Hugging Face's logo

crossroderick
/
occitan-distilgpt2-medium

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
crossroderick commited on
Commit
21971a9
•
1 Parent(s): 35568d5

Model save

Browse files
Files changed (4) hide show
  1. README.md +10 -17
  2. logs/events.out.tfevents.1708965912.AI-Machine.65818.0 +2 -2
  3. model.safetensors +1 -1
  4. saved_model/model.safetensors +1 -1
README.md CHANGED
@@ -1,28 +1,21 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: crossroderick/occitan-distilgpt2-medium
6
  model-index:
7
  - name: occitan-distilgpt2-medium
8
  results: []
9
- widget:
10
- - text: "Adieusatz! Ieu soi Micheu e"
11
- example_title: "Example 1"
12
- - text: "A mon vejaire"
13
- example_title: "Example 2"
14
- - text: "Mercés plan per la"
15
- example_title: "Example 3"
16
- - text: "Vòstres mots son mai"
17
- example_title: "Example 4"
18
  ---
19
- # occitan-distilgpt2-medium
20
 
21
- *Adieusatz brave monde!*
 
22
 
23
- This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the Occitan language section of the Wikipedia dataset, and is part of a personal effort to study the Occitan language in an NLP environment. It achieves the following results on the evaluation set:
24
 
25
- - Loss: 2.5887
 
 
26
 
27
  ## Model description
28
 
@@ -55,9 +48,9 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:-----:|:----:|:---------------:|
58
- | 2.7616 | 1.0 | 625 | 2.6216 |
59
- | 2.7159 | 2.0 | 1250 | 2.5982 |
60
- | 2.6617 | 3.0 | 1875 | 2.5887 |
61
 
62
 
63
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: crossroderick/occitan-distilgpt2-medium
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 [crossroderick/occitan-distilgpt2-medium](https://huggingface.co/crossroderick/occitan-distilgpt2-medium) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.5078
19
 
20
  ## Model description
21
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.6799 | 1.0 | 625 | 2.5352 |
52
+ | 2.6429 | 2.0 | 1250 | 2.5180 |
53
+ | 2.6121 | 3.0 | 1875 | 2.5078 |
54
 
55
 
56
  ### Framework versions
logs/events.out.tfevents.1708965912.AI-Machine.65818.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9e32827247e874d3a050f2c37a36119181f7527872967fbb5ff8e90636126c2
3
- size 6131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6250ea360716df23c41be86c0d0e218b3abf71ea621ec4ad1c9b3b13c90a242c
3
+ size 6756
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32b0b938b50f3891c0e24ae1958ebf2a6cad3004af7a0ca77c2581bfe9ccc8f4
3
  size 327657928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddb5844ddca24db1ad4801923f73824729ebcb0a4532e32fe6441a2ac4fcb095
3
  size 327657928
saved_model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15b7d55510f04af63e54ef50f36404bc6dcc363bb9f7b0e43fd4600f4e8dc091
3
  size 327657928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddb5844ddca24db1ad4801923f73824729ebcb0a4532e32fe6441a2ac4fcb095
3
  size 327657928