update model card README.md
Browse files
README.md
CHANGED
@@ -6,7 +6,6 @@ tags:
|
|
6 |
model-index:
|
7 |
- name: llama-3-WP
|
8 |
results: []
|
9 |
-
library_name: peft
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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: 2.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -32,28 +31,6 @@ More information needed
|
|
32 |
|
33 |
## Training procedure
|
34 |
|
35 |
-
|
36 |
-
The following `bitsandbytes` quantization config was used during training:
|
37 |
-
- load_in_8bit: False
|
38 |
-
- load_in_4bit: True
|
39 |
-
- llm_int8_threshold: 6.0
|
40 |
-
- llm_int8_skip_modules: None
|
41 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
42 |
-
- llm_int8_has_fp16_weight: False
|
43 |
-
- bnb_4bit_quant_type: nf4
|
44 |
-
- bnb_4bit_use_double_quant: True
|
45 |
-
- bnb_4bit_compute_dtype: float16
|
46 |
-
|
47 |
-
The following `bitsandbytes` quantization config was used during training:
|
48 |
-
- load_in_8bit: False
|
49 |
-
- load_in_4bit: True
|
50 |
-
- llm_int8_threshold: 6.0
|
51 |
-
- llm_int8_skip_modules: None
|
52 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
53 |
-
- llm_int8_has_fp16_weight: False
|
54 |
-
- bnb_4bit_quant_type: nf4
|
55 |
-
- bnb_4bit_use_double_quant: True
|
56 |
-
- bnb_4bit_compute_dtype: float16
|
57 |
### Training hyperparameters
|
58 |
|
59 |
The following hyperparameters were used during training:
|
@@ -70,14 +47,12 @@ The following hyperparameters were used during training:
|
|
70 |
|
71 |
| Training Loss | Epoch | Step | Validation Loss |
|
72 |
|:-------------:|:-----:|:----:|:---------------:|
|
73 |
-
| 2.
|
74 |
-
| 2.
|
75 |
|
76 |
|
77 |
### Framework versions
|
78 |
|
79 |
-
- PEFT 0.4.0
|
80 |
-
- PEFT 0.4.0
|
81 |
- Transformers 4.31.0
|
82 |
- Pytorch 2.1.2
|
83 |
- Datasets 2.19.1
|
|
|
6 |
model-index:
|
7 |
- name: llama-3-WP
|
8 |
results: []
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
15 |
|
16 |
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.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.1808
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
31 |
|
32 |
## Training procedure
|
33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 2.2077 | 0.4 | 200 | 2.2084 |
|
51 |
+
| 2.3065 | 0.81 | 400 | 2.1808 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
55 |
|
|
|
|
|
56 |
- Transformers 4.31.0
|
57 |
- Pytorch 2.1.2
|
58 |
- Datasets 2.19.1
|