Upload 11 files
Browse files- config.json +54 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- trainer_state.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "monologg/kobigbird-bert-base",
|
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": 5,
|
10 |
+
"classifier_dropout": null,
|
11 |
+
"eos_token_id": 6,
|
12 |
+
"gradient_checkpointing": false,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "IT\uacfc\ud559",
|
18 |
+
"1": "\uacbd\uc81c",
|
19 |
+
"2": "\uc0ac\ud68c",
|
20 |
+
"3": "\uc0dd\ud65c\ubb38\ud654",
|
21 |
+
"4": "\uc138\uacc4",
|
22 |
+
"5": "\uc2a4\ud3ec\uce20",
|
23 |
+
"6": "\uc815\uce58"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"IT\uacfc\ud559": 0,
|
29 |
+
"\uacbd\uc81c": 1,
|
30 |
+
"\uc0ac\ud68c": 2,
|
31 |
+
"\uc0dd\ud65c\ubb38\ud654": 3,
|
32 |
+
"\uc138\uacc4": 4,
|
33 |
+
"\uc2a4\ud3ec\uce20": 5,
|
34 |
+
"\uc815\uce58": 6
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"max_position_embeddings": 4096,
|
38 |
+
"model_type": "big_bird",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"num_random_blocks": 3,
|
42 |
+
"pad_token_id": 0,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"problem_type": "single_label_classification",
|
45 |
+
"rescale_embeddings": false,
|
46 |
+
"sep_token_id": 3,
|
47 |
+
"tokenizer_class": "BertTokenizer",
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.31.0",
|
50 |
+
"type_vocab_size": 2,
|
51 |
+
"use_bias": true,
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 32500
|
54 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9cb439b3d7bf839db4d60f6ccd5e8d40e776504af15fb1ed2eceb66f96369f7
|
3 |
+
size 910191813
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbfb8f3c572f070992633fd555bebbc2ae7fece46b52119fb7a19803907d6735
|
3 |
+
size 457468345
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8d17d02fa3a36682b85de97f3c311a595e811931a885c199e2b4dd41c425d0b
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca4beeb0b784325d62c6dff8ef2e9803ca680b4c40048f5b2befb14560487429
|
3 |
+
size 627
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_basic_tokenize": true,
|
6 |
+
"do_lower_case": false,
|
7 |
+
"eos_token": "</s>",
|
8 |
+
"mask_token": "[MASK]",
|
9 |
+
"model_max_length": 4096,
|
10 |
+
"never_split": null,
|
11 |
+
"pad_token": "[PAD]",
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.38396790623664856,
|
3 |
+
"best_model_checkpoint": "topic_model/checkpoint-2855",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 2855,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.18,
|
12 |
+
"learning_rate": 1.649737302977233e-05,
|
13 |
+
"loss": 0.793,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.35,
|
18 |
+
"learning_rate": 1.2994746059544661e-05,
|
19 |
+
"loss": 0.4523,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.53,
|
24 |
+
"learning_rate": 9.492119089316989e-06,
|
25 |
+
"loss": 0.4045,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.7,
|
30 |
+
"learning_rate": 5.989492119089317e-06,
|
31 |
+
"loss": 0.3818,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.88,
|
36 |
+
"learning_rate": 2.4868651488616464e-06,
|
37 |
+
"loss": 0.3745,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.0,
|
42 |
+
"eval_accuracy": 0.8704293400680795,
|
43 |
+
"eval_loss": 0.38396790623664856,
|
44 |
+
"eval_runtime": 14.2779,
|
45 |
+
"eval_samples_per_second": 637.837,
|
46 |
+
"eval_steps_per_second": 39.922,
|
47 |
+
"step": 2855
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"max_steps": 2855,
|
51 |
+
"num_train_epochs": 1,
|
52 |
+
"total_flos": 495932362009212.0,
|
53 |
+
"trial_name": null,
|
54 |
+
"trial_params": null
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7613ac9261f831f5d5f6d363ee82a37d50c9bda3660cdd5a3b64ab63e16ef82
|
3 |
+
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|