Hugging Face's logo

nzm97
/
math_question_grade_detection_v12-15-24

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
nzm97 commited on
Commit
e43a260
·
verified ·
1 Parent(s): f399364

Initial model push after training

Browse files
Files changed (6) hide show
  1. README.md +145 -0
  2. config.json +116 -0
  3. model.safetensors +3 -0
  4. runs/Dec15_06-36-27_b168db0e3ed8/events.out.tfevents.1734244634.b168db0e3ed8.129.0 +3 -0
  5. runs/Dec15_06-53-20_b168db0e3ed8/events.out.tfevents.1734245629.b168db0e3ed8.258.0 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: allenai/scibert_scivocab_uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: math_question_grade_detection_v12-15-24
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # math_question_grade_detection_v12-15-24
20
+
21
+ This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.8318
24
+ - Accuracy: 0.7810
25
+ - Precision: 0.7846
26
+ - Recall: 0.7810
27
+ - F1: 0.7777
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
+ - lr_scheduler_type: linear
52
+ - training_steps: 4000
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | No log | 0.0855 | 50 | 3.1015 | 0.1873 | 0.1326 | 0.1873 | 0.1319 |
59
+ | No log | 0.1709 | 100 | 2.7556 | 0.2498 | 0.3005 | 0.2498 | 0.1722 |
60
+ | No log | 0.2564 | 150 | 2.4127 | 0.3689 | 0.3262 | 0.3689 | 0.2958 |
61
+ | No log | 0.3419 | 200 | 2.1657 | 0.4102 | 0.3757 | 0.4102 | 0.3555 |
62
+ | No log | 0.4274 | 250 | 1.9785 | 0.4659 | 0.3911 | 0.4659 | 0.4013 |
63
+ | No log | 0.5128 | 300 | 1.8232 | 0.5014 | 0.4838 | 0.5014 | 0.4474 |
64
+ | No log | 0.5983 | 350 | 1.7162 | 0.5139 | 0.4598 | 0.5139 | 0.4605 |
65
+ | No log | 0.6838 | 400 | 1.6189 | 0.5274 | 0.5116 | 0.5274 | 0.4710 |
66
+ | No log | 0.7692 | 450 | 1.5503 | 0.5408 | 0.5207 | 0.5408 | 0.4957 |
67
+ | 2.1698 | 0.8547 | 500 | 1.5007 | 0.5552 | 0.5385 | 0.5552 | 0.5075 |
68
+ | 2.1698 | 0.9402 | 550 | 1.4402 | 0.5514 | 0.5148 | 0.5514 | 0.5036 |
69
+ | 2.1698 | 1.0256 | 600 | 1.4091 | 0.5812 | 0.5586 | 0.5812 | 0.5472 |
70
+ | 2.1698 | 1.1111 | 650 | 1.3141 | 0.6042 | 0.5869 | 0.6042 | 0.5613 |
71
+ | 2.1698 | 1.1966 | 700 | 1.2728 | 0.6167 | 0.6115 | 0.6167 | 0.5899 |
72
+ | 2.1698 | 1.2821 | 750 | 1.2387 | 0.6119 | 0.5836 | 0.6119 | 0.5788 |
73
+ | 2.1698 | 1.3675 | 800 | 1.1677 | 0.6436 | 0.6098 | 0.6436 | 0.6134 |
74
+ | 2.1698 | 1.4530 | 850 | 1.1942 | 0.6378 | 0.6137 | 0.6378 | 0.6068 |
75
+ | 2.1698 | 1.5385 | 900 | 1.1496 | 0.6551 | 0.6176 | 0.6551 | 0.6252 |
76
+ | 2.1698 | 1.6239 | 950 | 1.0941 | 0.6513 | 0.6178 | 0.6513 | 0.6200 |
77
