Michael Beukman commited on
Commit
55e3b5b
1 Parent(s): f59bb2d

Initial Commit

Browse files

config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Davlan/xlm-roberta-base-finetuned-swahili",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
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-DATE",
17
+ "2": "I-DATE",
18
+ "3": "B-PER",
19
+ "4": "I-PER",
20
+ "5": "B-ORG",
21
+ "6": "I-ORG",
22
+ "7": "B-LOC",
23
+ "8": "I-LOC"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "B-DATE": 1,
29
+ "B-LOC": 7,
30
+ "B-ORG": 5,
31
+ "B-PER": 3,
32
+ "I-DATE": 2,
33
+ "I-LOC": 8,
34
+ "I-ORG": 6,
35
+ "I-PER": 4,
36
+ "O": 0
37
+ },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 514,
40
+ "model_type": "xlm-roberta",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "output_past": true,
44
+ "pad_token_id": 1,
45
+ "position_embedding_type": "absolute",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.11.3",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
eval_results.txt ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ f1 = 0.896838602329451
2
+ loss = 0.15985548422772808
3
+ precision = 0.8953488372093024
4
+ recall = 0.8983333333333333
5
+ report = precision recall f1-score support
6
+
7
+ DATE 0.76 0.75 0.76 91
8
+ LOC 0.90 0.91 0.90 172
9
+ ORG 0.95 0.91 0.93 169
10
+ PER 0.91 0.95 0.93 168
11
+
12
+ micro avg 0.90 0.90 0.90 600
13
+ macro avg 0.88 0.88 0.88 600
14
+ weighted avg 0.90 0.90 0.90 600
15
+
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb890390dfae53dceac5bb275501a0f5562ce502c15b64719844884379b2f72
3
+ size 1109924593
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
test_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
test_results.txt ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ f1 = 0.8492693110647181
2
+ loss = 0.23357212637886277
3
+ precision = 0.8363486842105263
4
+ recall = 0.8625954198473282
5
+ report = precision recall f1-score support
6
+
7
+ DATE 0.69 0.72 0.70 145
8
+ LOC 0.84 0.91 0.88 338
9
+ ORG 0.90 0.89 0.89 351
10
+ PER 0.83 0.85 0.84 345
11
+
12
+ micro avg 0.84 0.86 0.85 1179
13
+ macro avg 0.82 0.84 0.83 1179
14
+ weighted avg 0.84 0.86 0.85 1179
15
+
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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "Davlan/xlm-roberta-base-finetuned-swahili", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899fc378f826ee61faf19eef78e0bf0db58df9a0da370d1bdf0fa84ceb736b86
3
+ size 1583