RLHF model of StarCoder

README.md

@@ -3,6 +3,8 @@ license: bigcode-openrail-m
 base_model: bigcode/tiny_starcoder_py
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: tinystarcoder-rlhf-model
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # tinystarcoder-rlhf-model
 
 This model is a fine-tuned version of [bigcode/tiny_starcoder_py](https://huggingface.co/bigcode/tiny_starcoder_py) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Accuracy: 0.0
 
 ## Model description
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f206842b394375ce8dd60f5edf39401997bfd0396500066ba579c06125b548
+oid sha256:8e0724433c3fd05e3d29d70c6b9628301756eb170194225ce7b6bca14b4415a7
 size 656652573

tokenizer_config.json

@@ -24,16 +24,8 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "max_length": 256,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152
 }