+ | 1.1604 | 1.7094 | 1000 | 1.0942 | 0.6561 | 0.6194 | 0.6561 | 0.6241 |
78
+ | 1.1604 | 1.7949 | 1050 | 1.0372 | 0.6734 | 0.6388 | 0.6734 | 0.6466 |
79
+ | 1.1604 | 1.8803 | 1100 | 1.0042 | 0.6926 | 0.6532 | 0.6926 | 0.6637 |
80
+ | 1.1604 | 1.9658 | 1150 | 1.0170 | 0.6763 | 0.6470 | 0.6763 | 0.6508 |
81
+ | 1.1604 | 2.0513 | 1200 | 1.0328 | 0.6801 | 0.6412 | 0.6801 | 0.6507 |
82
+ | 1.1604 | 2.1368 | 1250 | 0.9747 | 0.6849 | 0.6691 | 0.6849 | 0.6608 |
83
+ | 1.1604 | 2.2222 | 1300 | 0.9740 | 0.6840 | 0.6913 | 0.6840 | 0.6654 |
84
+ | 1.1604 | 2.3077 | 1350 | 0.9806 | 0.6984 | 0.7010 | 0.6984 | 0.6793 |
85
+ | 1.1604 | 2.3932 | 1400 | 0.9327 | 0.7157 | 0.7259 | 0.7157 | 0.6943 |
86
+ | 1.1604 | 2.4786 | 1450 | 0.9040 | 0.7109 | 0.7128 | 0.7109 | 0.6961 |
87
+ | 0.8113 | 2.5641 | 1500 | 0.9086 | 0.7243 | 0.7340 | 0.7243 | 0.7086 |
88
+ | 0.8113 | 2.6496 | 1550 | 0.9190 | 0.7099 | 0.7230 | 0.7099 | 0.6925 |
89
+ | 0.8113 | 2.7350 | 1600 | 0.9221 | 0.7099 | 0.7067 | 0.7099 | 0.6913 |
90
+ | 0.8113 | 2.8205 | 1650 | 0.9628 | 0.7070 | 0.7256 | 0.7070 | 0.6914 |
91
+ | 0.8113 | 2.9060 | 1700 | 0.9023 | 0.7166 | 0.7246 | 0.7166 | 0.6991 |
92
+ | 0.8113 | 2.9915 | 1750 | 0.9015 | 0.7243 | 0.7205 | 0.7243 | 0.7083 |
93
+ | 0.8113 | 3.0769 | 1800 | 0.8744 | 0.7368 | 0.7546 | 0.7368 | 0.7257 |
94
+ | 0.8113 | 3.1624 | 1850 | 0.8957 | 0.7301 | 0.7385 | 0.7301 | 0.7158 |
95
+ | 0.8113 | 3.2479 | 1900 | 0.8821 | 0.7176 | 0.7236 | 0.7176 | 0.7040 |
96
+ | 0.8113 | 3.3333 | 1950 | 0.8755 | 0.7291 | 0.7392 | 0.7291 | 0.7153 |
97
+ | 0.5683 | 3.4188 | 2000 | 0.8881 | 0.7358 | 0.7385 | 0.7358 | 0.7233 |
98
+ | 0.5683 | 3.5043 | 2050 | 0.8840 | 0.7291 | 0.7427 | 0.7291 | 0.7210 |
99
+ | 0.5683 | 3.5897 | 2100 | 0.8520 | 0.7281 | 0.7382 | 0.7281 | 0.7172 |
100
+ | 0.5683 | 3.6752 | 2150 | 0.8350 | 0.7349 | 0.7422 | 0.7349 | 0.7237 |
101
+ | 0.5683 | 3.7607 | 2200 | 0.8230 | 0.7435 | 0.7394 | 0.7435 | 0.7289 |
102
+ | 0.5683 | 3.8462 | 2250 | 0.8454 | 0.7474 | 0.7513 | 0.7474 | 0.7384 |
103
+ | 0.5683 | 3.9316 | 2300 | 0.8278 | 0.7541 | 0.7573 | 0.7541 | 0.7454 |
104
+ | 0.5683 | 4.0171 | 2350 | 0.8252 | 0.7589 | 0.7618 | 0.7589 | 0.7520 |
105
+ | 0.5683 | 4.1026 | 2400 | 0.8250 | 0.7608 | 0.7584 | 0.7608 | 0.7525 |
106
+ | 0.5683 | 4.1880 | 2450 | 0.8608 | 0.7493 | 0.7549 | 0.7493 | 0.7425 |
107
+ | 0.3936 | 4.2735 | 2500 | 0.8701 | 0.7435 | 0.7434 | 0.7435 | 0.7322 |
108
+ | 0.3936 | 4.3590 | 2550 | 0.8313 | 0.7541 | 0.7591 | 0.7541 | 0.7476 |
109
+ | 0.3936 | 4.4444 | 2600 | 0.8121 | 0.7627 | 0.7677 | 0.7627 | 0.7572 |
110
