Training in progress, step 48

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -7,14 +7,14 @@
   "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 1536,
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 8960,
+  "intermediate_size": 4864,
   "max_position_embeddings": 32768,
   "max_window_layers": 21,
   "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 28,
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a505f90682ddc90903fbfe471186b6b4687d3692e310bbc8daed0f5cfc3b9be
-size 3087467144
+oid sha256:d5f25dc1bac1c03c0070e56c769df94309d68f9b4da7c2086c3a33be46323abb
+size 988097824

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4b9fa85f4f8edf11cce7f790d620d99161660705ee300bf084cd3d928c66f2
-size 7480
+oid sha256:ec1bbb164ee281a2f597db1457fef857aec56d974637d09fc7aba9202405918b
+size 6072