Hugging Face's logo

Shakhovak
/
llama-7b-absa-restaurants

Generated from Trainer
Model card Files Community
Shakhovak commited on
Commit
3c60718
•
1 Parent(s): b1d8836

End of training

Browse files
Files changed (3) hide show
  1. README.md +17 -12
  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: 0.0117
19
 
20
  ## Model description
21
 
@@ -43,23 +43,28 @@ 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: 400
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.113 | 0.13 | 40 | 0.0350 |
54
- | 0.0291 | 0.25 | 80 | 0.0262 |
55
- | 0.0232 | 0.38 | 120 | 0.0237 |
56
- | 0.0186 | 0.51 | 160 | 0.0203 |
57
- | 0.0181 | 0.63 | 200 | 0.0182 |
58
- | 0.0153 | 0.76 | 240 | 0.0157 |
59
- | 0.014 | 0.89 | 280 | 0.0147 |
60
- | 0.0125 | 1.01 | 320 | 0.0126 |
61
- | 0.0066 | 1.14 | 360 | 0.0124 |
62
- | 0.0063 | 1.27 | 400 | 0.0117 |
 
 
 
 
 
63
 
64
 
65
  ### 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: 0.0039
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: 600
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.1052 | 0.12 | 40 | 0.0312 |
54
+ | 0.0269 | 0.25 | 80 | 0.0266 |
55
+ | 0.0243 | 0.37 | 120 | 0.0226 |
56
+ | 0.0219 | 0.5 | 160 | 0.0183 |
57
+ | 0.0177 | 0.62 | 200 | 0.0162 |
58
+ | 0.0152 | 0.74 | 240 | 0.0139 |
59
+ | 0.0137 | 0.87 | 280 | 0.0125 |
60
+ | 0.0117 | 0.99 | 320 | 0.0098 |
61
+ | 0.0074 | 1.12 | 360 | 0.0096 |
62
+ | 0.0072 | 1.24 | 400 | 0.0083 |
63
+ | 0.0054 | 1.36 | 440 | 0.0074 |
64
+ | 0.0047 | 1.49 | 480 | 0.0062 |
65
+ | 0.0038 | 1.61 | 520 | 0.0057 |
66
+ | 0.0032 | 1.74 | 560 | 0.0044 |
67
+ | 0.0022 | 1.86 | 600 | 0.0039 |
68
 
69
 
70
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e24ae7de78102e675819ee2c7d741081d99b4b5f5951dd4b9956febfbda07c3
3
  size 268528394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02579b894044dcc962e9bae60935e1ab52d3867a51add726296ffab690bf17e3
3
  size 268528394
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b57b331d5d2428ed50233ca107b985e9da895ae86f28dd79ad8bff656e4b546
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59536812d5beee73a373bdc6c23abc18944306f581ec0fefb7830ec3439ef2f
3
  size 4984