Upload folder using huggingface_hub
Browse files- config.json +95 -0
- eval_results.txt +4 -0
- model.safetensors +3 -0
- model_args.json +1 -0
- optimizer.pt +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +20 -0
- tokenizer_config.json +93 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"CamembertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B_BRN",
|
17 |
+
"2": "B_DES",
|
18 |
+
"3": "B_DTM",
|
19 |
+
"4": "B_LOC",
|
20 |
+
"5": "B_MEA",
|
21 |
+
"6": "B_NUM",
|
22 |
+
"7": "B_ORG",
|
23 |
+
"8": "B_PER",
|
24 |
+
"9": "B_TRM",
|
25 |
+
"10": "B_TTL",
|
26 |
+
"11": "I_BRN",
|
27 |
+
"12": "I_DES",
|
28 |
+
"13": "I_DTM",
|
29 |
+
"14": "I_LOC",
|
30 |
+
"15": "I_MEA",
|
31 |
+
"16": "I_NUM",
|
32 |
+
"17": "I_ORG",
|
33 |
+
"18": "I_PER",
|
34 |
+
"19": "I_TRM",
|
35 |
+
"20": "I_TTL",
|
36 |
+
"21": "E_BRN",
|
37 |
+
"22": "E_DES",
|
38 |
+
"23": "E_DTM",
|
39 |
+
"24": "E_LOC",
|
40 |
+
"25": "E_MEA",
|
41 |
+
"26": "E_NUM",
|
42 |
+
"27": "E_ORG",
|
43 |
+
"28": "E_PER",
|
44 |
+
"29": "E_TRM",
|
45 |
+
"30": "E_TTL"
|
46 |
+
},
|
47 |
+
"initializer_range": 0.02,
|
48 |
+
"intermediate_size": 3072,
|
49 |
+
"label2id": {
|
50 |
+
"B_BRN": 1,
|
51 |
+
"B_DES": 2,
|
52 |
+
"B_DTM": 3,
|
53 |
+
"B_LOC": 4,
|
54 |
+
"B_MEA": 5,
|
55 |
+
"B_NUM": 6,
|
56 |
+
"B_ORG": 7,
|
57 |
+
"B_PER": 8,
|
58 |
+
"B_TRM": 9,
|
59 |
+
"B_TTL": 10,
|
60 |
+
"E_BRN": 21,
|
61 |
+
"E_DES": 22,
|
62 |
+
"E_DTM": 23,
|
63 |
+
"E_LOC": 24,
|
64 |
+
"E_MEA": 25,
|
65 |
+
"E_NUM": 26,
|
66 |
+
"E_ORG": 27,
|
67 |
+
"E_PER": 28,
|
68 |
+
"E_TRM": 29,
|
69 |
+
"E_TTL": 30,
|
70 |
+
"I_BRN": 11,
|
71 |
+
"I_DES": 12,
|
72 |
+
"I_DTM": 13,
|
73 |
+
"I_LOC": 14,
|
74 |
+
"I_MEA": 15,
|
75 |
+
"I_NUM": 16,
|
76 |
+
"I_ORG": 17,
|
77 |
+
"I_PER": 18,
|
78 |
+
"I_TRM": 19,
|
79 |
+
"I_TTL": 20,
|
80 |
+
"O": 0
|
81 |
+
},
|
82 |
+
"layer_norm_eps": 1e-12,
|
83 |
+
"max_position_embeddings": 512,
|
84 |
+
"model_type": "camembert",
|
85 |
+
"num_attention_head": 12,
|
86 |
+
"num_attention_heads": 12,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"pad_token_id": 1,
|
89 |
+
"position_embedding_type": "absolute",
|
90 |
+
"torch_dtype": "float32",
|
91 |
+
"transformers_version": "4.41.2",
|
92 |
+
"type_vocab_size": 1,
|
93 |
+
"use_cache": true,
|
94 |
+
"vocab_size": 25005
|
95 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.20749381397451674
|
2 |
+
f1_score = 0.6845588961701847
|
3 |
+
precision = 0.6727508090614887
|
4 |
+
recall = 0.6967888985720989
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81b130f8e8e698d002d302d4489c41980c535059cca569fca8c29cdfc5b70143
|
3 |
+
size 418734556
|
model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 256, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 4, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 81, "model_name": "airesearch/wangchanberta-base-att-spm-uncased", "model_type": "camembert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 12, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 10, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 256, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 14, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["O", "B_BRN", "B_DES", "B_DTM", "B_LOC", "B_MEA", "B_NUM", "B_ORG", "B_PER", "B_TRM", "B_TTL", "I_BRN", "I_DES", "I_DTM", "I_LOC", "I_MEA", "I_NUM", "I_ORG", "I_PER", "I_TRM", "I_TTL", "E_BRN", "E_DES", "E_DTM", "E_LOC", "E_MEA", "E_NUM", "E_ORG", "E_PER", "E_TRM", "E_TTL"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d7de694ba65988fd5a36c20cb4f55714e3416a07e4322112ae6e4ddafc6287e
|
3 |
+
size 837587642
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45f839982f839c48027f07cff6986694e63d967790974759b99b9f369f0fe277
|
3 |
+
size 1064
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
|
3 |
+
size 904693
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED",
|
5 |
+
"<_>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"cls_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"mask_token": {
|
11 |
+
"content": "<mask>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>NOTUSED",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>NOTUSED",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "<unk>NOTUSED",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "<s>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "</s>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<mask>",
|
61 |
+
"lstrip": true,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "<_>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
}
|
75 |
+
},
|
76 |
+
"additional_special_tokens": [
|
77 |
+
"<s>NOTUSED",
|
78 |
+
"</s>NOTUSED",
|
79 |
+
"<_>"
|
80 |
+
],
|
81 |
+
"bos_token": "<s>",
|
82 |
+
"clean_up_tokenization_spaces": true,
|
83 |
+
"cls_token": "<s>",
|
84 |
+
"do_lower_case": false,
|
85 |
+
"eos_token": "</s>",
|
86 |
+
"mask_token": "<mask>",
|
87 |
+
"model_max_length": 1000000000000000019884624838656,
|
88 |
+
"pad_token": "<pad>",
|
89 |
+
"sep_token": "</s>",
|
90 |
+
"sp_model_kwargs": {},
|
91 |
+
"tokenizer_class": "CamembertTokenizer",
|
92 |
+
"unk_token": "<unk>"
|
93 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b001e681c778fa494351b626c856f065e9d9ad610a047cbd7db545ffe3e5f516
|
3 |
+
size 3832
|