Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_doc_qa_v3_3e-5_lora2

Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
de6439e
·
verified ·
1 Parent(s): 529e398

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_doc_qa_v3
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: lmind_nq_train6000_eval6489_v1_doc_qa_v3_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_doc_qa_v3
18
- type: tyzhu/lmind_nq_train6000_eval6489_v1_doc_qa_v3
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.5422564102564102
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_doc_qa_v3_3e-5_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_doc_qa_v3 dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 2.0598
33
  - Accuracy: 0.5423
 
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
- | 1.3948 | 1.0 | 529 | 1.3087 | 0.6132 |
71
- | 1.3789 | 2.0 | 1058 | 1.2897 | 0.6146 |
72
- | 1.3259 | 3.0 | 1587 | 1.2849 | 0.6179 |
73
- | 1.2853 | 4.0 | 2116 | 1.3169 | 0.6159 |
74
- | 1.2556 | 5.0 | 2645 | 1.3532 | 0.6132 |
75
- | 1.1972 | 6.0 | 3174 | 1.4135 | 0.6126 |
76
- | 1.1839 | 7.0 | 3703 | 1.5007 | 0.6081 |
77
- | 1.1334 | 8.0 | 4232 | 1.5242 | 0.6074 |
78
- | 1.0966 | 9.0 | 4761 | 1.6107 | 0.5803 |
79
- | 1.0485 | 10.0 | 5290 | 1.6749 | 0.6049 |
80
- | 1.021 | 11.0 | 5819 | 1.7324 | 0.6015 |
81
- | 0.9918 | 12.0 | 6348 | 1.7632 | 0.6007 |
82
- | 0.947 | 13.0 | 6877 | 1.8303 | 0.6011 |
83
- | 0.9376 | 14.0 | 7406 | 1.8873 | 0.5991 |
84
- | 0.898 | 15.0 | 7935 | 1.9688 | 0.5976 |
85
- | 0.8559 | 16.0 | 8464 | 1.9724 | 0.5988 |
86
- | 0.8348 | 17.0 | 8993 | 1.9815 | 0.5714 |
87
- | 0.8106 | 18.0 | 9522 | 2.0386 | 0.598 |
88
- | 0.7848 | 19.0 | 10051 | 2.0627 | 0.5964 |
89
- | 0.745 | 20.0 | 10580 | 2.0825 | 0.5966 |
90
- | 0.7208 | 21.0 | 11109 | 2.0959 | 0.5959 |
91
- | 0.6842 | 22.0 | 11638 | 2.1534 | 0.5968 |
92
- | 0.6661 | 23.0 | 12167 | 2.1792 | 0.5975 |
93
- | 0.6193 | 24.0 | 12696 | 2.1530 | 0.5967 |
94
- | 0.6064 | 25.0 | 13225 | 2.1720 | 0.5958 |
95
- | 0.5776 | 26.0 | 13754 | 2.2162 | 0.5966 |
96
- | 0.5492 | 27.0 | 14283 | 2.2382 | 0.5862 |
97
- | 0.5256 | 28.0 | 14812 | 2.2273 | 0.5963 |
98
- | 0.5128 | 29.0 | 15341 | 2.2448 | 0.5948 |
99
- | 0.4846 | 30.0 | 15870 | 2.2697 | 0.5846 |
100
- | 0.4623 | 31.0 | 16399 | 2.2425 | 0.5968 |
101
- | 0.4468 | 32.0 | 16928 | 2.2654 | 0.5936 |
102
- | 0.4714 | 33.0 | 17457 | 2.1317 | 0.5957 |
103
- | 0.8308 | 34.0 | 17986 | 1.9392 | 0.5973 |
104
- | 0.6478 | 35.0 | 18515 | 2.0346 | 0.5979 |
105
- | 0.612 | 36.0 | 19044 | 2.0882 | 0.5978 |
106
- | 0.5928 | 37.0 | 19573 | 2.1420 | 0.5970 |
107
- | 0.5698 | 38.0 | 20102 | 2.1569 | 0.5966 |
108
- | 0.5444 | 39.0 | 20631 | 2.1954 | 0.5956 |
109
- | 0.5404 | 40.0 | 21160 | 2.1724 | 0.5942 |
110
- | 0.5124 | 41.0 | 21689 | 2.2020 | 0.5939 |
111
- | 0.5342 | 42.0 | 22218 | 2.1955 | 0.5938 |
112
- | 0.5385 | 43.0 | 22747 | 2.1431 | 0.5946 |
113
- | 0.5673 | 44.0 | 23276 | 2.1269 | 0.5948 |
114
- | 0.7034 | 45.0 | 23805 | 2.0601 | 0.5917 |
115
- | 1.0751 | 46.0 | 24334 | 1.8910 | 0.5861 |
116
- | 1.9072 | 47.0 | 24863 | 2.1388 | 0.5518 |
117
- | 5.2339 | 48.0 | 25392 | 4.4877 | 0.3825 |
118
- | 2.573 | 49.0 | 25921 | 2.2255 | 0.5283 |
119
- | 2.1439 | 50.0 | 26450 | 2.0598 | 0.5423 |
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_doc_qa_v3_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_doc_qa_v3_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
  - Accuracy: 0.5423
21
+ - Loss: 2.0598
22
 
