andresvv commited on
Commit
6c895e2
1 Parent(s): 6a167fd

Upload TFEsmForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +62 -0
  2. config.json +37 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: esm2_t6_8M_UR50D-finetuned-Xmas-project
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # esm2_t6_8M_UR50D-finetuned-Xmas-project
14
+
15
+ This model is a fine-tuned version of [facebook/esm2_t6_8M_UR50D](https://huggingface.co/facebook/esm2_t6_8M_UR50D) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 56.7855
18
+ - Validation Loss: 101.4410
19
+ - Epoch: 9
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.0}
39
+ - training_precision: float32
40
+
41
+ ### Training results
42
+
43
+ | Train Loss | Validation Loss | Epoch |
44
+ |:----------:|:---------------:|:-----:|
45
+ | 494.7048 | 197.2008 | 0 |
46
+ | 149.9308 | 127.9843 | 1 |
47
+ | 110.7755 | 105.5121 | 2 |
48
+ | 94.8339 | 100.2063 | 3 |
49
+ | 83.1885 | 101.8379 | 4 |
50
+ | 75.9772 | 108.3454 | 5 |
51
+ | 69.3844 | 110.1212 | 6 |
52
+ | 64.3868 | 97.5026 | 7 |
53
+ | 60.4573 | 100.1366 | 8 |
54
+ | 56.7855 | 101.4410 | 9 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.25.1
60
+ - TensorFlow 2.9.2
61
+ - Datasets 2.8.0
62
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/esm2_t6_8M_UR50D",
3
+ "architectures": [
4
+ "EsmForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout": null,
8
+ "emb_layer_norm_before": false,
9
+ "esmfold_config": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 320,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1280,
18
+ "is_folding_model": false,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "mask_token_id": 32,
24
+ "max_position_embeddings": 1026,
25
+ "model_type": "esm",
26
+ "num_attention_heads": 20,
27
+ "num_hidden_layers": 6,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "rotary",
30
+ "problem_type": "regression",
31
+ "token_dropout": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.25.1",
34
+ "use_cache": true,
35
+ "vocab_list": null,
36
+ "vocab_size": 33
37
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3557f162a49e157a1de304f5cf3198f7204773efa91f9988d18930106d30436
3
+ size 30208956