Hugging Face's logo

Litzy619
/
V0305P3

Safetensors
Generated from Trainer
Model card Files Community
Litzy619 commited on
Commit
a3943c9
·
verified ·
1 Parent(s): f3936bb

End of training

Browse files
Files changed (4) hide show
  1. README.md +36 -36
  2. adapter_model.bin +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [yahma/llama-7b-hf](https://huggingface.co/yahma/llama-7b-hf) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0688
19
 
20
  ## Model description
21
 
@@ -50,41 +50,41 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 1.8281 | 0.09 | 10 | 0.6608 |
54
- | 0.252 | 0.17 | 20 | 0.1557 |
55
- | 0.1573 | 0.26 | 30 | 0.1553 |
56
- | 0.1528 | 0.34 | 40 | 0.1464 |
57
- | 0.1494 | 0.43 | 50 | 0.1468 |
58
- | 0.1511 | 0.51 | 60 | 0.1345 |
59
- | 0.1353 | 0.6 | 70 | 0.1163 |
60
- | 0.1308 | 0.68 | 80 | 0.0978 |
61
- | 0.1115 | 0.77 | 90 | 0.1005 |
62
- | 0.1151 | 0.85 | 100 | 0.0949 |
63
- | 0.1095 | 0.94 | 110 | 0.0947 |
64
- | 0.1035 | 1.02 | 120 | 0.0957 |
65
- | 0.0961 | 1.11 | 130 | 0.0888 |
66
- | 0.0898 | 1.19 | 140 | 0.0821 |
67
- | 0.089 | 1.28 | 150 | 0.0784 |
68
- | 0.0867 | 1.37 | 160 | 0.0784 |
69
- | 0.0875 | 1.45 | 170 | 0.0770 |
70
- | 0.078 | 1.54 | 180 | 0.0810 |
71
- | 0.0838 | 1.62 | 190 | 0.0780 |
72
- | 0.0896 | 1.71 | 200 | 0.0746 |
73
- | 0.0861 | 1.79 | 210 | 0.0746 |
74
- | 0.0821 | 1.88 | 220 | 0.0693 |
75
- | 0.0777 | 1.96 | 230 | 0.0710 |
76
- | 0.0675 | 2.05 | 240 | 0.0718 |
77
- | 0.0559 | 2.13 | 250 | 0.0786 |
78
- | 0.055 | 2.22 | 260 | 0.0742 |
79
- | 0.0553 | 2.3 | 270 | 0.0765 |
80
- | 0.0569 | 2.39 | 280 | 0.0711 |
81
- | 0.0597 | 2.47 | 290 | 0.0679 |
82
- | 0.0566 | 2.56 | 300 | 0.0690 |
83
- | 0.0602 | 2.65 | 310 | 0.0673 |
84
- | 0.0502 | 2.73 | 320 | 0.0681 |
85
- | 0.0563 | 2.82 | 330 | 0.0684 |
86
- | 0.0524 | 2.9 | 340 | 0.0687 |
87
- | 0.0531 | 2.99 | 350 | 0.0688 |
88
 
89
 
90
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [yahma/llama-7b-hf](https://huggingface.co/yahma/llama-7b-hf) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0716
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.5189 | 0.09 | 10 | 0.1892 |
54
+ | 0.1724 | 0.17 | 20 | 0.1543 |
55
+ | 0.1556 | 0.26 | 30 | 0.1534 |
56
+ | 0.1522 | 0.34 | 40 | 0.1523 |
57
+ | 0.1512 | 0.43 | 50 | 0.1487 |
58
+ | 0.1563 | 0.51 | 60 | 0.1495 |
59
+ | 0.1515 | 0.6 | 70 | 0.1474 |
60
+ | 0.1514 | 0.68 | 80 | 0.1419 |
61
+ | 0.1389 | 0.77 | 90 | 0.1194 |
62
+ | 0.1287 | 0.85 | 100 | 0.1003 |
63
+ | 0.1242 | 0.94 | 110 | 0.0968 |
64
+ | 0.1122 | 1.02 | 120 | 0.1009 |
65
+ | 0.1066 | 1.11 | 130 | 0.1001 |
66
+ | 0.0971 | 1.19 | 140 | 0.0963 |
67
+ | 0.0957 | 1.28 | 150 | 0.0882 |
68
+ | 0.0928 | 1.37 | 160 | 0.0883 |
69
+ | 0.0917 | 1.45 | 170 | 0.0809 |
70
+ | 0.0832 | 1.54 | 180 | 0.0893 |
71
+ | 0.085 | 1.62 | 190 | 0.0865 |
72
+ | 0.0906 | 1.71 | 200 | 0.0773 |
73
+ | 0.0879 | 1.79 | 210 | 0.0748 |
74
+ | 0.0852 | 1.88 | 220 | 0.0674 |
75
+ | 0.0796 | 1.96 | 230 | 0.0717 |
76
+ | 0.0674 | 2.05 | 240 | 0.0711 |
77
+ | 0.0518 | 2.13 | 250 | 0.0751 |
78
+ | 0.0521 | 2.22 | 260 | 0.0739 |
79
+ | 0.0504 | 2.3 | 270 | 0.0770 |
80
+ | 0.0556 | 2.39 | 280 | 0.0730 |
81
+ | 0.0605 | 2.47 | 290 | 0.0725 |
82
+ | 0.0515 | 2.56 | 300 | 0.0759 |
83
+ | 0.0526 | 2.65 | 310 | 0.0711 |
84
+ | 0.0494 | 2.73 | 320 | 0.0716 |
85
+ | 0.0518 | 2.82 | 330 | 0.0724 |
86
+ | 0.0508 | 2.9 | 340 | 0.0716 |
87
+ | 0.0509 | 2.99 | 350 | 0.0716 |
88
 
89
 
90
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43724cf4af7d68852bab6befd38fc2633c6cc31121bf145cd09f0b7e9d9e7fdc
3
  size 277233383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc0a1d91704aa2f7b4d7d8823b46c24261e34c32436e248508268500edeb59ef
3
  size 277233383
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa4b1082acd4c135767380c9ebdd75af32b6f2262b09de9886f6fee5bbfacce6
3
  size 13753862632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5da593b59b6aa5c5463ff900f9ccc595001a15eff585540137469391ee4d3d5
3
  size 13753862632
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2a9fd3b36338eb24dcc0cef169e7a5e985202b199d1a5bfaac604e1b858c14f
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c069a15a553da2a122f13c16c52e702f332ba6df5a16245efe9541dba389a478
3
  size 5240