23
  ## Model description
24
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
57
+ |:-------------:|:-----:|:-----:|:--------:|:---------------:|
58
+ | 1.3948 | 1.0 | 529 | 0.6132 | 1.3087 |
59
+ | 1.3789 | 2.0 | 1058 | 0.6146 | 1.2897 |
60
+ | 1.3259 | 3.0 | 1587 | 0.6179 | 1.2849 |
61
+ | 1.2853 | 4.0 | 2116 | 0.6159 | 1.3169 |
62
+ | 1.2556 | 5.0 | 2645 | 0.6132 | 1.3532 |
63
+ | 1.1972 | 6.0 | 3174 | 0.6126 | 1.4135 |
64
+ | 1.1839 | 7.0 | 3703 | 0.6081 | 1.5007 |
65
+ | 1.1334 | 8.0 | 4232 | 0.6074 | 1.5242 |
66
+ | 1.0966 | 9.0 | 4761 | 0.5803 | 1.6107 |
67
+ | 1.0485 | 10.0 | 5290 | 0.6049 | 1.6749 |
68
+ | 1.021 | 11.0 | 5819 | 0.6015 | 1.7324 |
69
+ | 0.9918 | 12.0 | 6348 | 0.6007 | 1.7632 |
70
+ | 0.947 | 13.0 | 6877 | 0.6011 | 1.8303 |
71
+ | 0.9376 | 14.0 | 7406 | 0.5991 | 1.8873 |
72
+ | 0.898 | 15.0 | 7935 | 0.5976 | 1.9688 |
73
+ | 0.8559 | 16.0 | 8464 | 0.5988 | 1.9724 |
74
+ | 0.8348 | 17.0 | 8993 | 0.5714 | 1.9815 |
75
+ | 0.8106 | 18.0 | 9522 | 0.598 | 2.0386 |
76
+ | 0.7848 | 19.0 | 10051 | 0.5964 | 2.0627 |
77
+ | 0.745 | 20.0 | 10580 | 0.5966 | 2.0825 |
78
+ | 0.7208 | 21.0 | 11109 | 0.5959 | 2.0959 |
79
+ | 0.6842 | 22.0 | 11638 | 0.5968 | 2.1534 |
80
+ | 0.6661 | 23.0 | 12167 | 0.5975 | 2.1792 |
81
+ | 0.6193 | 24.0 | 12696 | 0.5967 | 2.1530 |
82
+ | 0.6064 | 25.0 | 13225 | 0.5958 | 2.1720 |
83
+ | 0.5776 | 26.0 | 13754 | 0.5966 | 2.2162 |
84
+ | 0.5492 | 27.0 | 14283 | 0.5862 | 2.2382 |
85
+ | 0.5256 | 28.0 | 14812 | 0.5963 | 2.2273 |
86
+ | 0.5128 | 29.0 | 15341 | 0.5948 | 2.2448 |
87
+ | 0.4846 | 30.0 | 15870 | 0.5846 | 2.2697 |
88
+ | 0.4623 | 31.0 | 16399 | 0.5968 | 2.2425 |
89
+ | 0.4468 | 32.0 | 16928 | 0.5936 | 2.2654 |
90
+ | 0.4714 | 33.0 | 17457 | 0.5957 | 2.1317 |
91
+ | 0.8308 | 34.0 | 17986 | 0.5973 | 1.9392 |
92
+ | 0.6478 | 35.0 | 18515 | 0.5979 | 2.0346 |
93
+ | 0.612 | 36.0 | 19044 | 0.5978 | 2.0882 |
94
+ | 0.5928 | 37.0 | 19573 | 0.5970 | 2.1420 |
95
+ | 0.5698 | 38.0 | 20102 | 0.5966 | 2.1569 |
96
+ | 0.5444 | 39.0 | 20631 | 0.5956 | 2.1954 |
97
+ | 0.5404 | 40.0 | 21160 | 0.5942 | 2.1724 |
98
+ | 0.5124 | 41.0 | 21689 | 0.5939 | 2.2020 |
99
+ | 0.5342 | 42.0 | 22218 | 0.5938 | 2.1955 |
100
+ | 0.5385 | 43.0 | 22747 | 0.5946 | 2.1431 |
101
+ | 0.5673 | 44.0 | 23276 | 0.5948 | 2.1269 |
102
+ | 0.7034 | 45.0 | 23805 | 0.5917 | 2.0601 |
103
+ | 1.0751 | 46.0 | 24334 | 0.5861 | 1.8910 |
104
+ | 1.9072 | 47.0 | 24863 | 0.5518 | 2.1388 |
105
+ | 5.2339 | 48.0 | 25392 | 0.3825 | 4.4877 |
106
+ | 2.573 | 49.0 | 25921 | 0.5283 | 2.2255 |
107
+ | 2.1439 | 50.0 | 26450 | 0.5423 | 2.0598 |
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:ec9dd2a1e083127818a65cb4d99f38a0a803e54a476491027d2e996644eba47c
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4927a165ad0bda5fcf25660788e30b61c46f37ad0bd48f9d4b3b55e8e00380a
3
  size 4728