End of training
Browse files
README.md
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/MiniLM-L12-H384-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: MiniLM_uncased_classification_tools_qlora_fr
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# MiniLM_uncased_classification_tools_qlora_fr
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.7495
|
21 |
+
- Accuracy: 0.5
|
22 |
+
- Learning Rate: 0.0
|
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: 0.0001
|
42 |
+
- train_batch_size: 24
|
43 |
+
- eval_batch_size: 192
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 60
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Rate |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
53 |
+
| No log | 1.0 | 7 | 2.0845 | 0.075 | 0.0001 |
|
54 |
+
| No log | 2.0 | 14 | 2.0852 | 0.075 | 0.0001 |
|
55 |
+
| No log | 3.0 | 21 | 2.0851 | 0.075 | 0.0001 |
|
56 |
+
| No log | 4.0 | 28 | 2.0855 | 0.075 | 0.0001 |
|
57 |
+
| No log | 5.0 | 35 | 2.0858 | 0.075 | 0.0001 |
|
58 |
+
| No log | 6.0 | 42 | 2.0861 | 0.075 | 9e-05 |
|
59 |
+
| No log | 7.0 | 49 | 2.0863 | 0.075 | 0.0001 |
|
60 |
+
| No log | 8.0 | 56 | 2.0859 | 0.075 | 0.0001 |
|
61 |
+
| No log | 9.0 | 63 | 2.0856 | 0.075 | 0.0001 |
|
62 |
+
| No log | 10.0 | 70 | 2.0855 | 0.075 | 0.0001 |
|
63 |
+
| No log | 11.0 | 77 | 2.0848 | 0.075 | 0.0001 |
|
64 |
+
| No log | 12.0 | 84 | 2.0844 | 0.075 | 8e-05 |
|
65 |
+
| No log | 13.0 | 91 | 2.0829 | 0.075 | 0.0001 |
|
66 |
+
| No log | 14.0 | 98 | 2.0825 | 0.075 | 0.0001 |
|
67 |
+
| No log | 15.0 | 105 | 2.0811 | 0.1 | 0.0001 |
|
68 |
+
| No log | 16.0 | 112 | 2.0793 | 0.175 | 0.0001 |
|
69 |
+
| No log | 17.0 | 119 | 2.0771 | 0.125 | 0.0001 |
|
70 |
+
| No log | 18.0 | 126 | 2.0750 | 0.175 | 7e-05 |
|
71 |
+
| No log | 19.0 | 133 | 2.0723 | 0.175 | 0.0001 |
|
72 |
+
| No log | 20.0 | 140 | 2.0683 | 0.175 | 0.0001 |
|
73 |
+
| No log | 21.0 | 147 | 2.0637 | 0.175 | 0.0001 |
|
74 |
+
| No log | 22.0 | 154 | 2.0574 | 0.175 | 0.0001 |
|
75 |
+
| No log | 23.0 | 161 | 2.0507 | 0.2 | 0.0001 |
|
76 |
+
| No log | 24.0 | 168 | 2.0419 | 0.325 | 6e-05 |
|
77 |
+
| No log | 25.0 | 175 | 2.0318 | 0.35 | 0.0001 |
|
78 |
+
| No log | 26.0 | 182 | 2.0214 | 0.4 | 0.0001 |
|
79 |
+
| No log | 27.0 | 189 | 2.0083 | 0.4 | 0.0001 |
|
80 |
+
| No log | 28.0 | 196 | 1.9949 | 0.4 | 0.0001 |
|
81 |
+
| No log | 29.0 | 203 | 1.9781 | 0.4 | 0.0001 |
|
82 |
+
| No log | 30.0 | 210 | 1.9609 | 0.4 | 5e-05 |
|
83 |
+
| No log | 31.0 | 217 | 1.9475 | 0.425 | 0.0000 |
|
84 |
+
| No log | 32.0 | 224 | 1.9317 | 0.45 | 0.0000 |
|
85 |
+
| No log | 33.0 | 231 | 1.9131 | 0.45 | 0.0000 |
|
86 |
+
| No log | 34.0 | 238 | 1.9015 | 0.475 | 0.0000 |
|
87 |
+
| No log | 35.0 | 245 | 1.8906 | 0.5 | 0.0000 |
|
88 |
+
| No log | 36.0 | 252 | 1.8740 | 0.475 | 4e-05 |
|
89 |
+
| No log | 37.0 | 259 | 1.8613 | 0.5 | 0.0000 |
|
90 |
+
| No log | 38.0 | 266 | 1.8552 | 0.525 | 0.0000 |
|
91 |
+
| No log | 39.0 | 273 | 1.8389 | 0.5 | 0.0000 |
|
92 |
+
| No log | 40.0 | 280 | 1.8302 | 0.5 | 0.0000 |
|
93 |
+
| No log | 41.0 | 287 | 1.8228 | 0.5 | 0.0000 |
|
94 |
+
| No log | 42.0 | 294 | 1.8244 | 0.525 | 3e-05 |
|
95 |
+
| No log | 43.0 | 301 | 1.8048 | 0.5 | 0.0000 |
|
96 |
+
| No log | 44.0 | 308 | 1.7944 | 0.525 | 0.0000 |
|
97 |
+
| No log | 45.0 | 315 | 1.7929 | 0.5 | 0.0000 |
|
98 |
+
| No log | 46.0 | 322 | 1.7904 | 0.5 | 0.0000 |
|
99 |
+
| No log | 47.0 | 329 | 1.7810 | 0.5 | 0.0000 |
|
100 |
+
| No log | 48.0 | 336 | 1.7790 | 0.5 | 2e-05 |
|
101 |
+
| No log | 49.0 | 343 | 1.7758 | 0.5 | 0.0000 |
|
102 |
+
| No log | 50.0 | 350 | 1.7677 | 0.525 | 0.0000 |
|
103 |
+
| No log | 51.0 | 357 | 1.7626 | 0.525 | 0.0000 |
|
104 |
+
| No log | 52.0 | 364 | 1.7579 | 0.525 | 0.0000 |
|
105 |
+
| No log | 53.0 | 371 | 1.7552 | 0.525 | 0.0000 |
|
106 |
+
| No log | 54.0 | 378 | 1.7544 | 0.525 | 1e-05 |
|
107 |
+
| No log | 55.0 | 385 | 1.7523 | 0.525 | 0.0000 |
|
108 |
+
| No log | 56.0 | 392 | 1.7510 | 0.525 | 0.0000 |
|
109 |
+
| No log | 57.0 | 399 | 1.7501 | 0.525 | 5e-06 |
|
110 |
+
| No log | 58.0 | 406 | 1.7498 | 0.525 | 0.0000 |
|
111 |
+
| No log | 59.0 | 413 | 1.7496 | 0.525 | 0.0000 |
|
112 |
+
| No log | 60.0 | 420 | 1.7495 | 0.5 | 0.0 |
|
113 |
+
|
114 |
+
|
115 |
+
### Framework versions
|
116 |
+
|
117 |
+
- Transformers 4.34.0
|
118 |
+
- Pytorch 2.0.1+cu117
|
119 |
+
- Datasets 2.14.5
|
120 |
+
- Tokenizers 0.14.1
|