Hugging Face's logo

mixtralyanis
/
bart_opensource

Transformers
TensorBoard
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
mixtralyanis commited on
Commit
f3ee077
·
verified ·
1 Parent(s): 8e22283

End of training

Browse files
Files changed (11) hide show
  1. README.md +119 -0
  2. config.json +70 -0
  3. generation_config.json +16 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. runs/Feb25_17-52-10_971fc8f515f7/events.out.tfevents.1708883532.971fc8f515f7.1081.1 +3 -0
  7. special_tokens_map.json +15 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: facebook/bart-large-cnn
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: bart_opensource
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_opensource
15
+
16
+ This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0482
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: 5e-05
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 4
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 6
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 9.8079 | 0.16 | 1 | 8.9151 |
53
+ | 9.1097 | 0.32 | 2 | 8.0683 |
54
+ | 8.4063 | 0.48 | 3 | 7.6347 |
55
+ | 7.9015 | 0.63 | 4 | 7.0205 |
56
+ | 7.1888 | 0.79 | 5 | 6.2919 |
57
+ | 6.1386 | 0.95 | 6 | 5.0961 |
58
+ | 5.3555 | 1.11 | 7 | 3.9489 |
59
+ | 4.3548 | 1.27 | 8 | 3.2123 |
60
+ | 3.5788 | 1.43 | 9 | 2.1911 |
61
+ | 2.5912 | 1.58 | 10 | 1.6834 |
62
+ | 2.0914 | 1.74 | 11 | 1.3562 |
63
+ | 1.6921 | 1.9 | 12 | 1.0628 |
64
+ | 1.3658 | 2.06 | 13 | 0.8702 |
65
+ | 1.1674 | 2.22 | 14 | 0.7202 |
66
+ | 0.9204 | 2.38 | 15 | 0.5962 |
67
+ | 0.8154 | 2.53 | 16 | 0.5179 |
68
+ | 0.7057 | 2.69 | 17 | 0.4552 |
69
+ | 0.5991 | 2.85 | 18 | 0.4022 |
70
+ | 0.5438 | 3.01 | 19 | 0.3600 |
71
+ | 0.4795 | 3.17 | 20 | 0.3242 |
72
+ | 0.4323 | 3.33 | 21 | 0.2925 |
73
+ | 0.4137 | 3.49 | 22 | 0.2638 |
74
+ | 0.372 | 3.64 | 23 | 0.2373 |
75
+ | 0.3277 | 3.8 | 24 | 0.2146 |
76
+ | 0.2988 | 3.96 | 25 | 0.1970 |
77
+ | 0.2767 | 4.12 | 26 | 0.1822 |
78
+ | 0.2668 | 4.28 | 27 | 0.1686 |
79
+ | 0.2297 | 4.44 | 28 | 0.1565 |
80
+ | 0.219 | 4.59 | 29 | 0.1459 |
81
+ | 0.1973 | 4.75 | 30 | 0.1360 |
82
+ | 0.185 | 4.91 | 31 | 0.1265 |
83
+ | 0.1782 | 5.07 | 32 | 0.1179 |
84
+ | 0.1643 | 5.23 | 33 | 0.1102 |
85
+ | 0.157 | 5.39 | 34 | 0.1034 |
86
+ | 0.1449 | 5.54 | 35 | 0.0976 |
87
+ | 0.1389 | 5.7 | 36 | 0.0927 |
88
+ | 0.1292 | 5.86 | 37 | 0.0883 |
89
+ | 0.1145 | 6.02 | 38 | 0.0840 |
90
+ | 0.1143 | 6.18 | 39 | 0.0799 |
91
+ | 0.1082 | 6.34 | 40 | 0.0762 |
92
+ | 0.1048 | 6.5 | 41 | 0.0728 |
93
+ | 0.0982 | 6.65 | 42 | 0.0697 |
94
+ | 0.0974 | 6.81 | 43 | 0.0668 |
95
+ | 0.09 | 6.97 | 44 | 0.0644 |
96
+ | 0.0856 | 7.13 | 45 | 0.0624 |
97
+ | 0.0781 | 7.29 | 46 | 0.0604 |
98
+ | 0.0816 | 7.45 | 47 | 0.0586 |
99
+ | 0.0816 | 7.6 | 48 | 0.0568 |
100
+ | 0.0763 | 7.76 | 49 | 0.0554 |
101
+ | 0.0742 | 7.92 | 50 | 0.0543 |
102
+ | 0.0716 | 8.08 | 51 | 0.0531 |
103
+ | 0.068 | 8.24 | 52 | 0.0521 |
104
+ | 0.069 | 8.4 | 53 | 0.0511 |
105
+ | 0.0647 | 8.55 | 54 | 0.0504 |
106
+ | 0.0641 | 8.71 | 55 | 0.0498 |
107
+ | 0.0677 | 8.87 | 56 | 0.0494 |
108
+ | 0.0664 | 9.03 | 57 | 0.0490 |
109
+ | 0.0639 | 9.19 | 58 | 0.0486 |
110
+ | 0.0635 | 9.35 | 59 | 0.0484 |
111
+ | 0.0641 | 9.5 | 60 | 0.0482 |
112
+
113
+
114
+ ### Framework versions
115
+
116
+ - Transformers 4.38.1
117
+ - Pytorch 2.1.0+cu121
118
+ - Datasets 2.17.1
119
+ - Tokenizers 0.15.2
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": "4.38.1",
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": "4.38.1"
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:c230e7a2795d536624f553f26300e669884c4d0d6419c6d220c1c68bc7a89e9a
3
+ size 1625422896
runs/Feb25_17-52-10_971fc8f515f7/events.out.tfevents.1708883532.971fc8f515f7.1081.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33b0a244c7e209e497edaa8d0cc35cbc188fe2e383a9b2a93ef515fcc4c7f13b
3
+ size 34267
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 sha256:8b5413ff07fe00a7088ab1939f5d290dbcb3a0542a828596306bb84fa06416c3
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff