vldsavelyev
commited on
Commit
•
ba810ec
1
Parent(s):
e520818
Update model card
Browse files
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
@@ -8,24 +10,20 @@ model-index:
|
|
8 |
results: []
|
9 |
---
|
10 |
|
11 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
-
should probably proofread and complete it, then remove this comment. -->
|
13 |
-
|
14 |
# murakami_rugpt3small
|
15 |
|
16 |
-
This model was trained from scratch on the murakami dataset.
|
17 |
-
|
18 |
## Model description
|
19 |
|
20 |
-
|
21 |
|
22 |
## Intended uses & limitations
|
23 |
|
24 |
-
|
25 |
|
26 |
## Training and evaluation data
|
27 |
|
28 |
-
|
|
|
29 |
|
30 |
## Training procedure
|
31 |
|
@@ -38,8 +36,9 @@ The following hyperparameters were used during training:
|
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
|
|
41 |
- num_epochs: 3.0
|
42 |
-
- mixed_precision_training: Native AMP
|
43 |
|
44 |
### Training results
|
45 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- ru
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
10 |
results: []
|
11 |
---
|
12 |
|
|
|
|
|
|
|
13 |
# murakami_rugpt3small
|
14 |
|
|
|
|
|
15 |
## Model description
|
16 |
|
17 |
+
Fine-tuned from [sberbank-ai/rugpt3small_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3small_based_on_gpt2)
|
18 |
|
19 |
## Intended uses & limitations
|
20 |
|
21 |
+
Generate articles
|
22 |
|
23 |
## Training and evaluation data
|
24 |
|
25 |
+
Fine-tuned on [murakami](https://huggingface.co/datasets/vldsavelyev/murakami) dataset,
|
26 |
+
which was built from Russian translations of novels by Haruki Murakami.
|
27 |
|
28 |
## Training procedure
|
29 |
|
|
|
36 |
- seed: 42
|
37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
- lr_scheduler_type: linear
|
39 |
+
- gradient_checkpointing: True
|
40 |
- num_epochs: 3.0
|
41 |
+
- mixed_precision_training: Native AMP (fp16=True)
|
42 |
|
43 |
### Training results
|
44 |
|