Model save
Browse files
README.md
CHANGED
@@ -1,26 +1,13 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
datasets:
|
7 |
-
- tyzhu/lmind_nq_train6000_eval6489_v1_qa
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
11 |
- name: lmind_nq_train6000_eval6489_v1_qa_3e-5_lora2
|
12 |
-
results:
|
13 |
-
- task:
|
14 |
-
name: Causal Language Modeling
|
15 |
-
type: text-generation
|
16 |
-
dataset:
|
17 |
-
name: tyzhu/lmind_nq_train6000_eval6489_v1_qa
|
18 |
-
type: tyzhu/lmind_nq_train6000_eval6489_v1_qa
|
19 |
-
metrics:
|
20 |
-
- name: Accuracy
|
21 |
-
type: accuracy
|
22 |
-
value: 0.5511794871794872
|
23 |
-
library_name: peft
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -28,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# lmind_nq_train6000_eval6489_v1_qa_3e-5_lora2
|
30 |
|
31 |
-
This model is a fine-tuned version of [
|
32 |
It achieves the following results on the evaluation set:
|
33 |
-
- Loss: 2.
|
34 |
-
- Accuracy: 0.
|
35 |
|
36 |
## Model description
|
37 |
|
@@ -66,64 +53,63 @@ The following hyperparameters were used during training:
|
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
-
| Training Loss | Epoch
|
70 |
-
|
71 |
-
|
|
72 |
-
| 1.
|
73 |
-
| 1.
|
74 |
-
| 1.
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.
|
105 |
-
| 0.
|
106 |
-
| 0.
|
107 |
-
| 0.
|
108 |
-
| 0.
|
109 |
-
| 0.
|
110 |
-
| 0.
|
111 |
-
| 0.
|
112 |
-
| 0.
|
113 |
-
| 0.
|
114 |
-
| 0.
|
115 |
-
| 0.
|
116 |
-
| 0.
|
117 |
-
| 0.
|
118 |
-
| 0.
|
119 |
-
| 0.
|
120 |
-
| 0.
|
121 |
|
122 |
|
123 |
### Framework versions
|
124 |
|
125 |
-
-
|
126 |
-
- Transformers 4.41.1
|
127 |
- Pytorch 2.1.0+cu121
|
128 |
-
- Datasets 2.
|
129 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
+
license: llama2
|
3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
model-index:
|
9 |
- name: lmind_nq_train6000_eval6489_v1_qa_3e-5_lora2
|
10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
15 |
|
16 |
# lmind_nq_train6000_eval6489_v1_qa_3e-5_lora2
|
17 |
|
18 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.4443
|
21 |
+
- Accuracy: 0.5966
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
58 |
+
| 2.0369 | 1.0 | 187 | 1.2953 | 0.6128 |
|
59 |
+
| 1.2821 | 2.0 | 375 | 1.2741 | 0.6146 |
|
60 |
+
| 1.1987 | 3.0 | 562 | 1.2715 | 0.6162 |
|
61 |
+
| 1.066 | 4.0 | 750 | 1.3011 | 0.6151 |
|
62 |
+
| 0.9381 | 5.0 | 937 | 1.3728 | 0.6126 |
|
63 |
+
| 0.8238 | 6.0 | 1125 | 1.4599 | 0.6091 |
|
64 |
