Hugging Face's logo

Mardiyyah
/
variant_tapt_freeze_llrd_LR_5e

Token Classification
Transformers
Safetensors
English
bert
Generated from Trainer
Model card Files
xet
 Community
Mardiyyah commited on
Commit
aef8bce
·
verified ·
1 Parent(s): e4554e9

Model save

Browse files
Files changed (4) hide show
  1. README.md +28 -30
  2. config.json +80 -80
  3. model.safetensors +1 -1
  4. training_args.bin +2 -2
README.md CHANGED
@@ -1,7 +1,5 @@
1
  ---
2
  library_name: transformers
3
- language:
4
- - en
5
  license: apache-2.0
6
  base_model: Mardiyyah/variant-tapt_freeze_llrd-LR_5e-05
7
  tags:
@@ -12,22 +10,22 @@ metrics:
12
  - f1
13
  - accuracy
14
  model-index:
15
- - name: Variant_new_pubmed_extended_reinit_llrd
16
  results: []
17
  ---
18
 
19
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
  should probably proofread and complete it, then remove this comment. -->
21
 
22
- # Variant_new_pubmed_extended_reinit_llrd
23
 
24
- This model is a fine-tuned version of [Mardiyyah/variant-tapt_freeze_llrd-LR_5e-05](https://huggingface.co/Mardiyyah/variant-tapt_freeze_llrd-LR_5e-05) on the OTAR3088/PDBE_IOB_all dataset.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.2385
27
- - Precision: 0.9080
28
- - Recall: 0.9184
29
- - F1: 0.9132
30
- - Accuracy: 0.9619
31
 
32
  ## Model description
33
 
@@ -60,26 +58,26 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
62
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
63
- | 1.8707 | 1.0 | 352 | 0.7671 | 0.3723 | 0.4464 | 0.4060 | 0.8007 |
64
- | 0.524 | 2.0 | 704 | 0.3271 | 0.7191 | 0.7442 | 0.7314 | 0.9135 |
65
- | 0.2663 | 3.0 | 1056 | 0.2196 | 0.8207 | 0.8361 | 0.8283 | 0.9411 |
66
- | 0.165 | 4.0 | 1408 | 0.1924 | 0.8731 | 0.8549 | 0.8639 | 0.9498 |
67
- | 0.1117 | 5.0 | 1760 | 0.1843 | 0.8813 | 0.8809 | 0.8811 | 0.9542 |
68
- | 0.0812 | 6.0 | 2112 | 0.1785 | 0.8813 | 0.8957 | 0.8884 | 0.9558 |
69
- | 0.06 | 7.0 | 2464 | 0.1926 | 0.8850 | 0.9044 | 0.8946 | 0.9570 |
70
- | 0.0459 | 8.0 | 2816 | 0.1997 | 0.8868 | 0.9118 | 0.8991 | 0.9583 |
71
- | 0.035 | 9.0 | 3168 | 0.1951 | 0.8930 | 0.9123 | 0.9025 | 0.9594 |
72
- | 0.0278 | 10.0 | 3520 | 0.2095 | 0.8897 | 0.9153 | 0.9023 | 0.9598 |
73
- | 0.0225 | 11.0 | 3872 | 0.2092 | 0.9045 | 0.9119 | 0.9082 | 0.9609 |
74
- | 0.0184 | 12.0 | 4224 | 0.2202 | 0.8969 | 0.9155 | 0.9061 | 0.9600 |
75
- | 0.0146 | 13.0 | 4576 | 0.2188 | 0.9012 | 0.9176 | 0.9093 | 0.9612 |
76
- | 0.013 | 14.0 | 4928 | 0.2250 | 0.8987 | 0.9169 | 0.9077 | 0.9601 |
77
- | 0.0103 | 15.0 | 5280 | 0.2343 | 0.8977 | 0.9213 | 0.9094 | 0.9610 |
78
- | 0.0091 | 16.0 | 5632 | 0.2332 | 0.9043 | 0.9176 | 0.9109 | 0.9616 |
79
- | 0.0077 | 17.0 | 5984 | 0.2343 | 0.9052 | 0.9159 | 0.9105 | 0.9613 |
80
- | 0.007 | 18.0 | 6336 | 0.2380 | 0.9081 | 0.9184 | 0.9132 | 0.9619 |
81
- | 0.0061 | 19.0 | 6688 | 0.2389 | 0.9055 | 0.9191 | 0.9122 | 0.9615 |
82
- | 0.0057 | 20.0 | 7040 | 0.2425 | 0.9048 | 0.9191 | 0.9119 | 0.9615 |
83
 
