Model save
Browse files- README.md +101 -11
- model.safetensors +1 -1
README.md
CHANGED
@@ -1,14 +1,104 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
example_title: Example 2
|
8 |
-
datasets:
|
9 |
-
- sinonimayzer/mixed-data
|
10 |
-
language:
|
11 |
-
- uz
|
12 |
-
pipeline_tag: fill-mask
|
13 |
---
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: UzRoBERTa-v2
|
6 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# UzRoBERTa-v2
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 1.9097
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 92
|
37 |
+
- eval_batch_size: 92
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- training_steps: 500000
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:------:|:---------------:|
|
47 |
+
| 6.3907 | 0.03 | 10000 | 6.3152 |
|
48 |
+
| 5.9936 | 0.05 | 20000 | 5.7963 |
|
49 |
+
| 3.6265 | 0.08 | 30000 | 3.5652 |
|
50 |
+
| 3.0828 | 0.1 | 40000 | 3.1101 |
|
51 |
+
| 2.8485 | 0.13 | 50000 | 2.8866 |
|
52 |
+
| 2.6924 | 0.15 | 60000 | 2.7570 |
|
53 |
+
| 2.5799 | 0.18 | 70000 | 2.6464 |
|
54 |
+
| 2.4943 | 0.2 | 80000 | 2.5785 |
|
55 |
+
| 2.4246 | 0.23 | 90000 | 2.5101 |
|
56 |
+
| 2.3673 | 0.25 | 100000 | 2.4588 |
|
57 |
+
| 2.3233 | 0.28 | 110000 | 2.4183 |
|
58 |
+
| 2.28 | 0.3 | 120000 | 2.3632 |
|
59 |
+
| 2.2451 | 0.33 | 130000 | 2.3335 |
|
60 |
+
| 2.2113 | 0.36 | 140000 | 2.3124 |
|
61 |
+
| 2.1853 | 0.38 | 150000 | 2.2717 |
|
62 |
+
| 2.1566 | 0.41 | 160000 | 2.2435 |
|
63 |
+
| 2.1344 | 0.43 | 170000 | 2.2302 |
|
64 |
+
| 2.1157 | 0.46 | 180000 | 2.2068 |
|
65 |
+
| 2.0926 | 0.48 | 190000 | 2.1794 |
|
66 |
+
| 2.0797 | 0.51 | 200000 | 2.1653 |
|
67 |
+
| 2.056 | 0.53 | 210000 | 2.1497 |
|
68 |
+
| 2.043 | 0.56 | 220000 | 2.1302 |
|
69 |
+
| 2.0217 | 0.58 | 230000 | 2.1162 |
|
70 |
+
| 2.0112 | 0.61 | 240000 | 2.1003 |
|
71 |
+
| 1.9934 | 0.64 | 250000 | 2.0877 |
|
72 |
+
| 1.9855 | 0.66 | 260000 | 2.0697 |
|
73 |
+
| 1.9756 | 0.69 | 270000 | 2.0601 |
|
74 |
+
| 1.9596 | 0.71 | 280000 | 2.0457 |
|
75 |
+
| 1.9477 | 0.74 | 290000 | 2.0407 |
|
76 |
+
| 1.9369 | 0.76 | 300000 | 2.0265 |
|
77 |
+
| 1.9342 | 0.79 | 310000 | 2.0106 |
|
78 |
+
| 1.9183 | 0.81 | 320000 | 2.0076 |
|
79 |
+
| 1.9076 | 0.84 | 330000 | 1.9999 |
|
80 |
+
| 1.8994 | 0.86 | 340000 | 1.9924 |
|
81 |
+
| 1.8968 | 0.89 | 350000 | 1.9871 |
|
82 |
+
| 1.8897 | 0.91 | 360000 | 1.9787 |
|
83 |
+
| 1.8769 | 0.94 | 370000 | 1.9678 |
|
84 |
+
| 1.8727 | 0.97 | 380000 | 1.9659 |
|
85 |
+
| 1.8675 | 0.99 | 390000 | 1.9546 |
|
86 |
+
| 1.8545 | 1.02 | 400000 | 1.9456 |
|
87 |
+
| 1.8515 | 1.04 | 410000 | 1.9425 |
|
88 |
+
| 1.8397 | 1.07 | 420000 | 1.9416 |
|
89 |
+
| 1.8406 | 1.09 | 430000 | 1.9343 |
|
90 |
+
| 1.8332 | 1.12 | 440000 | 1.9273 |
|
91 |
+
| 1.8325 | 1.14 | 450000 | 1.9257 |
|
92 |
+
| 1.8258 | 1.17 | 460000 | 1.9219 |
|
93 |
+
| 1.8239 | 1.19 | 470000 | 1.9168 |
|
94 |
+
| 1.8173 | 1.22 | 480000 | 1.9163 |
|
95 |
+
| 1.8155 | 1.25 | 490000 | 1.9113 |
|
96 |
+
| 1.8133 | 1.27 | 500000 | 1.9101 |
|
97 |
+
|
98 |
+
|
99 |
+
### Framework versions
|
100 |
+
|
101 |
+
- Transformers 4.35.2
|
102 |
+
- Pytorch 2.1.1+cu121
|
103 |
+
- Datasets 2.15.0
|
104 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 504144664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:539572f9c9e63008a508959c1b4eadbcf0809a048272d849c63432ff2597d779
|
3 |
size 504144664
|