Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +49 -0
- pytorch_model.bin +3 -0
- runs/Aug07_03-23-01_299bce13a1a6/events.out.tfevents.1691378599.299bce13a1a6.182.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Lowin/chinese-bigbird-wwm-base-4096",
|
3 |
+
"architectures": [
|
4 |
+
"BigBirdForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"attention_type": "block_sparse",
|
8 |
+
"block_size": 64,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": null,
|
11 |
+
"directionality": "bidi",
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"gradient_checkpointing": false,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"id2label": {
|
18 |
+
"0": "Down",
|
19 |
+
"1": "Up"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"Down": 0,
|
25 |
+
"Up": 1
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"max_position_embeddings": 4096,
|
29 |
+
"model_type": "big_bird",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"num_random_blocks": 3,
|
33 |
+
"output_past": true,
|
34 |
+
"pad_token_id": 1,
|
35 |
+
"pooler_fc_size": 768,
|
36 |
+
"pooler_num_attention_heads": 12,
|
37 |
+
"pooler_num_fc_layers": 3,
|
38 |
+
"pooler_size_per_head": 128,
|
39 |
+
"pooler_type": "first_token_transform",
|
40 |
+
"problem_type": "single_label_classification",
|
41 |
+
"rescale_embeddings": false,
|
42 |
+
"sep_token_id": 66,
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.31.0",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_bias": true,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 21128
|
49 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5a79322efc06bf085a27f7678f353c27a77d8f0ddcb3507e746bf2d364e95b
|
3 |
+
size 422518201
|
runs/Aug07_03-23-01_299bce13a1a6/events.out.tfevents.1691378599.299bce13a1a6.182.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e1caec1113253a3abff015e8080d08d7445b6d587ab5dcfb66d3916cccfec96
|
3 |
+
size 5085
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e778d70a39e7d8d97c780c0009a9f28db7271794e442f9cb9c7f4c9e4db960c4
|
3 |
+
size 4091
|