sakren commited on
Commit
91b952e
1 Parent(s): e6baf94

sakren/distil-bert

Browse files
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/MiniLM-L12-H384-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - emotion
8
+ metrics:
9
+ - f1
10
+ model-index:
11
+ - name: minilm-emotion
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: emotion
18
+ type: emotion
19
+ config: split
20
+ split: validation
21
+ args: split
22
+ metrics:
23
+ - name: F1
24
+ type: f1
25
+ value: 0.7776664523081279
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # minilm-emotion
32
+
33
+ This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the emotion dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.7866
36
+ - F1: 0.7777
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
+ - train_batch_size: 64
57
+ - eval_batch_size: 64
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 3
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
66
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
67
+ | 1.4807 | 1.0 | 250 | 1.1974 | 0.4675 |
68
+ | 1.062 | 2.0 | 500 | 0.8748 | 0.7255 |
69
+ | 0.8603 | 3.0 | 750 | 0.7866 | 0.7777 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.39.3
75
+ - Pytorch 2.1.2
76
+ - Datasets 2.18.0
77
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d55a8abaebb934a298486a8393bf0a967fff23ae17cb20cec8e9283ef58aa7ff
3
  size 133472536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77cedc32ee520f9f44148d449ee9bb790834e5d86d4a9e2bf45701c3c0be2fa0
3
  size 133472536
runs/May14_21-08-52_491ac2b658d6/events.out.tfevents.1715720971.491ac2b658d6.34.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e113551e88de06f3a061f3a7def3d6490f9f5aee2a44c23704a94c460c1cec98
3
- size 5533
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7757ceb1c7a6835fdace319a47b4a6cfc9be8f3ef5b619a5d348ef5e07aff5
3
+ size 6732