Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_qa_5e-5_lora2

Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
408f63b
·
verified ·
1 Parent(s): a587adb

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_5e-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: 0.597948717948718
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_5e-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_qa dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 2.3327
33
  - Accuracy: 0.5979
 
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
- | 1.7923 | 1.0 | 187 | 1.2805 | 0.6128 |
71
- | 1.2488 | 2.0 | 375 | 1.2677 | 0.6168 |
72
- | 1.1097 | 3.0 | 562 | 1.2943 | 0.6162 |
73
- | 0.9244 | 4.0 | 750 | 1.3598 | 0.6126 |
74
- | 0.7924 | 5.0 | 937 | 1.4714 | 0.6089 |
75
- | 0.6864 | 6.0 | 1125 | 1.5761 | 0.6045 |
76
- | 0.6101 | 7.0 | 1312 | 1.6554 | 0.6029 |
77
- | 0.562 | 8.0 | 1500 | 1.7485 | 0.6011 |
78
- | 0.5015 | 9.0 | 1687 | 1.8067 | 0.5998 |
79
- | 0.4855 | 10.0 | 1875 | 1.8643 | 0.5996 |
80
- | 0.4736 | 11.0 | 2062 | 1.9771 | 0.5966 |
81
- | 0.465 | 12.0 | 2250 | 1.9610 | 0.5989 |
82
- | 0.4603 | 13.0 | 2437 | 1.9498 | 0.5982 |
83
- | 0.4537 | 14.0 | 2625 | 2.0510 | 0.5979 |
84
- | 0.4489 | 15.0 | 2812 | 2.0862 | 0.5996 |
85
- | 0.4488 | 16.0 | 3000 | 2.0370 | 0.5995 |
86
- | 0.4238 | 17.0 | 3187 | 2.0638 | 0.5990 |
87
- | 0.4245 | 18.0 | 3375 | 2.0635 | 0.6001 |
88
- | 0.4241 | 19.0 | 3562 | 2.1451 | 0.5988 |
89
- | 0.4236 | 20.0 | 3750 | 2.1509 | 0.6003 |
90
- | 0.4241 | 21.0 | 3937 | 2.1745 | 0.5987 |
91
- | 0.4239 | 22.0 | 4125 | 2.1752 | 0.5991 |
92
- | 0.4245 | 23.0 | 4312 | 2.1659 | 0.5983 |
93
- | 0.4229 | 24.0 | 4500 | 2.2126 | 0.5981 |
94
- | 0.4059 | 25.0 | 4687 | 2.1568 | 0.5997 |
95
- | 0.4064 | 26.0 | 4875 | 2.1777 | 0.5979 |
96
- | 0.4089 | 27.0 | 5062 | 2.2200 | 0.5979 |
97
- | 0.4099 | 28.0 | 5250 | 2.2412 | 0.5976 |
98
- | 0.4103 | 29.0 | 5437 | 2.2093 | 0.5983 |
99
- | 0.4112 | 30.0 | 5625 | 2.2145 | 0.6002 |
100
- | 0.4113 | 31.0 | 5812 | 2.2514 | 0.5990 |
101
- | 0.4124 | 32.0 | 6000 | 2.3170 | 0.5979 |
102
- | 0.3961 | 33.0 | 6187 | 2.2557 | 0.5978 |
103
- | 0.4002 | 34.0 | 6375 | 2.2739 | 0.5979 |
104
- | 0.3998 | 35.0 | 6562 | 2.2498 | 0.5976 |
105
- | 0.4022 | 36.0 | 6750 | 2.3118 | 0.5972 |
106
- | 0.4038 | 37.0 | 6937 | 2.3259 | 0.5970 |
107
- | 0.404 | 38.0 | 7125 | 2.3276 | 0.5973 |
108
- | 0.4072 | 39.0 | 7312 | 2.2854 | 0.5994 |
109
- | 0.4077 | 40.0 | 7500 | 2.3036 | 0.5982 |
110
- | 0.3943 | 41.0 | 7687 | 2.3361 | 0.5987 |
111
- | 0.3939 | 42.0 | 7875 | 2.2148 | 0.5995 |
112
- | 0.3977 | 43.0 | 8062 | 2.3393 | 0.5985 |
113
- | 0.3988 | 44.0 | 8250 | 2.2875 | 0.5983 |
114
- | 0.402 | 45.0 | 8437 | 2.2981 | 0.5995 |
115
- | 0.4002 | 46.0 | 8625 | 2.3163 | 0.5981 |
116
- | 0.4004 | 47.0 | 8812 | 2.3085 | 0.5987 |
117
- | 0.402 | 48.0 | 9000 | 2.3341 | 0.5977 |
118
- | 0.3895 | 49.0 | 9187 | 2.2953 | 0.5984 |
119
- | 0.3927 | 49.87 | 9350 | 2.3327 | 0.5979 |
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_5e-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_5e-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: 0.5979
21
+ - Loss: 2.3327
22
 
23
  ## Model description
24
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
58
+ | 1.7923 | 1.0 | 187 | 0.6128 | 1.2805 |
59
+ | 1.2488 | 2.0 | 375 | 0.6168 | 1.2677 |
60
+ | 1.1097 | 3.0 | 562 | 0.6162 | 1.2943 |
61
+ | 0.9244 | 4.0 | 750 | 0.6126 | 1.3598 |
62
+ | 0.7924 | 5.0 | 937 | 0.6089 | 1.4714 |
63
+ | 0.6864 | 6.0 | 1125 | 0.6045 | 1.5761 |
64
+ | 0.6101 | 7.0 | 1312 | 0.6029 | 1.6554 |
65
+ | 0.562 | 8.0 | 1500 | 0.6011 | 1.7485 |
66
+ | 0.5015 | 9.0 | 1687 | 0.5998 | 1.8067 |
67
+ | 0.4855 | 10.0 | 1875 | 0.5996 | 1.8643 |
68
+ | 0.4736 | 11.0 | 2062 | 0.5966 | 1.9771 |
69
+ | 0.465 | 12.0 | 2250 | 0.5989 | 1.9610 |
70
+ | 0.4603 | 13.0 | 2437 | 0.5982 | 1.9498 |
71
+ | 0.4537 | 14.0 | 2625 | 0.5979 | 2.0510 |
72
+ | 0.4489 | 15.0 | 2812 | 0.5996 | 2.0862 |
73
+ | 0.4488 | 16.0 | 3000 | 0.5995 | 2.0370 |
74
+ | 0.4238 | 17.0 | 3187 | 0.5990 | 2.0638 |
75
+ | 0.4245 | 18.0 | 3375 | 0.6001 | 2.0635 |
76
+ | 0.4241 | 19.0 | 3562 | 0.5988 | 2.1451 |
77
+ | 0.4236 | 20.0 | 3750 | 0.6003 | 2.1509 |
78
+ | 0.4241 | 21.0 | 3937 | 0.5987 | 2.1745 |
79
+ | 0.4239 | 22.0 | 4125 | 0.5991 | 2.1752 |
80
+ | 0.4245 | 23.0 | 4312 | 0.5983 | 2.1659 |
81
+ | 0.4229 | 24.0 | 4500 | 0.5981 | 2.2126 |
82
+ | 0.4059 | 25.0 | 4687 | 0.5997 | 2.1568 |
83
+ | 0.4064 | 26.0 | 4875 | 0.5979 | 2.1777 |
84
+ | 0.4089 | 27.0 | 5062 | 0.5979 | 2.2200 |
85
+ | 0.4099 | 28.0 | 5250 | 0.5976 | 2.2412 |
86
+ | 0.4103 | 29.0 | 5437 | 0.5983 | 2.2093 |
87
+ | 0.4112 | 30.0 | 5625 | 0.6002 | 2.2145 |
88
+ | 0.4113 | 31.0 | 5812 | 0.5990 | 2.2514 |
89
+ | 0.4124 | 32.0 | 6000 | 0.5979 | 2.3170 |
90
+ | 0.3961 | 33.0 | 6187 | 0.5978 | 2.2557 |
91
+ | 0.4002 | 34.0 | 6375 | 0.5979 | 2.2739 |
92
+ | 0.3998 | 35.0 | 6562 | 0.5976 | 2.2498 |
93
+ | 0.4022 | 36.0 | 6750 | 0.5972 | 2.3118 |
94
+ | 0.4038 | 37.0 | 6937 | 0.5970 | 2.3259 |
95
+ | 0.404 | 38.0 | 7125 | 0.5973 | 2.3276 |
96
+ | 0.4072 | 39.0 | 7312 | 0.5994 | 2.2854 |
97
+ | 0.4077 | 40.0 | 7500 | 0.5982 | 2.3036 |
98
+ | 0.3943 | 41.0 | 7687 | 0.5987 | 2.3361 |
99
+ | 0.3939 | 42.0 | 7875 | 0.5995 | 2.2148 |
100
+ | 0.3977 | 43.0 | 8062 | 0.5985 | 2.3393 |
101
+ | 0.3988 | 44.0 | 8250 | 0.5983 | 2.2875 |
102
+ | 0.402 | 45.0 | 8437 | 0.5995 | 2.2981 |
103
+ | 0.4002 | 46.0 | 8625 | 0.5981 | 2.3163 |
104
+ | 0.4004 | 47.0 | 8812 | 0.5987 | 2.3085 |
105
+ | 0.402 | 48.0 | 9000 | 0.5977 | 2.3341 |
106
+ | 0.3895 | 49.0 | 9187 | 0.5984 | 2.2953 |
107
+ | 0.3927 | 49.87 | 9350 | 0.5979 | 2.3327 |
108
 
109
 
110
  ### Framework versions
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:742db4eb1b1050153055c5b82de0ef39604f0c615b7ee389916bfc19979a9577
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db32be4240adfbfb25a22c212d8a8982f2f3ec732434a1bb965148e1477b964c
3
  size 4728