Upload TFEsmForSequenceClassification
Browse files- README.md +75 -0
- config.json +38 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: facebook/esm2_t30_150M_UR50D
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_keras_callback
|
| 6 |
+
model-index:
|
| 7 |
+
- name: esm2_t30_150M_UR50D-finetuned-AMP_Antibacteria-classification
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 12 |
+
probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# esm2_t30_150M_UR50D-finetuned-AMP_Antibacteria-classification
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [facebook/esm2_t30_150M_UR50D](https://huggingface.co/facebook/esm2_t30_150M_UR50D) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 0.0433
|
| 19 |
+
- Train Accuracy: 0.9871
|
| 20 |
+
- Validation Loss: 0.7702
|
| 21 |
+
- Validation Accuracy: 0.8014
|
| 22 |
+
- Epoch: 19
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- 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}
|
| 42 |
+
- training_precision: float32
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
| 47 |
+
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
| 48 |
+
| 0.6498 | 0.6047 | 0.6345 | 0.6288 | 0 |
|
| 49 |
+
| 0.5714 | 0.6877 | 0.5871 | 0.6882 | 1 |
|
| 50 |
+
| 0.3898 | 0.8198 | 0.5698 | 0.7242 | 2 |
|
| 51 |
+
| 0.2481 | 0.8921 | 0.5758 | 0.7696 | 3 |
|
| 52 |
+
| 0.1838 | 0.9248 | 0.6483 | 0.7730 | 4 |
|
| 53 |
+
| 0.1475 | 0.9390 | 0.6187 | 0.7904 | 5 |
|
| 54 |
+
| 0.1147 | 0.9541 | 0.6663 | 0.8007 | 6 |
|
| 55 |
+
| 0.0948 | 0.9618 | 0.7591 | 0.7819 | 7 |
|
| 56 |
+
| 0.0800 | 0.9701 | 0.7534 | 0.7959 | 8 |
|
| 57 |
+
| 0.0709 | 0.9739 | 0.8595 | 0.7810 | 9 |
|
| 58 |
+
| 0.0629 | 0.9767 | 0.8192 | 0.7907 | 10 |
|
| 59 |
+
| 0.0578 | 0.9792 | 0.8855 | 0.7946 | 11 |
|
| 60 |
+
| 0.0532 | 0.9814 | 0.9993 | 0.7762 | 12 |
|
| 61 |
+
| 0.0586 | 0.9801 | 0.9058 | 0.7761 | 13 |
|
| 62 |
+
| 0.0534 | 0.9816 | 0.8338 | 0.7786 | 14 |
|
| 63 |
+
| 0.0508 | 0.9824 | 0.7899 | 0.8033 | 15 |
|
| 64 |
+
| 0.0472 | 0.9840 | 0.9000 | 0.7800 | 16 |
|
| 65 |
+
| 0.0441 | 0.9851 | 0.8732 | 0.7911 | 17 |
|
| 66 |
+
| 0.0486 | 0.9846 | 0.8166 | 0.8088 | 18 |
|
| 67 |
+
| 0.0433 | 0.9871 | 0.7702 | 0.8014 | 19 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.40.1
|
| 73 |
+
- TensorFlow 2.15.0
|
| 74 |
+
- Datasets 2.19.1
|
| 75 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/esm2_t30_150M_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": 640,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "negative",
|
| 15 |
+
"1": "positive"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 2560,
|
| 19 |
+
"is_folding_model": false,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"negative": 0,
|
| 22 |
+
"positive": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-05,
|
| 25 |
+
"mask_token_id": 32,
|
| 26 |
+
"max_position_embeddings": 1026,
|
| 27 |
+
"model_type": "esm",
|
| 28 |
+
"num_attention_heads": 20,
|
| 29 |
+
"num_hidden_layers": 30,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "rotary",
|
| 32 |
+
"token_dropout": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.40.1",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_list": null,
|
| 37 |
+
"vocab_size": 33
|
| 38 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65ddcc9ae19b3ae6734ca99c5c30430583d71ff76020d26fb4c061b93bb1505c
|
| 3 |
+
size 595896088
|