Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_doc_qa_v3_3e-4_lora2

Safetensors
Generated from Trainer
Model card Files Community
tyzhu commited on
Commit
e43ba4a
·
verified ·
1 Parent(s): 1ae9651

Model save

Browse files
Files changed (1) hide show
  1. README.md +115 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_doc_qa_v3_3e-4_lora2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # lmind_nq_train6000_eval6489_v1_doc_qa_v3_3e-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
+ - Loss: nan
21
+ - Accuracy: 0.1684
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0003
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 4
47
+ - total_train_batch_size: 32
48
+ - total_eval_batch_size: 8
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: constant
51
+ - lr_scheduler_warmup_ratio: 0.05
52
+ - num_epochs: 50.0
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
58
+ | 1.3822 | 1.0 | 529 | 1.2977 | 0.6172 |
59
+ | 1.2744 | 2.0 | 1058 | 1.3745 | 0.6032 |
60
+ | 1.1768 | 3.0 | 1587 | 1.3319 | 0.6157 |
61
+ | 0.9247 | 4.0 | 2116 | 1.4367 | 0.6102 |
62
+ | 1.1836 | 5.0 | 2645 | 1.9168 | 0.5569 |
63
+ | 2.035 | 6.0 | 3174 | 2.0794 | 0.5377 |
64
+ | 3.7483 | 7.0 | 3703 | 2.6723 | 0.4881 |
65
+ | 7.127 | 8.0 | 4232 | 7.0410 | 0.1922 |
66
+ | 7.5321 | 9.0 | 4761 | 6.6488 | 0.1941 |
67
+ | 7.3806 | 10.0 | 5290 | 6.8427 | 0.2197 |
68
+ | 7.8159 | 11.0 | 5819 | 6.8836 | 0.2197 |
69
+ | 7.975 | 12.0 | 6348 | 6.8763 | 0.2197 |
70
+ | 7.9902 | 13.0 | 6877 | 6.8726 | 0.2197 |
71
+ | 7.8585 | 14.0 | 7406 | 6.8236 | 0.2195 |
72
+ | 7.3449 | 15.0 | 7935 | 7.1997 | 0.1922 |
73
+ | 7.3133 | 16.0 | 8464 | 6.7455 | 0.1869 |
74
+ | 7.305 | 17.0 | 8993 | 6.7454 | 0.1869 |
75
+ | 7.7463 | 18.0 | 9522 | 8.8319 | 0.1870 |
76
+ | 9.9696 | 19.0 | 10051 | 10.0702 | 0.1692 |
77
+ | 9.9845 | 20.0 | 10580 | 10.0702 | 0.1692 |
78
+ | 9.9502 | 21.0 | 11109 | 10.0702 | 0.1692 |
79
+ | 9.9726 | 22.0 | 11638 | 10.0702 | 0.1692 |
80
+ | 9.9648 | 23.0 | 12167 | 10.0702 | 0.1692 |
81
+ | 9.9579 | 24.0 | 12696 | 10.0702 | 0.1692 |
82
+ | 9.9519 | 25.0 | 13225 | 10.0702 | 0.1692 |
83
+ | 9.9849 | 26.0 | 13754 | 10.0702 | 0.1692 |
84
+ | 9.9591 | 27.0 | 14283 | 10.0702 | 0.1692 |
85
+ | 9.9701 | 28.0 | 14812 | 10.0702 | 0.1692 |
86
+ | 9.998 | 29.0 | 15341 | 10.0702 | 0.1692 |
87
+ | 9.9878 | 30.0 | 15870 | 10.0702 | 0.1692 |
88
+ | 9.9882 | 31.0 | 16399 | 10.0702 | 0.1692 |
89
+ | 9.9741 | 32.0 | 16928 | 10.0702 | 0.1692 |
90
+ | 9.9545 | 33.0 | 17457 | 10.0702 | 0.1692 |
91
+ | 9.9538 | 34.0 | 17986 | 10.0702 | 0.1692 |
92
+ | 9.995 | 35.0 | 18515 | 10.0702 | 0.1692 |
93
+ | 9.974 | 36.0 | 19044 | 10.0702 | 0.1692 |
94
+ | 9.9763 | 37.0 | 19573 | 10.0702 | 0.1692 |
95
+ | 9.991 | 38.0 | 20102 | 10.0702 | 0.1692 |
96
+ | 9.9502 | 39.0 | 20631 | 10.0702 | 0.1692 |
97
+ | 9.9284 | 40.0 | 21160 | 10.0702 | 0.1692 |
98
+ | 12.7665 | 41.0 | 21689 | 9.6482 | 0.1747 |
99
+ | 1855.3142 | 42.0 | 22218 | nan | 0.1684 |
100
+ | 0.0 | 43.0 | 22747 | nan | 0.1684 |
101
+ | 0.0 | 44.0 | 23276 | nan | 0.1684 |
102
+ | 0.0 | 45.0 | 23805 | nan | 0.1684 |
103
+ | 0.0 | 46.0 | 24334 | nan | 0.1684 |
104
+ | 0.0 | 47.0 | 24863 | nan | 0.1684 |
105
+ | 0.0 | 48.0 | 25392 | nan | 0.1684 |
106
+ | 0.0 | 49.0 | 25921 | nan | 0.1684 |
107
+ | 0.0 | 50.0 | 26450 | nan | 0.1684 |
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