Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_qa_1e-4_lora2

Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
e72de6d
·
verified ·
1 Parent(s): a37eb0a

Model save

Browse files
Files changed (2) hide show
  1. README.md +55 -67
  2. training_args.bin +1 -1
README.md CHANGED
@@ -3,23 +3,11 @@ license: llama2
3
  base_model: meta-llama/Llama-2-7b-hf
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_1e-4_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: 0.6010769230769231
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  # lmind_nq_train6000_eval6489_v1_qa_1e-4_lora2
29
 
30
- This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the tyzhu/lmind_nq_train6000_eval6489_v1_qa dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 2.0414
33
  - Accuracy: 0.6011
 
34
 
35
  ## Model description
36
 
@@ -65,58 +53,58 @@ The following hyperparameters were used during training:
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.598 | 1.0 | 187 | 1.2692 | 0.6147 |
71
- | 1.1923 | 2.0 | 375 | 1.2733 | 0.6176 |
72
- | 0.9732 | 3.0 | 562 | 1.3396 | 0.6136 |
73
- | 0.7763 | 4.0 | 750 | 1.4358 | 0.6104 |
74
- | 0.6498 | 5.0 | 937 | 1.5630 | 0.6052 |
75
- | 0.57 | 6.0 | 1125 | 1.6599 | 0.6031 |
76
- | 0.5253 | 7.0 | 1312 | 1.7480 | 0.6027 |
77
- | 0.4958 | 8.0 | 1500 | 1.8060 | 0.6021 |
78
- | 0.4521 | 9.0 | 1687 | 1.8599 | 0.6013 |
79
- | 0.443 | 10.0 | 1875 | 1.9468 | 0.6013 |
80
- | 0.439 | 11.0 | 2062 | 1.9500 | 0.6015 |
81
- | 0.433 | 12.0 | 2250 | 1.9104 | 0.6021 |
82
- | 0.4323 | 13.0 | 2437 | 2.0079 | 0.6001 |
83
- | 0.4281 | 14.0 | 2625 | 1.9881 | 0.6008 |
84
- | 0.4277 | 15.0 | 2812 | 2.0305 | 0.6005 |
85
- | 0.4298 | 16.0 | 3000 | 2.0478 | 0.6005 |
86
- | 0.4082 | 17.0 | 3187 | 2.0539 | 0.6007 |
87
- | 0.411 | 18.0 | 3375 | 2.0314 | 0.6005 |
88
- | 0.4113 | 19.0 | 3562 | 2.0368 | 0.6011 |
89
- | 0.4121 | 20.0 | 3750 | 2.1022 | 0.6017 |
90
- | 0.414 | 21.0 | 3937 | 2.0512 | 0.6007 |
91
- | 0.4163 | 22.0 | 4125 | 2.1147 | 0.6016 |
92
- | 0.4172 | 23.0 | 4312 | 2.0942 | 0.6007 |
93
- | 0.4156 | 24.0 | 4500 | 2.1201 | 0.6008 |
94
- | 0.3997 | 25.0 | 4687 | 2.0660 | 0.6010 |
95
- | 0.3994 | 26.0 | 4875 | 2.0832 | 0.6006 |
96
- | 0.4032 | 27.0 | 5062 | 2.1423 | 0.6003 |
97
- | 0.4058 | 28.0 | 5250 | 2.1000 | 0.6015 |
98
- | 0.4065 | 29.0 | 5437 | 2.1065 | 0.6009 |
99
- | 0.4068 | 30.0 | 5625 | 2.1389 | 0.6006 |
100
- | 0.4091 | 31.0 | 5812 | 2.1241 | 0.6005 |
101
- | 0.4103 | 32.0 | 6000 | 2.1241 | 0.6010 |
102
- | 0.3959 | 33.0 | 6187 | 2.1206 | 0.6021 |
103
- | 0.3974 | 34.0 | 6375 | 2.1061 | 0.6017 |
104
- | 0.3983 | 35.0 | 6562 | 2.1041 | 0.6013 |
105
- | 0.4034 | 36.0 | 6750 | 2.0843 | 0.6017 |
106
- | 0.4035 | 37.0 | 6937 | 2.0837 | 0.6035 |
107
- | 0.4013 | 38.0 | 7125 | 2.1708 | 0.6015 |
108
- | 0.4063 | 39.0 | 7312 | 2.0946 | 0.602 |
109
- | 0.4049 | 40.0 | 7500 | 2.1671 | 0.6019 |
110
- | 0.391 | 41.0 | 7687 | 2.1508 | 0.6026 |
111
- | 0.3913 | 42.0 | 7875 | 2.2062 | 0.5998 |
112
- | 0.3945 | 43.0 | 8062 | 2.2214 | 0.6012 |
113
- | 0.3953 | 44.0 | 8250 | 2.2576 | 0.6005 |
114
- | 0.3959 | 45.0 | 8437 | 2.2755 | 0.6001 |
115
- | 0.3961 | 46.0 | 8625 | 2.3085 | 0.6014 |
116
- | 0.3982 | 47.0 | 8812 | 2.3093 | 0.5992 |
117
- | 0.4028 | 48.0 | 9000 | 2.1926 | 0.6007 |
118
- | 0.3915 | 49.0 | 9187 | 2.0674 | 0.6018 |
119
- | 0.4009 | 49.87 | 9350 | 2.0414 | 0.6011 |
120
 
121
 
122
  ### Framework versions
 
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_1e-4_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_1e-4_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
  - Accuracy: 0.6011
21
+ - Loss: 2.0414
22
 
23
  ## Model description
24
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
58
+ | 1.598 | 1.0 | 187 | 0.6147 | 1.2692 |
59
+ | 1.1923 | 2.0 | 375 | 0.6176 | 1.2733 |
60
+ | 0.9732 | 3.0 | 562 | 0.6136 | 1.3396 |
61
+ | 0.7763 | 4.0 | 750 | 0.6104 | 1.4358 |
62
+ | 0.6498 | 5.0 | 937 | 0.6052 | 1.5630 |
63
+ | 0.57 | 6.0 | 1125 | 0.6031 | 1.6599 |
64
+ | 0.5253 | 7.0 | 1312 | 0.6027 | 1.7480 |
65
+ | 0.4958 | 8.0 | 1500 | 0.6021 | 1.8060 |
66
+ | 0.4521 | 9.0 | 1687 | 0.6013 | 1.8599 |
67
+ | 0.443 | 10.0 | 1875 | 0.6013 | 1.9468 |
68
+ | 0.439 | 11.0 | 2062 | 0.6015 | 1.9500 |
69
+ | 0.433 | 12.0 | 2250 | 0.6021 | 1.9104 |
70
+ | 0.4323 | 13.0 | 2437 | 0.6001 | 2.0079 |
71
+ | 0.4281 | 14.0 | 2625 | 0.6008 | 1.9881 |
72
+ | 0.4277 | 15.0 | 2812 | 0.6005 | 2.0305 |
73
+ | 0.4298 | 16.0 | 3000 | 0.6005 | 2.0478 |
74
+ | 0.4082 | 17.0 | 3187 | 0.6007 | 2.0539 |
75
+ | 0.411 | 18.0 | 3375 | 0.6005 | 2.0314 |
76
+ | 0.4113 | 19.0 | 3562 | 0.6011 | 2.0368 |
77
+ | 0.4121 | 20.0 | 3750 | 0.6017 | 2.1022 |
78
+ | 0.414 | 21.0 | 3937 | 0.6007 | 2.0512 |
79
+ | 0.4163 | 22.0 | 4125 | 0.6016 | 2.1147 |
80
+ | 0.4172 | 23.0 | 4312 | 0.6007 | 2.0942 |
81
+ | 0.4156 | 24.0 | 4500 | 0.6008 | 2.1201 |
82
+ | 0.3997 | 25.0 | 4687 | 0.6010 | 2.0660 |
83
+ | 0.3994 | 26.0 | 4875 | 0.6006 | 2.0832 |
84
+ | 0.4032 | 27.0 | 5062 | 0.6003 | 2.1423 |
85
+ | 0.4058 | 28.0 | 5250 | 0.6015 | 2.1000 |
86
+ | 0.4065 | 29.0 | 5437 | 0.6009 | 2.1065 |
87
+ | 0.4068 | 30.0 | 5625 | 0.6006 | 2.1389 |
88
+ | 0.4091 | 31.0 | 5812 | 0.6005 | 2.1241 |
89
+ | 0.4103 | 32.0 | 6000 | 0.6010 | 2.1241 |
90
+ | 0.3959 | 33.0 | 6187 | 0.6021 | 2.1206 |
91
+ | 0.3974 | 34.0 | 6375 | 0.6017 | 2.1061 |
92
+ | 0.3983 | 35.0 | 6562 | 0.6013 | 2.1041 |
93
+ | 0.4034 | 36.0 | 6750 | 0.6017 | 2.0843 |
94
+ | 0.4035 | 37.0 | 6937 | 0.6035 | 2.0837 |
95
+ | 0.4013 | 38.0 | 7125 | 0.6015 | 2.1708 |
96
+ | 0.4063 | 39.0 | 7312 | 0.602 | 2.0946 |
97
+ | 0.4049 | 40.0 | 7500 | 0.6019 | 2.1671 |
98
+ | 0.391 | 41.0 | 7687 | 0.6026 | 2.1508 |
99
+ | 0.3913 | 42.0 | 7875 | 0.5998 | 2.2062 |
100
+ | 0.3945 | 43.0 | 8062 | 0.6012 | 2.2214 |
101
+ | 0.3953 | 44.0 | 8250 | 0.6005 | 2.2576 |
102
+ | 0.3959 | 45.0 | 8437 | 0.6001 | 2.2755 |
103
+ | 0.3961 | 46.0 | 8625 | 0.6014 | 2.3085 |
104
+ | 0.3982 | 47.0 | 8812 | 0.5992 | 2.3093 |
105
+ | 0.4028 | 48.0 | 9000 | 0.6007 | 2.1926 |
106
+ | 0.3915 | 49.0 | 9187 | 0.6018 | 2.0674 |
107
+ | 0.4009 | 49.87 | 9350 | 0.6011 | 2.0414 |
108
 
109
 
110
  ### Framework versions
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfdad39e2291c20f000713e6b820dbeb747acc6873c9eec22bd69c854755aa38
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0cc30559cc8e85fb16db81c11d600f31a60cf5198ee0ffb93595eb34eaea23
3
  size 4728