finiteautomata
commited on
Commit
•
2c5fed9
1
Parent(s):
9c3a718
Initial commit
Browse files- config.json +70 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_results.json +38 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pysentimiento/robertuito-base-uncased",
|
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": "O",
|
16 |
+
"1": "B-EVENT",
|
17 |
+
"2": "I-EVENT",
|
18 |
+
"3": "B-GROUP",
|
19 |
+
"4": "I-GROUP",
|
20 |
+
"5": "B-LOC",
|
21 |
+
"6": "I-LOC",
|
22 |
+
"7": "B-ORG",
|
23 |
+
"8": "I-ORG",
|
24 |
+
"9": "B-OTHER",
|
25 |
+
"10": "I-OTHER",
|
26 |
+
"11": "B-PER",
|
27 |
+
"12": "I-PER",
|
28 |
+
"13": "B-PROD",
|
29 |
+
"14": "I-PROD",
|
30 |
+
"15": "B-TIME",
|
31 |
+
"16": "I-TIME",
|
32 |
+
"17": "B-TITLE",
|
33 |
+
"18": "I-TITLE"
|
34 |
+
},
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": 3072,
|
37 |
+
"label2id": {
|
38 |
+
"B-EVENT": 1,
|
39 |
+
"B-GROUP": 3,
|
40 |
+
"B-LOC": 5,
|
41 |
+
"B-ORG": 7,
|
42 |
+
"B-OTHER": 9,
|
43 |
+
"B-PER": 11,
|
44 |
+
"B-PROD": 13,
|
45 |
+
"B-TIME": 15,
|
46 |
+
"B-TITLE": 17,
|
47 |
+
"I-EVENT": 2,
|
48 |
+
"I-GROUP": 4,
|
49 |
+
"I-LOC": 6,
|
50 |
+
"I-ORG": 8,
|
51 |
+
"I-OTHER": 10,
|
52 |
+
"I-PER": 12,
|
53 |
+
"I-PROD": 14,
|
54 |
+
"I-TIME": 16,
|
55 |
+
"I-TITLE": 18,
|
56 |
+
"O": 0
|
57 |
+
},
|
58 |
+
"layer_norm_eps": 1e-12,
|
59 |
+
"max_position_embeddings": 130,
|
60 |
+
"model_type": "roberta",
|
61 |
+
"num_attention_heads": 12,
|
62 |
+
"num_hidden_layers": 12,
|
63 |
+
"pad_token_id": 1,
|
64 |
+
"position_embedding_type": "absolute",
|
65 |
+
"torch_dtype": "float32",
|
66 |
+
"transformers_version": "4.13.0",
|
67 |
+
"type_vocab_size": 1,
|
68 |
+
"use_cache": true,
|
69 |
+
"vocab_size": 30002
|
70 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68de2679921a7b304ff5d7fa6288efd3ac9ed62bf3839d558d55dd0a48ab8b8b
|
3 |
+
size 432932657
|
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 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"test_loss": 0.07815752178430557,
|
3 |
+
"test_precision": 0.6620947630922693,
|
4 |
+
"test_recall": 0.6764331210191082,
|
5 |
+
"test_macro_f1": 0.5127434670879479,
|
6 |
+
"test_micro_f1": 0.669187145557656,
|
7 |
+
"test_accuracy": 0.9862053222019306,
|
8 |
+
"test_EVENT_f1": 0.35714285714285715,
|
9 |
+
"test_EVENT_precision": 0.39473684210526316,
|
10 |
+
"test_EVENT_recall": 0.32608695652173914,
|
11 |
+
"test_GROUP_f1": 0.5677966101694916,
|
12 |
+
"test_GROUP_precision": 0.5677966101694916,
|
13 |
+
"test_GROUP_recall": 0.5677966101694916,
|
14 |
+
"test_LOC_f1": 0.730188679245283,
|
15 |
+
"test_LOC_precision": 0.7049180327868853,
|
16 |
+
"test_LOC_recall": 0.7573385518590998,
|
17 |
+
"test_ORG_f1": 0.41638225255972694,
|
18 |
+
"test_ORG_precision": 0.43884892086330934,
|
19 |
+
"test_ORG_recall": 0.3961038961038961,
|
20 |
+
"test_OTHER_f1": 0.3035714285714286,
|
21 |
+
"test_OTHER_precision": 0.3617021276595745,
|
22 |
+
"test_OTHER_recall": 0.26153846153846155,
|
23 |
+
"test_PER_f1": 0.8129164531009737,
|
24 |
+
"test_PER_precision": 0.7843719090009891,
|
25 |
+
"test_PER_recall": 0.8436170212765958,
|
26 |
+
"test_PROD_f1": 0.5320388349514563,
|
27 |
+
"test_PROD_precision": 0.528957528957529,
|
28 |
+
"test_PROD_recall": 0.53515625,
|
29 |
+
"test_TIME_f1": 0.4166666666666667,
|
30 |
+
"test_TIME_precision": 0.47619047619047616,
|
31 |
+
"test_TIME_recall": 0.37037037037037035,
|
32 |
+
"test_TITLE_f1": 0.4779874213836478,
|
33 |
+
"test_TITLE_precision": 0.4720496894409938,
|
34 |
+
"test_TITLE_recall": 0.4840764331210191,
|
35 |
+
"test_runtime": 20.0879,
|
36 |
+
"test_samples_per_second": 502.043,
|
37 |
+
"test_steps_per_second": 31.412
|
38 |
+
}
|
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-uncased/special_tokens_map.json", "name_or_path": "pysentimiento/robertuito-base-uncased", "tokenizer_class": "PreTrainedTokenizerFast"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7a69886b1e2877fe532f080aad04c3b7bc882bc929e4eb2ba3660de684f6ca3
|
3 |
+
size 2863
|