End of training
Browse files- README.md +74 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: bsd-3-clause
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: hugohrban/progen2-small
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: progen2-small-lora-64-remote-homology-filtered
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# progen2-small-lora-64-remote-homology-filtered
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [hugohrban/progen2-small](https://huggingface.co/hugohrban/progen2-small) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1353
|
24 |
+
- Precision: 0.9499
|
25 |
+
- Recall: 0.9699
|
26 |
+
- F1-score: 0.9598
|
27 |
+
- Accuracy: 0.9595
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 0.0002
|
47 |
+
- train_batch_size: 192
|
48 |
+
- eval_batch_size: 192
|
49 |
+
- seed: 42
|
50 |
+
- gradient_accumulation_steps: 2
|
51 |
+
- total_train_batch_size: 384
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: cosine
|
54 |
+
- lr_scheduler_warmup_ratio: 0.1
|
55 |
+
- num_epochs: 5
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1-score | Accuracy |
|
60 |
+
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
|
61 |
+
| 0.3088 | 0.9985 | 332 | 0.2490 | 0.8692 | 0.9277 | 0.8975 | 0.8943 |
|
62 |
+
| 0.1806 | 2.0 | 665 | 0.1541 | 0.9259 | 0.9507 | 0.9382 | 0.9375 |
|
63 |
+
| 0.1036 | 2.9985 | 997 | 0.1190 | 0.9522 | 0.9541 | 0.9532 | 0.9532 |
|
64 |
+
| 0.0533 | 4.0 | 1330 | 0.1140 | 0.9538 | 0.9628 | 0.9582 | 0.9581 |
|
65 |
+
| 0.0272 | 4.9925 | 1660 | 0.1353 | 0.9499 | 0.9699 | 0.9598 | 0.9595 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- PEFT 0.10.0
|
71 |
+
- Transformers 4.40.2
|
72 |
+
- Pytorch 2.3.0+cu121
|
73 |
+
- Datasets 2.19.1
|
74 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "hugohrban/progen2-small",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"out_proj",
|
24 |
+
"qkv_proj"
|
25 |
+
],
|
26 |
+
"task_type": "SEQ_CLS",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cabe7f9a4dc74ff900356df9ef268636ce7e12173f25d83e25f008cecd6b7380
|
3 |
+
size 18888696
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7763586d7d04568a7fcbe08c1497b5fa926e9b06cdf36ce80c83c3079a22b7c8
|
3 |
+
size 5112
|