prinsINT/deberta-v3-base-uner-down200

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/deberta-v3-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+- accuracy
+model-index:
+- name: deberta-v3-base-uner-down200
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# deberta-v3-base-uner-down200
+
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1055
+- F1: 0.6677
+- Precision: 0.6249
+- Recall: 0.7168
+- Accuracy: 0.9765
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2.5e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | F1     | Precision | Recall | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:------:|:---------:|:------:|:--------:|
+| 0.0587        | 1.5385  | 20   | 0.2010          | 0.0    | 0.0       | 0.0    | 0.9422   |
+| 0.0916        | 3.0769  | 40   | 0.1425          | 0.2535 | 0.3108    | 0.2141 | 0.9535   |
+| 0.0571        | 4.6154  | 60   | 0.1251          | 0.3194 | 0.3126    | 0.3265 | 0.9594   |
+| 0.0289        | 6.1538  | 80   | 0.1168          | 0.4129 | 0.3915    | 0.4368 | 0.9651   |
+| 0.0144        | 7.6923  | 100  | 0.1160          | 0.4527 | 0.4473    | 0.4584 | 0.9671   |
+| 0.0041        | 9.2308  | 120  | 0.1040          | 0.5464 | 0.4822    | 0.6303 | 0.9713   |
+| 0.0036        | 10.7692 | 140  | 0.1011          | 0.5780 | 0.5410    | 0.6205 | 0.9728   |
+| 0.0026        | 12.3077 | 160  | 0.1000          | 0.6219 | 0.5760    | 0.6757 | 0.9743   |
+| 0.0025        | 13.8462 | 180  | 0.1004          | 0.6285 | 0.5867    | 0.6768 | 0.9749   |
+| 0.003         | 15.3846 | 200  | 0.1018          | 0.6373 | 0.5989    | 0.6811 | 0.9753   |
+| 0.0032        | 16.9231 | 220  | 0.1034          | 0.6484 | 0.6117    | 0.6897 | 0.9758   |
+| 0.0022        | 18.4615 | 240  | 0.1035          | 0.6529 | 0.6105    | 0.7016 | 0.9760   |
+| 0.0002        | 20.0    | 260  | 0.1044          | 0.6552 | 0.6154    | 0.7005 | 0.9763   |
+| 0.0021        | 21.5385 | 280  | 0.1046          | 0.6629 | 0.6240    | 0.7070 | 0.9767   |
+| 0.0029        | 23.0769 | 300  | 0.1041          | 0.6643 | 0.6215    | 0.7135 | 0.9764   |
+| 0.0043        | 24.6154 | 320  | 0.1046          | 0.6663 | 0.6234    | 0.7157 | 0.9765   |
+| 0.0012        | 26.1538 | 340  | 0.1052          | 0.6673 | 0.6251    | 0.7157 | 0.9765   |
+| 0.0014        | 27.6923 | 360  | 0.1054          | 0.6680 | 0.6255    | 0.7168 | 0.9765   |
+| 0.0009        | 29.2308 | 380  | 0.1055          | 0.6677 | 0.6249    | 0.7168 | 0.9765   |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu128
+- Datasets 4.3.0
+- Tokenizers 0.22.1

added_tokens.json

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

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "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,
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a196120f89a1f08ab3358b82b6dd1ab2faa8fe5ca6f91d3e0d8087db5638c23
+size 735372116

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 +1,60 @@
+{
+  "add_prefix_space": false,
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "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"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1f56d57d2afc830f871ae1baee2c5a8779ca9ccc6b31253e04bdf79564cbdf
+size 5841