Hugging Face's logo

RazinAleks
/
working

Text2Text Generation
Transformers
PyTorch
mt5
Generated from Trainer
Inference Endpoints
Model card Files Community
RazinAleks commited on
Commit
b749175
•
1 Parent(s): e7d1410

RazinAleks/mT5-fine-tune

Browse files
Files changed (5) hide show
  1. README.md +12 -12
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. tokenizer.json +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/mt5-small
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # working
17
 
18
- This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 3.0221
21
- - Rouge1: 0.0464
22
- - Rouge2: 0.0119
23
- - Rougel: 0.0464
24
- - Rougelsum: 0.0463
25
- - Gen Len: 16.2531
26
 
27
  ## Model description
28
 
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
56
- | 4.0764 | 1.0 | 938 | 3.1099 | 0.0429 | 0.0098 | 0.0428 | 0.0428 | 14.8533 |
57
- | 3.8336 | 2.0 | 1876 | 3.0549 | 0.043 | 0.0103 | 0.0429 | 0.0427 | 15.4201 |
58
- | 3.7839 | 3.0 | 2814 | 3.0356 | 0.0474 | 0.0116 | 0.0472 | 0.0471 | 16.3025 |
59
- | 3.7851 | 4.0 | 3752 | 3.0221 | 0.0464 | 0.0119 | 0.0464 | 0.0463 | 16.2531 |
60
 
61
 
62
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: RazinAleks/working
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # working
17
 
18
+ This model is a fine-tuned version of [RazinAleks/working](https://huggingface.co/RazinAleks/working) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.2209
21
+ - Rouge1: 0.0485
22
+ - Rouge2: 0.0137
23
+ - Rougel: 0.0481
24
+ - Rougelsum: 0.0484
25
+ - Gen Len: 17.5748
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
56
+ | 4.267 | 1.0 | 938 | 3.3590 | 0.0423 | 0.0117 | 0.042 | 0.0421 | 17.3022 |
57
+ | 3.9878 | 2.0 | 1876 | 3.2691 | 0.0437 | 0.0116 | 0.0435 | 0.0437 | 17.3476 |
58
+ | 3.9117 | 3.0 | 2814 | 3.2318 | 0.0483 | 0.014 | 0.0479 | 0.0481 | 17.61 |
59
+ | 3.8808 | 4.0 | 3752 | 3.2209 | 0.0485 | 0.0137 | 0.0481 | 0.0484 | 17.5748 |
60
 
61
 
62
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "google/mt5-small",
3
  "architectures": [
4
  "MT5ForConditionalGeneration"
5
  ],
 
1
  {
2
+ "_name_or_path": "RazinAleks/working",
3
  "architectures": [
4
  "MT5ForConditionalGeneration"
5
  ],
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b771923d04bca5fc65155133d32939890769a42ae67fa88552ea6abd8b67c58
3
  size 1200772613
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb552b98ce77b877d709d47149f2e846f2e5eaf879927a8281f116988f0ddbb
3
  size 1200772613
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
3
- size 16330369
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
3
+ size 16315219
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac1717689fc86acd742988396c601144859aa73eabe110acdfdf3a9a685bcc7c
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf9140b977dc411227766975c5d390856c3e0bbdb77a961f700ccd866a4177c
3
  size 4219