sunilregmi commited on Apr 5

Commit

1ab791b

•

1 Parent(s): a214c17

Upload folder using huggingface_hub

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

checkpoint-1353-epoch-3/config.json +44 -0
checkpoint-1353-epoch-3/model.safetensors +3 -0
checkpoint-1353-epoch-3/model_args.json +1 -0
checkpoint-1353-epoch-3/optimizer.pt +3 -0
checkpoint-1353-epoch-3/scheduler.pt +3 -0
checkpoint-1353-epoch-3/special_tokens_map.json +7 -0
checkpoint-1353-epoch-3/tokenizer_config.json +58 -0
checkpoint-1353-epoch-3/training_args.bin +3 -0
checkpoint-1353-epoch-3/vocab.txt +0 -0
checkpoint-1804-epoch-4/config.json +44 -0
checkpoint-1804-epoch-4/model.safetensors +3 -0
checkpoint-1804-epoch-4/model_args.json +1 -0
checkpoint-1804-epoch-4/optimizer.pt +3 -0
checkpoint-1804-epoch-4/scheduler.pt +3 -0
checkpoint-1804-epoch-4/special_tokens_map.json +7 -0
checkpoint-1804-epoch-4/tokenizer_config.json +58 -0
checkpoint-1804-epoch-4/training_args.bin +3 -0
checkpoint-1804-epoch-4/vocab.txt +0 -0
checkpoint-2000/config.json +166 -0
checkpoint-2000/model.safetensors +3 -0
checkpoint-2000/model_args.json +1 -0
checkpoint-2000/optimizer.pt +3 -0
checkpoint-2000/scheduler.pt +3 -0
checkpoint-2000/special_tokens_map.json +7 -0
checkpoint-2000/tokenizer_config.json +58 -0
checkpoint-2000/training_args.bin +3 -0
checkpoint-2000/vocab.txt +0 -0
checkpoint-2255-epoch-5/config.json +44 -0
checkpoint-2255-epoch-5/model.safetensors +3 -0
checkpoint-2255-epoch-5/model_args.json +1 -0
checkpoint-2255-epoch-5/optimizer.pt +3 -0
checkpoint-2255-epoch-5/scheduler.pt +3 -0
checkpoint-2255-epoch-5/special_tokens_map.json +7 -0
checkpoint-2255-epoch-5/tokenizer_config.json +58 -0
checkpoint-2255-epoch-5/training_args.bin +3 -0
checkpoint-2255-epoch-5/vocab.txt +0 -0
checkpoint-451-epoch-1/config.json +44 -0
checkpoint-451-epoch-1/model.safetensors +3 -0
checkpoint-451-epoch-1/model_args.json +1 -0
checkpoint-451-epoch-1/optimizer.pt +3 -0
checkpoint-451-epoch-1/scheduler.pt +3 -0
checkpoint-451-epoch-1/special_tokens_map.json +7 -0
checkpoint-451-epoch-1/tokenizer_config.json +58 -0
checkpoint-451-epoch-1/training_args.bin +3 -0
checkpoint-451-epoch-1/vocab.txt +0 -0
checkpoint-902-epoch-2/config.json +44 -0
checkpoint-902-epoch-2/model.safetensors +3 -0
checkpoint-902-epoch-2/model_args.json +1 -0
checkpoint-902-epoch-2/optimizer.pt +3 -0
checkpoint-902-epoch-2/scheduler.pt +3 -0

checkpoint-1353-epoch-3/config.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+  "_name_or_path": "NepBERTa/NepBERTa",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "O",
+    "2": "I-LOC",
+    "3": "B-PER",
+    "4": "B-ORG",
+    "5": "I-PER",
+    "6": "I-ORG"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-ORG": 4,
+    "B-PER": 3,
+    "I-LOC": 2,
+    "I-ORG": 6,
+    "I-PER": 5,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_state": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-1353-epoch-3/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f049ab429a4697e96a055432d6ea4e786a05c8ae4b4f4be74545cfabc48ec4
+size 435611468

checkpoint-1353-epoch-3/model_args.json ADDED Viewed

	@@ -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": 0.0001, "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": "NepBERTa/NepBERTa", "model_type": "bert", "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": 8, "train_custom_parameters_only": false, "trust_remote_code": 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": 136, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["B-LOC", "O", "I-LOC", "B-PER", "B-ORG", "I-PER", "I-ORG"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

checkpoint-1353-epoch-3/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:93cf90f57c772bed1ab0694b1c61b20d70073420f70bdec3399b40bc61e309e1
+size 871342650

checkpoint-1353-epoch-3/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e05079cc1ad0c8611bb08b3ea7663fa61e96f7b77dad09026711f1a6b0e9aa6
+size 1064

checkpoint-1353-epoch-3/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1353-epoch-3/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "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": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "from_tf": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-1353-epoch-3/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:87dc53d5ea23f82a753872c573fd1e5400357b6a8bb49ae88d5e9d1783129665
+size 3512

