Training in progress, step 100
Browse files
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hfl/chinese-roberta-wwm-ext",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "\u5718\u9ad4\u4e3b\u7fa9\u884c\u52d5",
|
16 |
+
"1": "\u500b\u4eba\u4e3b\u7fa9\u884c\u52d5",
|
17 |
+
"2": "\u76f4\u89ba\u7d71\u6574\u8a8d\u77e5",
|
18 |
+
"3": "\u89c0\u5bdf\u611f\u53d7\u8a8d\u77e5",
|
19 |
+
"4": "\u7406\u6027\u5f15\u5c0e\u6c7a\u7b56",
|
20 |
+
"5": "\u611f\u6027\u5f15\u5c0e\u6c7a\u7b56",
|
21 |
+
"6": "\u5b89\u5168\u7a69\u5b9a\u56ae\u5f80",
|
22 |
+
"7": "\u6a5f\u6703\u8b8a\u5316\u56ae\u5f80"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"max_position_embeddings": 512,
|
28 |
+
"model_type": "bert",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"output_past": true,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"pooler_fc_size": 768,
|
34 |
+
"pooler_num_attention_heads": 12,
|
35 |
+
"pooler_num_fc_layers": 3,
|
36 |
+
"pooler_size_per_head": 128,
|
37 |
+
"pooler_type": "first_token_transform",
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"problem_type": "multi_label_classification",
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.25.1",
|
42 |
+
"type_vocab_size": 2,
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 21128
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58474ac7077b7ce65feb8d2882837d3ac32e9759ad2103d2e421aff19111d607
|
3 |
+
size 409167989
|
runs/Jan17_00-14-27_eec551641185/1673914481.8196719/events.out.tfevents.1673914481.eec551641185.324.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:373da55a905c717e9383bbf2c57572caf355b0979cffa73de87d585c2cd02d73
|
3 |
+
size 5513
|
runs/Jan17_00-14-27_eec551641185/events.out.tfevents.1673914481.eec551641185.324.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c7ded5f567b364e6e60c46de2b684b83971d35a672570948c2ad3c77e8bca7a
|
3 |
+
size 4779
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a8125f416a005320f0278a8e48b26ab03761f058fd7c98cdb4aa66bea40ac1
|
3 |
+
size 3387
|