Update Reward Model

config.json

@@ -6,7 +6,7 @@
   ],
   "attn_pdrop": 0.1,
   "author": "Heewon Jeon(madjakarta@gmail.com)",
-  "bos_token_id": 51200,
+  "bos_token_id": 0,
   "created_date": "2021-04-28",
   "dtype": "float32",
   "embd_pdrop": 0.1,
@@ -29,7 +29,6 @@
   "n_layer": 12,
   "n_positions": 1024,
   "pad_token_id": 51200,
-  "problem_type": "regression",
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -45,7 +44,7 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.57.2",
+  "transformers_version": "4.57.3",
   "use_cache": true,
   "vocab_size": 51201
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f353d3182d5b99b2705c1cb534f40d32070a86c5f66be1d78a01a5da4962fc34
+oid sha256:7028f9aba04ba5aa38f9e8d8f49d69552d30712ed0db0ad5530e03b0de88ab09
 size 500677328

tokenizer_config.json

@@ -3014,8 +3014,12 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
+  "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546ebdf1c089a507e64f661ca19e7b3298dac9786fb18afaf980c6c9250ed6dc
+oid sha256:ca683a62f95130e9a73fe9d5c69c9c1a6e6ccc21ef226861ccaa5a97239d03fc
 size 5777