checkpoint-1353-epoch-3/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-1804-epoch-4/config.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+  "_name_or_path": "NepBERTa/NepBERTa",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "O",
+    "2": "I-LOC",
+    "3": "B-PER",
+    "4": "B-ORG",
+    "5": "I-PER",
+    "6": "I-ORG"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-ORG": 4,
+    "B-PER": 3,
+    "I-LOC": 2,
+    "I-ORG": 6,
+    "I-PER": 5,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_state": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-1804-epoch-4/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7740f7f628b3e30a0de4bf85ac6cd00ccd11efc9c23d33d28cd3d8f46fbf359b
+size 435611468

checkpoint-1804-epoch-4/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

checkpoint-1804-epoch-4/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0a7915473e01e3705582ee655879bec855dbbcb7c2c807c8358693563d60e6
+size 871342650

checkpoint-1804-epoch-4/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:92e14973499563b2c2125c4e45c313274d3ed56f9182ff998b322e9b680deb1b
+size 1064

checkpoint-1804-epoch-4/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1804-epoch-4/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "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": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "from_tf": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-1804-epoch-4/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:87dc53d5ea23f82a753872c573fd1e5400357b6a8bb49ae88d5e9d1783129665
+size 3512

checkpoint-1804-epoch-4/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-2000/config.json ADDED Viewed

	@@ -0,0 +1,166 @@

+{
+  "_name_or_path": "NepBERTa/NepBERTa",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NN",
+    "1": "IKO",
+    "2": "FB",
+    "3": "II",
+    "4": "JX",
+    "5": "CC",
+    "6": "IKM",
+    "7": "VVYN1",
+    "8": "YF",
+    "9": "DDX",
+    "10": "IE",
+    "11": "NP",
+    "12": "VQ",
+    "13": "VE",
+    "14": "IA",
+    "15": "VVYX2",
+    "16": "DJX",
+    "17": "TT",
+    "18": "VI",
+    "19": "RR",
+    "20": "MM",
+    "21": "VDX",
+    "22": "RD",
+    "23": "IKF",
+    "24": "VN",
+    "25": "IKX",
+    "26": "MLO",
+    "27": "IH",
+    "28": "PXH",
+    "29": "JM",
+    "30": "PRF",
+    "31": "YM",
+    "32": "MOX",
+    "33": "MOM",
+    "34": "PMXKO",
+    "35": "JO",
+    "36": "DKM",
+    "37": "CSB",
+    "38": "VVMX1",
+    "39": "DKX",
+    "40": "PRFKO",
+    "41": "PRFKX",
+    "42": "DDM",
+    "43": "PMXKM",
+    "44": "PMX",
+    "45": "VVMX2",
+    "46": "RK",
+    "47": "VDO",
+    "48": "MLX",
+    "49": "DDO",
+    "50": "PRFKM",
+    "51": "FZ",
+    "52": "PTH",
+    "53": "DGX",
+    "54": "VOYN1",
+    "55": "VCM",
+    "56": "VVYM1F",
+    "57": "DGM",
+    "58": "RJ",
+    "59": "VDM",
+    "60": "FF",
+    "61": "VR",
+    "62": "PMXKX",
+    "63": "DKO",
+    "64": "DGO",
+    "65": "VOMX2",
+    "66": "VVYN1F",
+    "67": "MLF"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "CC": 5,
+    "CSB": 37,
+    "DDM": 42,
+    "DDO": 49,
+    "DDX": 9,
+    "DGM": 57,
+    "DGO": 64,
+    "DGX": 53,
+    "DJX": 16,
+    "DKM": 36,
+    "DKO": 63,
+    "DKX": 39,
+    "FB": 2,
+    "FF": 60,
+    "FZ": 51,
+    "IA": 14,
+    "IE": 10,
+    "IH": 27,
+    "II": 3,
+    "IKF": 23,
+    "IKM": 6,
+    "IKO": 1,
+    "IKX": 25,
+    "JM": 29,
+    "JO": 35,
+    "JX": 4,
+    "MLF": 67,
+    "MLO": 26,
+    "MLX": 48,
+    "MM": 20,
+    "MOM": 33,
+    "MOX": 32,
+    "NN": 0,
+    "NP": 11,
+    "PMX": 44,
+    "PMXKM": 43,
+    "PMXKO": 34,
+    "PMXKX": 62,
+    "PRF": 30,
+    "PRFKM": 50,
+    "PRFKO": 40,
+    "PRFKX": 41,
+    "PTH": 52,
+    "PXH": 28,
+    "RD": 22,
+    "RJ": 58,
+    "RK": 46,
+    "RR": 19,
+    "TT": 17,
+    "VCM": 55,
+    "VDM": 59,
+    "VDO": 47,
+    "VDX": 21,
+    "VE": 13,
+    "VI": 18,
+    "VN": 24,
+    "VOMX2": 65,
+    "VOYN1": 54,
+    "VQ": 12,
+    "VR": 61,
+    "VVMX1": 38,
+    "VVMX2": 45,
+    "VVYM1F": 56,
+    "VVYN1": 7,
+    "VVYN1F": 66,
+    "VVYX2": 15,
+    "YF": 8,
+    "YM": 31
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_state": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2000/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c88d77cd0236bd6f04a6ba8c775c0c888c8d72fad518c18773d91426adc156b9
+size 435799104

