End of training
Browse files- README.md +87 -0
- config.json +70 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model.safetensors +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 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: facebook/bart-large-cnn
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
+
- bleu
|
9 |
+
model-index:
|
10 |
+
- name: PhysicalScienceBARTPrincipal
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# PhysicalScienceBARTPrincipal
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 4.5862
|
22 |
+
- Rouge1: 49.7214
|
23 |
+
- Rouge2: 15.9205
|
24 |
+
- Rougel: 34.8099
|
25 |
+
- Rougelsum: 45.9442
|
26 |
+
- Bertscore Precision: 81.8626
|
27 |
+
- Bertscore Recall: 83.3072
|
28 |
+
- Bertscore F1: 82.5744
|
29 |
+
- Bleu: 0.1065
|
30 |
+
- Gen Len: 196.3779
|
31 |
+
|
32 |
+
## Model description
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Intended uses & limitations
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training and evaluation data
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training procedure
|
45 |
+
|
46 |
+
### Training hyperparameters
|
47 |
+
|
48 |
+
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 5e-05
|
50 |
+
- train_batch_size: 1
|
51 |
+
- eval_batch_size: 1
|
52 |
+
- seed: 42
|
53 |
+
- gradient_accumulation_steps: 16
|
54 |
+
- total_train_batch_size: 16
|
55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
+
- lr_scheduler_type: linear
|
57 |
+
- lr_scheduler_warmup_steps: 500
|
58 |
+
- num_epochs: 1
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore Precision | Bertscore Recall | Bertscore F1 | Bleu | Gen Len |
|
63 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------------------:|:----------------:|:------------:|:------:|:--------:|
|
64 |
+
| 6.4881 | 0.0620 | 100 | 6.2790 | 38.9402 | 10.9737 | 28.0473 | 36.4124 | 78.6712 | 80.7927 | 79.7123 | 0.0702 | 196.3779 |
|
65 |
+
| 5.9838 | 0.1239 | 200 | 5.8574 | 39.6094 | 11.61 | 28.6653 | 36.6426 | 78.5563 | 81.2374 | 79.8672 | 0.0773 | 196.3779 |
|
66 |
+
| 5.5757 | 0.1859 | 300 | 5.5425 | 43.235 | 12.5595 | 30.3069 | 40.1431 | 79.7016 | 81.7103 | 80.6878 | 0.0826 | 196.3779 |
|
67 |
+
| 5.4752 | 0.2478 | 400 | 5.3518 | 45.0647 | 13.1878 | 31.0925 | 41.4826 | 79.7122 | 82.0455 | 80.8554 | 0.0880 | 196.3779 |
|
68 |
+
| 5.3711 | 0.3098 | 500 | 5.2193 | 47.1793 | 13.5223 | 31.7989 | 43.5774 | 80.6424 | 82.3476 | 81.4813 | 0.0892 | 196.3779 |
|
69 |
+
| 5.1653 | 0.3717 | 600 | 5.0858 | 45.2081 | 13.4909 | 31.8919 | 41.7813 | 80.7104 | 82.4561 | 81.5689 | 0.0897 | 196.3779 |
|
70 |
+
| 5.0684 | 0.4337 | 700 | 4.9837 | 46.4035 | 14.2034 | 32.654 | 42.8883 | 80.4628 | 82.4529 | 81.4399 | 0.0941 | 196.3779 |
|
71 |
+
| 4.9625 | 0.4957 | 800 | 4.9084 | 48.2088 | 14.8904 | 33.2025 | 44.5397 | 81.1668 | 82.8469 | 81.9935 | 0.0986 | 196.3779 |
|
72 |
+
| 4.8858 | 0.5576 | 900 | 4.8370 | 48.5919 | 14.7721 | 33.5041 | 44.7923 | 81.2656 | 82.8635 | 82.0522 | 0.0974 | 196.3779 |
|
73 |
+
| 4.8251 | 0.6196 | 1000 | 4.7813 | 49.2512 | 15.4584 | 34.0164 | 45.5215 | 81.4958 | 83.0067 | 82.2398 | 0.1030 | 196.3779 |
|
74 |
+
| 4.8581 | 0.6815 | 1100 | 4.7307 | 48.7203 | 15.379 | 34.0451 | 45.0395 | 81.7154 | 83.106 | 82.4008 | 0.1027 | 196.3779 |
|
75 |
+
| 4.7934 | 0.7435 | 1200 | 4.6861 | 49.5987 | 15.6207 | 34.3261 | 45.8512 | 81.7656 | 83.1546 | 82.4502 | 0.1042 | 196.3779 |
|
76 |
+
| 4.7163 | 0.8055 | 1300 | 4.6518 | 48.9818 | 15.5333 | 34.3788 | 45.3444 | 81.6763 | 83.1451 | 82.3998 | 0.1039 | 196.3779 |
|
77 |
+
| 4.6855 | 0.8674 | 1400 | 4.6199 | 49.1462 | 15.5914 | 34.5149 | 45.5788 | 81.7027 | 83.1199 | 82.401 | 0.1037 | 196.3779 |
|
78 |
+
| 4.615 | 0.9294 | 1500 | 4.5987 | 49.6903 | 15.8973 | 34.7628 | 45.9111 | 81.8545 | 83.302 | 82.5678 | 0.1064 | 196.3779 |
|
79 |
+
| 4.5964 | 0.9913 | 1600 | 4.5862 | 49.7214 | 15.9205 | 34.8099 | 45.9442 | 81.8626 | 83.3072 | 82.5744 | 0.1065 | 196.3779 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.41.2
|
85 |
+
- Pytorch 2.3.1+cu121
|
86 |
+
- Datasets 2.20.0
|
87 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"scale_embedding": false,
|
56 |
+
"task_specific_params": {
|
57 |
+
"summarization": {
|
58 |
+
"early_stopping": true,
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"no_repeat_ngram_size": 3,
|
63 |
+
"num_beams": 4
|
64 |
+
}
|
65 |
+
},
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.41.2",
|
68 |
+
"use_cache": true,
|
69 |
+
"vocab_size": 50264
|
70 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"length_penalty": 2.0,
|
10 |
+
"max_length": 142,
|
11 |
+
"min_length": 56,
|
12 |
+
"no_repeat_ngram_size": 3,
|
13 |
+
"num_beams": 4,
|
14 |
+
"pad_token_id": 1,
|
15 |
+
"transformers_version": "4.41.2"
|
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 sha256:73e3f0ead0db1bee980c4e40884bfff49a6ce84a111373dbcedaf30670b2ebf7
|
3 |
+
size 1625422896
|
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 |
+
"4": {
|
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 sha256:85bb2898b85f138ac5134134a437ce8ef5daf74c7148dbe50effe1aeb259670c
|
3 |
+
size 5112
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|