zhiyil commited on
Commit
aa4bc81
1 Parent(s): 78ab942

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - snips_built_in_intents
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: roberta-base-finetuned-intent-ipu
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # roberta-base-finetuned-intent-ipu
18
+
19
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the snips_built_in_intents dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1503
22
+ - Accuracy: 1.0
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 1
43
+ - eval_batch_size: 1
44
+ - seed: 42
45
+ - distributed_type: IPU
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 8
48
+ - total_eval_batch_size: 5
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 10
52
+ - training precision: Mixed Precision
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
58
+ | 1.2478 | 1.0 | 75 | 0.6069 | 0.96 |
59
+ | 0.2522 | 2.0 | 150 | 0.1503 | 1.0 |
60
+ | 0.0903 | 3.0 | 225 | 0.0712 | 1.0 |
61
+ | 0.0883 | 4.0 | 300 | 0.0350 | 1.0 |
62
+ | 0.0491 | 5.0 | 375 | 0.0267 | 1.0 |
63
+ | 0.0305 | 6.0 | 450 | 0.0218 | 1.0 |
64
+ | 0.0461 | 7.0 | 525 | 0.0191 | 1.0 |
65
+ | 0.039 | 8.0 | 600 | 0.0174 | 1.0 |
66
+ | 0.0337 | 9.0 | 675 | 0.0166 | 1.0 |
67
+ | 0.0164 | 10.0 | 750 | 0.0162 | 1.0 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.20.1
73
+ - Pytorch 1.10.0+cpu
74
+ - Datasets 2.7.1
75
+ - Tokenizers 0.12.0