84
 
85
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
  base_model: Mardiyyah/variant-tapt_freeze_llrd-LR_5e-05
5
  tags:
 
10
  - f1
11
  - accuracy
12
  model-index:
13
+ - name: variant_tapt_freeze_llrd_LR_5e
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
+ # variant_tapt_freeze_llrd_LR_5e
21
 
22
+ This model is a fine-tuned version of [Mardiyyah/variant-tapt_freeze_llrd-LR_5e-05](https://huggingface.co/Mardiyyah/variant-tapt_freeze_llrd-LR_5e-05) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.2420
25
+ - Precision: 0.9084
26
+ - Recall: 0.9208
27
+ - F1: 0.9145
28
+ - Accuracy: 0.9611
29
 
30
  ## Model description
31
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
+ | 1.9616 | 1.0 | 352 | 0.8090 | 0.4440 | 0.4431 | 0.4435 | 0.7943 |
62
+ | 0.5637 | 2.0 | 704 | 0.3524 | 0.7245 | 0.7551 | 0.7395 | 0.9077 |
63
+ | 0.2766 | 3.0 | 1056 | 0.2292 | 0.8258 | 0.8408 | 0.8332 | 0.9383 |
64
+ | 0.1736 | 4.0 | 1408 | 0.2102 | 0.8722 | 0.8553 | 0.8637 | 0.9463 |
65
+ | 0.1209 | 5.0 | 1760 | 0.1951 | 0.8693 | 0.8861 | 0.8776 | 0.9506 |
66
+ | 0.0846 | 6.0 | 2112 | 0.1981 | 0.8914 | 0.8908 | 0.8911 | 0.9544 |
67
+ | 0.0641 | 7.0 | 2464 | 0.1917 | 0.8956 | 0.9030 | 0.8993 | 0.9560 |
68
+ | 0.0485 | 8.0 | 2816 | 0.2001 | 0.8958 | 0.9096 | 0.9027 | 0.9575 |
69
+ | 0.0374 | 9.0 | 3168 | 0.1962 | 0.8938 | 0.9123 | 0.9030 | 0.9577 |
70
+ | 0.0299 | 10.0 | 3520 | 0.2070 | 0.8966 | 0.9160 | 0.9062 | 0.9590 |
71
+ | 0.0238 | 11.0 | 3872 | 0.2104 | 0.9030 | 0.9171 | 0.9100 | 0.9591 |
72
+ | 0.0195 | 12.0 | 4224 | 0.2170 | 0.8996 | 0.9169 | 0.9082 | 0.9593 |
73
+ | 0.0158 | 13.0 | 4576 | 0.2184 | 0.9051 | 0.9183 | 0.9116 | 0.9608 |
74
+ | 0.013 | 14.0 | 4928 | 0.2255 | 0.9017 | 0.9211 | 0.9113 | 0.9602 |
75
+ | 0.011 | 15.0 | 5280 | 0.2366 | 0.9037 | 0.9190 | 0.9113 | 0.9600 |
76
+ | 0.0101 | 16.0 | 5632 | 0.2317 | 0.9092 | 0.9215 | 0.9153 | 0.9613 |
77
+ | 0.0083 | 17.0 | 5984 | 0.2344 | 0.9118 | 0.9193 | 0.9155 | 0.9617 |
78
+ | 0.007 | 18.0 | 6336 | 0.2400 | 0.9091 | 0.9214 | 0.9152 | 0.9615 |
79
+ | 0.0067 | 19.0 | 6688 | 0.2395 | 0.9075 | 0.9213 | 0.9144 | 0.9611 |
80
+ | 0.0063 | 20.0 | 7040 | 0.2420 | 0.9084 | 0.9208 | 0.9145 | 0.9611 |
81
 
