DNA-LLM/synth_model_medium_v2
Browse files- README.md +12 -9
- config.json +6 -6
- generation_config.json +1 -1
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
|
4 |
-
base_model: DNA-LLM/virus-pythia-85M-2048-two_d_plus_ce
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
@@ -14,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# virus-pythia-1.2M-2048-ce_synthetic
|
16 |
|
17 |
-
This model is a fine-tuned version of [DNA-LLM/virus-pythia-
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -34,19 +33,23 @@ More information needed
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 5e-05
|
37 |
-
- train_batch_size:
|
38 |
-
- eval_batch_size:
|
39 |
- seed: 42
|
40 |
- gradient_accumulation_steps: 4
|
41 |
-
- total_train_batch_size:
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
- lr_scheduler_warmup_steps: 1
|
45 |
- num_epochs: 1
|
46 |
|
|
|
|
|
|
|
|
|
47 |
### Framework versions
|
48 |
|
49 |
-
- Transformers 4.45.
|
50 |
-
- Pytorch 2.4.
|
51 |
- Datasets 3.0.1
|
52 |
-
- Tokenizers 0.20.
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
base_model: DNA-LLM/virus-pythia-1.2M-2048-ce_plus_energy
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# virus-pythia-1.2M-2048-ce_synthetic
|
15 |
|
16 |
+
This model is a fine-tuned version of [DNA-LLM/virus-pythia-1.2M-2048-ce_plus_energy](https://huggingface.co/DNA-LLM/virus-pythia-1.2M-2048-ce_plus_energy) on an unknown dataset.
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 480
|
37 |
+
- eval_batch_size: 4
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 4
|
40 |
+
- total_train_batch_size: 1920
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 1
|
44 |
- num_epochs: 1
|
45 |
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
### Framework versions
|
51 |
|
52 |
+
- Transformers 4.45.2
|
53 |
+
- Pytorch 2.4.1+cu121
|
54 |
- Datasets 3.0.1
|
55 |
+
- Tokenizers 0.20.1
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "DNA-LLM/virus-pythia-
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
@@ -10,14 +10,14 @@
|
|
10 |
"eos_token_id": 0,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout": 0.0,
|
13 |
-
"hidden_size":
|
14 |
"initializer_range": 0.02,
|
15 |
-
"intermediate_size":
|
16 |
"layer_norm_eps": 1e-05,
|
17 |
"max_position_embeddings": 2048,
|
18 |
"model_type": "gpt_neox",
|
19 |
-
"num_attention_heads":
|
20 |
-
"num_hidden_layers":
|
21 |
"partial_rotary_factor": 0.25,
|
22 |
"rope_scaling": null,
|
23 |
"rope_theta": 10000,
|
@@ -25,7 +25,7 @@
|
|
25 |
"rotary_pct": 0.25,
|
26 |
"tie_word_embeddings": false,
|
27 |
"torch_dtype": "float32",
|
28 |
-
"transformers_version": "4.45.
|
29 |
"use_cache": true,
|
30 |
"use_parallel_residual": true,
|
31 |
"vocab_size": 1867
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "DNA-LLM/virus-pythia-1.2M-2048-ce_plus_energy",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
|
|
10 |
"eos_token_id": 0,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 128,
|
14 |
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 512,
|
16 |
"layer_norm_eps": 1e-05,
|
17 |
"max_position_embeddings": 2048,
|
18 |
"model_type": "gpt_neox",
|
19 |
+
"num_attention_heads": 4,
|
20 |
+
"num_hidden_layers": 6,
|
21 |
"partial_rotary_factor": 0.25,
|
22 |
"rope_scaling": null,
|
23 |
"rope_theta": 10000,
|
|
|
25 |
"rotary_pct": 0.25,
|
26 |
"tie_word_embeddings": false,
|
27 |
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.45.2",
|
29 |
"use_cache": true,
|
30 |
"use_parallel_residual": true,
|
31 |
"vocab_size": 1867
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 0,
|
5 |
-
"transformers_version": "4.45.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.45.2"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96717780fbae26014418efece25e3f70f2dc13855c69b2fae50835fc78b60de8
|
3 |
+
size 6679704
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c4575a22107a1146a8cc4ab2f80f2f84d8531feb64d908608cde0bfcdfd8118
|
3 |
size 5176
|