54data commited on
Commit
bd578cf
1 Parent(s): 427cec0

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "skt/kogpt2-base-v2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "author": "Heewon Jeon(madjakarta@gmail.com)",
10
+ "bos_token_id": 0,
11
+ "created_date": "2021-04-28",
12
+ "early_stopping": true,
13
+ "embd_pdrop": 0.1,
14
+ "eos_token_id": 1,
15
+ "gradient_checkpointing": false,
16
+ "id2label": {
17
+ "0": "LABEL_0"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0
22
+ },
23
+ "layer_norm_epsilon": 1e-05,
24
+ "length_penalty": 5.0,
25
+ "license": "CC-BY-NC-SA 4.0",
26
+ "min_length": 30,
27
+ "model_type": "gpt2",
28
+ "n_ctx": 1024,
29
+ "n_embd": 768,
30
+ "n_head": 12,
31
+ "n_inner": null,
32
+ "n_layer": 12,
33
+ "n_positions": 1024,
34
+ "no_repeat_ngram_size": 2,
35
+ "num_beams": 5,
36
+ "pad_token_id": 3,
37
+ "reorder_and_upcast_attn": false,
38
+ "resid_pdrop": 0.1,
39
+ "scale_attn_by_inverse_layer_idx": false,
40
+ "scale_attn_weights": true,
41
+ "sep_token_id": 51200,
42
+ "summary_activation": null,
43
+ "summary_first_dropout": 0.1,
44
+ "summary_proj_to_labels": true,
45
+ "summary_type": "cls_index",
46
+ "summary_use_proj": true,
47
+ "task_specific_params": {
48
+ "text-generation": {
49
+ "do_sample": true,
50
+ "max_length": 50
51
+ }
52
+ },
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.25.1",
55
+ "use_cache": true,
56
+ "vocab_size": 51201
57
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5675c43aff76105fe888bb25355704876a193b09e59a7fc9a00a791c925f4e
3
+ size 513296489
runs/Jan28_19-24-16_24c5be87015a/1674933885.3037817/events.out.tfevents.1674933885.24c5be87015a.2893.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfca4088b728074f4531bf02f25f13115a85b9bc56eb73c0f6c3b890816f0f55
3
+ size 5562
runs/Jan28_19-24-16_24c5be87015a/events.out.tfevents.1674933885.24c5be87015a.2893.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f695e1a39787dd4ab8a45bbc560645f5efa82b2b2d7a433fac2d263722818d44
3
+ size 4865
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "sep_token": "<sep>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "model_max_length": 1000000000000000019884624838656,
4
+ "name_or_path": "skt/kogpt2-base-v2",
5
+ "pad_token": "<pad>",
6
+ "sep_token": "<sep>",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "PreTrainedTokenizerFast",
9
+ "unk_token": "<unk>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0587081860b4465bab066eca7a6f258d8d3726eae1731308defcc608fae6d102
3
+ size 3503