82
 
83
  ### Framework versions
config.json CHANGED
@@ -9,92 +9,92 @@
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
11
  "id2label": {
12
- "0": "B-ptm",
13
- "1": "B-residue_name",
14
- "2": "I-ptm",
15
- "3": "I-residue_name_number",
16
- "4": "I-mutant",
17
- "5": "B-site",
18
- "6": "I-bond_interaction",
19
- "7": "I-residue_name",
20
- "8": "I-taxonomy_domain",
21
- "9": "B-residue_name_number",
22
- "10": "B-protein_type",
23
- "11": "I-experimental_method",
24
- "12": "B-oligomeric_state",
25
- "13": "B-residue_range",
26
- "14": "B-gene",
27
- "15": "B-protein",
28
- "16": "B-structure_element",
29
- "17": "B-complex_assembly",
30
- "18": "I-protein_type",
31
- "19": "I-chemical",
32
- "20": "B-evidence",
33
- "21": "B-species",
34
- "22": "I-residue_number",
35
  "23": "B-mutant",
36
- "24": "I-protein",
37
- "25": "I-oligomeric_state",
38
- "26": "I-gene",
39
- "27": "B-bond_interaction",
40
- "28": "I-site",
41
- "29": "I-evidence",
42
- "30": "I-structure_element",
43
- "31": "B-experimental_method",
44
- "32": "O",
45
- "33": "I-complex_assembly",
46
- "34": "B-chemical",
47
- "35": "B-protein_state",
48
- "36": "I-protein_state",
49
- "37": "I-residue_range",
50
- "38": "I-species",
51
- "39": "B-residue_number",
52
- "40": "B-taxonomy_domain"
53
  },
54
  "initializer_range": 0.02,
55
  "intermediate_size": 3072,
56
  "label2id": {
57
- "B-bond_interaction": 27,
58
- "B-chemical": 34,
59
- "B-complex_assembly": 17,
60
- "B-evidence": 20,
61
- "B-experimental_method": 31,
62
- "B-gene": 14,
63
  "B-mutant": 23,
64
- "B-oligomeric_state": 12,
65
- "B-protein": 15,
66
- "B-protein_state": 35,
67
- "B-protein_type": 10,
68
- "B-ptm": 0,
69
- "B-residue_name": 1,
70
- "B-residue_name_number": 9,
71
- "B-residue_number": 39,
72
- "B-residue_range": 13,
73
- "B-site": 5,
74
- "B-species": 21,
75
- "B-structure_element": 16,
76
- "B-taxonomy_domain": 40,
77
- "I-bond_interaction": 6,
78
- "I-chemical": 19,
79
- "I-complex_assembly": 33,
80
- "I-evidence": 29,
81
- "I-experimental_method": 11,
82
- "I-gene": 26,
83
- "I-mutant": 4,
84
- "I-oligomeric_state": 25,
85
- "I-protein": 24,
86
- "I-protein_state": 36,
87
- "I-protein_type": 18,
88
- "I-ptm": 2,
89
- "I-residue_name": 7,
90
- "I-residue_name_number": 3,
91
- "I-residue_number": 22,
92
- "I-residue_range": 37,
93
- "I-site": 28,
94
- "I-species": 38,
95
- "I-structure_element": 30,
96
- "I-taxonomy_domain": 8,
97
- "O": 32
98
  },
99
  "layer_norm_eps": 1e-12,
100
  "max_position_embeddings": 512,
 
