Training
Browse files- README.md +71 -0
- generation_config.json +9 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: IlyaGusev/rut5_base_sum_gazeta
|
| 4 |
+
tags:
|
| 5 |
+
- summarization_3
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- rouge
|
| 9 |
+
model-index:
|
| 10 |
+
- name: rut5_base_sum_gazeta-finetuned_week_gpt
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# rut5_base_sum_gazeta-finetuned_week_gpt
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [IlyaGusev/rut5_base_sum_gazeta](https://huggingface.co/IlyaGusev/rut5_base_sum_gazeta) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.0665
|
| 22 |
+
- Rouge1: 38.7802
|
| 23 |
+
- Rouge2: 18.8758
|
| 24 |
+
- Rougel: 38.1542
|
| 25 |
+
- Rougelsum: 38.195
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 5.6e-05
|
| 45 |
+
- train_batch_size: 16
|
| 46 |
+
- eval_batch_size: 16
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 8
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
| 56 |
+
| No log | 1.0 | 555 | 1.1788 | 36.7978 | 17.6912 | 36.1337 | 36.1391 |
|
| 57 |
+
| 1.3896 | 2.0 | 1110 | 1.0992 | 37.9462 | 18.6497 | 37.3932 | 37.4791 |
|
| 58 |
+
| 1.3896 | 3.0 | 1665 | 1.1053 | 38.8205 | 18.8297 | 38.0614 | 38.1843 |
|
| 59 |
+
| 1.1331 | 4.0 | 2220 | 1.1029 | 38.3632 | 18.7051 | 37.654 | 37.7872 |
|
| 60 |
+
| 1.1331 | 5.0 | 2775 | 1.0798 | 39.1371 | 18.8761 | 38.4425 | 38.4942 |
|
| 61 |
+
| 1.0312 | 6.0 | 3330 | 1.0602 | 38.6421 | 18.9015 | 38.0504 | 38.0638 |
|
| 62 |
+
| 1.0312 | 7.0 | 3885 | 1.0650 | 39.2291 | 19.0341 | 38.6098 | 38.6528 |
|
| 63 |
+
| 0.975 | 8.0 | 4440 | 1.0665 | 38.7802 | 18.8758 | 38.1542 | 38.195 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.33.0
|
| 69 |
+
- Pytorch 2.0.0
|
| 70 |
+
- Datasets 2.1.0
|
| 71 |
+
- Tokenizers 0.13.3
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"max_length": 200,
|
| 6 |
+
"num_beams": 5,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.33.0"
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 977334453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e389c8ec092a2cfb7b459edd3c94c4b026e98bc049e5704d8b90237db798e33f
|
| 3 |
size 977334453
|