saikancharlareddy commited on
Commit
cf9d4fa
1 Parent(s): e082eea

Model save

Browse files
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/bart-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: bart-base-finetuned-BBC
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # bart-base-finetuned-BBC
17
+
18
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2173
21
+ - Rouge1: 0.169
22
+ - Rouge2: 0.1419
23
+ - Rougel: 0.1624
24
+ - Rougelsum: 0.1651
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5.6e-05
44
+ - train_batch_size: 8
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 8
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
55
+ | 1.0798 | 1.0 | 7 | 0.4261 | 0.1312 | 0.0749 | 0.0947 | 0.0967 |
56
+ | 0.4858 | 2.0 | 14 | 0.2775 | 0.1419 | 0.1037 | 0.1285 | 0.1288 |
57
+ | 0.3719 | 3.0 | 21 | 0.2435 | 0.16 | 0.1307 | 0.151 | 0.1523 |
58
+ | 0.298 | 4.0 | 28 | 0.2311 | 0.1619 | 0.1292 | 0.1527 | 0.1554 |
59
+ | 0.2607 | 5.0 | 35 | 0.2318 | 0.1593 | 0.1259 | 0.1493 | 0.1526 |
60
+ | 0.2276 | 6.0 | 42 | 0.2211 | 0.1566 | 0.1259 | 0.1479 | 0.151 |
61
+ | 0.2173 | 7.0 | 49 | 0.2177 | 0.169 | 0.1419 | 0.1624 | 0.1651 |
62
+ | 0.1801 | 8.0 | 56 | 0.2173 | 0.169 | 0.1419 | 0.1624 | 0.1651 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.40.1
68
+ - Pytorch 2.2.1+cu121
69
+ - Datasets 2.19.0
70
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -69,7 +69,7 @@
69
  }
70
  },
71
  "torch_dtype": "float32",
72
- "transformers_version": "4.30.2",
73
  "use_cache": true,
74
  "vocab_size": 50265
75
  }
 
69
  }
70
  },
71
  "torch_dtype": "float32",
72
+ "transformers_version": "4.40.1",
73
  "use_cache": true,
74
  "vocab_size": 50265
75
  }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 0,
7
+ "forced_eos_token_id": 2,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.40.1"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bd23704e502324c63ccd7cd8345747817a30aa2dd86cef385b755ae9bb48547
3
+ size 557912620
runs/Apr28_03-28-28_2458b2b7b46d/events.out.tfevents.1714274909.2458b2b7b46d.4428.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c36c0885d5cd8d7155df924c1bcf70103b23b75fdccb038eab8ac3f51e7db0c
3
+ size 11876
runs/Apr28_04-05-29_2458b2b7b46d/events.out.tfevents.1714277129.2458b2b7b46d.4428.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0862c8c636a56090726f9534342a5aff1f869cb7fa661b16b4cc12a3212a7f
3
+ size 11876
special_tokens_map.json CHANGED
@@ -5,7 +5,7 @@
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
8
- "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
8
+ "normalized": true,
9
  "rstrip": false,
10
  "single_word": false
11
  },
tokenizer.json CHANGED
@@ -14,7 +14,7 @@
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
- "normalized": false,
18
  "special": true
19
  },
20
  {
@@ -23,7 +23,7 @@
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
- "normalized": false,
27
  "special": true
28
  },
29
  {
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
- "normalized": false,
36
  "special": true
37
  },
38
  {
@@ -41,7 +41,7 @@
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
- "normalized": false,
45
  "special": true
46
  },
47
  {
@@ -50,7 +50,7 @@
50
  "single_word": false,
51
  "lstrip": true,
52
  "rstrip": false,
53
- "normalized": false,
54
  "special": true
55
  }
56
  ],
@@ -88,6 +88,7 @@
88
  "end_of_word_suffix": "",
89
  "fuse_unk": false,
90
  "byte_fallback": false,
 
91
  "vocab": {
92
  "<s>": 0,
93
  "<pad>": 1,
 
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
+ "normalized": true,
18
  "special": true
19
  },
20
  {
 
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
+ "normalized": true,
27
  "special": true
28
  },
29
  {
 
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
+ "normalized": true,
36
  "special": true
37
  },
38
  {
 
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
+ "normalized": true,
45
  "special": true
46
  },
47
  {
 
50
  "single_word": false,
51
  "lstrip": true,
52
  "rstrip": false,
53
+ "normalized": true,
54
  "special": true
55
  }
56
  ],
 
88
  "end_of_word_suffix": "",
89
  "fuse_unk": false,
90
  "byte_fallback": false,
91
+ "ignore_merges": false,
92
  "vocab": {
93
  "<s>": 0,
94
  "<pad>": 1,
tokenizer_config.json CHANGED
@@ -1,12 +1,54 @@
1
  {
2
  "add_prefix_space": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
  "errors": "replace",
8
  "mask_token": "<mask>",
9
- "model_max_length": 1024,
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
12
  "tokenizer_class": "BartTokenizer",
 
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",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:311532d4bc359a94e718007e2fb8f967f9059b58fc1eac964d0d427b4d5be7cd
3
- size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926eb54d443a731e4c9c91da1dc8db877befe79def6dbf8c9cc96cd9e980c9ae
3
+ size 5176