Update README.md

README.md

@@ -11,26 +11,24 @@ model-index:
 <!-- 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. -->
 
-# 2.7b
+# Neo-VN-2.7B
 
-This model is a fine-tuned version of [/notebooks/convogpt/gpt-neo-2.7B/](https://huggingface.co//notebooks/convogpt/gpt-neo-2.7B/) on an unknown dataset.
+Work-in-progress. Current version is very bad.
+
+This model is a fine-tuned version of [huggingface.co/EleutherAI/opt-neo-2.7b](https://huggingface.co//notebooks/convogpt/gpt-neo-2.7B/) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.4748
 - Accuracy: 0.4671
 
 ## Model description
 
-More information needed
-
-## Intended uses & limitations
+Neo-VN-2.7B is a transformer model based on EleutherAI's replication of GPT-3.
 
-More information needed
 
-## Training and evaluation data
+## Training procedure
 
-More information needed
+Fine-tuned on 233MB of conversational data.
 
-## Training procedure
 
 ### Training hyperparameters
 
@@ -49,7 +47,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Accuracy | Validation Loss |
 |:-------------:|:-----:|:-----:|:--------:|:---------------:|
-| 2.3941        | 0.48  | 10000 | 0.4671   | 2.4748          |
+| 2.3941        | 1  | 20460 | 0.4671   | 2.4748          |
 
 
 ### Framework versions