Hugging Face's logo

KanisornPutta
/
MichaelPorterJrBERT

Question Answering
Transformers
TensorBoard
Safetensors
mpnet
Generated from Trainer
Model card Files
xet
 Metrics Community
KanisornPutta commited on
Commit
4e1f362
路
verified 路
1 Parent(s): 6c33935

MichaelPorterJrBERT

Browse files
Files changed (19) hide show
  1. README.md +59 -0
  2. config.json +23 -0
  3. model.safetensors +3 -0
  4. runs/May09_09-29-45_018d82d9deea/events.out.tfevents.1746783000.018d82d9deea.31.0 +3 -0
  5. runs/May09_09-30-27_018d82d9deea/events.out.tfevents.1746783034.018d82d9deea.31.1 +3 -0
  6. runs/May09_09-30-27_018d82d9deea/events.out.tfevents.1746783080.018d82d9deea.31.2 +3 -0
  7. runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746786910.018d82d9deea.31.3 +3 -0
  8. runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787021.018d82d9deea.31.4 +3 -0
  9. runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787103.018d82d9deea.31.5 +3 -0
  10. runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787272.018d82d9deea.31.6 +3 -0
  11. runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787373.018d82d9deea.31.7 +3 -0
  12. runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787632.018d82d9deea.31.8 +3 -0
  13. runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787732.018d82d9deea.31.9 +3 -0
  14. runs/May09_10-53-03_018d82d9deea/events.out.tfevents.1746787992.018d82d9deea.31.10 +3 -0
  15. special_tokens_map.json +51 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +73 -0
  18. training_args.bin +3 -0
  19. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: sentence-transformers/all-mpnet-base-v2
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: weights
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
+ # weights
16
+
17
+ This model is a fine-tuned version of [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.5439
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 32
40
+ - eval_batch_size: 32
41
+ - seed: 42
42
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 2
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 0.7022 | 1.0 | 2500 | 0.6527 |
51
+ | 0.5206 | 2.0 | 5000 | 0.5439 |
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.51.1
57
+ - Pytorch 2.5.1+cu124
58
+ - Datasets 3.5.0
59
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MPNetForQuestionAnswering"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 514,
15
+ "model_type": "mpnet",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 1,
19
+ "relative_attention_num_buckets": 32,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.51.1",
22
+ "vocab_size": 30527
23
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27db5cc258c3111ccf817e811e791e6dbce3e1fa2cba0906a5e8b793b8224f4
3
+ size 435612632
runs/May09_09-29-45_018d82d9deea/events.out.tfevents.1746783000.018d82d9deea.31.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2afa76695fd86e82523d26e62791bd082edf6f7366dd88907d2c4c1f9f0c17
3
+ size 4868
runs/May09_09-30-27_018d82d9deea/events.out.tfevents.1746783034.018d82d9deea.31.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0c60afcc6840b467f08001a80dae898760dcb6ba3dbbf7971ea5c4c2b11613
3
+ size 4868
runs/May09_09-30-27_018d82d9deea/events.out.tfevents.1746783080.018d82d9deea.31.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0639fc0d2a92c24953cb4881d33830fe6896d83d76436817c1e5eddbc0146a39
3
+ size 10139
runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746786910.018d82d9deea.31.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5384f2ab4d51fc5f430bd4dbf6b96738894f699013b455d2f296d0c4b2dee38
3
+ size 4868
runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787021.018d82d9deea.31.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bdbcd9562140c80e86aed13fabbea62b314d9e9d6dae92a484fc6e3ea7750b
3
+ size 4868
runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787103.018d82d9deea.31.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c77797cedd10238e8904f9f1bfb4d0d949f177926df65085ff01e4959d1a44
3
+ size 4868
runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787272.018d82d9deea.31.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240c18e65385718923e9d1ac8c5dce499265ade36c45072f447b9f199f03f6fb
3
+ size 4868
runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787373.018d82d9deea.31.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a831156d0d526c675dcd57ed7d84b04343e78e92e25eb0c2f7da150b9afbca24
3
+ size 4868
runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787632.018d82d9deea.31.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f774cc627da1e6754aad29ff205e64dabbdd8fcb08d2ca1770a56e5fa40ba7e3
3
+ size 4868
runs/May09_10-34-56_018d82d9deea/events.out.tfevents.1746787732.018d82d9deea.31.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665bd3cc0edfa196f12b4f524e7b85079703c30b2782e9d9e3f05ba97cf668f2
3
+ size 5134
runs/May09_10-53-03_018d82d9deea/events.out.tfevents.1746787992.018d82d9deea.31.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7487a71b094a2330bbccc7a8dc88f52cdf730772a67307dcc403f4230bf72d22
3
+ size 16310
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": false,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "extra_special_tokens": {},
58
+ "mask_token": "<mask>",
59
+ "max_length": 128,
60
+ "model_max_length": 512,
61
+ "pad_to_multiple_of": null,
62
+ "pad_token": "<pad>",
63
+ "pad_token_type_id": 0,
64
+ "padding_side": "right",
65
+ "sep_token": "</s>",
66
+ "stride": 0,
67
+ "strip_accents": null,
68
+ "tokenize_chinese_chars": true,
69
+ "tokenizer_class": "MPNetTokenizer",
70
+ "truncation_side": "right",
71
+ "truncation_strategy": "longest_first",
72
+ "unk_token": "[UNK]"
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f457c313efc113a4defa5b1ccfdc653adb70ea64a78a8736ff03a618fde5b907
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff