Hugging Face's logo

Holmeister
/
Llama3_ei_oc_mixed_train

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
Holmeister commited on
Commit
d4bbfbf
•
1 Parent(s): 3aeeddc

Model save

Browse files
Files changed (2) hide show
  1. README.md +12 -14
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -2,22 +2,21 @@
2
  library_name: peft
3
  tags:
4
  - llama-factory
5
- - lora
6
  - generated_from_trainer
7
  base_model: meta-llama/Meta-Llama-3-8B
8
  model-index:
9
- - name: LLaMA3_ei_oc_mixed_train
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
- # LLaMA3_ei_oc_mixed_train
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the emollms_ei_oc_mixed dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0802
21
 
22
  ## Model description
23
 
@@ -50,15 +49,14 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 0.3319 | 0.3320 | 10 | 0.1265 |
54
- | 0.113 | 0.6639 | 20 | 0.0951 |
55
- | 0.0961 | 0.9959 | 30 | 0.0864 |
56
- | 0.0908 | 1.3278 | 40 | 0.0838 |
57
- | 0.0846 | 1.6598 | 50 | 0.0816 |
58
- | 0.0806 | 1.9917 | 60 | 0.0802 |
59
- | 0.0756 | 2.3237 | 70 | 0.0810 |
60
- | 0.0751 | 2.6556 | 80 | 0.0805 |
61
- | 0.0719 | 2.9876 | 90 | 0.0806 |
62
 
63
 
64
  ### Framework versions
 
2
  library_name: peft
3
  tags:
4
  - llama-factory
 
5
  - generated_from_trainer
6
  base_model: meta-llama/Meta-Llama-3-8B
7
  model-index:
8
+ - name: Llama3_ei_oc_mixed_train
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # Llama3_ei_oc_mixed_train
16
 
17
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1010
20
 
21
  ## Model description
22
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:------:|:----:|:---------------:|
52
+ | 0.3349 | 0.3604 | 10 | 0.1279 |
53
+ | 0.1057 | 0.7207 | 20 | 0.1124 |
54
+ | 0.0941 | 1.0811 | 30 | 0.1047 |
55
+ | 0.0853 | 1.4414 | 40 | 0.0996 |
56
+ | 0.0793 | 1.8018 | 50 | 0.0993 |
57
+ | 0.0768 | 2.1622 | 60 | 0.0987 |
58
+ | 0.0688 | 2.5225 | 70 | 0.1036 |
59
+ | 0.072 | 2.8829 | 80 | 0.1010 |
 
60
 
61
 
62
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed23dbc4781ee8b4ccdd5746bf99d595d4af4d1a5116a497e1546837b648ba8d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ddafbe0c3c326f6fedee4574dfc65ca9e03b32e3bafc163fe0ed8bd7157cb5d
3
  size 83945296