Hugging Face's logo

thrunlab
/
t5-large_rte_dense_sp0_ar0

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
lukeleeai commited on
Commit
d2b6001
•
1 Parent(s): 61beb8a

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -13
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.4304
36
  - Accuracy: 0.0
37
 
38
  ## Model description
@@ -53,11 +53,11 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 16
57
- - eval_batch_size: 32
58
  - seed: 1
59
  - gradient_accumulation_steps: 2
60
- - total_train_batch_size: 32
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 20
@@ -67,15 +67,22 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.7246 | 0.32 | 25 | 0.6956 | 0.5054 |
71
- | 0.6873 | 0.64 | 50 | 0.6589 | 0.6462 |
72
- | 0.5328 | 0.96 | 75 | 0.5163 | 0.7942 |
73
- | 0.3942 | 1.28 | 100 | 0.3964 | 0.8556 |
74
- | 0.3563 | 1.6 | 125 | 0.3320 | 0.8917 |
75
- | 0.2756 | 1.92 | 150 | 0.4182 | 0.8520 |
76
- | 0.1572 | 2.24 | 175 | 0.4141 | 0.8700 |
77
- | 0.1338 | 2.56 | 200 | 0.5244 | 0.8628 |
78
- | 0.1802 | 2.88 | 225 | 0.8758 | 0.8700 |
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
 
32
 
33
  This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.9322
36
  - Accuracy: 0.0
37
 
38
  ## Model description
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 16
58
  - seed: 1
59
  - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 16
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 20
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.6781 | 0.16 | 25 | 0.6834 | 0.5487 |
71
+ | 0.7041 | 0.32 | 50 | 0.6878 | 0.5523 |
72
+ | 0.689 | 0.48 | 75 | 0.6836 | 0.6065 |
73
+ | 0.6902 | 0.64 | 100 | 0.6630 | 0.5740 |
74
+ | 0.6458 | 0.8 | 125 | 0.5695 | 0.7112 |
75
+ | 0.5973 | 0.96 | 150 | 0.6138 | 0.6823 |
76
+ | 0.5697 | 1.12 | 175 | 0.5707 | 0.7581 |
77
+ | 0.4567 | 1.28 | 200 | 0.6558 | 0.7256 |
78
+ | 0.3796 | 1.44 | 225 | 0.4968 | 0.7870 |
79
+ | 0.3749 | 1.6 | 250 | 0.5082 | 0.8123 |
80
+ | 0.5187 | 1.76 | 275 | 0.4428 | 0.8123 |
81
+ | 0.4176 | 1.92 | 300 | 0.3940 | 0.8556 |
82
+ | 0.2678 | 2.08 | 325 | 0.4938 | 0.8484 |
83
+ | 0.0761 | 2.24 | 350 | 0.6533 | 0.8520 |
84
+ | 0.2082 | 2.4 | 375 | 0.5901 | 0.8484 |
85
+ | 0.4081 | 2.56 | 400 | 0.5939 | 0.8520 |
86
 
87
 
88
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:478b27b7d8c659ef0337f32d9b1887092987a5c179453a0a2434c41b4022220e
3
  size 2955086993
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4473827ccdd022c98a6e75d616692f35386aca080653af6462d38c33fcdcfea2
3
  size 2955086993