End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: mit
+base_model: facebook/xlm-roberta-xl
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: 5e-6_xlm-R-xl_Conspiracy_training_with_callbacks
+  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. -->
+
+# 5e-6_xlm-R-xl_Conspiracy_training_with_callbacks
+
+This model is a fine-tuned version of [facebook/xlm-roberta-xl](https://huggingface.co/facebook/xlm-roberta-xl) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0624
+- Macro F1: 0.9918
+- Micro F1: 0.9919
+- Accuracy: 0.9919
+
+## 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: 5e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Macro F1 | Micro F1 | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:--------:|
+| 0.6122        | 1.0   | 502   | 0.2712          | 0.9549   | 0.9559   | 0.9559   |
+| 0.1503        | 2.0   | 1004  | 0.1047          | 0.9741   | 0.9744   | 0.9744   |
+| 0.0508        | 3.0   | 1506  | 0.0734          | 0.9835   | 0.9837   | 0.9837   |
+| 0.0226        | 4.0   | 2008  | 0.0837          | 0.9811   | 0.9814   | 0.9814   |
+| 0.014         | 5.0   | 2510  | 0.0562          | 0.9882   | 0.9884   | 0.9884   |
+| 0.0014        | 6.0   | 3012  | 0.0514          | 0.9894   | 0.9895   | 0.9895   |
+| 0.0016        | 7.0   | 3514  | 0.0501          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0002        | 8.0   | 4016  | 0.0554          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0001        | 9.0   | 4518  | 0.0607          | 0.9906   | 0.9907   | 0.9907   |
+| 0.0001        | 10.0  | 5020  | 0.0856          | 0.9859   | 0.9861   | 0.9861   |
+| 0.0143        | 11.0  | 5522  | 0.0377          | 0.9929   | 0.9930   | 0.9930   |
+| 0.0001        | 12.0  | 6024  | 0.0538          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0001        | 13.0  | 6526  | 0.0568          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0012        | 14.0  | 7028  | 0.0582          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0           | 15.0  | 7530  | 0.0500          | 0.9929   | 0.9930   | 0.9930   |
+| 0.0001        | 16.0  | 8032  | 0.0649          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0           | 17.0  | 8534  | 0.0649          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0           | 18.0  | 9036  | 0.0648          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0009        | 19.0  | 9538  | 0.0621          | 0.9918   | 0.9919   | 0.9919   |
+| 0.0           | 20.0  | 10040 | 0.0624          | 0.9918   | 0.9919   | 0.9919   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea0ec310356b0c579f84908e536bf36b0d4b374b032d44c00210233e8a3763f
+size 4987059600

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d172be6eb434629e1df6cb77c4d8ba5ec5f586656c370a4dc0956458d823c668
+size 4930427680

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5be89a401ab9e319ceeb42b8488ea213ee3b4cf072b8216d7980710e4c4d6a
+size 4012548680

model.safetensors.index.json

@@ -0,0 +1,592 @@
+{
+  "metadata": {
+    "total_size": 13929963528
+  },
+  "weight_map": {
+    "classifier.dense.bias": "model-00003-of-00003.safetensors",
+    "classifier.dense.weight": "model-00003-of-00003.safetensors",
+    "classifier.out_proj.bias": "model-00003-of-00003.safetensors",
+    "classifier.out_proj.weight": "model-00003-of-00003.safetensors",
+    "roberta.embeddings.position_embeddings.weight": "model-00001-of-00003.safetensors",
+    "roberta.embeddings.token_type_embeddings.weight": "model-00001-of-00003.safetensors",
+    "roberta.embeddings.word_embeddings.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.0.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.0.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.1.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.10.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.10.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.11.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.12.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.13.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.14.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.15.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.16.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.17.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.18.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.19.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.2.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.2.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.20.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.20.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.21.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.22.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.23.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.23.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.23.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.23.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.23.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.24.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.25.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.26.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.27.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.28.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.29.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.3.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.3.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.30.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.30.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.31.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.32.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.33.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.34.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.attention.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.output.dense.bias": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.35.output.dense.weight": "model-00003-of-00003.safetensors",
+    "roberta.encoder.layer.4.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.4.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.5.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.6.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.7.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.attention.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "roberta.encoder.layer.7.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.7.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.8.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.attention.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.output.dense.bias": "model-00002-of-00003.safetensors",
+    "roberta.encoder.layer.9.output.dense.weight": "model-00002-of-00003.safetensors"
+  }
+}

runs/Jun28_17-41-29_hercules/events.out.tfevents.1719585691.hercules.3498431.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a79024806e1d8c64da7f1a148c406c62736106db0004d6eacca726a2f963cd
-size 17772
+oid sha256:e141202b8ef580a6b4c8b971dc30054a78b88d7a229f833778f71c8aae19e7b5
+size 18126