Model save
Browse files
README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
---
|
2 |
base_model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
|
3 |
tags:
|
|
|
|
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
- name: Meta-Llama-3-8B-Instruct-function-calling-json-mode-VisitorRequests
|
@@ -13,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# Meta-Llama-3-8B-Instruct-function-calling-json-mode-VisitorRequests
|
15 |
|
16 |
-
This model is a fine-tuned version of [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode) on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -46,12 +48,44 @@ The following hyperparameters were used during training:
|
|
46 |
|
47 |
### Training results
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
- PEFT 0.5.0
|
54 |
-
- Transformers 4.
|
55 |
- Pytorch 2.1.0+cu118
|
56 |
- Datasets 2.16.0
|
57 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
base_model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
|
3 |
tags:
|
4 |
+
- trl
|
5 |
+
- sft
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: Meta-Llama-3-8B-Instruct-function-calling-json-mode-VisitorRequests
|
|
|
15 |
|
16 |
# Meta-Llama-3-8B-Instruct-function-calling-json-mode-VisitorRequests
|
17 |
|
18 |
+
This model is a fine-tuned version of [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.7458
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
53 |
+
| 2.0583 | 0.0630 | 1 | 3.3171 |
|
54 |
+
| 3.2898 | 0.1260 | 2 | 1.8112 |
|
55 |
+
| 1.7495 | 0.1890 | 3 | 1.3350 |
|
56 |
+
| 1.3176 | 0.2520 | 4 | 5.6302 |
|
57 |
+
| 5.9627 | 0.3150 | 5 | 2.1688 |
|
58 |
+
| 2.1926 | 0.3780 | 6 | 1.4297 |
|
59 |
+
| 1.3724 | 0.4409 | 7 | 1.2279 |
|
60 |
+
| 1.2125 | 0.5039 | 8 | 0.9445 |
|
61 |
+
| 0.9749 | 0.5669 | 9 | 1.1901 |
|
62 |
+
| 1.2164 | 0.6299 | 10 | 0.9843 |
|
63 |
+
| 0.9808 | 0.6929 | 11 | 0.9213 |
|
64 |
+
| 0.8698 | 0.7559 | 12 | 0.8721 |
|
65 |
+
| 0.8668 | 0.8189 | 13 | 0.9308 |
|
66 |
+
| 0.8635 | 0.8819 | 14 | 0.8319 |
|
67 |
+
| 0.7789 | 0.9449 | 15 | 0.8164 |
|
68 |
+
| 0.7402 | 1.0079 | 16 | 0.8220 |
|
69 |
+
| 0.7312 | 1.0709 | 17 | 0.8305 |
|
70 |
+
| 0.7561 | 1.1339 | 18 | 0.9768 |
|
71 |
+
| 0.9879 | 1.1969 | 19 | 0.8437 |
|
72 |
+
| 0.7647 | 1.2598 | 20 | 0.8364 |
|
73 |
+
| 0.7093 | 1.3228 | 21 | 0.8028 |
|
74 |
+
| 0.7358 | 1.3858 | 22 | 0.8184 |
|
75 |
+
| 0.7301 | 1.4488 | 23 | 0.8050 |
|
76 |
+
| 0.7607 | 1.5118 | 24 | 0.7652 |
|
77 |
+
| 0.6892 | 1.5748 | 25 | 0.7317 |
|
78 |
+
| 0.7158 | 1.6378 | 26 | 0.7236 |
|
79 |
+
| 0.6701 | 1.7008 | 27 | 0.7130 |
|
80 |
+
| 0.6905 | 1.7638 | 28 | 0.7529 |
|
81 |
+
| 0.6791 | 1.8268 | 29 | 0.7813 |
|
82 |
+
| 0.7093 | 1.8898 | 30 | 0.7458 |
|
83 |
|
84 |
|
85 |
### Framework versions
|
86 |
|
87 |
- PEFT 0.5.0
|
88 |
+
- Transformers 4.44.0
|
89 |
- Pytorch 2.1.0+cu118
|
90 |
- Datasets 2.16.0
|
91 |
+
- Tokenizers 0.19.1
|
runs/Aug19_13-37-37_chimera13/events.out.tfevents.1724089976.chimera13.237850.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:481cf27bbd3fa04125467f3f30e0457f6188e42b5913fff95906cd7437f177e7
|
3 |
+
size 354
|