tanoManzo commited on
Commit
095c102
1 Parent(s): c1bba07

End of training

Browse files
Files changed (5) hide show
  1. README.md +77 -0
  2. config.json +37 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer_config.json +70 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bsd-3-clause
3
+ base_model: LongSafari/hyenadna-medium-160k-seqlen-hf
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - accuracy
10
+ model-index:
11
+ - name: hyenadna-medium-160k-seqlen-hf_ft_BioS45_1kbpHG19_DHSs_H3K27AC
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
+ # hyenadna-medium-160k-seqlen-hf_ft_BioS45_1kbpHG19_DHSs_H3K27AC
19
+
20
+ This model is a fine-tuned version of [LongSafari/hyenadna-medium-160k-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-medium-160k-seqlen-hf) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.5104
23
+ - F1 Score: 0.8100
24
+ - Precision: 0.8002
25
+ - Recall: 0.8202
26
+ - Accuracy: 0.7993
27
+ - Auc: 0.8765
28
+ - Prc: 0.8748
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 1e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 20
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc | Prc |
59
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
60
+ | 0.5145 | 0.4205 | 500 | 0.4663 | 0.7945 | 0.8003 | 0.7887 | 0.7871 | 0.8575 | 0.8420 |
61
+ | 0.4678 | 0.8410 | 1000 | 0.4667 | 0.8075 | 0.7334 | 0.8984 | 0.7766 | 0.8691 | 0.8628 |
62
+ | 0.4586 | 1.2616 | 1500 | 0.4759 | 0.8157 | 0.7463 | 0.8992 | 0.7880 | 0.8674 | 0.8598 |
63
+ | 0.4467 | 1.6821 | 2000 | 0.4349 | 0.8134 | 0.7961 | 0.8315 | 0.8010 | 0.8798 | 0.8751 |
64
+ | 0.4298 | 2.1026 | 2500 | 0.4558 | 0.8170 | 0.7480 | 0.9 | 0.7897 | 0.8749 | 0.8679 |
65
+ | 0.4068 | 2.5231 | 3000 | 0.4374 | 0.7982 | 0.8139 | 0.7831 | 0.7934 | 0.8830 | 0.8793 |
66
+ | 0.4299 | 2.9437 | 3500 | 0.4358 | 0.8117 | 0.8033 | 0.8202 | 0.8014 | 0.8816 | 0.8787 |
67
+ | 0.3994 | 3.3642 | 4000 | 0.4543 | 0.8120 | 0.8287 | 0.7960 | 0.8077 | 0.8815 | 0.8781 |
68
+ | 0.3742 | 3.7847 | 4500 | 0.4463 | 0.8139 | 0.7948 | 0.8339 | 0.8010 | 0.8796 | 0.8733 |
69
+ | 0.345 | 4.2052 | 5000 | 0.5104 | 0.8100 | 0.8002 | 0.8202 | 0.7993 | 0.8765 | 0.8748 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.42.3
75
+ - Pytorch 2.3.0+cu121
76
+ - Datasets 2.18.0
77
+ - Tokenizers 0.19.0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LongSafari/hyenadna-medium-160k-seqlen-hf",
3
+ "activation_freq": 10,
4
+ "architectures": [
5
+ "HyenaDNAForSequenceClassification"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "LongSafari/hyenadna-medium-160k-seqlen-hf--configuration_hyena.HyenaConfig",
9
+ "AutoModel": "LongSafari/hyenadna-medium-160k-seqlen-hf--modeling_hyena.HyenaDNAModel",
10
+ "AutoModelForCausalLM": "LongSafari/hyenadna-medium-160k-seqlen-hf--modeling_hyena.HyenaDNAForCausalLM",
11
+ "AutoModelForSequenceClassification": "LongSafari/hyenadna-medium-160k-seqlen-hf--modeling_hyena.HyenaDNAForSequenceClassification"
12
+ },
13
+ "d_inner": 1024,
14
+ "d_model": 256,
15
+ "emb_dim": 5,
16
+ "embed_dropout": 0.1,
17
+ "filter_order": 64,
18
+ "hyena_dropout": 0.0,
19
+ "hyena_filter_dropout": 0.0,
20
+ "hyena_order": 2,
21
+ "initializer_range": 0.02,
22
+ "layer_norm_epsilon": 1e-05,
23
+ "max_seq_len": 160002,
24
+ "model_type": "hyenadna",
25
+ "n_layer": 8,
26
+ "num_inner_mlps": 2,
27
+ "pad_token_id": 4,
28
+ "pad_vocab_size_multiple": 8,
29
+ "problem_type": "single_label_classification",
30
+ "short_filter_order": 3,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "float32",
33
+ "train_freq": true,
34
+ "transformers_version": "4.42.3",
35
+ "use_bias": true,
36
+ "vocab_size": 12
37
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd64eb41de44ed36dd42bc970162805342d3212a9b7b22c7e758deac0f87955a
3
+ size 57008026
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
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": "[SEP]",
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_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[CLS]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[SEP]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[BOS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[MASK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[PAD]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "6": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ }
52
+ },
53
+ "auto_map": {
54
+ "AutoTokenizer": [
55
+ "LongSafari/hyenadna-medium-160k-seqlen-hf--tokenization_hyena.HyenaDNATokenizer",
56
+ null
57
+ ]
58
+ },
59
+ "bos_token": "[BOS]",
60
+ "clean_up_tokenization_spaces": true,
61
+ "cls_token": "[CLS]",
62
+ "eos_token": "[SEP]",
63
+ "mask_token": "[MASK]",
64
+ "model_max_length": 160002,
65
+ "pad_token": "[PAD]",
66
+ "padding_side": "left",
67
+ "sep_token": "[SEP]",
68
+ "tokenizer_class": "HyenaDNATokenizer",
69
+ "unk_token": "[UNK]"
70
+ }