Training in progress, step 112

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
+  "bos_token_id": 128002,
   "eos_token_id": 128001,
   "head_dim": 64,
   "hidden_act": "silu",
@@ -12,7 +12,7 @@
   "initializer_range": 0.041666666666666664,
   "intermediate_size": 1536,
   "is_llama_config": true,
-  "max_position_embeddings": 1024,
+  "max_position_embeddings": 512,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 9,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e78c20132b659c16742c52376f641a51e6b2726bc17c859d3fa229cd3ba9a6
+oid sha256:3dc6958f2b5435709e4011b6fa61af00ef9217f7203fc7c236af528d4baed6ef
 size 360189624

special_tokens_map.json

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

tokenizer_config.json

@@ -2057,7 +2057,7 @@
       "special": true
     }
   },
-  "bos_token": "<|begin_of_text|>",
+  "bos_token": "<|im_start|>",
   "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 sha256:6cc7a8230e6d9aca6d4d808f01a593a81a8e7b17530714b16dd6818420482ea4
+oid sha256:b524355529cb5c6ced08bdc825cfef9ef61f1a85fe77a2fe62399a5c592d1636
 size 6904