finetuned_RuReCl8
Browse files- README.md +13 -3
- config.json +1 -1
- generation_config.json +0 -1
- model.safetensors +1 -1
- runs/May21_12-10-30_ebc91b8fe69c/events.out.tfevents.1716293432.ebc91b8fe69c.34.4 +3 -0
- tokenizer.json +2 -16
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
---
|
2 |
-
base_model: mika5883/
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: RuReCl8
|
7 |
results: []
|
@@ -12,7 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# RuReCl8
|
14 |
|
15 |
-
This model is a fine-tuned version of [mika5883/
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
@@ -31,7 +37,7 @@ More information needed
|
|
31 |
### Training hyperparameters
|
32 |
|
33 |
The following hyperparameters were used during training:
|
34 |
-
- learning_rate:
|
35 |
- train_batch_size: 128
|
36 |
- eval_batch_size: 16
|
37 |
- seed: 42
|
@@ -42,6 +48,10 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
### Training results
|
44 |
|
|
|
|
|
|
|
|
|
45 |
|
46 |
|
47 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: mika5883/RuReCl8
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
model-index:
|
8 |
- name: RuReCl8
|
9 |
results: []
|
|
|
14 |
|
15 |
# RuReCl8
|
16 |
|
17 |
+
This model is a fine-tuned version of [mika5883/RuReCl8](https://huggingface.co/mika5883/RuReCl8) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.1825
|
20 |
+
- Bleu: 61.2481
|
21 |
+
- Gen Len: 16.234
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 3.83229e-05
|
41 |
- train_batch_size: 128
|
42 |
- eval_batch_size: 16
|
43 |
- seed: 42
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
53 |
+
| No log | 1.0 | 20 | 0.1898 | 61.0474 | 16.2296 |
|
54 |
+
| No log | 2.0 | 40 | 0.1825 | 61.2481 | 16.234 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "mika5883/
|
3 |
"_num_labels": 2,
|
4 |
"architectures": [
|
5 |
"T5ForConditionalGeneration"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mika5883/RuReCl8",
|
3 |
"_num_labels": 2,
|
4 |
"architectures": [
|
5 |
"T5ForConditionalGeneration"
|
generation_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_from_model_config": true,
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 0,
|
|
|
1 |
{
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 2,
|
4 |
"pad_token_id": 0,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891644712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e91a14b61917f87f71c84957b118627e8de5f5259588c0db45913086026e0ade
|
3 |
size 891644712
|
runs/May21_12-10-30_ebc91b8fe69c/events.out.tfevents.1716293432.ebc91b8fe69c.34.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:908896730288c43e87679acec6226e96f4667eb2c5bf036cf0d453a9284504f4
|
3 |
+
size 6704
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 50,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 50
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 0,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "<pad>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55bdfec7b769f1a6b45e2b28e5859996fbb0ddec0bdf92e0ac1c2890d30f1762
|
3 |
size 5048
|