Upload 8 files

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "loodos/albert-base-turkish-uncased",
+  "architectures": [
+    "AlbertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-YEMEK",
+    "1": "O",
+    "2": "B-ICECEK_BUYUKLUK",
+    "3": "B-ICECEK",
+    "4": "B-ADRES",
+    "5": "B-ODEME",
+    "6": "B-YEMEK_CESIT",
+    "7": "B-YEMEK_ADET",
+    "8": "B-ICECEK_ICERIK",
+    "9": "I-ADRES",
+    "10": "I-YEMEK",
+    "11": "B-YEMEK_BUYUKLUK",
+    "12": "B-YEMEK_ICERIK",
+    "13": "I-YEMEK_ICERIK",
+    "14": "I-ICECEK",
+    "15": "I-YEMEK_BUYUKLUK",
+    "16": "I-YEMEK_CESIT",
+    "17": "B-ICECEK_ADET",
+    "18": "I-ODEME",
+    "19": "I-YEMEK_ADET"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ADRES": 4,
+    "B-ICECEK": 3,
+    "B-ICECEK_ADET": 17,
+    "B-ICECEK_BUYUKLUK": 2,
+    "B-ICECEK_ICERIK": 8,
+    "B-ODEME": 5,
+    "B-YEMEK": 0,
+    "B-YEMEK_ADET": 7,
+    "B-YEMEK_BUYUKLUK": 11,
+    "B-YEMEK_CESIT": 6,
+    "B-YEMEK_ICERIK": 12,
+    "I-ADRES": 9,
+    "I-ICECEK": 14,
+    "I-ODEME": 18,
+    "I-YEMEK": 10,
+    "I-YEMEK_ADET": 19,
+    "I-YEMEK_BUYUKLUK": 15,
+    "I-YEMEK_CESIT": 16,
+    "I-YEMEK_ICERIK": 13,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "vocab_size": 32000
+}

eval_results.txt

@@ -0,0 +1,22 @@
+                 precision    recall  f1-score   support
+
+          ADRES     0.9983    1.0000    0.9991       579
+         ICECEK     0.9926    1.0000    0.9963       135
+    ICECEK_ADET     0.9672    0.9833    0.9752        60
+ICECEK_BUYUKLUK     1.0000    1.0000    1.0000        21
+  ICECEK_ICERIK     1.0000    1.0000    1.0000        10
+          ODEME     0.9914    0.9931    0.9923       583
+          YEMEK     0.8685    0.9189    0.8930       740
+     YEMEK_ADET     0.9790    0.9894    0.9842       283
+ YEMEK_BUYUKLUK     0.9077    0.9008    0.9042       131
+    YEMEK_CESIT     0.8557    0.8592    0.8574       483
+   YEMEK_ICERIK     0.7482    0.6887    0.7172       151
+
+      micro avg     0.9269    0.9383    0.9326      3176
+      macro avg     0.9371    0.9394    0.9381      3176
+   weighted avg     0.9269    0.9383    0.9324      3176
+
+eval_loss = 0.1106654754251502
+f1_score = 0.9325614144891252
+precision = 0.926905132192846
+recall = 0.9382871536523929

model_args.json

@@ -0,0 +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": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 3e-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": "loodos/albert-base-turkish-uncased", "model_type": "albert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "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": 4, "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": 223, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": true, "labels_list": ["B-YEMEK", "O", "B-ICECEK_BUYUKLUK", "B-ICECEK", "B-ADRES", "B-ODEME", "B-YEMEK_CESIT", "B-YEMEK_ADET", "B-ICECEK_ICERIK", "I-ADRES", "I-YEMEK", "B-YEMEK_BUYUKLUK", "B-YEMEK_ICERIK", "I-YEMEK_ICERIK", "I-ICECEK", "I-YEMEK_BUYUKLUK", "I-YEMEK_CESIT", "B-ICECEK_ADET", "I-ODEME", "I-YEMEK_ADET"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350d013addd74cf77b153391f10ef435f4a8b605e3bd463b03465b3d7e937789
+size 45470591

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0906192fc8a73500782d11318813c4554fb0aeeb2ded6899b69839f09958ee99
+size 862541

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--loodos--albert-base-turkish-uncased/snapshots/3275004703c3ea35b5dcde5b684b707d32e5a69e/special_tokens_map.json",
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ed257d9191b79c6c33901827369ae662118782febb345d94bb0c5ec88b78de
+size 3323