Kanonenbombe
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -1,67 +1,63 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
- meta-llama/Llama-3.2-1B
|
14 |
-
---
|
15 |
|
16 |
-
|
17 |
-
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
# llama3.2-1B-Function-calling
|
20 |
|
21 |
-
This model
|
22 |
-
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.1491
|
24 |
|
25 |
## Model description
|
26 |
|
27 |
-
|
28 |
|
29 |
## Intended uses & limitations
|
30 |
|
31 |
-
|
32 |
|
33 |
## Training and evaluation data
|
34 |
|
35 |
-
More information needed
|
36 |
|
37 |
## Training procedure
|
38 |
|
39 |
### Training hyperparameters
|
40 |
|
41 |
-
The following hyperparameters were used during training:
|
42 |
-
- learning_rate: 2e-05
|
43 |
-
- train_batch_size: 1
|
44 |
-
- eval_batch_size: 1
|
45 |
-
- seed: 42
|
46 |
-
- gradient_accumulation_steps: 32
|
47 |
-
- total_train_batch_size: 32
|
48 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
-
- lr_scheduler_type: linear
|
50 |
-
- num_epochs: 3
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
-
|:-------------:|:------:|:----:|:---------------:|
|
57 |
-
| 0.3083 | 0.9997 | 1687 | 0.3622 |
|
58 |
-
| 0.202 | 2.0 | 3375 | 0.2844 |
|
59 |
| 0.1655 | 2.9997 | 5061 | 0.1491 |
|
60 |
|
|
|
61 |
|
62 |
-
|
63 |
|
64 |
-
- Transformers 4.45.2
|
65 |
-
- Pytorch 2.4.1+cu121
|
66 |
-
- Datasets 3.0.1
|
67 |
- Tokenizers 0.20.0
|
|
|
1 |
+
library_name: transformers
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: llama3.2-1B-Function-calling
|
6 |
+
results: []
|
7 |
+
datasets:
|
8 |
+
- Salesforce/xlam-function-calling-60k
|
9 |
+
language:
|
10 |
+
- en
|
11 |
+
base_model:
|
12 |
+
- meta-llama/Llama-3.2-1B
|
|
|
|
|
13 |
|
14 |
+
---
|
|
|
15 |
|
16 |
# llama3.2-1B-Function-calling
|
17 |
|
18 |
+
**⚠️ Important: This model is still under development and has not been fully fine-tuned. It is not yet suitable for use in production and should be treated as a work-in-progress. The results and performance metrics shared here are preliminary and subject to change.**
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
22 |
+
This model was trained from scratch on an unknown dataset and is intended for function-calling tasks. As it is still in early stages, further development is required to optimize its performance.
|
23 |
|
24 |
## Intended uses & limitations
|
25 |
|
26 |
+
Currently, this model is not fully trained or optimized for any specific task. It is intended to handle function-calling tasks but should not be used in production until more comprehensive fine-tuning and evaluation are completed.
|
27 |
|
28 |
## Training and evaluation data
|
29 |
|
30 |
+
More information is needed regarding the dataset used for training. The model has not yet been fully evaluated, and additional testing is required to confirm its capabilities.
|
31 |
|
32 |
## Training procedure
|
33 |
|
34 |
### Training hyperparameters
|
35 |
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 1
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 32
|
42 |
+
- total_train_batch_size: 32
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 3
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:------:|:----:|:---------------:|
|
52 |
+
| 0.3083 | 0.9997 | 1687 | 0.3622 |
|
53 |
+
| 0.202 | 2.0 | 3375 | 0.2844 |
|
54 |
| 0.1655 | 2.9997 | 5061 | 0.1491 |
|
55 |
|
56 |
+
These results are preliminary, and further training will be necessary to refine the model's performance.
|
57 |
|
58 |
+
## Framework versions
|
59 |
|
60 |
+
- Transformers 4.45.2
|
61 |
+
- Pytorch 2.4.1+cu121
|
62 |
+
- Datasets 3.0.1
|
63 |
- Tokenizers 0.20.0
|