crscardellino
commited on
Merge branch 'main' of https://huggingface.co/crscardellino/flisol-cba-martin-fierro
Browse files- README.md +57 -17
- config.json +40 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,25 +1,65 @@
|
|
1 |
-
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
|
4 |
-
|
5 |
-
|
6 |
-
del [FLISoL de Córdoba](https://cordoba.flisol.org.ar), Argentina, de 2023.
|
7 |
|
8 |
-
|
9 |
-
[`git-lfs`](https://git-lfs.com/).
|
10 |
|
11 |
-
|
|
|
|
|
12 |
|
13 |
-
|
14 |
|
15 |
-
|
16 |
|
17 |
-
|
18 |
-
$ source ./flisol-venv/bin/activate
|
19 |
-
(flisol-venv) $ pip install -r requirements.txt
|
20 |
|
21 |
-
|
22 |
-
3.8. En los requerimientos está organizado para instalar
|
23 |
-
[PyTorch](https://pytorch.org/) v2.0.0 para cpu, pero pueden ajustarlo para
|
24 |
-
utilizar GPUs suponiendo que cumplan los requerimientos de CUDA.
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: flisol-cba-martin-fierro
|
7 |
+
results: []
|
8 |
+
---
|
9 |
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
|
|
12 |
|
13 |
+
# flisol-cba-martin-fierro
|
|
|
14 |
|
15 |
+
This model is a fine-tuned version of [DeepESP/gpt2-spanish](https://huggingface.co/DeepESP/gpt2-spanish) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 3.9067
|
18 |
|
19 |
+
## Model description
|
20 |
|
21 |
+
More information needed
|
22 |
|
23 |
+
## Intended uses & limitations
|
|
|
|
|
24 |
|
25 |
+
More information needed
|
|
|
|
|
|
|
26 |
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 2e-05
|
37 |
+
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 10
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
+
| 4.3864 | 1.0 | 18 | 4.2025 |
|
49 |
+
| 3.948 | 2.0 | 36 | 4.0440 |
|
50 |
+
| 3.7962 | 3.0 | 54 | 3.9804 |
|
51 |
+
| 3.6105 | 4.0 | 72 | 3.9458 |
|
52 |
+
| 3.4444 | 5.0 | 90 | 3.9280 |
|
53 |
+
| 3.3855 | 6.0 | 108 | 3.9192 |
|
54 |
+
| 3.3142 | 7.0 | 126 | 3.9091 |
|
55 |
+
| 3.2192 | 8.0 | 144 | 3.9074 |
|
56 |
+
| 3.1615 | 9.0 | 162 | 3.9070 |
|
57 |
+
| 3.1637 | 10.0 | 180 | 3.9067 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.28.1
|
63 |
+
- Pytorch 2.0.0+cpu
|
64 |
+
- Datasets 2.11.0
|
65 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DeepESP/gpt2-spanish",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.28.1",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 50257
|
40 |
+
}
|
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": "4.28.1"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1e06b84b625ee566a1e8dcc2c7dd064d63481f644349828709ab7757e9dfce0
|
3 |
+
size 510395581
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:402f127db0f19abbb4782498dd89f615bb96f958fb37ddfd8087acf6cc097fe4
|
3 |
+
size 3579
|