RishuD7/Llama3.1_question_answer_model_1
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,9 +43,9 @@ The following `bitsandbytes` quantization config was used during training:
|
|
43 |
- llm_int8_skip_modules: None
|
44 |
- llm_int8_enable_fp32_cpu_offload: False
|
45 |
- llm_int8_has_fp16_weight: False
|
46 |
-
- bnb_4bit_quant_type:
|
47 |
- bnb_4bit_use_double_quant: False
|
48 |
-
- bnb_4bit_compute_dtype:
|
49 |
- bnb_4bit_quant_storage: uint8
|
50 |
- load_in_4bit: False
|
51 |
- load_in_8bit: True
|
@@ -66,9 +66,9 @@ The following hyperparameters were used during training:
|
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss |
|
68 |
|:-------------:|:------:|:----:|:---------------:|
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2020
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- llm_int8_skip_modules: None
|
44 |
- llm_int8_enable_fp32_cpu_offload: False
|
45 |
- llm_int8_has_fp16_weight: False
|
46 |
+
- bnb_4bit_quant_type: nf4
|
47 |
- bnb_4bit_use_double_quant: False
|
48 |
+
- bnb_4bit_compute_dtype: bfloat16
|
49 |
- bnb_4bit_quant_storage: uint8
|
50 |
- load_in_4bit: False
|
51 |
- load_in_8bit: True
|
|
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss |
|
68 |
|:-------------:|:------:|:----:|:---------------:|
|
69 |
+
| 0.0968 | 0.9996 | 1150 | 0.1602 |
|
70 |
+
| 0.076 | 2.0 | 2301 | 0.1828 |
|
71 |
+
| 0.0678 | 2.9987 | 3450 | 0.2020 |
|
72 |
|
73 |
|
74 |
### Framework versions
|