Hugging Face's logo

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

Generated from Trainer
Model card Files Community
Shakhovak commited on
Commit
332e27b
•
1 Parent(s): ba3fbeb

End of training

Browse files
Files changed (3) hide show
  1. README.md +31 -31
  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: 0.0044
19
 
20
  ## Model description
21
 
@@ -50,36 +50,36 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.0881 | 0.13 | 40 | 0.0330 |
54
- | 0.0269 | 0.25 | 80 | 0.0251 |
55
- | 0.0207 | 0.38 | 120 | 0.0227 |
56
- | 0.0199 | 0.51 | 160 | 0.0192 |
57
- | 0.0167 | 0.63 | 200 | 0.0186 |
58
- | 0.0155 | 0.76 | 240 | 0.0151 |
59
- | 0.0146 | 0.89 | 280 | 0.0146 |
60
- | 0.0145 | 1.01 | 320 | 0.0149 |
61
- | 0.0097 | 1.14 | 360 | 0.0141 |
62
- | 0.0081 | 1.27 | 400 | 0.0123 |
63
- | 0.0076 | 1.39 | 440 | 0.0104 |
64
- | 0.0061 | 1.52 | 480 | 0.0102 |
65
- | 0.0059 | 1.65 | 520 | 0.0101 |
66
- | 0.0068 | 1.77 | 560 | 0.0097 |
67
- | 0.0051 | 1.9 | 600 | 0.0088 |
68
- | 0.0053 | 2.03 | 640 | 0.0089 |
69
- | 0.003 | 2.15 | 680 | 0.0079 |
70
- | 0.0027 | 2.28 | 720 | 0.0060 |
71
- | 0.0017 | 2.41 | 760 | 0.0065 |
72
- | 0.0017 | 2.53 | 800 | 0.0052 |
73
- | 0.0016 | 2.66 | 840 | 0.0055 |
74
- | 0.0012 | 2.78 | 880 | 0.0057 |
75
- | 0.0011 | 2.91 | 920 | 0.0051 |
76
- | 0.001 | 3.04 | 960 | 0.0048 |
77
- | 0.0003 | 3.16 | 1000 | 0.0050 |
78
- | 0.0002 | 3.29 | 1040 | 0.0049 |
79
- | 0.0002 | 3.42 | 1080 | 0.0050 |
80
- | 0.0002 | 3.54 | 1120 | 0.0046 |
81
- | 0.0002 | 3.67 | 1160 | 0.0045 |
82
- | 0.0003 | 3.8 | 1200 | 0.0044 |
83
 
84
 
85
  ### 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: 0.0032
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.089 | 0.13 | 40 | 0.0323 |
54
+ | 0.0253 | 0.25 | 80 | 0.0248 |
55
+ | 0.0231 | 0.38 | 120 | 0.0213 |
56
+ | 0.0214 | 0.51 | 160 | 0.0194 |
57
+ | 0.017 | 0.63 | 200 | 0.0153 |
58
+ | 0.0162 | 0.76 | 240 | 0.0137 |
59
+ | 0.0129 | 0.89 | 280 | 0.0141 |
60
+ | 0.0119 | 1.01 | 320 | 0.0119 |
61
+ | 0.0079 | 1.14 | 360 | 0.0109 |
62
+ | 0.0072 | 1.27 | 400 | 0.0113 |
63
+ | 0.0074 | 1.39 | 440 | 0.0099 |
64
+ | 0.006 | 1.52 | 480 | 0.0091 |
65
+ | 0.0067 | 1.65 | 520 | 0.0078 |
66
+ | 0.0046 | 1.77 | 560 | 0.0091 |
67
+ | 0.0055 | 1.9 | 600 | 0.0064 |
68
+ | 0.0032 | 2.03 | 640 | 0.0058 |
69
+ | 0.002 | 2.15 | 680 | 0.0066 |
70
+ | 0.002 | 2.28 | 720 | 0.0061 |
71
+ | 0.0018 | 2.41 | 760 | 0.0063 |
72
+ | 0.0018 | 2.53 | 800 | 0.0057 |
73
+ | 0.0021 | 2.66 | 840 | 0.0048 |
74
+ | 0.0017 | 2.78 | 880 | 0.0046 |
75
+ | 0.0013 | 2.91 | 920 | 0.0044 |
76
+ | 0.0008 | 3.04 | 960 | 0.0036 |
77
+ | 0.0005 | 3.16 | 1000 | 0.0043 |
78
+ | 0.0004 | 3.29 | 1040 | 0.0042 |
79
+ | 0.0004 | 3.42 | 1080 | 0.0036 |
80
+ | 0.0004 | 3.54 | 1120 | 0.0039 |
81
+ | 0.0003 | 3.67 | 1160 | 0.0034 |
82
+ | 0.0002 | 3.8 | 1200 | 0.0032 |
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:fdb8c5f872b8e2d1aec878bd8a90c74408b16bddc3a416ccfdab337e280b56ee
3
  size 268528394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ad6e6fafdd515d90760313d35de44e9347e453aad8bc1ccada041d19c1c317
3
  size 268528394
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2306cb33d4c9ec22c37a38e291e46c2c3026097a9973b40fb324c7d98430584
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49f0b7c23f2332adcaef7be5a197408bf06c615d94f049d1e2981ea0f15fa40
3
  size 4984