End of training

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+base_model: microsoft/deberta-v2-xxlarge
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [microsoft/deberta-v2-xxlarge](https://huggingface.co/microsoft/deberta-v2-xxlarge) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7550
+- Accuracy: 0.6786
+- Macro F1: 0.6773
+
+## 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: 3e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Macro F1 |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|
+| 1.6193        | 0.2286 | 100  | 1.6018          | 0.2184   | 0.1357   |
+| 1.305         | 0.4571 | 200  | 0.9285          | 0.591    | 0.5953   |
+| 0.8772        | 0.6857 | 300  | 0.8561          | 0.6256   | 0.6250   |
+| 0.8552        | 0.9143 | 400  | 0.8332          | 0.6511   | 0.6473   |
+| 0.798         | 1.1429 | 500  | 0.8210          | 0.6641   | 0.6579   |
+| 0.7713        | 1.3714 | 600  | 0.7759          | 0.666    | 0.6669   |
+| 0.7758        | 1.6    | 700  | 0.7634          | 0.6667   | 0.6615   |
+| 0.7442        | 1.8286 | 800  | 0.7960          | 0.6613   | 0.6590   |
+| 0.752         | 2.0571 | 900  | 0.7715          | 0.667    | 0.6690   |
+| 0.7123        | 2.2857 | 1000 | 0.7600          | 0.6696   | 0.6698   |
+| 0.7066        | 2.5143 | 1100 | 0.7599          | 0.6701   | 0.6684   |
+| 0.7024        | 2.7429 | 1200 | 0.7551          | 0.6757   | 0.6763   |
+| 0.7117        | 2.9714 | 1300 | 0.7550          | 0.6786   | 0.6773   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.2
+- Datasets 2.19.0
+- Tokenizers 0.19.1

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416ebc6dfc285dfeabb8764599064b3cdc7dc919699d0c09b71740e1186e68b7
+size 4999085984

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f039c09f76e7a055ae0b842bd6bb3dd1cce220b3e0173f6b7ae6c07c513c7d
+size 1268684852

model.safetensors.index.json

@@ -0,0 +1,789 @@
+{
+  "metadata": {
+    "total_size": 6267672596
+  },
+  "weight_map": {
+    "classifier.bias": "model-00002-of-00002.safetensors",
+    "classifier.weight": "model-00002-of-00002.safetensors",
+    "deberta.embeddings.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.embeddings.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.conv.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.conv.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.conv.conv.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.conv.conv.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.rel_embeddings.weight": "model-00002-of-00002.safetensors",
+    "pooler.dense.bias": "model-00002-of-00002.safetensors",
+    "pooler.dense.weight": "model-00002-of-00002.safetensors"
+  }
+}