nbroad HF staff commited on
Commit
55d3bf3
1 Parent(s): 9114ab2

Model save

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/xtremedistil-l12-h384-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: finer-139-xtremedistil-l12-h384-v2
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # finer-139-xtremedistil-l12-h384-v2
20
+
21
+ This model is a fine-tuned version of [microsoft/xtremedistil-l12-h384-uncased](https://huggingface.co/microsoft/xtremedistil-l12-h384-uncased) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0133
24
+ - Precision: 0.6104
25
+ - Recall: 0.6581
26
+ - F1: 0.6334
27
+ - Accuracy: 0.9961
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 5e-05
47
+ - train_batch_size: 256
48
+ - eval_batch_size: 512
49
+ - seed: 42
50
+ - distributed_type: multi-GPU
51
+ - num_devices: 2
52
+ - total_train_batch_size: 512
53
+ - total_eval_batch_size: 1024
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: linear
56
+ - lr_scheduler_warmup_steps: 100
57
+ - num_epochs: 5.0
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
62
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
63
+ | 0.0438 | 1.0 | 1759 | 0.0389 | 0.4777 | 0.1593 | 0.2389 | 0.9937 |
64
+ | 0.0266 | 2.0 | 3518 | 0.0234 | 0.5432 | 0.4129 | 0.4692 | 0.9949 |
65
+ | 0.0186 | 3.0 | 5277 | 0.0165 | 0.5980 | 0.5516 | 0.5739 | 0.9957 |
66
+ | 0.0154 | 4.0 | 7036 | 0.0143 | 0.5932 | 0.6447 | 0.6179 | 0.9959 |
67
+ | 0.0137 | 5.0 | 8795 | 0.0133 | 0.6104 | 0.6581 | 0.6334 | 0.9961 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.34.0
73
+ - Pytorch 2.1.0a0+b5021ba
74
+ - Datasets 2.14.5
75
+ - Tokenizers 0.14.1