Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +58 -0
- pytorch_model.bin +3 -0
- runs/Dec09_19-28-20_6e8951ea9318/1670614114.0279014/events.out.tfevents.1670614114.6e8951ea9318.23.1 +3 -0
- runs/Dec09_19-28-20_6e8951ea9318/events.out.tfevents.1670614114.6e8951ea9318.23.0 +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "funnel-transformer/xlarge",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"architectures": [
|
5 |
+
"FunnelForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"attention_type": "relative_shift",
|
9 |
+
"block_repeats": [
|
10 |
+
1,
|
11 |
+
1,
|
12 |
+
1
|
13 |
+
],
|
14 |
+
"block_sizes": [
|
15 |
+
10,
|
16 |
+
10,
|
17 |
+
10
|
18 |
+
],
|
19 |
+
"d_head": 64,
|
20 |
+
"d_inner": 4096,
|
21 |
+
"d_model": 1024,
|
22 |
+
"hidden_act": "gelu_new",
|
23 |
+
"hidden_dropout": 0.1,
|
24 |
+
"id2label": {
|
25 |
+
"0": "O",
|
26 |
+
"1": "B-PER",
|
27 |
+
"2": "I-PER",
|
28 |
+
"3": "B-ORG",
|
29 |
+
"4": "I-ORG",
|
30 |
+
"5": "B-LOC",
|
31 |
+
"6": "I-LOC"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.1,
|
34 |
+
"initializer_std": null,
|
35 |
+
"label2id": {
|
36 |
+
"B-LOC": 5,
|
37 |
+
"B-ORG": 3,
|
38 |
+
"B-PER": 1,
|
39 |
+
"I-LOC": 6,
|
40 |
+
"I-ORG": 4,
|
41 |
+
"I-PER": 2,
|
42 |
+
"O": 0
|
43 |
+
},
|
44 |
+
"layer_norm_eps": 1e-09,
|
45 |
+
"max_position_embeddings": 512,
|
46 |
+
"model_type": "funnel",
|
47 |
+
"n_head": 16,
|
48 |
+
"num_decoder_layers": 2,
|
49 |
+
"pool_q_only": true,
|
50 |
+
"pooling_type": "mean",
|
51 |
+
"rel_attn_type": "factorized",
|
52 |
+
"separate_cls": true,
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.20.1",
|
55 |
+
"truncate_seq": true,
|
56 |
+
"type_vocab_size": 3,
|
57 |
+
"vocab_size": 30522
|
58 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4474e5608d6231664cdcc305b1de5365d7e56c732c70a9fa934538b9575af50d
|
3 |
+
size 1872330807
|
runs/Dec09_19-28-20_6e8951ea9318/1670614114.0279014/events.out.tfevents.1670614114.6e8951ea9318.23.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07d06f58adc77af491a101181a71798be001fb62984a4416d307fad8e898b693
|
3 |
+
size 5404
|
runs/Dec09_19-28-20_6e8951ea9318/events.out.tfevents.1670614114.6e8951ea9318.23.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a80b7640f6eb6156f295999cb2f5d3a10baa2eb82ca5ef0db22a5fd79e5fd230
|
3 |
+
size 6140
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<cls>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "<sep>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_text": true,
|
4 |
+
"cls_token": "<cls>",
|
5 |
+
"do_lower_case": true,
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"mask_token": "<mask>",
|
8 |
+
"model_max_length": 512,
|
9 |
+
"name_or_path": "funnel-transformer/xlarge",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "<sep>",
|
12 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/b060e6ffd92654022c863f0c068a27c55b66816d017806195b2bda0c20651aa1.34a22f495fc6b4fddbf5d6b2c62637ae42a7204b6355bbd999c44fee4001336d",
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "FunnelTokenizer",
|
16 |
+
"unk_token": "<unk>",
|
17 |
+
"wordpieces_prefix": "##"
|
18 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfbbf167a4c83476b2d9c864c2178c2e5ec40765b46490fd3e1da471ce57fcb0
|
3 |
+
size 3375
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|