Hugging Face's logo

Shakhovak
/
flan-t5-xl-absa-rest

Generated from Trainer
Model card Files Community
Shakhovak commited on
Commit
9188277
•
1 Parent(s): 4f4779e

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -14
  2. adapter_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.1978
18
 
19
  ## Model description
20
 
@@ -46,19 +46,19 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 3.6285 | 0.9 | 200 | 0.9654 |
50
- | 0.5625 | 1.8 | 400 | 0.3241 |
51
- | 0.334 | 2.7 | 600 | 0.2687 |
52
- | 0.278 | 3.6 | 800 | 0.2444 |
53
- | 0.2492 | 4.5 | 1000 | 0.2290 |
54
- | 0.2362 | 5.41 | 1200 | 0.2219 |
55
- | 0.2137 | 6.31 | 1400 | 0.2114 |
56
- | 0.2095 | 7.21 | 1600 | 0.2097 |
57
- | 0.1973 | 8.11 | 1800 | 0.2046 |
58
- | 0.1914 | 9.01 | 2000 | 0.2028 |
59
- | 0.1822 | 9.91 | 2200 | 0.2000 |
60
- | 0.1826 | 10.81 | 2400 | 0.1974 |
61
- | 0.1712 | 11.71 | 2600 | 0.1978 |
62
 
63
 
64
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.1658
18
 
19
  ## Model description
20
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 3.6689 | 0.9 | 200 | 0.8087 |
50
+ | 0.5615 | 1.8 | 400 | 0.2540 |
51
+ | 0.325 | 2.7 | 600 | 0.2220 |
52
+ | 0.2854 | 3.6 | 800 | 0.2019 |
53
+ | 0.2554 | 4.5 | 1000 | 0.1835 |
54
+ | 0.2341 | 5.41 | 1200 | 0.1783 |
55
+ | 0.2092 | 6.31 | 1400 | 0.1745 |
56
+ | 0.2091 | 7.21 | 1600 | 0.1675 |
57
+ | 0.2038 | 8.11 | 1800 | 0.1685 |
58
+ | 0.1906 | 9.01 | 2000 | 0.1668 |
59
+ | 0.1848 | 9.91 | 2200 | 0.1649 |
60
+ | 0.1818 | 10.81 | 2400 | 0.1654 |
61
+ | 0.1808 | 11.71 | 2600 | 0.1658 |
62
 
63
 
64
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d4694d361c3371c94505c098f8e6a449b5abfa6c11561ba7fc99f60c838e083
3
  size 37855242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffff084ca3b1cedee81bd83e4779a1b4ebabbb4f2bfca61d05fff157f9407324
3
  size 37855242
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f429d4144e35f48c569df484a98acdd84e04490c430ae7faa9590144875cc63d
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41268a4ebe1c84e5dfe60179c889e633b7c98b505fd41b17b38b0473f9b805af
3
  size 5112