mobashgr
commited on
Commit
•
ab28d27
0
Parent(s):
intial commit
Browse files- config.json +39 -0
- eval_results.txt +8 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_predictions.txt +0 -0
- test_results.txt +7 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "kamalkraj/bioelectra-base-discriminator-pubmed",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 768,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B-bio",
|
14 |
+
"1": "I-bio",
|
15 |
+
"2": "O"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B-bio": 0,
|
21 |
+
"I-bio": 1,
|
22 |
+
"O": 2
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "electra",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"summary_activation": "gelu",
|
32 |
+
"summary_last_dropout": 0.1,
|
33 |
+
"summary_type": "first",
|
34 |
+
"summary_use_proj": true,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.11.3",
|
37 |
+
"type_vocab_size": 2,
|
38 |
+
"vocab_size": 30522
|
39 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 4.506559889705386e-06
|
2 |
+
eval_precision = 1.0
|
3 |
+
eval_recall = 1.0
|
4 |
+
eval_f1 = 1.0
|
5 |
+
eval_runtime = 112.241
|
6 |
+
eval_samples_per_second = 41.001
|
7 |
+
eval_steps_per_second = 5.132
|
8 |
+
epoch = 20.0
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93532c43d0cf02304a7bf30b140ee2ba77e98ad0de2b9d26f7c3afd47da2d2df
|
3 |
+
size 435660465
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
test_predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
test_results.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
test_loss = 0.0624217763543129
|
2 |
+
test_precision = 0.9428359317000743
|
3 |
+
test_recall = 0.9433611884865367
|
4 |
+
test_f1 = 0.9430984869581361
|
5 |
+
test_runtime = 118.7495
|
6 |
+
test_samples_per_second = 40.522
|
7 |
+
test_steps_per_second = 5.069
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "kamalkraj/bioelectra-base-discriminator-pubmed", "tokenizer_class": "ElectraTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:173c30bd780ad7a71770c157a33dd14f08a250d19ae286b02ea312a7eb89ba22
|
3 |
+
size 2927
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|