deberta-v3-small-autextification-adapter

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+datasets:
+- autextification2023
+metrics:
+- accuracy
+model-index:
+- name: deberta-v3-small-autextification-adapter
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# deberta-v3-small-autextification-adapter
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the autextification2023 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Accuracy: 0.4969
+
+## 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: 0.0001
+- 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_steps: 500
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6967        | 1.0   | 3808 | 0.6931          | 0.4969   |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-small",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value_proj",
+    "query_proj"
+  ],
+  "task_type": "SEQ_CLS"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c417eaba8a8c570a3f0ab6cc9e612ca6416ab7d7a1b6d855cc0dfa0508ecd3d6
+size 1189552

logs/events.out.tfevents.1699282242.69dd0232d482.649.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d02cdbbcfc97df0737f421ed9d5c3d04f0caff6ccd06626cd40e1bd38f96f0
+size 184980

logs/events.out.tfevents.1699282785.69dd0232d482.649.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6affcb175ea546403e522171ab4fc77a01c7d624e112d12e4b5b98f2db97e03
+size 411

logs/events.out.tfevents.1699285132.69dd0232d482.649.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091a8bb6a8e7803303975c21e358f147b003d5ffb3c05dbaa67f4a6d273c1920
+size 346

logs/events.out.tfevents.1699287710.69dd0232d482.649.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454dd279b41c02230b66c291295daf3b4b5aa7907aee2913e4c5f93fbac709b7
+size 64700

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81115ffe776dd80a77e053dd8cfd3b46c5aa4ffc2a6d7e35331aaedc34ed7b1e
+size 4600