Commit
•
eaf84a5
1
Parent(s):
59d1cb1
Model save
Browse files- README.md +56 -6
- generation_config.json +6 -0
- logs/events.out.tfevents.1708722801.AI-Machine.14587.0 +2 -2
- model.safetensors +1 -1
- saved_model/config.json +3 -0
- saved_model/generation_config.json +3 -0
- saved_model/model.safetensors +3 -0
- saved_model/training_args.bin +3 -0
README.md
CHANGED
@@ -1,11 +1,61 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
-
|
|
|
|
|
|
|
6 |
---
|
|
|
|
|
|
|
|
|
7 |
# occitan-distilgpt2-medium
|
8 |
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
-
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilgpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: occitan-distilgpt2-medium
|
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 |
# occitan-distilgpt2-medium
|
15 |
|
16 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.3399
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 12
|
39 |
+
- eval_batch_size: 12
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 4
|
42 |
+
- total_train_batch_size: 48
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 3.0
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| No log | 1.0 | 208 | 3.5675 |
|
52 |
+
| No log | 2.0 | 417 | 3.3814 |
|
53 |
+
| 3.7591 | 2.99 | 624 | 3.3399 |
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
|
58 |
+
- Transformers 4.38.1
|
59 |
+
- Pytorch 2.0.1+cu117
|
60 |
+
- Datasets 2.17.1
|
61 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.38.1"
|
6 |
+
}
|
logs/events.out.tfevents.1708722801.AI-Machine.14587.0
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:a3f427f66217010b18903ec0724736b63e23fe65308d09146a552a0ded680965
|
3 |
+
size 6278
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 327657928
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61aa838062ffc0c83dafdb238c23adec8b2c5a7d1be6ea3a6ab239bc8ac82fc2
|
3 |
size 327657928
|
saved_model/config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8c187d32e251941d271eeb00df04da273767585c4ebe61bd45f273ee77825e1
|
3 |
+
size 1010
|
saved_model/generation_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10e418ac6bb2162fda2cd84e00c21f2cf7f9c5f70bd516ec07bd07b0a011014c
|
3 |
+
size 119
|
saved_model/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61aa838062ffc0c83dafdb238c23adec8b2c5a7d1be6ea3a6ab239bc8ac82fc2
|
3 |
+
size 327657928
|
saved_model/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71604a0894a56b58e7dec6079ff61364f87e022b3b3fe9d94101b643cc947107
|
3 |
+
size 4411
|