MikaSie commited on
Commit
2a30fc7
1 Parent(s): e9ca481

End of training

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/bart-large
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - arrow
8
+ model-index:
9
+ - name: LexLM_Longformer_BART_hybrid_V1
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
+ # LexLM_Longformer_BART_hybrid_V1
17
+
18
+ This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the arrow dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.0869
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 40
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 4.0806 | 1.0 | 69 | 2.3843 |
53
+ | 2.4153 | 2.0 | 138 | 2.1901 |
54
+ | 2.1675 | 3.0 | 207 | 2.1073 |
55
+ | 2.024 | 4.0 | 276 | 2.0852 |
56
+ | 1.8995 | 5.0 | 345 | 2.0690 |
57
+ | 1.7917 | 6.0 | 414 | 2.0499 |
58
+ | 1.7063 | 7.0 | 483 | 2.0448 |
59
+ | 1.6201 | 8.0 | 552 | 2.0468 |
60
+ | 1.5533 | 9.0 | 621 | 2.0546 |
61
+ | 1.4816 | 10.0 | 690 | 2.0826 |
62
+ | 1.4184 | 11.0 | 759 | 2.0995 |
63
+ | 1.3638 | 12.0 | 828 | 2.0869 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.40.1
69
+ - Pytorch 2.2.1+cu121
70
+ - Datasets 2.17.1
71
+ - Tokenizers 0.19.1
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": "4.40.1",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
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": "4.40.1"
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 sha256:8f641a8984bf3978296b9a9f9a656cdb82c6ec189a99e66960df10d5ad3105c2
3
+ size 1625426996
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": 1024,
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 sha256:8a48dada118226f065041454b220d49b49b45d44827ec0ed7bf3852a54a91448
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff