End of training
Browse files- README.md +81 -0
- logs/events.out.tfevents.1680696506.algo-1.63.0 +2 -2
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- clinc_oos
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: MiniLMv2-L12-H384-distilled-finetuned-clinc
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Text Classification
|
13 |
+
type: text-classification
|
14 |
+
dataset:
|
15 |
+
name: clinc_oos
|
16 |
+
type: clinc_oos
|
17 |
+
args: plus
|
18 |
+
metrics:
|
19 |
+
- name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.9529032258064516
|
22 |
+
---
|
23 |
+
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
+
|
27 |
+
# MiniLMv2-L12-H384-distilled-finetuned-clinc
|
28 |
+
|
29 |
+
This model is a fine-tuned version of [nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large) on the clinc_oos dataset.
|
30 |
+
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 0.3058
|
32 |
+
- Accuracy: 0.9529
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 0.0001
|
52 |
+
- train_batch_size: 64
|
53 |
+
- eval_batch_size: 64
|
54 |
+
- seed: 33
|
55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
+
- lr_scheduler_type: linear
|
57 |
+
- num_epochs: 10
|
58 |
+
- mixed_precision_training: Native AMP
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
64 |
+
| 1.9908 | 1.0 | 239 | 1.6816 | 0.3910 |
|
65 |
+
| 1.5212 | 2.0 | 478 | 1.2365 | 0.7697 |
|
66 |
+
| 1.129 | 3.0 | 717 | 0.9209 | 0.8706 |
|
67 |
+
| 0.8462 | 4.0 | 956 | 0.6978 | 0.9152 |
|
68 |
+
| 0.6497 | 5.0 | 1195 | 0.5499 | 0.9342 |
|
69 |
+
| 0.5124 | 6.0 | 1434 | 0.4447 | 0.9445 |
|
70 |
+
| 0.4196 | 7.0 | 1673 | 0.3797 | 0.9455 |
|
71 |
+
| 0.3587 | 8.0 | 1912 | 0.3358 | 0.95 |
|
72 |
+
| 0.3228 | 9.0 | 2151 | 0.3133 | 0.9513 |
|
73 |
+
| 0.3052 | 10.0 | 2390 | 0.3058 | 0.9529 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.17.0
|
79 |
+
- Pytorch 1.10.2+cu113
|
80 |
+
- Datasets 1.18.4
|
81 |
+
- Tokenizers 0.13.0
|
logs/events.out.tfevents.1680696506.algo-1.63.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a83f8e4ff09f35bbfa79fa9ac6c461b640c10f4c4ac6d46945dc9ba8636cf4da
|
3 |
+
size 16441
|