Hugging Face's logo

Shakhovak
/
llama-7b-absa-MT-restaurants

Generated from Trainer
Model card Files Community
Shakhovak commited on
Commit
c60e9cf
•
1 Parent(s): 449eca2

End of training

Browse files
Files changed (3) hide show
  1. README.md +32 -17
  2. adapter_model.bin +1 -1
  3. 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 [baffo32/decapoda-research-llama-7B-hf](https://huggingface.co/baffo32/decapoda-research-llama-7B-hf) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0061
19
 
20
  ## Model description
21
 
@@ -43,28 +43,43 @@ The following hyperparameters were used during training:
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 2
46
- - training_steps: 600
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.0939 | 0.13 | 40 | 0.0302 |
54
- | 0.0258 | 0.25 | 80 | 0.0237 |
55
- | 0.0223 | 0.38 | 120 | 0.0208 |
56
- | 0.0198 | 0.51 | 160 | 0.0182 |
57
- | 0.0159 | 0.63 | 200 | 0.0163 |
58
- | 0.0158 | 0.76 | 240 | 0.0137 |
59
- | 0.0125 | 0.89 | 280 | 0.0126 |
60
- | 0.0118 | 1.01 | 320 | 0.0111 |
61
- | 0.0078 | 1.14 | 360 | 0.0098 |
62
- | 0.0059 | 1.27 | 400 | 0.0095 |
63
- | 0.006 | 1.39 | 440 | 0.0091 |
64
- | 0.0052 | 1.52 | 480 | 0.0078 |
65
- | 0.0059 | 1.65 | 520 | 0.0068 |
66
- | 0.0045 | 1.77 | 560 | 0.0066 |
67
- | 0.0044 | 1.9 | 600 | 0.0061 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [baffo32/decapoda-research-llama-7B-hf](https://huggingface.co/baffo32/decapoda-research-llama-7B-hf) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0011
19
 
20
  ## Model description
21
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 2
46
+ - training_steps: 1200
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.086 | 0.13 | 40 | 0.0322 |
54
+ | 0.0272 | 0.25 | 80 | 0.0212 |
55
+ | 0.0208 | 0.38 | 120 | 0.0182 |
56
+ | 0.0179 | 0.51 | 160 | 0.0171 |
57
+ | 0.0176 | 0.63 | 200 | 0.0150 |
58
+ | 0.0161 | 0.76 | 240 | 0.0125 |
59
+ | 0.0129 | 0.89 | 280 | 0.0118 |
60
+ | 0.013 | 1.01 | 320 | 0.0113 |
61
+ | 0.0078 | 1.14 | 360 | 0.0092 |
62
+ | 0.007 | 1.27 | 400 | 0.0081 |
63
+ | 0.0065 | 1.39 | 440 | 0.0087 |
64
+ | 0.0064 | 1.52 | 480 | 0.0091 |
65
+ | 0.007 | 1.65 | 520 | 0.0063 |
66
+ | 0.0048 | 1.77 | 560 | 0.0053 |
67
+ | 0.005 | 1.9 | 600 | 0.0055 |
68
+ | 0.004 | 2.03 | 640 | 0.0051 |
69
+ | 0.0025 | 2.15 | 680 | 0.0040 |
70
+ | 0.002 | 2.28 | 720 | 0.0042 |
71
+ | 0.0021 | 2.41 | 760 | 0.0044 |
72
+ | 0.0018 | 2.53 | 800 | 0.0035 |
73
+ | 0.0015 | 2.66 | 840 | 0.0029 |
74
+ | 0.0011 | 2.78 | 880 | 0.0022 |
75
+ | 0.0012 | 2.91 | 920 | 0.0018 |
76
+ | 0.0011 | 3.04 | 960 | 0.0015 |
77
+ | 0.0002 | 3.16 | 1000 | 0.0013 |
78
+ | 0.0003 | 3.29 | 1040 | 0.0015 |
79
+ | 0.0002 | 3.42 | 1080 | 0.0014 |
80
+ | 0.0004 | 3.54 | 1120 | 0.0012 |
81
+ | 0.0002 | 3.67 | 1160 | 0.0011 |
82
+ | 0.0002 | 3.8 | 1200 | 0.0011 |
83
 
84
 
85
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca196defb4a050cca7a987d37c5e84ee7b60d34461e57c6ffd8fdab4b32fef29
3
  size 268528394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3e63f02b46c5e4a42b6c4d89613db5413bc1d3a0a46c59c314a461b53fa865
3
  size 268528394
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cd1692eca84d268b8028ce5704098898ae67a3d5c38d6dd1e3b59de6aaa82cf
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88db30135de728d1c9ef61d0cbb03ec3bae6803809713c5693c24ad571d6242d
3
  size 4984