Hugging Face's logo

HuggingFaceTB
/
python-edu-scorer

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
anton-l HF staff commited on
Commit
7a311db
•
1 Parent(s): 603e561

Model save

Browse files
Files changed (9) hide show
  1. README.md +98 -0
  2. final/config.json +33 -0
  3. final/model.safetensors +3 -0
  4. final/special_tokens_map.json +37 -0
  5. final/tokenizer.json +0 -0
  6. final/tokenizer_config.json +62 -0
  7. final/training_args.bin +3 -0
  8. final/vocab.txt +0 -0
  9. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Snowflake/snowflake-arctic-embed-m
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - accuracy
10
+ model-index:
11
+ - name: stack-edu-scorer
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # stack-edu-scorer
19
+
20
+ This model is a fine-tuned version of [Snowflake/snowflake-arctic-embed-m](https://huggingface.co/Snowflake/snowflake-arctic-embed-m) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3426
23
+ - Precision: 0.5188
24
+ - Recall: 0.3971
25
+ - F1 Macro: 0.4258
26
+ - Accuracy: 0.6350
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 0.0003
46
+ - train_batch_size: 256
47
+ - eval_batch_size: 128
48
+ - seed: 0
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 20
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
56
+ |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:--------:|:--------:|
57
+ | 0.3973 | 0.5787 | 1000 | 0.3904 | 0.4701 | 0.3433 | 0.3701 | 0.5885 |
58
+ | 0.3848 | 1.1574 | 2000 | 0.3803 | 0.5107 | 0.3574 | 0.3863 | 0.5974 |
59
+ | 0.3667 | 1.7361 | 3000 | 0.3715 | 0.6471 | 0.4478 | 0.4879 | 0.6103 |
60
+ | 0.3727 | 2.3148 | 4000 | 0.3655 | 0.6140 | 0.4375 | 0.4715 | 0.6121 |
61
+ | 0.3639 | 2.8935 | 5000 | 0.3617 | 0.6234 | 0.4519 | 0.4879 | 0.6176 |
62
+ | 0.3684 | 3.4722 | 6000 | 0.3626 | 0.6424 | 0.4632 | 0.5020 | 0.6211 |
63
+ | 0.3557 | 4.0509 | 7000 | 0.3589 | 0.5519 | 0.3739 | 0.4032 | 0.6175 |
64
+ | 0.3513 | 4.6296 | 8000 | 0.3650 | 0.6328 | 0.4671 | 0.5010 | 0.6241 |
65
+ | 0.3505 | 5.2083 | 9000 | 0.3535 | 0.5320 | 0.3850 | 0.4129 | 0.6259 |
66
+ | 0.3549 | 5.7870 | 10000 | 0.3526 | 0.6358 | 0.4588 | 0.4949 | 0.6248 |
67
+ | 0.3465 | 6.3657 | 11000 | 0.3580 | 0.5204 | 0.3712 | 0.3970 | 0.6166 |
68
+ | 0.3468 | 6.9444 | 12000 | 0.3498 | 0.5266 | 0.3936 | 0.4235 | 0.6293 |
69
+ | 0.3463 | 7.5231 | 13000 | 0.3497 | 0.6837 | 0.4661 | 0.4999 | 0.6300 |
70
+ | 0.3404 | 8.1019 | 14000 | 0.3557 | 0.6169 | 0.4940 | 0.5285 | 0.6307 |
71
+ | 0.3381 | 8.6806 | 15000 | 0.3493 | 0.5124 | 0.3871 | 0.4135 | 0.6290 |
72
+ | 0.342 | 9.2593 | 16000 | 0.3482 | 0.5265 | 0.3959 | 0.4247 | 0.6337 |
73
+ | 0.3397 | 9.8380 | 17000 | 0.3477 | 0.5210 | 0.3919 | 0.4191 | 0.6325 |
74
+ | 0.3407 | 10.4167 | 18000 | 0.3465 | 0.5380 | 0.3895 | 0.4202 | 0.6297 |
75
+ | 0.3303 | 10.9954 | 19000 | 0.3471 | 0.5273 | 0.3952 | 0.4234 | 0.6355 |
76
+ | 0.3296 | 11.5741 | 20000 | 0.3447 | 0.5428 | 0.3891 | 0.4173 | 0.6313 |
77
+ | 0.3299 | 12.1528 | 21000 | 0.3451 | 0.5173 | 0.3964 | 0.4248 | 0.6347 |
78
+ | 0.3316 | 12.7315 | 22000 | 0.3448 | 0.6321 | 0.4809 | 0.5167 | 0.6350 |
79
+ | 0.3289 | 13.3102 | 23000 | 0.3446 | 0.5100 | 0.3969 | 0.4242 | 0.6358 |
80
+ | 0.3278 | 13.8889 | 24000 | 0.3445 | 0.5451 | 0.3918 | 0.4223 | 0.6327 |
81
+ | 0.3249 | 14.4676 | 25000 | 0.3440 | 0.5282 | 0.3915 | 0.4194 | 0.6343 |
82
+ | 0.328 | 15.0463 | 26000 | 0.3438 | 0.5670 | 0.3880 | 0.4183 | 0.6316 |
83
+ | 0.3263 | 15.625 | 27000 | 0.3448 | 0.6290 | 0.4828 | 0.5191 | 0.6363 |
84
+ | 0.3243 | 16.2037 | 28000 | 0.3437 | 0.5534 | 0.3950 | 0.4252 | 0.6356 |
85
+ | 0.3265 | 16.7824 | 29000 | 0.3435 | 0.5432 | 0.3926 | 0.4217 | 0.6328 |
86
+ | 0.3193 | 17.3611 | 30000 | 0.3432 | 0.5231 | 0.3962 | 0.4238 | 0.6348 |
87
+ | 0.3261 | 17.9398 | 31000 | 0.3433 | 0.5517 | 0.3933 | 0.4235 | 0.6326 |
88
+ | 0.317 | 18.5185 | 32000 | 0.3431 | 0.5527 | 0.3929 | 0.4220 | 0.6334 |
89
+ | 0.3222 | 19.0972 | 33000 | 0.3429 | 0.5132 | 0.3976 | 0.4259 | 0.6357 |
90
+ | 0.3223 | 19.6759 | 34000 | 0.3426 | 0.5188 | 0.3971 | 0.4258 | 0.6350 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.40.1
96
+ - Pytorch 2.2.0+cu121
97
+ - Datasets 2.17.1
98
+ - Tokenizers 0.19.1
final/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Snowflake/snowflake-arctic-embed-m",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": 0.0,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "problem_type": "regression",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.40.1",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
final/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8fe896582277f741e6b0cc49f49febb06555ff62d9b22c060590dce312049eb
3
+ size 437955572
final/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
final/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 512,
49
+ "model_max_length": 512,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
final/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b672b5ef7540dbeb34cfe2d7a27c10448c4f1aed185a491f340a3cf0f78b671b
3
+ size 5048
final/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92c5b7759d996f2e4969060ee9fbde9f51dde033c5e85f44a46640c9d140c90c
3
  size 437955572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8fe896582277f741e6b0cc49f49febb06555ff62d9b22c060590dce312049eb
3
  size 437955572