Initial release: German target-abroad NLI model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: mit
+base_model: MoritzLaurer/mDeBERTa-v3-base-mnli-xnli
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs_target_abroad_de_final
+  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. -->
+
+# outputs_target_abroad_de_final
+
+This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-mnli-xnli](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-mnli-xnli) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+- Accuracy Mc: 0.5
+- Precision Macro: 0.25
+- Recall Macro: 0.5
+- F1 Macro: 0.3333
+- Precision Weighted: 0.25
+- Recall Weighted: 0.5
+- F1 Weighted: 0.3333
+- Accuracy Bin: 0.5
+- Precision Bin: 0.0
+- Recall Bin: 0.0
+- F1 Bin: 0.0
+- Auc Bin: nan
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- 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
+- lr_scheduler_warmup_steps: 0.06
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy Mc | Precision Macro | Recall Macro | F1 Macro | Precision Weighted | Recall Weighted | F1 Weighted | Accuracy Bin | Precision Bin | Recall Bin | F1 Bin | Auc Bin |
+|:-------------:|:-----:|:----:|:---------------:|:-----------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|:------------:|:-------------:|:----------:|:------:|:-------:|
+| 0.0           | 1.0   | 490  | nan             | 0.5         | 0.25            | 0.5          | 0.3333   | 0.25               | 0.5             | 0.3333      | 0.5          | 0.0           | 0.0        | 0.0    | nan     |
+| 0.0           | 2.0   | 980  | nan             | 0.5         | 0.25            | 0.5          | 0.3333   | 0.25               | 0.5             | 0.3333      | 0.5          | 0.0           | 0.0        | 0.0    | nan     |
+| 0.0           | 3.0   | 1470 | nan             | 0.5         | 0.25            | 0.5          | 0.3333   | 0.25               | 0.5             | 0.3333      | 0.5          | 0.0           | 0.0        | 0.0    | nan     |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.9.0+cu126
+- Datasets 4.5.0
+- Tokenizers 0.22.2

best_threshold.json

@@ -0,0 +1 @@
+{"best_threshold": 0.5}

config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b8ba7c2ffae85b1a074667b8d12f632c4d023a504c84e94a456cbc767e6dd9
+size 557647822

test_per_outlet_summary.csv

@@ -0,0 +1,7 @@
+outlet,support,precision_entailment,recall_entailment,f1_entailment,precision_contradiction,recall_contradiction,f1_contradiction,accuracy,macro_f1,weighted_f1
+Bild,180,0.0,0.0,0.0,0.8666666666666667,1.0,0.9285714285714286,0.8666666666666667,0.4642857142857143,0.8047619047619048
+FAZ,188,0.0,0.0,0.0,0.7393617021276596,1.0,0.8501529051987767,0.7393617021276596,0.42507645259938837,0.6285704990565424
+SZ,180,0.0,0.0,0.0,0.8833333333333333,1.0,0.9380530973451328,0.8833333333333333,0.4690265486725664,0.828613569321534
+Spiegel,180,0.0,0.0,0.0,0.85,1.0,0.918918918918919,0.85,0.4594594594594595,0.7810810810810812
+Welt,180,0.0,0.0,0.0,0.7722222222222223,1.0,0.8714733542319749,0.7722222222222223,0.43573667711598746,0.6729710902124696
+Zeit,180,0.0,0.0,0.0,0.7444444444444445,1.0,0.8535031847133758,0.7444444444444445,0.4267515923566879,0.6353857041755131

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66269b2b7b04009c9e482ef6a99accee231b6822b83e7eb6df36626b61db43a
+size 16014878

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e753d4489257ff1204be1153c33469bdc9d99fa3dd0ff788ac4d6457fbe250a
+size 5201