Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-EMAIL",
+    "1": "B-ID_NUM",
+    "2": "B-NAME_STUDENT",
+    "3": "B-PHONE_NUM",
+    "4": "B-STREET_ADDRESS",
+    "5": "B-URL_PERSONAL",
+    "6": "B-USERNAME",
+    "7": "I-ID_NUM",
+    "8": "I-NAME_STUDENT",
+    "9": "I-PHONE_NUM",
+    "10": "I-STREET_ADDRESS",
+    "11": "I-URL_PERSONAL",
+    "12": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EMAIL": 0,
+    "B-ID_NUM": 1,
+    "B-NAME_STUDENT": 2,
+    "B-PHONE_NUM": 3,
+    "B-STREET_ADDRESS": 4,
+    "B-URL_PERSONAL": 5,
+    "B-USERNAME": 6,
+    "I-ID_NUM": 7,
+    "I-NAME_STUDENT": 8,
+    "I-PHONE_NUM": 9,
+    "I-STREET_ADDRESS": 10,
+    "I-URL_PERSONAL": 11,
+    "O": 12
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63de2a96d4892c8383dadf29e4784bdf800b080ee375a9c8b36bedd0b04454b7
+size 735390572

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca58faf2e3d2b65cdc19d5d59f0ecc90ecfd96af963b6cfc8c73d33efe5da78
+size 1470899578

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8294981a71ea6c8dd92e73adacfc7a7bb92162b8de9dfdbdc49767734278892
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595958271b4b590c4c993cf95248164452f391418b84d72496acc7def9841d8a
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "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": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6246719160104988,
+  "eval_steps": 250,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.78477690288714e-06,
+      "loss": 0.1544,
+      "step": 250
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.999459669335349,
+      "eval_f1": 0.9975467196003112,
+      "eval_loss": 0.0030309667345136404,
+      "eval_precision": 0.9982040980913408,
+      "eval_recall": 0.9968902063873818,
+      "eval_runtime": 60.0322,
+      "eval_samples_per_second": 86.853,
+      "eval_steps_per_second": 2.715,
+      "step": 250
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 9.566054243219597e-06,
+      "loss": 0.0031,
+      "step": 500
+    },
+    {
+      "epoch": 1.31,
+      "eval_accuracy": 0.9995871243828395,
+      "eval_f1": 0.9981561132582728,
+      "eval_loss": 0.0018471144139766693,
+      "eval_precision": 0.9981616961615619,
+      "eval_recall": 0.9981505304174357,
+      "eval_runtime": 60.151,
+      "eval_samples_per_second": 86.682,
+      "eval_steps_per_second": 2.71,
+      "step": 500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 9.347331583552057e-06,
+      "loss": 0.0018,
+      "step": 750
+    },
+    {
+      "epoch": 1.97,
+      "eval_accuracy": 0.9996776715980452,
+      "eval_f1": 0.9985476091483844,
+      "eval_loss": 0.0015591623960062861,
+      "eval_precision": 0.9985718121205793,
+      "eval_recall": 0.9985234073494044,
+      "eval_runtime": 60.3172,
+      "eval_samples_per_second": 86.443,
+      "eval_steps_per_second": 2.702,
+      "step": 750
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 9.128608923884515e-06,
+      "loss": 0.0013,
+      "step": 1000
+    },
+    {
+      "epoch": 2.62,
+      "eval_accuracy": 0.9997411530695752,
+      "eval_f1": 0.9989185399543549,
+      "eval_loss": 0.0013504341477528214,
+      "eval_precision": 0.99902658068751,
+      "eval_recall": 0.9988105225870202,
+      "eval_runtime": 60.0207,
+      "eval_samples_per_second": 86.87,
+      "eval_steps_per_second": 2.716,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 11430,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 250,
+  "total_flos": 6990933228122340.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af76902d686cb65222b7f31ca87aca8cc76e2e17cc1a2218a8e06647fd10d5f3
+size 4664