Model save
Browse files- README.md +98 -0
- final/config.json +33 -0
- final/model.safetensors +3 -0
- final/special_tokens_map.json +37 -0
- final/tokenizer.json +0 -0
- final/tokenizer_config.json +62 -0
- final/training_args.bin +3 -0
- final/vocab.txt +0 -0
- 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:
|
3 |
size 437955572
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8fe896582277f741e6b0cc49f49febb06555ff62d9b22c060590dce312049eb
|
3 |
size 437955572
|