Model save

README.md

@@ -7,18 +7,18 @@ tags:
 - lora
 - generated_from_trainer
 model-index:
-- name: Sailor2-8B-Chat_sft_sg_values
+- name: Sailor2-8B-Chat_sft_sg_values_resp_split
   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. -->
 
-# Sailor2-8B-Chat_sft_sg_values
+# Sailor2-8B-Chat_sft_sg_values_resp_split
 
-This model is a fine-tuned version of [sail/Sailor2-8B-Chat](https://huggingface.co/sail/Sailor2-8B-Chat) on the sft_sg_values dataset.
+This model is a fine-tuned version of [sail/Sailor2-8B-Chat](https://huggingface.co/sail/Sailor2-8B-Chat) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1354
+- Loss: 0.1359
 
 ## Model description
 
@@ -52,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.4422        | 0.1869 | 250  | 0.2675          |
-| 0.1727        | 0.3738 | 500  | 0.1680          |
-| 0.1475        | 0.5607 | 750  | 0.1457          |
-| 0.1284        | 0.7477 | 1000 | 0.1373          |
-| 0.1066        | 0.9346 | 1250 | 0.1348          |
+| 0.3715        | 0.1710 | 250  | 0.2821          |
+| 0.1642        | 0.3419 | 500  | 0.1734          |
+| 0.1431        | 0.5129 | 750  | 0.1512          |
+| 0.1257        | 0.6839 | 1000 | 0.1415          |
+| 0.1281        | 0.8548 | 1250 | 0.1359          |
 
 
 ### Framework versions