nandavikas16
commited on
Commit
•
e93d129
1
Parent(s):
312a2eb
Model save
Browse files- README.md +72 -0
- config.json +71 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/May14_17-09-05_nqek2e3cs8/events.out.tfevents.1715706664.nqek2e3cs8.366.0 +3 -0
- runs/May14_17-09-05_nqek2e3cs8/events.out.tfevents.1715707813.nqek2e3cs8.366.1 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: facebook/bart-large-cnn
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
+
model-index:
|
9 |
+
- name: bart-large-cnn-finetuned-scope1-summarization
|
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-large-cnn-finetuned-scope1-summarization
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0612
|
21 |
+
- Rouge1: 55.9874
|
22 |
+
- Rouge2: 41.0458
|
23 |
+
- Rougel: 47.6072
|
24 |
+
- Rougelsum: 47.5635
|
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: 16
|
45 |
+
- eval_batch_size: 16
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 10
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
55 |
+
| No log | 1.0 | 17 | 0.1238 | 46.7806 | 30.4394 | 36.8259 | 36.8757 |
|
56 |
+
| 0.4762 | 2.0 | 34 | 0.1058 | 49.4907 | 32.4075 | 39.352 | 39.161 |
|
57 |
+
| 0.4762 | 3.0 | 51 | 0.0899 | 54.1557 | 35.6198 | 41.6488 | 41.4013 |
|
58 |
+
| 0.1104 | 4.0 | 68 | 0.0867 | 53.237 | 36.766 | 42.8508 | 42.7151 |
|
59 |
+
| 0.1104 | 5.0 | 85 | 0.0773 | 57.4084 | 39.3354 | 45.068 | 44.9505 |
|
60 |
+
| 0.0914 | 6.0 | 102 | 0.0736 | 56.9111 | 41.3118 | 48.1607 | 47.9965 |
|
61 |
+
| 0.0914 | 7.0 | 119 | 0.0699 | 58.6135 | 42.3985 | 48.7923 | 48.4873 |
|
62 |
+
| 0.0785 | 8.0 | 136 | 0.0673 | 59.5593 | 43.9205 | 51.7275 | 51.5617 |
|
63 |
+
| 0.0785 | 9.0 | 153 | 0.0618 | 62.0583 | 47.3928 | 53.3198 | 53.1472 |
|
64 |
+
| 0.0702 | 10.0 | 170 | 0.0612 | 55.9874 | 41.0458 | 47.6072 | 47.5635 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.40.2
|
70 |
+
- Pytorch 2.3.0+cu121
|
71 |
+
- Datasets 2.19.1
|
72 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large-cnn",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
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 |
+
"force_bos_token_to_be_generated": true,
|
28 |
+
"forced_bos_token_id": 0,
|
29 |
+
"forced_eos_token_id": 2,
|
30 |
+
"gradient_checkpointing": false,
|
31 |
+
"id2label": {
|
32 |
+
"0": "LABEL_0",
|
33 |
+
"1": "LABEL_1",
|
34 |
+
"2": "LABEL_2"
|
35 |
+
},
|
36 |
+
"init_std": 0.02,
|
37 |
+
"is_encoder_decoder": true,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1,
|
41 |
+
"LABEL_2": 2
|
42 |
+
},
|
43 |
+
"length_penalty": 2.0,
|
44 |
+
"max_length": 142,
|
45 |
+
"max_position_embeddings": 1024,
|
46 |
+
"min_length": 56,
|
47 |
+
"model_type": "bart",
|
48 |
+
"no_repeat_ngram_size": 3,
|
49 |
+
"normalize_before": false,
|
50 |
+
"num_beams": 4,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"output_past": true,
|
53 |
+
"pad_token_id": 1,
|
54 |
+
"prefix": " ",
|
55 |
+
"pretraining_tp": 1,
|
56 |
+
"scale_embedding": false,
|
57 |
+
"task_specific_params": {
|
58 |
+
"summarization": {
|
59 |
+
"early_stopping": true,
|
60 |
+
"length_penalty": 2.0,
|
61 |
+
"max_length": 142,
|
62 |
+
"min_length": 56,
|
63 |
+
"no_repeat_ngram_size": 3,
|
64 |
+
"num_beams": 4
|
65 |
+
}
|
66 |
+
},
|
67 |
+
"torch_dtype": "float32",
|
68 |
+
"transformers_version": "4.40.2",
|
69 |
+
"use_cache": false,
|
70 |
+
"vocab_size": 50264
|
71 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"length_penalty": 2.0,
|
9 |
+
"max_length": 142,
|
10 |
+
"min_length": 56,
|
11 |
+
"no_repeat_ngram_size": 3,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 1,
|
14 |
+
"transformers_version": "4.40.2",
|
15 |
+
"use_cache": false
|
16 |
+
}
|
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:dfc76fbcf34566cbdf198262b5f2b4cf6a41ebbfd3ed54b2470a39ec8700fc0b
|
3 |
+
size 1625422896
|
runs/May14_17-09-05_nqek2e3cs8/events.out.tfevents.1715706664.nqek2e3cs8.366.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddd0f9569f9e0836793771f32aefe801c299fce0ea123c4e77885d70ffc183ba
|
3 |
+
size 11981
|
runs/May14_17-09-05_nqek2e3cs8/events.out.tfevents.1715707813.nqek2e3cs8.366.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f2d8bf1db36dd82d855396487ae590b36030c2a64029698a6e15f27d45bba33
|
3 |
+
size 514
|
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": "</s>",
|
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": "</s>",
|
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:e48750928b539ad2b000838e912669b7fa49d7cb353fe6e1b36d498bf9bbdfec
|
3 |
+
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|