sansmislom
commited on
Commit
•
45345c8
1
Parent(s):
b8d4cff
Training complete
Browse files
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/mt5-small
|
4 |
+
tags:
|
5 |
+
- summarization
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- gazeta
|
9 |
+
metrics:
|
10 |
+
- rouge
|
11 |
+
model-index:
|
12 |
+
- name: mt5-small-finetuned-gazeta-ru
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Sequence-to-sequence Language Modeling
|
16 |
+
type: text2text-generation
|
17 |
+
dataset:
|
18 |
+
name: gazeta
|
19 |
+
type: gazeta
|
20 |
+
config: default
|
21 |
+
split: validation
|
22 |
+
args: default
|
23 |
+
metrics:
|
24 |
+
- name: Rouge1
|
25 |
+
type: rouge
|
26 |
+
value: 2.9422
|
27 |
+
---
|
28 |
+
|
29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
30 |
+
should probably proofread and complete it, then remove this comment. -->
|
31 |
+
|
32 |
+
# mt5-small-finetuned-gazeta-ru
|
33 |
+
|
34 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the gazeta dataset.
|
35 |
+
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 3.3287
|
37 |
+
- Rouge1: 2.9422
|
38 |
+
- Rouge2: 0.25
|
39 |
+
- Rougel: 2.9053
|
40 |
+
- Rougelsum: 2.9131
|
41 |
+
|
42 |
+
## Model description
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Intended uses & limitations
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training and evaluation data
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Training procedure
|
55 |
+
|
56 |
+
### Training hyperparameters
|
57 |
+
|
58 |
+
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 5.6e-05
|
60 |
+
- train_batch_size: 8
|
61 |
+
- eval_batch_size: 8
|
62 |
+
- seed: 42
|
63 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
+
- lr_scheduler_type: linear
|
65 |
+
- num_epochs: 8
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
70 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|
|
71 |
+
| 5.5708 | 1.0 | 1690 | 3.3106 | 1.8563 | 0.1911 | 1.8332 | 1.8348 |
|
72 |
+
| 4.0219 | 2.0 | 3380 | 3.3048 | 2.2018 | 0.1649 | 2.1978 | 2.2022 |
|
73 |
+
| 3.7276 | 3.0 | 5070 | 3.3320 | 3.2293 | 0.2173 | 3.194 | 3.2039 |
|
74 |
+
| 3.5835 | 4.0 | 6760 | 3.3308 | 3.2189 | 0.2932 | 3.1825 | 3.1841 |
|
75 |
+
| 3.4944 | 5.0 | 8450 | 3.3104 | 2.8833 | 0.1964 | 2.8521 | 2.8537 |
|
76 |
+
| 3.4203 | 6.0 | 10140 | 3.3032 | 2.9914 | 0.2723 | 2.9516 | 2.9542 |
|
77 |
+
| 3.3774 | 7.0 | 11830 | 3.3232 | 2.9982 | 0.3063 | 2.965 | 2.9642 |
|
78 |
+
| 3.348 | 8.0 | 13520 | 3.3287 | 2.9422 | 0.25 | 2.9053 | 2.9131 |
|
79 |
+
|
80 |
+
|
81 |
+
### Framework versions
|
82 |
+
|
83 |
+
- Transformers 4.42.4
|
84 |
+
- Pytorch 2.3.1+cu121
|
85 |
+
- Datasets 2.20.0
|
86 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.42.4"
|
6 |
+
}
|
runs/Aug10_20-26-12_97d016264cf1/events.out.tfevents.1723321574.97d016264cf1.271.0
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 sha256:58704f567c5f6d29abf626673288aee408550700d0f0b2e7f875fc9b27ac4d02
|
3 |
+
size 10991
|
runs/Aug10_20-26-12_97d016264cf1/events.out.tfevents.1723332578.97d016264cf1.271.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee0e085523e235cfcae6391e294da26259e494fe0837fdde961fe8c8aaf39bd9
|
3 |
+
size 562
|