finiteautomata
commited on
Commit
•
353662c
1
Parent(s):
d59c31c
First commit
Browse files- config.json +66 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_results.json +62 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pysentimiento/robertuito-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
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": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "B-VERB",
|
16 |
+
"1": "B-PUNCT",
|
17 |
+
"2": "B-PRON",
|
18 |
+
"3": "B-NOUN",
|
19 |
+
"4": "B-DET",
|
20 |
+
"5": "B-ADV",
|
21 |
+
"6": "B-ADP",
|
22 |
+
"7": "B-INTJ",
|
23 |
+
"8": "B-CONJ",
|
24 |
+
"9": "B-ADJ",
|
25 |
+
"10": "B-AUX",
|
26 |
+
"11": "B-SCONJ",
|
27 |
+
"12": "B-PART",
|
28 |
+
"13": "B-PROPN",
|
29 |
+
"14": "B-NUM",
|
30 |
+
"15": "B-UNK",
|
31 |
+
"16": "B-X"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"B-ADJ": 9,
|
37 |
+
"B-ADP": 6,
|
38 |
+
"B-ADV": 5,
|
39 |
+
"B-AUX": 10,
|
40 |
+
"B-CONJ": 8,
|
41 |
+
"B-DET": 4,
|
42 |
+
"B-INTJ": 7,
|
43 |
+
"B-NOUN": 3,
|
44 |
+
"B-NUM": 14,
|
45 |
+
"B-PART": 12,
|
46 |
+
"B-PRON": 2,
|
47 |
+
"B-PROPN": 13,
|
48 |
+
"B-PUNCT": 1,
|
49 |
+
"B-SCONJ": 11,
|
50 |
+
"B-UNK": 15,
|
51 |
+
"B-VERB": 0,
|
52 |
+
"B-X": 16
|
53 |
+
},
|
54 |
+
"layer_norm_eps": 1e-12,
|
55 |
+
"max_position_embeddings": 130,
|
56 |
+
"model_type": "roberta",
|
57 |
+
"num_attention_heads": 12,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"pad_token_id": 1,
|
60 |
+
"position_embedding_type": "absolute",
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.13.0",
|
63 |
+
"type_vocab_size": 1,
|
64 |
+
"use_cache": true,
|
65 |
+
"vocab_size": 30003
|
66 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52180c4a700faccc2bfd89e8ac69f72dbd9699d9098c927dd6905597f1b3bac3
|
3 |
+
size 432929585
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
|
test_results.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"test_loss": 0.09433817863464355,
|
3 |
+
"test_precision": 0.9727695306642675,
|
4 |
+
"test_recall": 0.9727695306642675,
|
5 |
+
"test_macro_f1": 0.9103428865750461,
|
6 |
+
"test_micro_f1": 0.9727695306642675,
|
7 |
+
"test_accuracy": 0.9727695306642675,
|
8 |
+
"test_ADJ_f1": 0.8951762523191095,
|
9 |
+
"test_ADJ_precision": 0.8985102420856611,
|
10 |
+
"test_ADJ_recall": 0.8918669131238447,
|
11 |
+
"test_ADP_f1": 0.9671580036203775,
|
12 |
+
"test_ADP_precision": 0.9749739311783108,
|
13 |
+
"test_ADP_recall": 0.9594663930220626,
|
14 |
+
"test_ADV_f1": 0.9267624914442164,
|
15 |
+
"test_ADV_precision": 0.9206708975521306,
|
16 |
+
"test_ADV_recall": 0.9329352319706018,
|
17 |
+
"test_AUX_f1": 0.9430004559963521,
|
18 |
+
"test_AUX_precision": 0.9306930693069307,
|
19 |
+
"test_AUX_recall": 0.955637707948244,
|
20 |
+
"test_CONJ_f1": 0.9970123772940673,
|
21 |
+
"test_CONJ_precision": 0.9982905982905983,
|
22 |
+
"test_CONJ_recall": 0.9957374254049446,
|
23 |
+
"test_DET_f1": 0.9765440068861632,
|
24 |
+
"test_DET_precision": 0.9709028669234061,
|
25 |
+
"test_DET_recall": 0.9822510822510823,
|
26 |
+
"test_INTJ_f1": 0.958139534883721,
|
27 |
+
"test_INTJ_precision": 0.9519408502772643,
|
28 |
+
"test_INTJ_recall": 0.9644194756554307,
|
29 |
+
"test_NOUN_f1": 0.9731118342181881,
|
30 |
+
"test_NOUN_precision": 0.9783057851239669,
|
31 |
+
"test_NOUN_recall": 0.9679727427597956,
|
32 |
+
"test_NUM_f1": 0.9908015768725361,
|
33 |
+
"test_NUM_precision": 0.9947229551451188,
|
34 |
+
"test_NUM_recall": 0.9869109947643979,
|
35 |
+
"test_PART_f1": 0.9842141386410432,
|
36 |
+
"test_PART_precision": 0.9795081967213115,
|
37 |
+
"test_PART_recall": 0.9889655172413793,
|
38 |
+
"test_PRON_f1": 0.984004625168626,
|
39 |
+
"test_PRON_precision": 0.9823008849557522,
|
40 |
+
"test_PRON_recall": 0.9857142857142858,
|
41 |
+
"test_PROPN_f1": 0.9891225525743292,
|
42 |
+
"test_PROPN_precision": 0.9869753979739508,
|
43 |
+
"test_PROPN_recall": 0.9912790697674418,
|
44 |
+
"test_PUNCT_f1": 1.0,
|
45 |
+
"test_PUNCT_precision": 1.0,
|
46 |
+
"test_PUNCT_recall": 1.0,
|
47 |
+
"test_SCONJ_f1": 0.9125364431486881,
|
48 |
+
"test_SCONJ_precision": 0.9214916584887144,
|
49 |
+
"test_SCONJ_recall": 0.9037536092396535,
|
50 |
+
"test_UNK_f1": 0.998003992015968,
|
51 |
+
"test_UNK_precision": 0.9960159362549801,
|
52 |
+
"test_UNK_recall": 1.0,
|
53 |
+
"test_VERB_f1": 0.9802407866923997,
|
54 |
+
"test_VERB_precision": 0.9835853928439691,
|
55 |
+
"test_VERB_recall": 0.9769188496061549,
|
56 |
+
"test_X_f1": 0.0,
|
57 |
+
"test_X_precision": 0.0,
|
58 |
+
"test_X_recall": 0.0,
|
59 |
+
"test_runtime": 7.575,
|
60 |
+
"test_samples_per_second": 567.395,
|
61 |
+
"test_steps_per_second": 35.512
|
62 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": "models/twerto-base-cased/special_tokens_map.json", "name_or_path": "pysentimiento/robertuito-base-cased", "tokenizer_class": "PreTrainedTokenizerFast"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b31f0f88eb6af616c32b715486d1c414cf8d63bab2b0deb3da954b854a6c6cc7
|
3 |
+
size 2863
|