Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
+  "_name_or_path": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 4864,
   "max_position_embeddings": 32768,
-  "max_window_layers": 21,
+  "max_window_layers": 24,
   "model_type": "qwen2",
   "num_attention_heads": 14,
   "num_hidden_layers": 24,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ee99008cb4e87a2f3491576cf084863f9065b9d990c4f56cba705c24325c2c1
+oid sha256:61890ffd63d404e99b32d294e3d29a00fd4500e8c6ed0425d414dfaabc704078
 size 1260367448

tokenizer_config.json

@@ -200,7 +200,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 131072,
+  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d547e70a2085971351f640a9aa1d8cbafc940de687b0e84caebdc776e867fc0
+oid sha256:a9a612c710f0bf70bf6aeb0a88d62d8be2de57cfebf04c4b04ccf6b14689f3c6
 size 8120