Training in progress, step 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -7,15 +7,15 @@
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 3584,
+  "hidden_size": 1536,
   "initializer_range": 0.02,
-  "intermediate_size": 18944,
+  "intermediate_size": 8960,
   "max_position_embeddings": 131072,
-  "max_window_layers": 28,
+  "max_window_layers": 21,
   "model_type": "qwen2",
-  "num_attention_heads": 28,
+  "num_attention_heads": 12,
   "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
+  "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000,
@@ -26,5 +26,5 @@
   "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,
-  "vocab_size": 152064
+  "vocab_size": 151936
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bea0a35dba47a078ac1750e001512a02837da37c70c3c806244efbe9efefc8
+size 3554214752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ccce9289009add9d2de091cf86638d65566b95b7034df81616d590d551a840
-size 7480
+oid sha256:28e1bf4b1deb14ddaea7982559222e8a093376be76b54fc5b61dc7a3bfad6c96
+size 7224