End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: DatPySci/pythia-1b-sft-full
 tags:
+- alignment-handbook
 - generated_from_trainer
+datasets:
+- DatPySci/SPIN_iter0
 model-index:
 - name: pythia-1b-kto-iter0-epoch1
   results: []
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # pythia-1b-kto-iter0-epoch1
 
-This model is a fine-tuned version of [DatPySci/pythia-1b-sft-full](https://huggingface.co/DatPySci/pythia-1b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [DatPySci/pythia-1b-sft-full](https://huggingface.co/DatPySci/pythia-1b-sft-full) on the DatPySci/SPIN_iter0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3355
 - Rewards/real: -0.0044

config.json

@@ -24,7 +24,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.1",
-  "use_cache": false,
+  "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50304
 }