esacalderonru
commited on
Commit
•
a36c438
1
Parent(s):
8d03307
Training in progress, epoch 1
Browse files- config.json +7 -7
- merges.txt +0 -0
- model.safetensors +2 -2
- runs/May29_23-18-23_9b2206e9c785/events.out.tfevents.1717024704.9b2206e9c785.828.0 +3 -0
- special_tokens_map.json +43 -7
- tokenizer.json +2 -2
- tokenizer_config.json +11 -7
- training_args.bin +1 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,14 +1,15 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0.
|
7 |
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
"eos_token_id": 2,
|
|
|
10 |
"hidden_act": "gelu",
|
11 |
-
"hidden_dropout_prob": 0.
|
12 |
"hidden_size": 768,
|
13 |
"id2label": {
|
14 |
"0": "O",
|
@@ -48,15 +49,14 @@
|
|
48 |
},
|
49 |
"layer_norm_eps": 1e-05,
|
50 |
"max_position_embeddings": 514,
|
51 |
-
"model_type": "
|
52 |
"num_attention_heads": 12,
|
53 |
"num_hidden_layers": 12,
|
54 |
-
"output_past": true,
|
55 |
"pad_token_id": 1,
|
56 |
"position_embedding_type": "absolute",
|
57 |
"torch_dtype": "float32",
|
58 |
"transformers_version": "4.41.1",
|
59 |
"type_vocab_size": 1,
|
60 |
"use_cache": true,
|
61 |
-
"vocab_size":
|
62 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
|
3 |
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
"hidden_size": 768,
|
14 |
"id2label": {
|
15 |
"0": "O",
|
|
|
49 |
},
|
50 |
"layer_norm_eps": 1e-05,
|
51 |
"max_position_embeddings": 514,
|
52 |
+
"model_type": "roberta",
|
53 |
"num_attention_heads": 12,
|
54 |
"num_hidden_layers": 12,
|
|
|
55 |
"pad_token_id": 1,
|
56 |
"position_embedding_type": "absolute",
|
57 |
"torch_dtype": "float32",
|
58 |
"transformers_version": "4.41.1",
|
59 |
"type_vocab_size": 1,
|
60 |
"use_cache": true,
|
61 |
+
"vocab_size": 50262
|
62 |
}
|
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
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 sha256:26b34d7681b00d06912e4fd2432fdb6a443c3e6aa39ebaff9ad7560f1e54ccad
|
3 |
+
size 496281012
|
runs/May29_23-18-23_9b2206e9c785/events.out.tfevents.1717024704.9b2206e9c785.828.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8eb86e36d3131d1b1b22c1703b675ec8314ccabcad58b372cc9dd8fd92794bf
|
3 |
+
size 6093
|
special_tokens_map.json
CHANGED
@@ -1,15 +1,51 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"mask_token": {
|
6 |
"content": "<mask>",
|
7 |
"lstrip": true,
|
8 |
-
"normalized":
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
-
"pad_token":
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"mask_token": {
|
24 |
"content": "<mask>",
|
25 |
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
}
|
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 sha256:7dced0d365b08173bcc280fb7c93c1c43a4ee6b3f87dd7848f337c1de51e4896
|
3 |
+
size 2213707
|
tokenizer_config.json
CHANGED
@@ -1,9 +1,10 @@
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<s>",
|
5 |
"lstrip": false,
|
6 |
-
"normalized":
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
@@ -11,7 +12,7 @@
|
|
11 |
"1": {
|
12 |
"content": "<pad>",
|
13 |
"lstrip": false,
|
14 |
-
"normalized":
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
@@ -19,7 +20,7 @@
|
|
19 |
"2": {
|
20 |
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
-
"normalized":
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
@@ -27,15 +28,15 @@
|
|
27 |
"3": {
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
30 |
-
"normalized":
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "<mask>",
|
37 |
"lstrip": true,
|
38 |
-
"normalized":
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
@@ -45,10 +46,13 @@
|
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "<s>",
|
47 |
"eos_token": "</s>",
|
|
|
48 |
"mask_token": "<mask>",
|
|
|
49 |
"model_max_length": 512,
|
50 |
"pad_token": "<pad>",
|
51 |
"sep_token": "</s>",
|
52 |
-
"tokenizer_class": "
|
|
|
53 |
"unk_token": "<unk>"
|
54 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": true,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
"content": "<s>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
|
|
12 |
"1": {
|
13 |
"content": "<pad>",
|
14 |
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
|
|
20 |
"2": {
|
21 |
"content": "</s>",
|
22 |
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
|
|
28 |
"3": {
|
29 |
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
},
|
36 |
+
"4": {
|
37 |
"content": "<mask>",
|
38 |
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
|
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
"cls_token": "<s>",
|
48 |
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
"mask_token": "<mask>",
|
51 |
+
"max_len": 512,
|
52 |
"model_max_length": 512,
|
53 |
"pad_token": "<pad>",
|
54 |
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
"unk_token": "<unk>"
|
58 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19b65a07fc069e6c5e7a59df7d20e2e1a0602c570404931d737b3cd11c72e89b
|
3 |
size 5176
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|