Training in progress, step 200

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128002,
+  "bos_token_id": 128000,
   "eos_token_id": 128001,
   "head_dim": 64,
   "hidden_act": "silu",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc6958f2b5435709e4011b6fa61af00ef9217f7203fc7c236af528d4baed6ef
+oid sha256:bf39ad430e97d5f9cd3db6c4485b8a75e1a17181b89104e703813f737a06d7df
 size 360189624

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
   "bos_token": {
-    "content": "<|im_start|>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -2057,7 +2057,7 @@
       "special": true
     }
   },
-  "bos_token": "<|im_start|>",
+  "bos_token": "<|begin_of_text|>",
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b524355529cb5c6ced08bdc825cfef9ef61f1a85fe77a2fe62399a5c592d1636
+oid sha256:dbbb75f69f02d5107fc7f040f1040649adad2f3b9603bd2170481b88204ef880
 size 6904