alexandra-barker/roberta-lora-gender-bias

README.md

@@ -1,11 +1,9 @@
 ---
 library_name: peft
 license: mit
-base_model: roberta-large
+base_model: roberta-base
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: lora_finetuned_roberta_mlm
   results: []
@@ -16,10 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lora_finetuned_roberta_mlm
 
-This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
-- Accuracy: 0.0
 
 ## Model description
 
@@ -48,10 +45,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0           | 1.0   | 4500 | nan             | 0.0      |
-| 0.0           | 2.0   | 9000 | nan             | 0.0      |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0           | 1.0   | 3000 | nan             |
+| 0.0           | 2.0   | 6000 | nan             |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "roberta-large",
+  "base_model_name_or_path": "roberta-base",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "key",
     "query",
+    "key",
     "value"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cb234b212707ca5eb4efa16885f9fbcc961be7e2d054b25425d5d48af0167c
-size 4953240
+oid sha256:b154cce916dda8dd7b321018a1584074450bf7f6df37fef4beabc9202d6f67d8
+size 1863152