End of training

README.md

@@ -2,9 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
+- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
+datasets:
+- sablo/HelpSteer_binarized
 base_model: sablo/sablo-pebble-mistral
 model-index:
 - name: sablo-pebble-mistral-dpo-lora-HelpSteer_binarized
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sablo-pebble-mistral-dpo-lora-HelpSteer_binarized
 
-This model is a fine-tuned version of [sablo/sablo-pebble-mistral](https://huggingface.co/sablo/sablo-pebble-mistral) on the None dataset.
+This model is a fine-tuned version of [sablo/sablo-pebble-mistral](https://huggingface.co/sablo/sablo-pebble-mistral) on the sablo/HelpSteer_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5371
 - Rewards/chosen: -0.9335

config.json

@@ -5,7 +5,7 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -22,5 +22,5 @@
   "torch_dtype": "float16",
   "transformers_version": "4.36.2",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 32002
 }