+
| 0.7289 | 7.0 | 1312 | 1.5455 | 0.6064 |
|
65 |
+
| 0.6559 | 8.0 | 1500 | 1.6359 | 0.6026 |
|
66 |
+
| 0.5733 | 9.0 | 1687 | 1.7149 | 0.6006 |
|
67 |
+
| 0.5336 | 10.0 | 1875 | 1.8006 | 0.5989 |
|
68 |
+
| 0.5116 | 11.0 | 2062 | 1.8851 | 0.5982 |
|
69 |
+
| 0.4934 | 12.0 | 2250 | 1.9262 | 0.5982 |
|
70 |
+
| 0.4823 | 13.0 | 2437 | 1.9413 | 0.5974 |
|
71 |
+
| 0.47 | 14.0 | 2625 | 2.0121 | 0.5967 |
|
72 |
+
| 0.4661 | 15.0 | 2812 | 2.0250 | 0.5968 |
|
73 |
+
| 0.462 | 16.0 | 3000 | 1.9805 | 0.5990 |
|
74 |
+
| 0.4357 | 17.0 | 3187 | 2.0656 | 0.5976 |
|
75 |
+
| 0.4348 | 18.0 | 3375 | 2.0308 | 0.5979 |
|
76 |
+
| 0.4331 | 19.0 | 3562 | 2.0629 | 0.5990 |
|
77 |
+
| 0.4341 | 20.0 | 3750 | 2.0815 | 0.5983 |
|
78 |
+
| 0.434 | 21.0 | 3937 | 2.1253 | 0.5968 |
|
79 |
+
| 0.4335 | 22.0 | 4125 | 2.1789 | 0.5971 |
|
80 |
+
| 0.4346 | 23.0 | 4312 | 2.1455 | 0.5952 |
|
81 |
+
| 0.4326 | 24.0 | 4500 | 2.1990 | 0.5971 |
|
82 |
+
| 0.4139 | 25.0 | 4687 | 2.1890 | 0.5976 |
|
83 |
+
| 0.4139 | 26.0 | 4875 | 2.1939 | 0.5968 |
|
84 |
+
| 0.4162 | 27.0 | 5062 | 2.2190 | 0.5965 |
|
85 |
+
| 0.4177 | 28.0 | 5250 | 2.2781 | 0.5955 |
|
86 |
+
| 0.4173 | 29.0 | 5437 | 2.2681 | 0.5976 |
|
87 |
+
| 0.4187 | 30.0 | 5625 | 2.2996 | 0.5959 |
|
88 |
+
| 0.4199 | 31.0 | 5812 | 2.2395 | 0.5981 |
|
89 |
+
| 0.4213 | 32.0 | 6000 | 2.2991 | 0.5957 |
|
90 |
+
| 0.4015 | 33.0 | 6187 | 2.3223 | 0.5952 |
|
91 |
+
| 0.4058 | 34.0 | 6375 | 2.3266 | 0.5957 |
|
92 |
+
| 0.4056 | 35.0 | 6562 | 2.3779 | 0.5946 |
|
93 |
+
| 0.4078 | 36.0 | 6750 | 2.3453 | 0.5951 |
|
94 |
+
| 0.4097 | 37.0 | 6937 | 2.3379 | 0.5965 |
|
95 |
+
| 0.4105 | 38.0 | 7125 | 2.3624 | 0.5969 |
|
96 |
+
| 0.4116 | 39.0 | 7312 | 2.3846 | 0.5962 |
|
97 |
+
| 0.4121 | 40.0 | 7500 | 2.3748 | 0.5945 |
|
98 |
+
| 0.3973 | 41.0 | 7687 | 2.3797 | 0.5956 |
|
99 |
+
| 0.3985 | 42.0 | 7875 | 2.3599 | 0.5967 |
|
100 |
+
| 0.4014 | 43.0 | 8062 | 2.3475 | 0.5971 |
|
101 |
+
| 0.4032 | 44.0 | 8250 | 2.3937 | 0.5987 |
|
102 |
+
| 0.4028 | 45.0 | 8437 | 2.3863 | 0.5967 |
|
103 |
+
| 0.4027 | 46.0 | 8625 | 2.4195 | 0.5956 |
|
104 |
+
| 0.4046 | 47.0 | 8812 | 2.3832 | 0.5970 |
|
105 |
+
| 0.4067 | 48.0 | 9000 | 2.3805 | 0.5973 |
|
106 |
+
| 0.3923 | 49.0 | 9187 | 2.4460 | 0.5957 |
|
107 |
+
| 0.3949 | 49.87 | 9350 | 2.4443 | 0.5966 |
|
108 |
|
109 |
|
110 |
### Framework versions
|
111 |
|
112 |
+
- Transformers 4.34.0
|
|
|
113 |
- Pytorch 2.1.0+cu121
|
114 |
+
- Datasets 2.18.0
|
115 |
+
- Tokenizers 0.14.1
|