End of training

README.md

@@ -1,9 +1,13 @@
 ---
 base_model: btherien/410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_sft-full
 tags:
+- alignment-handbook
+- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: 410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_dpo-full
   results: []
@@ -14,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_dpo-full
 
-This model is a fine-tuned version of [btherien/410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_sft-full](https://huggingface.co/btherien/410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_sft-full) on the None dataset.
+This model is a fine-tuned version of [btherien/410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_sft-full](https://huggingface.co/btherien/410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6500
 - Rewards/chosen: -0.4023

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50304
 }