Upload 8 files
Browse files- config.json +51 -0
- model_args.json +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/sysadmin/Desktop/Oguzhan/huggingface_models/convbert_base_turkish_cased",
|
3 |
+
"architectures": [
|
4 |
+
"ConvBertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"conv_kernel_size": 9,
|
10 |
+
"embedding_size": 768,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"head_ratio": 2,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "B-PER",
|
18 |
+
"1": "I-PER",
|
19 |
+
"2": "B-ADDR",
|
20 |
+
"3": "I-ADDR",
|
21 |
+
"4": "B-CITY",
|
22 |
+
"5": "I-CITY",
|
23 |
+
"6": "B-STAT",
|
24 |
+
"7": "I-STAT",
|
25 |
+
"8": "O"
|
26 |
+
},
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"label2id": {
|
30 |
+
"B-PER": 0,
|
31 |
+
"I-PER": 1,
|
32 |
+
"B-ADDR": 2,
|
33 |
+
"I-ADDR": 3,
|
34 |
+
"B-CITY": 4,
|
35 |
+
"I-CITY": 5,
|
36 |
+
"B-STAT": 6,
|
37 |
+
"I-STAT": 7,
|
38 |
+
"O": 8
|
39 |
+
},
|
40 |
+
"layer_norm_eps": 1e-12,
|
41 |
+
"max_position_embeddings": 512,
|
42 |
+
"model_type": "convbert",
|
43 |
+
"num_attention_heads": 12,
|
44 |
+
"num_groups": 1,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.22.1",
|
49 |
+
"type_vocab_size": 2,
|
50 |
+
"vocab_size": 32000
|
51 |
+
}
|
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_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": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": false, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 5e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "/home/sysadmin/Desktop/Oguzhan/huggingface_models/convbert_base_turkish_cased", "model_type": "auto", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": true, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "saved_model_0", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 18, "quantized_model": false, "reprocess_input_data": true, "save_best_model": false, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": -1, "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": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 30, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["B-PER", "I-PER", "B-ADDR", "I-ADDR", "B-CITY", "I-CITY", "B-STAT", "I-STAT", "O"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b74b817b9bdf6b2a6181bfde78645d328b16b40f122aaed2371240e8882d73cc
|
3 |
+
size 427391241
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"name_or_path": "/home/sysadmin/Desktop/Oguzhan/huggingface_models/convbert_base_turkish_cased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": false,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "ConvBertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ecd45e74acffbae49b9df1736ab31a49026043da88a8f0359ab6ba6a1c36b40
|
3 |
+
size 3055
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|