Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +70 -0
- pytorch_model.bin +3 -0
- runs/Dec08_17-46-16_3248153b7062/1670521587.4782217/events.out.tfevents.1670521587.3248153b7062.23.1 +3 -0
- runs/Dec08_17-46-16_3248153b7062/events.out.tfevents.1670521587.3248153b7062.23.0 +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-corporation",
|
27 |
+
"2": "I-corporation",
|
28 |
+
"3": "B-creative-work",
|
29 |
+
"4": "I-creative-work",
|
30 |
+
"5": "B-group",
|
31 |
+
"6": "I-group",
|
32 |
+
"7": "B-location",
|
33 |
+
"8": "I-location",
|
34 |
+
"9": "B-person",
|
35 |
+
"10": "I-person",
|
36 |
+
"11": "B-product",
|
37 |
+
"12": "I-product"
|
38 |
+
},
|
39 |
+
"initializer_range": 0.1,
|
40 |
+
"initializer_std": null,
|
41 |
+
"label2id": {
|
42 |
+
"B-corporation": 1,
|
43 |
+
"B-creative-work": 3,
|
44 |
+
"B-group": 5,
|
45 |
+
"B-location": 7,
|
46 |
+
"B-person": 9,
|
47 |
+
"B-product": 11,
|
48 |
+
"I-corporation": 2,
|
49 |
+
"I-creative-work": 4,
|
50 |
+
"I-group": 6,
|
51 |
+
"I-location": 8,
|
52 |
+
"I-person": 10,
|
53 |
+
"I-product": 12,
|
54 |
+
"O": 0
|
55 |
+
},
|
56 |
+
"layer_norm_eps": 1e-09,
|
57 |
+
"max_position_embeddings": 512,
|
58 |
+
"model_type": "funnel",
|
59 |
+
"n_head": 16,
|
60 |
+
"num_decoder_layers": 2,
|
61 |
+
"pool_q_only": true,
|
62 |
+
"pooling_type": "mean",
|
63 |
+
"rel_attn_type": "factorized",
|
64 |
+
"separate_cls": true,
|
65 |
+
"torch_dtype": "float32",
|
66 |
+
"transformers_version": "4.20.1",
|
67 |
+
"truncate_seq": true,
|
68 |
+
"type_vocab_size": 3,
|
69 |
+
"vocab_size": 30522
|
70 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba9296968cdb8b3483bbff6e8c520e549af6236d21bddeb137979d9ccf7cd96
|
3 |
+
size 1872355383
|
runs/Dec08_17-46-16_3248153b7062/1670521587.4782217/events.out.tfevents.1670521587.3248153b7062.23.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca6b222353a9211d420c43c46bbe017918a58d23ceb5cdd05f3d1751b4853a6d
|
3 |
+
size 5404
|
runs/Dec08_17-46-16_3248153b7062/events.out.tfevents.1670521587.3248153b7062.23.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6a6637fdf7bd0628a41722f3aba3af9e590e4367be31a785f372b63ee978355
|
3 |
+
size 4911
|
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 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_text": true,
|
5 |
+
"cls_token": "<cls>",
|
6 |
+
"do_lower_case": true,
|
7 |
+
"eos_token": "</s>",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"model_max_length": 512,
|
10 |
+
"name_or_path": "funnel-transformer/xlarge",
|
11 |
+
"pad_token": "<pad>",
|
12 |
+
"sep_token": "<sep>",
|
13 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/b060e6ffd92654022c863f0c068a27c55b66816d017806195b2bda0c20651aa1.34a22f495fc6b4fddbf5d6b2c62637ae42a7204b6355bbd999c44fee4001336d",
|
14 |
+
"strip_accents": null,
|
15 |
+
"tokenize_chinese_chars": true,
|
16 |
+
"tokenizer_class": "FunnelTokenizer",
|
17 |
+
"unk_token": "<unk>",
|
18 |
+
"wordpieces_prefix": "##"
|
19 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86dc78b7ab22046ebce60f0f327596af83b82b559c10cb40db8a058d2fe34215
|
3 |
+
size 3375
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|