Model save
Browse files- README.md +13 -25
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,23 +3,11 @@ license: other
|
|
3 |
base_model: Qwen/Qwen1.5-4B
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
datasets:
|
7 |
-
- tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
11 |
- name: lmind_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_lora2
|
12 |
-
results:
|
13 |
-
- task:
|
14 |
-
name: Causal Language Modeling
|
15 |
-
type: text-generation
|
16 |
-
dataset:
|
17 |
-
name: tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
|
18 |
-
type: tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
|
19 |
-
metrics:
|
20 |
-
- name: Accuracy
|
21 |
-
type: accuracy
|
22 |
-
value: 0.7780232896652111
|
23 |
library_name: peft
|
24 |
---
|
25 |
|
@@ -28,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# lmind_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_lora2
|
30 |
|
31 |
-
This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on
|
32 |
It achieves the following results on the evaluation set:
|
33 |
-
- Loss: 0.4804
|
34 |
- Accuracy: 0.7780
|
|
|
35 |
|
36 |
## Model description
|
37 |
|
@@ -78,16 +66,16 @@ The following hyperparameters were used during training:
|
|
78 |
| 0.6144 | 8.0 | 8714 | 0.7404 | 0.7907 |
|
79 |
| 0.5355 | 8.9998 | 9803 | 0.7469 | 0.7288 |
|
80 |
| 0.4584 | 9.9977 | 10890 | 0.7531 | 0.6794 |
|
81 |
-
| 0.413 | 10.9998 | 11979 | 0.
|
82 |
-
| 0.3731 | 11.9995 | 13068 | 0.
|
83 |
-
| 0.3423 | 12.9993 | 14157 | 0.
|
84 |
-
| 0.3185 | 14.0 | 15247 | 0.
|
85 |
-
| 0.2924 | 14.9998 | 16336 | 0.
|
86 |
-
| 0.2824 | 15.9995 | 17425 | 0.
|
87 |
-
| 0.2669 | 16.9993 | 18514 | 0.
|
88 |
-
| 0.2517 | 18.0 | 19604 | 0.
|
89 |
-
| 0.2376 | 18.9998 | 20693 | 0.
|
90 |
-
| 0.2316 | 19.9977 | 21780 | 0.
|
91 |
|
92 |
|
93 |
### Framework versions
|
|
|
3 |
base_model: Qwen/Qwen1.5-4B
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
model-index:
|
9 |
- name: lmind_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_lora2
|
10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
library_name: peft
|
12 |
---
|
13 |
|
|
|
16 |
|
17 |
# lmind_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_lora2
|
18 |
|
19 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
|
|
21 |
- Accuracy: 0.7780
|
22 |
+
- Loss: 0.4804
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
66 |
| 0.6144 | 8.0 | 8714 | 0.7404 | 0.7907 |
|
67 |
| 0.5355 | 8.9998 | 9803 | 0.7469 | 0.7288 |
|
68 |
| 0.4584 | 9.9977 | 10890 | 0.7531 | 0.6794 |
|
69 |
+
| 0.413 | 10.9998 | 11979 | 0.7577 | 0.6292 |
|
70 |
+
| 0.3731 | 11.9995 | 13068 | 0.7616 | 0.5926 |
|
71 |
+
| 0.3423 | 12.9993 | 14157 | 0.7656 | 0.5620 |
|
72 |
+
| 0.3185 | 14.0 | 15247 | 0.7682 | 0.5426 |
|
73 |
+
| 0.2924 | 14.9998 | 16336 | 0.7708 | 0.5232 |
|
74 |
+
| 0.2824 | 15.9995 | 17425 | 0.7727 | 0.5129 |
|
75 |
+
| 0.2669 | 16.9993 | 18514 | 0.7748 | 0.4988 |
|
76 |
+
| 0.2517 | 18.0 | 19604 | 0.7762 | 0.4892 |
|
77 |
+
| 0.2376 | 18.9998 | 20693 | 0.7773 | 0.4808 |
|
78 |
+
| 0.2316 | 19.9977 | 21780 | 0.7780 | 0.4804 |
|
79 |
|
80 |
|
81 |
### Framework versions
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c4b324b3d635603b7a499b3bae651530278432d8833a0e95b6ca0128c6aac73
|
3 |
size 5176
|