changed model

special_tokens_map.json

@@ -1,9 +1,6 @@
 {
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
   "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 256,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -230,16 +235,7 @@
     },
     {
       "id": 50277,
-      "content": "<|im_start|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 50278,
-      "content": "<|im_end|>",
+      "content": "<pad>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -3,7 +3,7 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "model_max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6fd8b171d9c3293f7b491bd99987013767cbf9f7f719831cb36476e8b3b7176
+oid sha256:bc9e1fde44399d127bf7e62feaeb5608f2344a3d4a2cd75ada116c02fbe20cd7
 size 3899