Training in progress, step 500

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: mit
+base_model: MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: Bert-Contact-NLI
+  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. -->
+
+# Bert-Contact-NLI
+
+This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8520
+- Model Preparation Time: 0.0063
+- Accuracy: 0.7222
+- Precision: 0.7086
+- Recall: 0.7284
+- F1: 0.7134
+- Ratio: 0.3611
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time | Accuracy | Precision | Recall | F1     | Ratio  |
+|:-------------:|:------:|:----:|:---------------:|:----------------------:|:--------:|:---------:|:------:|:------:|:------:|
+| No log        | 0.9895 | 47   | 0.8446          | 0.0063                 | 0.6142   | 0.6097    | 0.5667 | 0.5804 | 0.5340 |
+| No log        | 2.0    | 95   | 0.7677          | 0.0063                 | 0.6821   | 0.6774    | 0.6708 | 0.6636 | 0.3148 |
+| No log        | 2.9895 | 142  | 0.7705          | 0.0063                 | 0.7006   | 0.6919    | 0.6740 | 0.6805 | 0.4043 |
+| No log        | 4.0    | 190  | 0.7969          | 0.0063                 | 0.7006   | 0.6787    | 0.7153 | 0.6915 | 0.3951 |
+| No log        | 4.9474 | 235  | 0.8520          | 0.0063                 | 0.7222   | 0.7086    | 0.7284 | 0.7134 | 0.3611 |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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,
+  "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": "4.46.2",
+  "type_vocab_size": 0,
+  "vocab_size": 250511
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca11d0f156f923b452cab0a41de8782f6366394e0771f51318914216ed62d2d
+size 1113769068

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3527acd15170aa0096e3730ffaf1fb95b7bce821be6fc49ef50e1d5d72fddb7b
+size 5240