+ | 0.3936 | 4.5299 | 2650 | 0.8364 | 0.7627 | 0.7641 | 0.7627 | 0.7579 |
111
+ | 0.3936 | 4.6154 | 2700 | 0.8454 | 0.7656 | 0.7737 | 0.7656 | 0.7622 |
112
+ | 0.3936 | 4.7009 | 2750 | 0.8403 | 0.7646 | 0.7716 | 0.7646 | 0.7591 |
113
+ | 0.3936 | 4.7863 | 2800 | 0.8026 | 0.7714 | 0.7810 | 0.7714 | 0.7683 |
114
+ | 0.3936 | 4.8718 | 2850 | 0.8119 | 0.7819 | 0.7866 | 0.7819 | 0.7765 |
115
+ | 0.3936 | 4.9573 | 2900 | 0.7979 | 0.7723 | 0.7771 | 0.7723 | 0.7693 |
116
+ | 0.3936 | 5.0427 | 2950 | 0.8000 | 0.7656 | 0.7696 | 0.7656 | 0.7594 |
117
+ | 0.277 | 5.1282 | 3000 | 0.8160 | 0.7656 | 0.7754 | 0.7656 | 0.7610 |
118
+ | 0.277 | 5.2137 | 3050 | 0.8320 | 0.7589 | 0.7620 | 0.7589 | 0.7535 |
119
+ | 0.277 | 5.2991 | 3100 | 0.8460 | 0.7608 | 0.7665 | 0.7608 | 0.7559 |
120
+ | 0.277 | 5.3846 | 3150 | 0.8424 | 0.7608 | 0.7692 | 0.7608 | 0.7570 |
121
+ | 0.277 | 5.4701 | 3200 | 0.8251 | 0.7637 | 0.7698 | 0.7637 | 0.7588 |
122
+ | 0.277 | 5.5556 | 3250 | 0.8343 | 0.7743 | 0.7778 | 0.7743 | 0.7694 |
123
+ | 0.277 | 5.6410 | 3300 | 0.8514 | 0.7714 | 0.7776 | 0.7714 | 0.7674 |
124
+ | 0.277 | 5.7265 | 3350 | 0.8347 | 0.7695 | 0.7784 | 0.7695 | 0.7661 |
125
+ | 0.277 | 5.8120 | 3400 | 0.8309 | 0.7685 | 0.7716 | 0.7685 | 0.7651 |
126
+ | 0.277 | 5.8974 | 3450 | 0.8116 | 0.7704 | 0.7789 | 0.7704 | 0.7682 |
127
+ | 0.1904 | 5.9829 | 3500 | 0.8127 | 0.7819 | 0.7838 | 0.7819 | 0.7779 |
128
+ | 0.1904 | 6.0684 | 3550 | 0.8193 | 0.7781 | 0.7780 | 0.7781 | 0.7732 |
129
+ | 0.1904 | 6.1538 | 3600 | 0.8268 | 0.7819 | 0.7872 | 0.7819 | 0.7787 |
130
+ | 0.1904 | 6.2393 | 3650 | 0.8217 | 0.7829 | 0.7863 | 0.7829 | 0.7793 |
131
+ | 0.1904 | 6.3248 | 3700 | 0.8345 | 0.7781 | 0.7816 | 0.7781 | 0.7741 |
132
+ | 0.1904 | 6.4103 | 3750 | 0.8293 | 0.7839 | 0.7895 | 0.7839 | 0.7808 |
133
+ | 0.1904 | 6.4957 | 3800 | 0.8248 | 0.7800 | 0.7838 | 0.7800 | 0.7769 |
134
+ | 0.1904 | 6.5812 | 3850 | 0.8255 | 0.7762 | 0.7820 | 0.7762 | 0.7732 |
135
+ | 0.1904 | 6.6667 | 3900 | 0.8292 | 0.7791 | 0.7843 | 0.7791 | 0.7763 |
136
+ | 0.1904 | 6.7521 | 3950 | 0.8304 | 0.7819 | 0.7864 | 0.7819 | 0.7788 |
137
+ | 0.1479 | 6.8376 | 4000 | 0.8318 | 0.7810 | 0.7846 | 0.7810 | 0.7777 |
138
+
139
+
140
+ ### Framework versions
141
+
142
+ - Transformers 4.46.3
143
+ - Pytorch 2.4.0
144
+ - Datasets 3.1.0
145
+ - Tokenizers 0.20.3
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/scibert_scivocab_uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "1.G",
13
+ "1": "1.MD",
14
+ "2": "1.NBT",
15
+ "3": "1.OA",
16
+ "4": "2.G",
17
+ "5": "2.MD",
18
+ "6": "2.NBT",
19
+ "7": "2.OA",
20
+ "8": "3.G",
21
