aparajitha commited on
Commit
1906458
1 Parent(s): 6e1e0b6

aparajitha/bart-base-sci-tr

Browse files
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/bart-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: bart-base-sci-tr
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # bart-base-sci-tr
15
+
16
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.7617
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 4
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 30
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 3.5107 | 1.0 | 1393 | 3.0242 |
50
+ | 3.1138 | 2.0 | 2786 | 2.8770 |
51
+ | 2.9345 | 3.0 | 4179 | 2.8069 |
52
+ | 2.8044 | 4.0 | 5572 | 2.7668 |
53
+ | 2.7227 | 5.0 | 6965 | 2.7336 |
54
+ | 2.6341 | 6.0 | 8358 | 2.7276 |
55
+ | 2.5523 | 7.0 | 9751 | 2.7026 |
56
+ | 2.4846 | 8.0 | 11144 | 2.6961 |
57
+ | 2.4409 | 9.0 | 12537 | 2.6894 |
58
+ | 2.3699 | 10.0 | 13930 | 2.6853 |
59
+ | 2.3305 | 11.0 | 15323 | 2.6869 |
60
+ | 2.2822 | 12.0 | 16716 | 2.6924 |
61
+ | 2.2392 | 13.0 | 18109 | 2.7042 |
62
+ | 2.1889 | 14.0 | 19502 | 2.6943 |
63
+ | 2.1593 | 15.0 | 20895 | 2.6988 |
64
+ | 2.1228 | 16.0 | 22288 | 2.7032 |
65
+ | 2.0791 | 17.0 | 23681 | 2.7083 |
66
+ | 2.0594 | 18.0 | 25074 | 2.7034 |
67
+ | 2.0239 | 19.0 | 26467 | 2.7182 |
68
+ | 1.9943 | 20.0 | 27860 | 2.7235 |
69
+ | 1.9746 | 21.0 | 29253 | 2.7279 |
70
+ | 1.9624 | 22.0 | 30646 | 2.7337 |
71
+ | 1.9433 | 23.0 | 32039 | 2.7400 |
72
+ | 1.9138 | 24.0 | 33432 | 2.7457 |
73
+ | 1.8971 | 25.0 | 34825 | 2.7489 |
74
+ | 1.8896 | 26.0 | 36218 | 2.7527 |
75
+ | 1.873 | 27.0 | 37611 | 2.7576 |
76
+ | 1.8585 | 28.0 | 39004 | 2.7577 |
77
+ | 1.8564 | 29.0 | 40397 | 2.7594 |
78
+ | 1.852 | 30.0 | 41790 | 2.7617 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.43.4
84
+ - Pytorch 1.13.1
85
+ - Datasets 2.12.0
86
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
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": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
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
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.43.4",
73
+ "use_cache": true,
74
+ "vocab_size": 50265
75
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.43.4"
13
+ }
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 sha256:89931dde77e6e98b76977db3a7f9c6046dd95fce835dca69153b7681d15da1b6
3
+ size 557912620
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b5baab49dd2f1f45d5921780132a1d81ae941df68bb7736db9290f4692a891
3
+ size 4859
vocab.json ADDED
The diff for this file is too large to render. See raw diff