BramVanroy/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: 0.1172
+- F1: 0.7051
+- Precision: 0.6794
+- Recall: 0.7330
+- Accuracy: 0.9770
+
+## 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 |
+|:-------------:|:-------:|:----:|:---------------:|:------:|:---------:|:------:|:--------:|
+| 0.335         | 1.5385  | 20   | 0.2030          | 0.0331 | 0.3721    | 0.0173 | 0.9423   |
+| 0.1623        | 3.0769  | 40   | 0.1364          | 0.3033 | 0.2865    | 0.3222 | 0.9553   |
+| 0.0845        | 4.6154  | 60   | 0.1190          | 0.3897 | 0.3533    | 0.4346 | 0.9612   |
+| 0.0232        | 6.1538  | 80   | 0.1094          | 0.4755 | 0.4250    | 0.5395 | 0.9664   |
+| 0.0154        | 7.6923  | 100  | 0.1140          | 0.5512 | 0.5282    | 0.5762 | 0.9691   |
+| 0.0142        | 9.2308  | 120  | 0.1081          | 0.6218 | 0.5970    | 0.6486 | 0.9730   |
+| 0.0136        | 10.7692 | 140  | 0.1126          | 0.6316 | 0.6204    | 0.6432 | 0.9735   |
+| 0.0063        | 12.3077 | 160  | 0.1099          | 0.6684 | 0.6436    | 0.6951 | 0.9751   |
+| 0.0052        | 13.8462 | 180  | 0.1049          | 0.6788 | 0.6387    | 0.7243 | 0.9758   |
+| 0.0038        | 15.3846 | 200  | 0.1091          | 0.6677 | 0.6334    | 0.7059 | 0.9751   |
+| 0.001         | 16.9231 | 220  | 0.1117          | 0.6780 | 0.6467    | 0.7124 | 0.9758   |
+| 0.0008        | 18.4615 | 240  | 0.1120          | 0.6914 | 0.6604    | 0.7254 | 0.9764   |
+| 0.0014        | 20.0    | 260  | 0.1133          | 0.7060 | 0.6828    | 0.7308 | 0.9771   |
+| 0.0013        | 21.5385 | 280  | 0.1138          | 0.7009 | 0.6743    | 0.7297 | 0.9770   |
+| 0.0016        | 23.0769 | 300  | 0.1159          | 0.6996 | 0.6747    | 0.7265 | 0.9768   |
+| 0.0016        | 24.6154 | 320  | 0.1167          | 0.6997 | 0.6768    | 0.7243 | 0.9768   |
+| 0.0027        | 26.1538 | 340  | 0.1167          | 0.7010 | 0.6764    | 0.7276 | 0.9770   |
+| 0.0018        | 27.6923 | 360  | 0.1173          | 0.7045 | 0.6801    | 0.7308 | 0.9770   |
+| 0.0005        | 29.2308 | 380  | 0.1172          | 0.7051 | 0.6794    | 0.7330 | 0.9770   |
+
+
+### 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 sha256:34be165e9583d1a479db039813ffad427ccc5265651a3bdab6dc5ba42e587de6
+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:b25c98a4dfa3bb1e2044a746e3411b424833bb61cb3714e1cdbc2c5822434d29
+size 5841