+ "9": "3.MD",
22
+ "10": "3.NBT",
23
+ "11": "3.NF",
24
+ "12": "3.OA",
25
+ "13": "4.G",
26
+ "14": "4.MD",
27
+ "15": "4.NBT",
28
+ "16": "4.NF",
29
+ "17": "4.OA",
30
+ "18": "5.G",
31
+ "19": "5.MD",
32
+ "20": "5.NBT",
33
+ "21": "5.NF",
34
+ "22": "5.OA",
35
+ "23": "6.EE",
36
+ "24": "6.G",
37
+ "25": "6.NS",
38
+ "26": "6.RP",
39
+ "27": "6.SP",
40
+ "28": "7.EE",
41
+ "29": "7.G",
42
+ "30": "7.NS",
43
+ "31": "7.RP",
44
+ "32": "7.SP",
45
+ "33": "8.EE",
46
+ "34": "8.F",
47
+ "35": "8.G",
48
+ "36": "8.NS",
49
+ "37": "8.SP",
50
+ "38": "K.CC",
51
+ "39": "K.G",
52
+ "40": "K.MD",
53
+ "41": "K.NBT",
54
+ "42": "K.OA"
55
+ },
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 3072,
58
+ "label2id": {
59
+ "1.G": 0,
60
+ "1.MD": 1,
61
+ "1.NBT": 2,
62
+ "1.OA": 3,
63
+ "2.G": 4,
64
+ "2.MD": 5,
65
+ "2.NBT": 6,
66
+ "2.OA": 7,
67
+ "3.G": 8,
68
+ "3.MD": 9,
69
+ "3.NBT": 10,
70
+ "3.NF": 11,
71
+ "3.OA": 12,
72
+ "4.G": 13,
73
+ "4.MD": 14,
74
+ "4.NBT": 15,
75
+ "4.NF": 16,
76
+ "4.OA": 17,
77
+ "5.G": 18,
78
+ "5.MD": 19,
79
+ "5.NBT": 20,
80
+ "5.NF": 21,
81
+ "5.OA": 22,
82
+ "6.EE": 23,
83
+ "6.G": 24,
84
+ "6.NS": 25,
85
+ "6.RP": 26,
86
+ "6.SP": 27,
87
+ "7.EE": 28,
88
+ "7.G": 29,
89
+ "7.NS": 30,
90
+ "7.RP": 31,
91
+ "7.SP": 32,
92
+ "8.EE": 33,
93
+ "8.F": 34,
94
+ "8.G": 35,
95
+ "8.NS": 36,
96
+ "8.SP": 37,
97
+ "K.CC": 38,
98
+ "K.G": 39,
99
+ "K.MD": 40,
100
+ "K.NBT": 41,
101
+ "K.OA": 42
102
+ },
103
+ "layer_norm_eps": 1e-12,
104
+ "max_position_embeddings": 512,
105
+ "model_type": "bert",
106
+ "num_attention_heads": 12,
107
+ "num_hidden_layers": 12,
108
+ "pad_token_id": 0,
109
+ "position_embedding_type": "absolute",
110
+ "problem_type": "single_label_classification",
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.46.3",
113
+ "type_vocab_size": 2,
114
+ "use_cache": true,
115
+ "vocab_size": 31090
116
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e00e21ffd05aa0ad896c7b979eaa39d5dcb60d129e2758b1dd144ad7664734fd
3
+ size 439829660
runs/Dec15_06-36-27_b168db0e3ed8/events.out.tfevents.1734244634.b168db0e3ed8.129.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0513b4e110981dec163437391f90708f3ecc0c784dad7ee4336fdda7408587df
3
+ size 6521
runs/Dec15_06-53-20_b168db0e3ed8/events.out.tfevents.1734245629.b168db0e3ed8.258.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6ed26d12d4601da2169997089df87f2f959f408c37618f1b6f4aaa6e4c8362c
3
+ size 46305
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3952ad8bd621800793453a7ca802461070e59d77c81bff35e17203864347394
3
+ size 5304