stackoverflow_tag_classification/initial_run/deberta-v3-xsmall/overjoyed-flea-717

README.md

@@ -0,0 +1,54 @@
+---
+library_name: peft
+license: mit
+base_model: microsoft/deberta-v3-xsmall
+tags:
+- generated_from_trainer
+model-index:
+- name: overjoyed-flea-717
+  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. -->
+
+# overjoyed-flea-717
+
+This model is a fine-tuned version of [microsoft/deberta-v3-xsmall](https://huggingface.co/microsoft/deberta-v3-xsmall) on the None dataset.
+
+## 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: 6.778331903243384e-05
+- train_batch_size: 20
+- eval_batch_size: 20
+- seed: 2024
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu118
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "DebertaV2ForSequenceClassification",
+    "parent_library": "transformers.models.deberta_v2.modeling_deberta_v2"
+  },
+  "base_model_name_or_path": "microsoft/deberta-v3-xsmall",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 14,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "value_proj"
+  ],
+  "task_type": null,
+  "use_dora": true,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fcf3a13836d51d8de3c6bdde1f64b2effa70dd00beb7d14cd998f81be470917
+size 489904

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c948e4ea094fcd2088dbdaa9a19d281d95d75104b103e3cefc33b13236deb68
+size 5368