DanielAvelar09
commited on
Commit
•
7dd8e96
1
Parent(s):
c6af57c
End of training
Browse files- README.md +7 -7
- config.json +11 -20
- model.safetensors +2 -2
- runs/Feb18_00-20-52_ab13d288f27c/events.out.tfevents.1708215653.ab13d288f27c.1146.0 +3 -0
- special_tokens_map.json +0 -2
- tokenizer.json +2 -2
- tokenizer_config.json +15 -16
- training_args.bin +1 -1
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# mi_chatbot
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 4.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
|
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| No log | 1.0 | 7 |
|
50 |
-
| No log | 2.0 | 14 | 4.
|
51 |
-
| No log | 3.0 | 21 | 4.
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# mi_chatbot
|
15 |
|
16 |
+
This model is a fine-tuned version of [mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es](https://huggingface.co/mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 4.7305
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 7 | 5.2821 |
|
50 |
+
| No log | 2.0 | 14 | 4.8369 |
|
51 |
+
| No log | 3.0 | 21 | 4.7305 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
config.json
CHANGED
@@ -1,35 +1,26 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"hidden_act": "gelu",
|
8 |
"hidden_dropout_prob": 0.1,
|
9 |
"hidden_size": 768,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 3072,
|
12 |
-
"layer_norm_eps": 1e-
|
13 |
"max_position_embeddings": 512,
|
14 |
-
"
|
15 |
-
"model_type": "deberta-v2",
|
16 |
-
"norm_rel_ebd": "layer_norm",
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"pooler_hidden_size": 768,
|
23 |
-
"pos_att_type": [
|
24 |
-
"p2c",
|
25 |
-
"c2p"
|
26 |
-
],
|
27 |
-
"position_biased_input": false,
|
28 |
-
"position_buckets": 256,
|
29 |
-
"relative_attention": true,
|
30 |
-
"share_att_key": true,
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.35.2",
|
33 |
-
"type_vocab_size":
|
34 |
-
"
|
|
|
35 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es",
|
3 |
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
"hidden_size": 768,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
|
|
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 12,
|
18 |
+
"output_past": true,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.35.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 31002
|
26 |
}
|
model.safetensors
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:b1ddcef21642c9afe80154e815f8f60243ccb343f0a9982ad57dc8fdb66540c6
|
3 |
+
size 437070648
|
runs/Feb18_00-20-52_ab13d288f27c/events.out.tfevents.1708215653.ab13d288f27c.1146.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67d2800c5f3e446fd3631d259a858f587cf91eac72beb4eb0479d61ebcadbd94
|
3 |
+
size 5378
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,5 @@
|
|
1 |
{
|
2 |
-
"bos_token": "[CLS]",
|
3 |
"cls_token": "[CLS]",
|
4 |
-
"eos_token": "[SEP]",
|
5 |
"mask_token": "[MASK]",
|
6 |
"pad_token": "[PAD]",
|
7 |
"sep_token": "[SEP]",
|
|
|
1 |
{
|
|
|
2 |
"cls_token": "[CLS]",
|
|
|
3 |
"mask_token": "[MASK]",
|
4 |
"pad_token": "[PAD]",
|
5 |
"sep_token": "[SEP]",
|
tokenizer.json
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 sha256:0b2cb0a433da31658bd79f95e7beabf22a59aaaf0d39513b24f5474cef8edcfd
|
3 |
+
size 730166
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "[
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
@@ -9,31 +9,31 @@
|
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
-
"content": "[
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "[
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "[
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "[
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
@@ -41,18 +41,17 @@
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
-
"bos_token": "[CLS]",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "[CLS]",
|
47 |
-
"
|
48 |
-
"
|
49 |
"mask_token": "[MASK]",
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
51 |
"pad_token": "[PAD]",
|
52 |
"sep_token": "[SEP]",
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"tokenizer_class": "
|
56 |
-
"unk_token": "[UNK]"
|
57 |
-
"vocab_type": "spm"
|
58 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
+
"content": "[MASK]",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
|
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"3": {
|
20 |
+
"content": "[UNK]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"4": {
|
28 |
+
"content": "[CLS]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"5": {
|
36 |
+
"content": "[SEP]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
|
|
57 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0c4327c5a0233e76ccb3004547c83b4801f293d50f6770a80ceac56a0091d51
|
3 |
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|