Hugging Face's logo

xhorvat9
/
output

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
custom_code
Model card Files Metrics Community
xhorvat9 commited on
Commit
54ede2e
·
verified ·
1 Parent(s): d448e75

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. README.md +14 -17
  2. config.json +1 -31
  3. model.safetensors +2 -2
  4. runs/Oct10_01-15-06_aura.fi.muni.cz/events.out.tfevents.1728515711.aura.fi.muni.cz.2703744.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -20,12 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [zhihan1996/DNA_bert_6](https://huggingface.co/zhihan1996/DNA_bert_6) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.9545
24
- - Accuracy: 0.6326
25
- - Precision: 0.7326
26
- - Recall: 0.7248
27
- - F1: 0.7187
28
- - Mcc: 0.6857
29
 
30
  ## Model description
31
 
@@ -54,17 +53,15 @@ The following hyperparameters were used during training:
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Mcc |
58
- |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
59
- | 1.7375 | 0.4209 | 500 | 1.4156 | 0.3771 | 0.5528 | 0.5586 | 0.5239 | 0.4908 |
60
- | 1.334 | 0.8418 | 1000 | 1.2193 | 0.5040 | 0.6174 | 0.6212 | 0.6143 | 0.5661 |
61
- | 1.1545 | 1.2626 | 1500 | 1.1257 | 0.5406 | 0.6592 | 0.6543 | 0.6508 | 0.6037 |
62
- | 1.042 | 1.6835 | 2000 | 1.0398 | 0.5683 | 0.6838 | 0.6864 | 0.6739 | 0.6394 |
63
- | 0.9394 | 2.1044 | 2500 | 1.0141 | 0.5835 | 0.6974 | 0.6890 | 0.6809 | 0.6437 |
64
- | 0.8279 | 2.5253 | 3000 | 0.9895 | 0.6022 | 0.7070 | 0.7020 | 0.6934 | 0.6585 |
65
- | 0.8023 | 2.9461 | 3500 | 0.9273 | 0.6349 | 0.7246 | 0.7240 | 0.7189 | 0.6838 |
66
- | 0.6899 | 3.3670 | 4000 | 0.9374 | 0.6328 | 0.7272 | 0.7247 | 0.7194 | 0.6849 |
67
- | 0.6672 | 3.7879 | 4500 | 0.9545 | 0.6326 | 0.7326 | 0.7248 | 0.7187 | 0.6857 |
68
 
69
 
70
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [zhihan1996/DNA_bert_6](https://huggingface.co/zhihan1996/DNA_bert_6) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.3621
24
+ - Accuracy: 0.8538
25
+ - Precision: 0.8812
26
+ - Recall: 0.8210
27
+ - F1: 0.8500
 
28
 
29
  ## Model description
30
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.5241 | 0.3946 | 500 | 0.4448 | 0.7869 | 0.8057 | 0.7614 | 0.7829 |
59
+ | 0.4126 | 0.7893 | 1000 | 0.3896 | 0.8129 | 0.8379 | 0.7802 | 0.8080 |
60
+ | 0.3527 | 1.1839 | 1500 | 0.3613 | 0.8367 | 0.8267 | 0.8558 | 0.8410 |
61
+ | 0.3209 | 1.5785 | 2000 | 0.3744 | 0.8322 | 0.8702 | 0.7846 | 0.8252 |
62
+ | 0.3075 | 1.9732 | 2500 | 0.3244 | 0.8545 | 0.8673 | 0.8403 | 0.8535 |
63
+ | 0.2526 | 2.3678 | 3000 | 0.3407 | 0.8539 | 0.8595 | 0.8495 | 0.8544 |
64
+ | 0.2512 | 2.7624 | 3500 | 0.3621 | 0.8538 | 0.8812 | 0.8210 | 0.8500 |
 
 
65
 
66
 
67
  ### Framework versions
config.json CHANGED
@@ -17,38 +17,8 @@
17
  "hidden_act": "gelu",
18
  "hidden_dropout_prob": 0.1,
19
  "hidden_size": 768,
20
- "id2label": {
21
- "0": "LABEL_0",
22
- "1": "LABEL_1",
23
- "2": "LABEL_2",
24
- "3": "LABEL_3",
25
- "4": "LABEL_4",
26
- "5": "LABEL_5",
27
- "6": "LABEL_6",
28
- "7": "LABEL_7",
29
- "8": "LABEL_8",
30
- "9": "LABEL_9",
31
- "10": "LABEL_10",
32
- "11": "LABEL_11",
33
- "12": "LABEL_12"
34
- },
35
  "initializer_range": 0.02,
36
  "intermediate_size": 3072,
37
- "label2id": {
38
- "LABEL_0": 0,
39
- "LABEL_1": 1,
40
- "LABEL_10": 10,
41
- "LABEL_11": 11,
42
- "LABEL_12": 12,
43
- "LABEL_2": 2,
44
- "LABEL_3": 3,
45
- "LABEL_4": 4,
46
- "LABEL_5": 5,
47
- "LABEL_6": 6,
48
- "LABEL_7": 7,
49
- "LABEL_8": 8,
50
- "LABEL_9": 9
51
- },
52
  "layer_norm_eps": 1e-12,
53
  "max_position_embeddings": 512,
54
  "model_type": "bert",
@@ -58,7 +28,7 @@
58
  "output_past": true,
59
  "pad_token_id": 0,
60
  "position_embedding_type": "absolute",
61
- "problem_type": "multi_label_classification",
62
  "rnn": "lstm",
63
  "rnn_dropout": 0.0,
64
  "rnn_hidden": 768,
 
17
  "hidden_act": "gelu",
18
  "hidden_dropout_prob": 0.1,
19
  "hidden_size": 768,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "layer_norm_eps": 1e-12,
23
  "max_position_embeddings": 512,
24
  "model_type": "bert",
 
28
  "output_past": true,
29
  "pad_token_id": 0,
30
  "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
  "rnn": "lstm",
33
  "rnn_dropout": 0.0,
34
  "rnn_hidden": 768,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed0791527b896118ea31edbef3eaca2414f1703955c433c244ecd32b2d227392
3
- size 356827076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a92472ced539c9ed12112d1438d0b130c44951287db768670582929089c67b45
3
+ size 356793240
runs/Oct10_01-15-06_aura.fi.muni.cz/events.out.tfevents.1728515711.aura.fi.muni.cz.2703744.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ea952cdc52d3a22a3103edbc5db72bcab7feda8bc9bebff87dd00c6e0834e3
3
+ size 6188
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19be839c6b420bc29765950007a7d4d489872b31c62a0bccaea8cee5581aa46f
3
  size 4719
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5662e4985aecb11cdd9de961c61a71b4aa57d56799e2b3ddc56f4d9e79492415
3
  size 4719