Hugging Face's logo

abk20031218
/
checkpoints

Token Classification
Transformers
Safetensors
esm
Generated from Trainer
Model card Files
xet
 Community
abk20031218 commited on
Commit
fbcfb36
·
verified ·
1 Parent(s): d0ea73f

your-username/bcell-epitope-esm2

Browse files
Files changed (6) hide show
  1. README.md +72 -0
  2. config.json +35 -0
  3. model.safetensors +3 -0
  4. tokenizer_config.json +54 -0
  5. training_args.bin +3 -0
  6. vocab.txt +33 -0
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: facebook/esm2_t12_35M_UR50D
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: checkpoints
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # checkpoints
21
+
22
+ This model is a fine-tuned version of [facebook/esm2_t12_35M_UR50D](https://huggingface.co/facebook/esm2_t12_35M_UR50D) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.6773
25
+ - Accuracy: 0.7253
26
+ - Precision: 0.3633
27
+ - Recall: 0.4923
28
+ - F1: 0.4180
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: 2e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 5
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.6281 | 1.0 | 1028 | 0.6312 | 0.7622 | 0.4035 | 0.3903 | 0.3968 |
61
+ | 0.5836 | 2.0 | 2056 | 0.6297 | 0.7553 | 0.3973 | 0.4273 | 0.4118 |
62
+ | 0.5832 | 3.0 | 3084 | 0.6605 | 0.7754 | 0.4326 | 0.3880 | 0.4091 |
63
+ | 0.5177 | 4.0 | 4112 | 0.6891 | 0.7604 | 0.4052 | 0.4179 | 0.4114 |
64
+ | 0.5016 | 5.0 | 5140 | 0.6773 | 0.7253 | 0.3633 | 0.4923 | 0.4180 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 5.13.1
70
+ - Pytorch 2.11.0+cu128
71
+ - Datasets 4.0.0
72
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "EsmForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "emb_layer_norm_before": false,
11
+ "eos_token_id": 2,
12
+ "esmfold_config": null,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.0,
15
+ "hidden_size": 480,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1920,
18
+ "is_decoder": false,
19
+ "is_folding_model": false,
20
+ "layer_norm_eps": 1e-05,
21
+ "mask_token_id": 32,
22
+ "max_position_embeddings": 1026,
23
+ "model_type": "esm",
24
+ "num_attention_heads": 20,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "rotary",
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": true,
30
+ "token_dropout": true,
31
+ "transformers_version": "5.13.1",
32
+ "use_cache": false,
33
+ "vocab_list": null,
34
+ "vocab_size": 33
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1849b1778654dff68d21a84dcc7178274b256fde543f5e2c85260d69aae98590
3
+ size 133104524
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<cls>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<eos>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "backend": "custom",
45
+ "cls_token": "<cls>",
46
+ "eos_token": "<eos>",
47
+ "is_local": false,
48
+ "local_files_only": false,
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<pad>",
52
+ "tokenizer_class": "EsmTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796a6f1e7ec97b23daa44251c33c5c160fd6f9193406328c62247b0cb0bf6f8c
3
+ size 5201
vocab.txt ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <cls>
2
+ <pad>
3
+ <eos>
4
+ <unk>
5
+ L
6
+ A
7
+ G
8
+ V
9
+ S
10
+ E
11
+ R
12
+ T
13
+ I
14
+ D
15
+ P
16
+ K
17
+ Q
18
+ N
19
+ F
20
+ Y
21
+ M
22
+ H
23
+ W
24
+ C
25
+ X
26
+ B
27
+ U
28
+ Z
29
+ O
30
+ .
31
+ -
32
+ <null_1>
33
+ <mask>