checkpoint-2000/model_args.json ADDED Viewed

	@@ -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": 0.0001, "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": "NepBERTa/NepBERTa", "model_type": "bert", "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": false, "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": 8, "train_custom_parameters_only": false, "trust_remote_code": 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": 136, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["NN", "IKO", "FB", "II", "JX", "CC", "IKM", "VVYN1", "YF", "DDX", "IE", "NP", "VQ", "VE", "IA", "VVYX2", "DJX", "TT", "VI", "RR", "MM", "VDX", "RD", "IKF", "VN", "IKX", "MLO", "IH", "PXH", "JM", "PRF", "YM", "MOX", "MOM", "PMXKO", "JO", "DKM", "CSB", "VVMX1", "DKX", "PRFKO", "PRFKX", "DDM", "PMXKM", "PMX", "VVMX2", "RK", "VDO", "MLX", "DDO", "PRFKM", "FZ", "PTH", "DGX", "VOYN1", "VCM", "VVYM1F", "DGM", "RJ", "VDM", "FF", "VR", "PMXKX", "DKO", "DGO", "VOMX2", "VVYN1F", "MLF"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

checkpoint-2000/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:533200c36022eb9c7320d0d3f900fc61fa4dbdef3e5012a16cdb7142fa499487
+size 871717946

checkpoint-2000/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7b87825cd4df87507ff16a4fbca7645bf193e5af1fcaf0d1f733f49fad487816
+size 1064

checkpoint-2000/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-2000/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "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": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "from_tf": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-2000/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6ba489767cb2d1e6600114d94ad533d3938d6c743fdd4d2e3a3d2ff0c9a46d
+size 4152

checkpoint-2000/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-2255-epoch-5/config.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+  "_name_or_path": "NepBERTa/NepBERTa",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "O",
+    "2": "I-LOC",
+    "3": "B-PER",
+    "4": "B-ORG",
+    "5": "I-PER",
+    "6": "I-ORG"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-ORG": 4,
+    "B-PER": 3,
+    "I-LOC": 2,
+    "I-ORG": 6,
+    "I-PER": 5,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_state": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2255-epoch-5/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ebaaaa113701bac2fa50c292694fbf4fd3fd3d84bd981f984a771ed2a04f719f
+size 435611468

checkpoint-2255-epoch-5/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

checkpoint-2255-epoch-5/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:45d1e276d4d9feb5d03305eb6c953b0f1d74459358cef1d4924464606bd7546c
+size 871342650

checkpoint-2255-epoch-5/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3968933a8b2f9f50f0e634e985cbd5278e68dd275ee6bd8021f5151f0795cbe6
+size 1064

checkpoint-2255-epoch-5/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-2255-epoch-5/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "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": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "from_tf": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-2255-epoch-5/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:87dc53d5ea23f82a753872c573fd1e5400357b6a8bb49ae88d5e9d1783129665
+size 3512

checkpoint-2255-epoch-5/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-451-epoch-1/config.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+  "_name_or_path": "NepBERTa/NepBERTa",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "O",
+    "2": "I-LOC",
+    "3": "B-PER",
+    "4": "B-ORG",
+    "5": "I-PER",
+    "6": "I-ORG"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-ORG": 4,
+    "B-PER": 3,
+    "I-LOC": 2,
+    "I-ORG": 6,
+    "I-PER": 5,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_state": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-451-epoch-1/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c292f5db6d8160c07db3d74bc173ed8d36b9bd3ef12eae1859c36291f686f5c5
+size 435611468

checkpoint-451-epoch-1/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

checkpoint-451-epoch-1/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:775c1ed59de436294c40b3e2f0cc1761f9126bc62cdb2bb1cd0ba1d462f1bd62
+size 871342650

checkpoint-451-epoch-1/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fa5964fd47cb197a7e053fced6cb6deb04817917c01ce818917cc62dd39a1e
+size 1064

checkpoint-451-epoch-1/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-451-epoch-1/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "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": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "from_tf": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-451-epoch-1/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:87dc53d5ea23f82a753872c573fd1e5400357b6a8bb49ae88d5e9d1783129665
+size 3512

checkpoint-451-epoch-1/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-902-epoch-2/config.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+  "_name_or_path": "NepBERTa/NepBERTa",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "O",
+    "2": "I-LOC",
+    "3": "B-PER",
+    "4": "B-ORG",
+    "5": "I-PER",
+    "6": "I-ORG"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-ORG": 4,
+    "B-PER": 3,
+    "I-LOC": 2,
+    "I-ORG": 6,
+    "I-PER": 5,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_state": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-902-epoch-2/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:48bbdf90fdd6325828cb3cd00f8430e5e88dc3d609b0444a0f8f2c2340b74d2b
+size 435611468

checkpoint-902-epoch-2/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

checkpoint-902-epoch-2/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:71365293e6299304b928b74c83035acb0a489379183f7677334b0e9c229a1d31
+size 871342650

checkpoint-902-epoch-2/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:96f86d24852ba7173b3eede3843cc590412d49b970261ec0571103597d51a4a1
+size 1064