Hugging Face's logo

Shakhovak
/
flan-t5-xl-absa-rest

Generated from Trainer
Model card Files Community
Shakhovak commited on
Commit
699a683
•
1 Parent(s): 5ca6478

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
@@ -2,6 +2,8 @@
2
  base_model: ybelkada/flan-t5-xl-sharded-bf16
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: flan-t5-xl-absa-rest
7
  results: []
@@ -12,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # flan-t5-xl-absa-rest
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: 0.3362
18
 
19
  ## Model description
20
 
@@ -33,27 +35,30 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 1e-05
37
  - train_batch_size: 16
38
  - eval_batch_size: 16
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - lr_scheduler_warmup_ratio: 0.1
43
- - num_epochs: 8
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 4.6083 | 0.9 | 200 | 3.5721 |
50
- | 2.5382 | 1.8 | 400 | 1.3733 |
51
- | 1.133 | 2.7 | 600 | 0.7029 |
52
- | 0.7652 | 3.6 | 800 | 0.4796 |
53
- | 0.5812 | 4.5 | 1000 | 0.3836 |
54
- | 0.5035 | 5.41 | 1200 | 0.3557 |
55
- | 0.4842 | 6.31 | 1400 | 0.3437 |
56
- | 0.4591 | 7.21 | 1600 | 0.3362 |
 
 
 
57
 
58
 
59
  ### Framework versions
 
2
  base_model: ybelkada/flan-t5-xl-sharded-bf16
3
  tags:
4
  - generated_from_trainer
5
+ datasets:
6
+ - sem_eval2014_task4
7
  model-index:
8
  - name: flan-t5-xl-absa-rest
9
  results: []
 
14
 
15
  # flan-t5-xl-absa-rest
16
 
17
+ This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on the sem_eval2014_task4 dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1705
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
  - train_batch_size: 16
40
  - eval_batch_size: 16
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_ratio: 0.1
45
+ - num_epochs: 10
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 3.4491 | 0.9 | 200 | 0.7559 |
52
+ | 0.4855 | 1.8 | 400 | 0.2962 |
53
+ | 0.3356 | 2.7 | 600 | 0.2460 |
54
+ | 0.2742 | 3.6 | 800 | 0.2234 |
55
+ | 0.2529 | 4.5 | 1000 | 0.2087 |
56
+ | 0.2381 | 5.41 | 1200 | 0.1907 |
57
+ | 0.217 | 6.31 | 1400 | 0.1844 |
58
+ | 0.2101 | 7.21 | 1600 | 0.1796 |
59
+ | 0.2113 | 8.11 | 1800 | 0.1737 |
60
+ | 0.2026 | 9.01 | 2000 | 0.1722 |
61
+ | 0.1988 | 9.91 | 2200 | 0.1705 |
62
 
63
 
64
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:959eb5deccee0d19025879eb5d9f54246b5fae66125ad48e361439d45447f642
3
  size 37855242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790f7d2b23cfead6f640d9be3c275cae5b07887e1dbd22329e3b3d3d50ac47dd
3
  size 37855242
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:349a35d8a66dd4de58696eb8253598e256a350c3be46a96688029f6bf36a69a5
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a12e5e29897f79258729dfc9866ee029ed07a6060ba3452f6ba379e2252441e1
3
  size 5112