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
11
  "id2label": {
12
+ "0": "I-protein_state",
13
+ "1": "B-evidence",
14
+ "2": "I-protein",
15
+ "3": "I-experimental_method",
16
+ "4": "B-species",
17
+ "5": "I-chemical",
18
+ "6": "B-complex_assembly",
19
+ "7": "B-protein",
20
+ "8": "I-evidence",
21
+ "9": "B-oligomeric_state",
22
+ "10": "I-oligomeric_state",
23
+ "11": "B-chemical",
24
+ "12": "I-mutant",
25
+ "13": "I-taxonomy_domain",
26
+ "14": "I-complex_assembly",
27
+ "15": "B-bond_interaction",
28
+ "16": "B-experimental_method",
29
+ "17": "O",
30
+ "18": "I-gene",
31
+ "19": "B-residue_name_number",
32
+ "20": "B-gene",
33
+ "21": "I-bond_interaction",
34
+ "22": "B-structure_element",
35
  "23": "B-mutant",
36
+ "24": "B-residue_number",
37
+ "25": "I-ptm",
38
+ "26": "B-protein_type",
39
+ "27": "I-species",
40
+ "28": "B-taxonomy_domain",
41
+ "29": "B-protein_state",
42
+ "30": "I-residue_name_number",
43
+ "31": "I-structure_element",
44
+ "32": "B-site",
45
+ "33": "I-residue_number",
46
+ "34": "B-residue_range",
47
+ "35": "I-residue_range",
48
+ "36": "B-residue_name",
49
+ "37": "I-site",
50
+ "38": "I-protein_type",
51
+ "39": "I-residue_name",
52
+ "40": "B-ptm"
53
  },
54
  "initializer_range": 0.02,
55
  "intermediate_size": 3072,
56
  "label2id": {
57
+ "B-bond_interaction": 15,
58
+ "B-chemical": 11,
59
+ "B-complex_assembly": 6,
60
+ "B-evidence": 1,
61
+ "B-experimental_method": 16,
62
+ "B-gene": 20,
63
  "B-mutant": 23,
64
+ "B-oligomeric_state": 9,
65
+ "B-protein": 7,
66
+ "B-protein_state": 29,
67
+ "B-protein_type": 26,
68
+ "B-ptm": 40,
69
+ "B-residue_name": 36,
70
+ "B-residue_name_number": 19,
71
+ "B-residue_number": 24,
72
+ "B-residue_range": 34,
73
+ "B-site": 32,
74
+ "B-species": 4,
75
+ "B-structure_element": 22,
76
+ "B-taxonomy_domain": 28,
77
+ "I-bond_interaction": 21,
78
+ "I-chemical": 5,
79
+ "I-complex_assembly": 14,
80
+ "I-evidence": 8,
81
+ "I-experimental_method": 3,
82
+ "I-gene": 18,
83
+ "I-mutant": 12,
84
+ "I-oligomeric_state": 10,
85
+ "I-protein": 2,
86
+ "I-protein_state": 0,
87
+ "I-protein_type": 38,
88
+ "I-ptm": 25,
89
+ "I-residue_name": 39,
90
+ "I-residue_name_number": 30,
91
+ "I-residue_number": 33,
92
+ "I-residue_range": 35,
93
+ "I-site": 37,
94
+ "I-species": 27,
95
+ "I-structure_element": 31,
96
+ "I-taxonomy_domain": 13,
97
+ "O": 17
98
  },
99
  "layer_norm_eps": 1e-12,
100
  "max_position_embeddings": 512,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac73ec3753d872f121b8dbec34056beeb89008b902fe33894bca4ada0541c58b
3
  size 439648220
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93777ebbbed7a65b8211b402f5dba42d9486a4ac81c0e647a0241e56183f1022
3
  size 439648220
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea857bdabea89f7d3875ced8c65f40cf423c85095eccfe006c700c2c3f4a7cd4
3
- size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c169b4f59074613e94b0305f09cd9a566624bcee041b08e9cacfd53506a8ca
3
+ size 5560