Training completed!
Browse files- .gitignore +1 -0
- config.json +75 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May06_15-13-26_e6e30020e52d/1683386060.871226/events.out.tfevents.1683386060.e6e30020e52d.346.1 +3 -0
- runs/May06_15-13-26_e6e30020e52d/events.out.tfevents.1683386060.e6e30020e52d.346.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "skt/kogpt2-base-v2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2ForTokenClassification"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"author": "Heewon Jeon([email protected])",
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"created_date": "2021-04-28",
|
12 |
+
"embd_pdrop": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"gradient_checkpointing": false,
|
15 |
+
"id2label": {
|
16 |
+
"0": "B-DT",
|
17 |
+
"1": "I-DT",
|
18 |
+
"2": "B-LC",
|
19 |
+
"3": "I-LC",
|
20 |
+
"4": "B-OG",
|
21 |
+
"5": "I-OG",
|
22 |
+
"6": "B-PS",
|
23 |
+
"7": "I-PS",
|
24 |
+
"8": "B-QT",
|
25 |
+
"9": "I-QT",
|
26 |
+
"10": "B-TI",
|
27 |
+
"11": "I-TI",
|
28 |
+
"12": "O"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"label2id": {
|
32 |
+
"B-DT": 0,
|
33 |
+
"B-LC": 2,
|
34 |
+
"B-OG": 4,
|
35 |
+
"B-PS": 6,
|
36 |
+
"B-QT": 8,
|
37 |
+
"B-TI": 10,
|
38 |
+
"I-DT": 1,
|
39 |
+
"I-LC": 3,
|
40 |
+
"I-OG": 5,
|
41 |
+
"I-PS": 7,
|
42 |
+
"I-QT": 9,
|
43 |
+
"I-TI": 11,
|
44 |
+
"O": 12
|
45 |
+
},
|
46 |
+
"layer_norm_epsilon": 1e-05,
|
47 |
+
"license": "CC-BY-NC-SA 4.0",
|
48 |
+
"model_type": "gpt2",
|
49 |
+
"n_ctx": 1024,
|
50 |
+
"n_embd": 768,
|
51 |
+
"n_head": 12,
|
52 |
+
"n_inner": null,
|
53 |
+
"n_layer": 12,
|
54 |
+
"n_positions": 1024,
|
55 |
+
"pad_token_id": 3,
|
56 |
+
"reorder_and_upcast_attn": false,
|
57 |
+
"resid_pdrop": 0.1,
|
58 |
+
"scale_attn_by_inverse_layer_idx": false,
|
59 |
+
"scale_attn_weights": true,
|
60 |
+
"summary_activation": null,
|
61 |
+
"summary_first_dropout": 0.1,
|
62 |
+
"summary_proj_to_labels": true,
|
63 |
+
"summary_type": "cls_index",
|
64 |
+
"summary_use_proj": true,
|
65 |
+
"task_specific_params": {
|
66 |
+
"text-generation": {
|
67 |
+
"do_sample": true,
|
68 |
+
"max_length": 50
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.28.1",
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 51200
|
75 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:106a696bc99c318a4e334d460f9646d6e8b81deeeaeef6e25cca9a7d4901fee4
|
3 |
+
size 513335365
|
runs/May06_15-13-26_e6e30020e52d/1683386060.871226/events.out.tfevents.1683386060.e6e30020e52d.346.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75d5834008273d51516ebdceffb3c0473ec1afaf7215febb5803a7c59b4d6a69
|
3 |
+
size 5928
|
runs/May06_15-13-26_e6e30020e52d/events.out.tfevents.1683386060.e6e30020e52d.346.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cb1793119cfaa8baed2e0d839627c0d0cf22acec2ba9bd0d41c4d7fbbf2030c
|
3 |
+
size 6720
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "</s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "</s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": "<mask>",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"tokenizer_class": "GPT2Tokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be1c3b8e7cd3986869112ef9db8d8b715ef473f97c453a210e871545acd5f03f
|
3 |
+
size 3643
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|