Hugging Face's logo

alshelt
/
ctrlsum-bart-large-cnndm

Transformers
TensorBoard
Safetensors
bart
text2text-generation
Model card Files
xet
Metrics Community
alshelt commited on
Commit
baaf57b
·
verified ·
1 Parent(s): 5a881f7

Training in progress, step 500

Browse files
Files changed (17) hide show
  1. config.json +74 -0
  2. logs/events.out.tfevents.1713388557.node0393.palmetto.clemson.edu.929457.0 +3 -0
  3. logs/events.out.tfevents.1713389087.node0393.palmetto.clemson.edu.930128.0 +3 -0
  4. logs/events.out.tfevents.1713389627.node2106.palmetto.clemson.edu.2150924.0 +3 -0
  5. logs/events.out.tfevents.1713990817.node2090.palmetto.clemson.edu.378996.0 +3 -0
  6. logs/events.out.tfevents.1713994423.node0275.palmetto.clemson.edu.1491152.0 +3 -0
  7. logs/events.out.tfevents.1713995894.node0293.palmetto.clemson.edu.385138.0 +3 -0
  8. logs/events.out.tfevents.1713997576.node0275.palmetto.clemson.edu.1495362.0 +3 -0
  9. logs/events.out.tfevents.1714006763.node0376.palmetto.clemson.edu.3738362.0 +3 -0
  10. logs/events.out.tfevents.1714014803.node0373.palmetto.clemson.edu.3485540.0 +3 -0
  11. logs/events.out.tfevents.1714020333.node0373.palmetto.clemson.edu.3492883.0 +3 -0
  12. merges.txt +0 -0
  13. model.safetensors +3 -0
  14. special_tokens_map.json +51 -0
  15. tokenizer_config.json +56 -0
  16. training_args.bin +3 -0
  17. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.39.3",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
logs/events.out.tfevents.1713388557.node0393.palmetto.clemson.edu.929457.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a58b5696daf6384b5c7aa19bf3ba419735e99d72dfaaa207beabe9a250d7c0c7
3
+ size 55740
logs/events.out.tfevents.1713389087.node0393.palmetto.clemson.edu.930128.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1884f3ed69c507b3f96e6027359aca8d768137f29c60040ee872eb86d0b9d1d1
3
+ size 11609
logs/events.out.tfevents.1713389627.node2106.palmetto.clemson.edu.2150924.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c8e1b0aa8e0ef33ef9d4fd9595efaef754716d757a8f39a1104860c8e0f055
3
+ size 4631899
logs/events.out.tfevents.1713990817.node2090.palmetto.clemson.edu.378996.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd78b29ddaa947e5cd35136a01f2fe8608293919b67eb59a38d39af65162a4b7
3
+ size 5791
logs/events.out.tfevents.1713994423.node0275.palmetto.clemson.edu.1491152.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543756349f82cf30d3fd212fd081a57e88faf8f3e9d32c563f316ecf532e7d24
3
+ size 9119
logs/events.out.tfevents.1713995894.node0293.palmetto.clemson.edu.385138.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba042a32f02e42e45394cde56474b80c606b78830c3a66c2d1aaa9bcdbf5cb6
3
+ size 10596
logs/events.out.tfevents.1713997576.node0275.palmetto.clemson.edu.1495362.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a79e9e31a4e4da53d05c3b090631f9e7a4c1e079fc979f4eaa0edd51eeffd9f
3
+ size 16082
logs/events.out.tfevents.1714006763.node0376.palmetto.clemson.edu.3738362.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc77f91c02a1c0badaf3982f0d75d1b546bea8ef1865d170eacbba1fa213209b
3
+ size 16082
logs/events.out.tfevents.1714014803.node0373.palmetto.clemson.edu.3485540.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1cb18d7d1433556055d59b781e9ea35c631ec553f09e54a29cd67dc16e7af2b
3
+ size 5791
logs/events.out.tfevents.1714020333.node0373.palmetto.clemson.edu.3492883.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f45866a21032b5d6be5dfa400bb2d921a2e6fc123cf771eccb3920c1fdde792b
3
+ size 16564
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 sha256:4eb593f1266d4f9a5df27a641954bd8a15c2164c17a2c516b652507d5861ad67
3
+ size 1625426996
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
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
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ed76791f649f44833e37d9f4546e40b773ac4aa754c05d807f77f72eb4c3d7
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff