Upload folder using huggingface_hub

config.json

@@ -0,0 +1,95 @@
+{
+  "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B_BRN",
+    "2": "B_DES",
+    "3": "B_DTM",
+    "4": "B_LOC",
+    "5": "B_MEA",
+    "6": "B_NUM",
+    "7": "B_ORG",
+    "8": "B_PER",
+    "9": "B_TRM",
+    "10": "B_TTL",
+    "11": "I_BRN",
+    "12": "I_DES",
+    "13": "I_DTM",
+    "14": "I_LOC",
+    "15": "I_MEA",
+    "16": "I_NUM",
+    "17": "I_ORG",
+    "18": "I_PER",
+    "19": "I_TRM",
+    "20": "I_TTL",
+    "21": "E_BRN",
+    "22": "E_DES",
+    "23": "E_DTM",
+    "24": "E_LOC",
+    "25": "E_MEA",
+    "26": "E_NUM",
+    "27": "E_ORG",
+    "28": "E_PER",
+    "29": "E_TRM",
+    "30": "E_TTL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B_BRN": 1,
+    "B_DES": 2,
+    "B_DTM": 3,
+    "B_LOC": 4,
+    "B_MEA": 5,
+    "B_NUM": 6,
+    "B_ORG": 7,
+    "B_PER": 8,
+    "B_TRM": 9,
+    "B_TTL": 10,
+    "E_BRN": 21,
+    "E_DES": 22,
+    "E_DTM": 23,
+    "E_LOC": 24,
+    "E_MEA": 25,
+    "E_NUM": 26,
+    "E_ORG": 27,
+    "E_PER": 28,
+    "E_TRM": 29,
+    "E_TTL": 30,
+    "I_BRN": 11,
+    "I_DES": 12,
+    "I_DTM": 13,
+    "I_LOC": 14,
+    "I_MEA": 15,
+    "I_NUM": 16,
+    "I_ORG": 17,
+    "I_PER": 18,
+    "I_TRM": 19,
+    "I_TTL": 20,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 25005
+}

eval_results.txt

@@ -0,0 +1,4 @@
+eval_loss = 0.20749381397451674
+f1_score = 0.6845588961701847
+precision = 0.6727508090614887
+recall = 0.6967888985720989

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b130f8e8e698d002d302d4489c41980c535059cca569fca8c29cdfc5b70143
+size 418734556

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": 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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7de694ba65988fd5a36c20cb4f55714e3416a07e4322112ae6e4ddafc6287e
+size 837587642

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f839982f839c48027f07cff6986694e63d967790974759b99b9f369f0fe277
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
+size 904693

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,93 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<_>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b001e681c778fa494351b626c856f065e9d9ad610a047cbd7db545ffe3e5f516
+size 3832