39
+ "pad_token_id": 1,
40
+ "scale_embedding": false,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.40.1",
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.40.1"
9
+ }
logs/events.out.tfevents.1714306730.3c3bfa3584e6.237.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641b4475e3a4bf13335a87b0d386ec7486a24bb3728bd53d8919ad0d12469edf
3
+ size 5484
logs/events.out.tfevents.1714306945.3c3bfa3584e6.3085.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fa1dcf2988426ee6c3683e2030dd4d045aeb3b90f1c9694b41009856673ed5
3
+ size 4184
logs/events.out.tfevents.1714307091.3c3bfa3584e6.3967.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e11b6c396927ca30543ef5fa3cf63b839c077c45e9270bb7ddcd6f426eca78
3
+ size 4184
logs/events.out.tfevents.1714307222.3c3bfa3584e6.4719.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55dd765305717c6a3a14b9375aa2fb5584158c5455c4de11e69daa4ea322f520
3
+ size 5691
logs/events.out.tfevents.1714307630.3c3bfa3584e6.6592.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a05021518393ce43eb23e35225507c137444b279964babb1d32d106bec551d
3
+ size 5687
logs/events.out.tfevents.1714308659.3c3bfa3584e6.6592.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9998c28f6aeacd1299f3b07688b0e268777e7d5388991f94eb8d4584e936744a
3
+ size 5687
logs/events.out.tfevents.1714308727.3c3bfa3584e6.6592.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a48b8c7da24738517f366c5945300730fadf8160fad7b86dc7a347f8c753b919
3
+ size 5687
logs/events.out.tfevents.1714308943.3c3bfa3584e6.6592.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fe7e15dd04a99cc1232c26d4a91bf95f1a312ad5191a01c83bf58a320ab8b43
3
+ size 5687
logs/events.out.tfevents.1714309121.3c3bfa3584e6.6592.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132cf1e179d231a501e6adf9eb272f5cbd6b63a4bffe27c9232762457908feeb
3
+ size 7276
logs/events.out.tfevents.1714309726.3c3bfa3584e6.6592.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4fc2225c14be9fbbb20dd757e1e2db5568798f4d2f2297eaf4b58a5a2d75f1
3
+ size 5479
logs/events.out.tfevents.1714309846.3c3bfa3584e6.6592.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4fc64dd9d162d824f8ad401a25306631411a98fcbf7afb9fe890b4e035d8bf
3
+ size 5481
logs/events.out.tfevents.1714309906.3c3bfa3584e6.6592.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636c4fbbc0166c134af15200dab301daba296d8c9e17ea079599e05a3d460492
3
+ size 5481
logs/events.out.tfevents.1714310436.3c3bfa3584e6.6592.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b929e0afd0f46495d7ad36aa06a32c76a6988bae5a9674cba17018a36d6dd97
3
+ size 5481
logs/events.out.tfevents.1714310716.3c3bfa3584e6.6592.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bfc453506e93672d04b0559427652e3723c69d6462fa3c6f1b420cb4827f20a
3
+ size 5481
logs/events.out.tfevents.1714311103.3c3bfa3584e6.21342.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf90b3791ff5d365d040aa64bacbbde2b1247c23e1771c5e64cdd59345172cb1
3
+ size 5479
logs/events.out.tfevents.1714311190.3c3bfa3584e6.21342.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85513e5cd0b00987eb1df8c51b5a89e47afa61dd0243d8b849f2540e046247a
3
+ size 5479
logs/events.out.tfevents.1714313431.3c3bfa3584e6.21342.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a4567ae175d92b7fe0cddee22b18a33bffe1a4ca1dc498caa6c8113359b11be
3
+ size 4994
logs/events.out.tfevents.1714313474.3c3bfa3584e6.21342.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f9e7a86547ce99511477032238da5b5892514781f60625f07809eb0aef48372
3
+ size 5559
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021d5768a8b63930b0ee56fb40aa9c9f47ce2acda5de3802e73729ab1b0fc49b
3
+ size 359422252
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "is_split_into_words": true,
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1024,
53
+ "pad_token": "<pad>",
54
+ "padding": true,
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "BartTokenizer",
57
+ "truncation": true,
58
+ "unk_token": "<unk>"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d73d730c957f7d6e4612fa4a6d5a1238f6d22c684866493c0c3ec276083a03e
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff