Hugging Face's logo

Jukaboo
/
Llama2_7B_chat_meetingBank_ft_adapters_test

TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
Jukaboo commited on
Commit
a24151d
·
1 Parent(s): 5486893

Model save

Browse files
Files changed (2) hide show
  1. README.md +7 -28
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -2,8 +2,6 @@
2
  base_model: meta-llama/Llama-2-7b-chat-hf
3
  tags:
4
  - generated_from_trainer
5
- metrics:
6
- - rouge
7
  model-index:
8
  - name: Llama2_7B_chat_meetingBank_ft_adapters_test
9
  results: []
@@ -16,11 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.7332
20
- - Rouge1: 0.2850
21
- - Rouge2: 0.1973
22
- - Rougel: 0.2693
23
- - Rougelsum: 0.2798
24
 
25
  ## Model description
26
 
@@ -52,27 +46,12 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
56
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
57
- | 2.3663 | 0.05 | 17 | 2.2460 | 0.2908 | 0.2010 | 0.2755 | 0.2857 |
58
- | 2.1137 | 0.11 | 34 | 2.0062 | 0.3113 | 0.2116 | 0.2913 | 0.3063 |
59
- | 2.256 | 0.16 | 51 | 1.8972 | 0.2801 | 0.1973 | 0.2646 | 0.2749 |
60
- | 2.157 | 0.21 | 68 | 1.8604 | 0.2893 | 0.2 | 0.2741 | 0.2843 |
61
- | 2.0047 | 0.26 | 85 | 1.8361 | 0.2741 | 0.1865 | 0.2587 | 0.2690 |
62
- | 2.1333 | 0.32 | 102 | 1.7916 | 0.2691 | 0.1872 | 0.2533 | 0.2585 |
63
- | 2.1192 | 0.37 | 119 | 1.7839 | 0.2832 | 0.1986 | 0.2678 | 0.2781 |
64
- | 1.7643 | 0.42 | 136 | 1.7767 | 0.2772 | 0.1973 | 0.2617 | 0.2720 |
65
- | 2.2205 | 0.47 | 153 | 1.7569 | 0.2700 | 0.1862 | 0.2542 | 0.2647 |
66
- | 2.0877 | 0.53 | 170 | 1.7587 | 0.2784 | 0.1973 | 0.2627 | 0.2731 |
67
- | 1.8287 | 0.58 | 187 | 1.7497 | 0.2804 | 0.1944 | 0.2623 | 0.2729 |
68
- | 2.188 | 0.63 | 204 | 1.7407 | 0.2790 | 0.1930 | 0.2632 | 0.2737 |
69
- | 2.06 | 0.68 | 221 | 1.7417 | 0.2720 | 0.1833 | 0.2561 | 0.2667 |
70
- | 1.7886 | 0.74 | 238 | 1.7410 | 0.2781 | 0.1899 | 0.2601 | 0.2706 |
71
- | 2.1122 | 0.79 | 255 | 1.7351 | 0.2761 | 0.1928 | 0.2604 | 0.2709 |
72
- | 2.1699 | 0.84 | 272 | 1.7361 | 0.2826 | 0.1940 | 0.2667 | 0.2773 |
73
- | 1.7408 | 0.89 | 289 | 1.7351 | 0.2865 | 0.1983 | 0.2707 | 0.2812 |
74
- | 2.1391 | 0.95 | 306 | 1.7334 | 0.2889 | 0.1963 | 0.2732 | 0.2836 |
75
- | 1.3669 | 1.0 | 323 | 1.7332 | 0.2850 | 0.1973 | 0.2693 | 0.2798 |
76
 
77
 
78
  ### Framework versions
 
2
  base_model: meta-llama/Llama-2-7b-chat-hf
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: Llama2_7B_chat_meetingBank_ft_adapters_test
7
  results: []
 
14
 
15
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.9378
 
 
 
 
18
 
19
  ## Model description
20
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.1525 | 0.2 | 65 | 2.0533 |
52
+ | 2.0143 | 0.4 | 130 | 1.9829 |
53
+ | 1.6408 | 0.6 | 195 | 1.9513 |
54
+ | 2.1303 | 0.8 | 260 | 1.9378 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65041d065ba35be5b7ebaad645f4addbca4c228f4d76dd35dc9c69283bd62949
3
  size 16794200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01264a602bf7621e6982c5f3701ba965dd00f5cc8a9c9d1aabdf2f1bc2aa51b
3
  size 16794200