Update README.md
Browse files
README.md
CHANGED
|
@@ -1,72 +1,72 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: transformers
|
| 3 |
-
license:
|
| 4 |
-
base_model: unsloth/Llama-3.2-3B-Instruct
|
| 5 |
-
tags:
|
| 6 |
-
- llama-factory
|
| 7 |
-
- freeze
|
| 8 |
-
- generated_from_trainer
|
| 9 |
-
model-index:
|
| 10 |
-
- name: Llama-3.2-3B-Instruct-24-9-29
|
| 11 |
-
results: []
|
| 12 |
-
---
|
| 13 |
-
|
| 14 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
-
|
| 17 |
-
# Llama-3.2-3B-Instruct-24-9-29
|
| 18 |
-
|
| 19 |
-
This model is a fine-tuned version of [unsloth/Llama-3.2-3B-Instruct](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct) on the lmsys_chat dataset.
|
| 20 |
-
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 1.1817
|
| 22 |
-
|
| 23 |
-
## Model description
|
| 24 |
-
|
| 25 |
-
More information needed
|
| 26 |
-
|
| 27 |
-
## Intended uses & limitations
|
| 28 |
-
|
| 29 |
-
More information needed
|
| 30 |
-
|
| 31 |
-
## Training and evaluation data
|
| 32 |
-
|
| 33 |
-
More information needed
|
| 34 |
-
|
| 35 |
-
## Training procedure
|
| 36 |
-
|
| 37 |
-
### Training hyperparameters
|
| 38 |
-
|
| 39 |
-
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate: 0.0001
|
| 41 |
-
- train_batch_size: 2
|
| 42 |
-
- eval_batch_size: 2
|
| 43 |
-
- seed: 42
|
| 44 |
-
- gradient_accumulation_steps: 8
|
| 45 |
-
- total_train_batch_size: 16
|
| 46 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
-
- lr_scheduler_type: cosine
|
| 48 |
-
- training_steps: 1000
|
| 49 |
-
- mixed_precision_training: Native AMP
|
| 50 |
-
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
-
| 1.256 | 0.0160 | 100 | 1.1817 |
|
| 56 |
-
| 1.236 | 0.0320 | 200 | 1.1817 |
|
| 57 |
-
| 1.2212 | 0.0480 | 300 | 1.1817 |
|
| 58 |
-
| 1.1804 | 0.0641 | 400 | 1.1817 |
|
| 59 |
-
| 1.2801 | 0.0801 | 500 | 1.1817 |
|
| 60 |
-
| 1.2232 | 0.0961 | 600 | 1.1817 |
|
| 61 |
-
| 1.2433 | 0.1121 | 700 | 1.1817 |
|
| 62 |
-
| 1.2231 | 0.1281 | 800 | 1.1817 |
|
| 63 |
-
| 1.2272 | 0.1441 | 900 | 1.1817 |
|
| 64 |
-
| 1.2843 | 0.1602 | 1000 | 1.1817 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
### Framework versions
|
| 68 |
-
|
| 69 |
-
- Transformers 4.45.0
|
| 70 |
-
- Pytorch 2.4.0+cu124
|
| 71 |
-
- Datasets 2.19.1
|
| 72 |
-
- Tokenizers 0.20.0
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: llama3.2
|
| 4 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- freeze
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Llama-3.2-3B-Instruct-24-9-29
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Llama-3.2-3B-Instruct-24-9-29
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [unsloth/Llama-3.2-3B-Instruct](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct) on the lmsys_chat dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.1817
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0001
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
+
- eval_batch_size: 2
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 16
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- training_steps: 1000
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
+
| 1.256 | 0.0160 | 100 | 1.1817 |
|
| 56 |
+
| 1.236 | 0.0320 | 200 | 1.1817 |
|
| 57 |
+
| 1.2212 | 0.0480 | 300 | 1.1817 |
|
| 58 |
+
| 1.1804 | 0.0641 | 400 | 1.1817 |
|
| 59 |
+
| 1.2801 | 0.0801 | 500 | 1.1817 |
|
| 60 |
+
| 1.2232 | 0.0961 | 600 | 1.1817 |
|
| 61 |
+
| 1.2433 | 0.1121 | 700 | 1.1817 |
|
| 62 |
+
| 1.2231 | 0.1281 | 800 | 1.1817 |
|
| 63 |
+
| 1.2272 | 0.1441 | 900 | 1.1817 |
|
| 64 |
+
| 1.2843 | 0.1602 | 1000 | 1.1817 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.45.0
|
| 70 |
+
- Pytorch 2.4.0+cu124
|
| 71 |
+
- Datasets 2.19.1
|
| 72 |
+
- Tokenizers 0.20.0
|