Hugging Face's logo

onionLad
/
generalize-bart

Translation
Transformers
TensorBoard
Safetensors
bart
text2text-generation
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
onionLad commited on
Commit
679e6a3
•
1 Parent(s): 998e491

Training complete

Browse files
Files changed (26) hide show
  1. README.md +53 -0
  2. config.json +75 -0
  3. generation_config.json +13 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. runs/Jul24_14-18-06_cn2350/events.out.tfevents.1721845122.cn2350.6808.0 +3 -0
  7. runs/Jul24_14-25-49_cn2350/events.out.tfevents.1721845554.cn2350.8474.0 +3 -0
  8. runs/Jul24_14-28-07_cn2350/events.out.tfevents.1721845691.cn2350.8593.0 +3 -0
  9. runs/Jul24_16-50-53_cn0828/events.out.tfevents.1721854260.cn0828.2653521.0 +3 -0
  10. runs/Jul24_16-59-55_cn0828/events.out.tfevents.1721854799.cn0828.2654202.0 +3 -0
  11. runs/Jul24_17-04-22_cn0828/events.out.tfevents.1721855068.cn0828.2654332.0 +3 -0
  12. runs/Jul25_09-45-12_cn1102/events.out.tfevents.1721915118.cn1102.1923022.0 +3 -0
  13. runs/Jul25_09-48-02_cn1102/events.out.tfevents.1721915284.cn1102.1923224.0 +3 -0
  14. runs/Jul25_09-48-49_cn1102/events.out.tfevents.1721915331.cn1102.1923314.0 +3 -0
  15. runs/Jul25_09-50-47_cn1102/events.out.tfevents.1721915450.cn1102.1923449.0 +3 -0
  16. runs/Jul25_09-54-16_cn1102/events.out.tfevents.1721915662.cn1102.1923541.0 +3 -0
  17. runs/Jul25_10-04-26_cn1102/events.out.tfevents.1721916269.cn1102.1923699.0 +3 -0
  18. runs/Jul25_10-16-39_cn1102/events.out.tfevents.1721917004.cn1102.1924259.0 +3 -0
  19. runs/Jul25_10-18-00_cn1102/events.out.tfevents.1721917084.cn1102.1924683.0 +3 -0
  20. runs/Jul25_15-17-12_cn2350/events.out.tfevents.1721935038.cn2350.223076.0 +3 -0
  21. runs/Jul25_15-32-31_cn2350/events.out.tfevents.1721935954.cn2350.223076.1 +3 -0
  22. special_tokens_map.json +15 -0
  23. tokenizer.json +0 -0
  24. tokenizer_config.json +57 -0
  25. training_args.bin +3 -0
  26. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/bart-base
4
+ tags:
5
+ - translation
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: generalize-bart
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # generalize-bart
16
+
17
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.41.0
51
+ - Pytorch 1.11.0
52
+ - Datasets 2.19.1
53
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
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": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
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
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.41.0",
73
+ "use_cache": true,
74
+ "vocab_size": 50265
75
+ }
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": "4.41.0"
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 sha256:56ee32b7737c3d4ee31999af870ac4bd8ecde51c47601930c358f8833262b794
3
+ size 557912620
runs/Jul24_14-18-06_cn2350/events.out.tfevents.1721845122.cn2350.6808.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2940566dc1b3280fe489eac9d8d028de6a6e8bee0b70b6311483a12bbf61f99
3
+ size 5917
runs/Jul24_14-25-49_cn2350/events.out.tfevents.1721845554.cn2350.8474.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1beb6034bb2c00629b66ffb45fd1ea4049e6dd670b3d5906d98a410c513aef
3
+ size 5915
runs/Jul24_14-28-07_cn2350/events.out.tfevents.1721845691.cn2350.8593.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5a2108bc4152b68b6554a081ba8e5eb81a98e26fee3b4c5f17f1905e3b0fa8
3
+ size 5920
runs/Jul24_16-50-53_cn0828/events.out.tfevents.1721854260.cn0828.2653521.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2534d6993b7327ea91fe44cd635b677049fdabdc3d847a70bd4bf8befaa31e48
3
+ size 40
runs/Jul24_16-59-55_cn0828/events.out.tfevents.1721854799.cn0828.2654202.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44580c7e196b3e4bf92c118093cc05a5c08ea762e3e6cc229559685fb7e708c8
3
+ size 40
runs/Jul24_17-04-22_cn0828/events.out.tfevents.1721855068.cn0828.2654332.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb044de0cc8bd2c771ce29329413672e67c6be1400c9c58fb87e06fd3802181
3
+ size 40
runs/Jul25_09-45-12_cn1102/events.out.tfevents.1721915118.cn1102.1923022.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb91ad728861f1af1584e89d697ac785b95e37d1bab8d501f1433b96f74802f
3
+ size 40
runs/Jul25_09-48-02_cn1102/events.out.tfevents.1721915284.cn1102.1923224.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f77bb157c7bb4d65f3eeff8fa8f2ed3a5326f84002ba1dddecc919e891fb9f
3
+ size 40
runs/Jul25_09-48-49_cn1102/events.out.tfevents.1721915331.cn1102.1923314.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e31f5b0f64d4bd47cd189bf7d4d7d87f7a9f69b59d078e09b7a434ec5564905
3
+ size 40
runs/Jul25_09-50-47_cn1102/events.out.tfevents.1721915450.cn1102.1923449.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2533a98b118f1db20979c0db6107345ab8b3d6ff531c8df1ff3b0966b61a051
3
+ size 40
runs/Jul25_09-54-16_cn1102/events.out.tfevents.1721915662.cn1102.1923541.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd5c4ebae0413b2062803231a0c7d81612540209d24444d4e3b951cd28512b1
3
+ size 40
runs/Jul25_10-04-26_cn1102/events.out.tfevents.1721916269.cn1102.1923699.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c4a720a7b04aa6e32d6ff1a07f25ca5f8f12b66b238e0369259f759212a73d
3
+ size 40
runs/Jul25_10-16-39_cn1102/events.out.tfevents.1721917004.cn1102.1924259.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c1c7230c8db7e3dd54d81de38f19d17f465971a8637da14715a788b7577327
3
+ size 40
runs/Jul25_10-18-00_cn1102/events.out.tfevents.1721917084.cn1102.1924683.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f106712b1daf432bc7750729c2836ea66745dd6517f1c211643f8d7da74de9
3
+ size 40
runs/Jul25_15-17-12_cn2350/events.out.tfevents.1721935038.cn2350.223076.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5f751600817ee63d75c4494aa45eeba2933c88da29c78bdb935e901aeb443f
3
+ size 5976
runs/Jul25_15-32-31_cn2350/events.out.tfevents.1721935954.cn2350.223076.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46e33efa8e276e5300465c08c2cb7e6fee0b465946f0d143ce2c6dbf855425cf
3
+ size 6328
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": 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 sha256:359cafd59a26cc945048f1bbe9609143ffccc6900c4eaedcd8b3c679cd885e85
3
+ size 4783
vocab.json ADDED
The diff for this file is too large to render. See raw diff