rishavranaut
commited on
Commit
•
a3562ec
1
Parent(s):
04d8a72
rishavranaut/QWEN_2_7B_Fact_U
Browse files
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: Qwen/Qwen2-7B
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: QWEN_2_7B_Fact_U
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# QWEN_2_7B_Fact_U
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.0739
|
24 |
+
- Accuracy: 0.7812
|
25 |
+
- Precision: 0.8033
|
26 |
+
- Recall: 0.7670
|
27 |
+
- F1 score: 0.7847
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 0.0001
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 4
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Accuracy | F1 score | Precision | Recall | Validation Loss |
|
57 |
+
|:-------------:|:------:|:----:|:--------:|:--------:|:---------:|:------:|:---------------:|
|
58 |
+
| 0.9778 | 0.2509 | 200 | 0.6529 | 0.7128 | 0.6256 | 0.8281 | 0.8856 |
|
59 |
+
| 0.8085 | 0.5019 | 400 | 0.7376 | 0.7514 | 0.7407 | 0.7624 | 0.7247 |
|
60 |
+
| 0.728 | 0.7528 | 600 | 0.7541 | 0.7628 | 0.7654 | 0.7602 | 0.6549 |
|
61 |
+
| 0.6569 | 1.0038 | 800 | 0.6584 | 0.7671 | 0.7891 | 0.7534 | 0.7708 |
|
62 |
+
| 0.4831 | 1.2547 | 1000 | 0.7161 | 0.7118 | 0.6756 | 0.8575 | 0.7557 |
|
63 |
+
| 0.4952 | 1.5056 | 1200 | 0.6699 | 0.7788 | 0.7848 | 0.7919 | 0.7883 |
|
64 |
+
| 0.4992 | 1.7566 | 1400 | 0.6185 | 0.7824 | 0.8173 | 0.7489 | 0.7816 |
|
65 |
+
| 0.4104 | 2.0075 | 1600 | 0.6325 | 0.7753 | 0.7770 | 0.7964 | 0.7866 |
|
66 |
+
| 0.3071 | 2.2585 | 1800 | 0.6979 | 0.7635 | 0.7796 | 0.7602 | 0.7698 |
|
67 |
+
| 0.3557 | 2.5094 | 2000 | 0.7270 | 0.7694 | 0.7617 | 0.8100 | 0.7851 |
|
68 |
+
| 0.3088 | 2.7604 | 2200 | 0.7186 | 0.7788 | 0.8024 | 0.7624 | 0.7819 |
|
69 |
+
| 0.3848 | 3.0113 | 2400 | 0.6926 | 0.7718 | 0.7857 | 0.7715 | 0.7785 |
|
70 |
+
| 0.2186 | 3.2622 | 2600 | 0.7965 | 0.7835 | 0.8225 | 0.7443 | 0.7815 |
|
71 |
+
| 0.2531 | 3.5132 | 2800 | 0.7843 | 0.78 | 0.8364 | 0.7172 | 0.7722 |
|
72 |
+
| 0.2134 | 3.7641 | 3000 | 0.7977 | 0.7729 | 0.7849 | 0.7760 | 0.7804 |
|
73 |
+
| 0.1961 | 4.0151 | 3200 | 0.8438 | 0.7871 | 0.8443 | 0.7240 | 0.7795 |
|
74 |
+
| 0.1464 | 4.2660 | 3400 | 0.9256 | 0.7835 | 0.8225 | 0.7443 | 0.7815 |
|
75 |
+
| 0.1132 | 4.5169 | 3600 | 1.0431 | 0.7824 | 0.8052 | 0.7670 | 0.7856 |
|
76 |
+
| 0.1323 | 4.7679 | 3800 | 1.0739 | 0.7812 | 0.8033 | 0.7670 | 0.7847 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- PEFT 0.11.1
|
82 |
+
- Transformers 4.44.2
|
83 |
+
- Pytorch 2.3.0+cu121
|
84 |
+
- Datasets 2.19.1
|
85 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40428968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84900bf961ca05c407184c04d77682f971c283ea88b5ee3fc579acb6d205d34b
|
3 |
size 40428968
|
runs/Sep25_21-40-14_iit-p/events.out.tfevents.1727280616.iit-p
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49fe1271d8e87935fe639f2c32bef4f97e1e3d078ebff638f68341c2acb7e8ff
|
3 |
+
size 16876
|