Update README.md

README.md

@@ -4,33 +4,28 @@ tags:
 metrics:
 - accuracy
 model-index:
-- name: pygmalion-training
+- name: pygmalion-350m
   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. -->
+# pygmalion-350m
 
-# pygmalion-training
-
-This model is a fine-tuned version of [/notebooks/pygmalion/pygmalion-350m/](https://huggingface.co//notebooks/pygmalion/pygmalion-350m/) on an unknown dataset.
+This model is a fine-tuned version of [PygmalionAI/pygmalion-350m](https://huggingface.co/PygmalionAI/pygmalion-350m/) on a 2.4MB dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.2731
 - Accuracy: 0.5187
 
 ## Model description
 
-More information needed
-
-## Intended uses & limitations
+A proof-of-concept model based on PygmalionAI/pygmalion-350m, which was in turn based on OPT-350m.
 
-More information needed
+This model was fine-tuned purely for testing purposes.
 
-## Training and evaluation data
+## Fine-tuning process
 
-More information needed
+Fine-tuned on an A100-80GB with HF's `run_clm.py` script. It was run through 3 epochs with 8 batch size using 2.4MB dataset (split 75/25 between training and validation sets).
 
-## Training procedure
+## Training and evaluation data
 
 ### Training hyperparameters
 
@@ -43,10 +38,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3.0
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.27.0.dev0