Commit
•
5cb046e
1
Parent(s):
173d941
Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: facebook/esm2_t12_35M_UR50D
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- spearmanr
|
| 8 |
+
model-index:
|
| 9 |
+
- name: esm2_t12_35M_UR50D-finetuned-rep7868aav2-v0
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# esm2_t12_35M_UR50D-finetuned-rep7868aav2-v0
|
| 17 |
+
|
| 18 |
+
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.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0513
|
| 21 |
+
- Spearmanr: 0.7389
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 20
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Spearmanr |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|
|
| 53 |
+
| 0.118 | 1.0 | 1180 | 0.1154 | 0.3185 |
|
| 54 |
+
| 0.1156 | 2.0 | 2360 | 0.1109 | 0.3383 |
|
| 55 |
+
| 0.1143 | 3.0 | 3540 | 0.1162 | 0.3194 |
|
| 56 |
+
| 0.1192 | 4.0 | 4720 | 0.1111 | 0.2974 |
|
| 57 |
+
| 0.1147 | 5.0 | 5900 | 0.1125 | 0.4043 |
|
| 58 |
+
| 0.1196 | 6.0 | 7080 | 0.1116 | 0.1580 |
|
| 59 |
+
| 0.1171 | 7.0 | 8260 | 0.1114 | 0.2923 |
|
| 60 |
+
| 0.1177 | 8.0 | 9440 | 0.1106 | 0.3592 |
|
| 61 |
+
| 0.1126 | 9.0 | 10620 | 0.1105 | 0.3724 |
|
| 62 |
+
| 0.1152 | 10.0 | 11800 | 0.1135 | 0.4947 |
|
| 63 |
+
| 0.1159 | 11.0 | 12980 | 0.1082 | 0.5113 |
|
| 64 |
+
| 0.0953 | 12.0 | 14160 | 0.0820 | 0.6096 |
|
| 65 |
+
| 0.0798 | 13.0 | 15340 | 0.0688 | 0.6442 |
|
| 66 |
+
| 0.074 | 14.0 | 16520 | 0.0710 | 0.6738 |
|
| 67 |
+
| 0.0704 | 15.0 | 17700 | 0.0816 | 0.6736 |
|
| 68 |
+
| 0.0678 | 16.0 | 18880 | 0.0596 | 0.7142 |
|
| 69 |
+
| 0.0599 | 17.0 | 20060 | 0.0689 | 0.7187 |
|
| 70 |
+
| 0.0568 | 18.0 | 21240 | 0.0566 | 0.7308 |
|
| 71 |
+
| 0.0534 | 19.0 | 22420 | 0.0518 | 0.7340 |
|
| 72 |
+
| 0.0522 | 20.0 | 23600 | 0.0513 | 0.7389 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.35.2
|
| 78 |
+
- Pytorch 2.1.0+cu121
|
| 79 |
+
- Datasets 2.16.1
|
| 80 |
+
- Tokenizers 0.15.1
|