lewtun HF staff commited on
Commit
1e90b7d
1 Parent(s): a0cddfa

End of training

Browse files
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - clinc_oos
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: roberta-large-finetuned-clinc
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: clinc_oos
17
+ type: clinc_oos
18
+ args: plus
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.9767741935483871
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # roberta-large-finetuned-clinc
29
+
30
+ This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the clinc_oos dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.1545
33
+ - Accuracy: 0.9768
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 2e-05
53
+ - train_batch_size: 16
54
+ - eval_batch_size: 16
55
+ - seed: 42
56
+ - distributed_type: sagemaker_data_parallel
57
+ - num_devices: 8
58
+ - total_train_batch_size: 128
59
+ - total_eval_batch_size: 128
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_steps: 500
63
+ - num_epochs: 5
64
+ - mixed_precision_training: Native AMP
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 5.0548 | 1.0 | 120 | 5.0359 | 0.0071 |
71
+ | 4.4725 | 2.0 | 240 | 2.9385 | 0.7558 |
72
+ | 1.8924 | 3.0 | 360 | 0.6456 | 0.9374 |
73
+ | 0.4552 | 4.0 | 480 | 0.2297 | 0.9626 |
74
+ | 0.1589 | 5.0 | 600 | 0.1545 | 0.9768 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.17.0
80
+ - Pytorch 1.10.2+cu113
81
+ - Datasets 1.18.4
82
+ - Tokenizers 0.11.6
eval_results.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epoch = 5.0
2
+ eval_accuracy = 0.9767741935483871
3
+ eval_loss = 0.15451878309249878
4
+ eval_runtime = 2.6267
5
+ eval_samples_per_second = 1180.186
6
+ eval_steps_per_second = 9.518
logs/events.out.tfevents.1649839227.algo-1.599.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e007047f652430db66fe960c72732ad004110fc45cbdec7fde22932b2a0168db
3
- size 13592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b9ee7cc6c28999508bf1026b6dafff5d95b809aa16d7fee46521f96a71d1aa
3
+ size 13946
logs/events.out.tfevents.1649839515.algo-1.599.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e5e033dc51e9efd8780deafbd47a5add0c061cfbb57932d60d61dbe8f02104
3
+ size 363