Training in progress, step 500

config.json

@@ -6,23 +6,23 @@
   "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 3584,
+  "hidden_size": 1536,
   "initializer_range": 0.02,
-  "intermediate_size": 18944,
+  "intermediate_size": 8960,
   "max_position_embeddings": 32768,
-  "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": 1000000.0,
-  "sliding_window": 131072,
-  "tie_word_embeddings": false,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
   "use_cache": false,
   "use_sliding_window": false,
-  "vocab_size": 152064
+  "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:740facf5fc512081e4a1060daf771bd61342f4b803e997b416951a38dcd029dc
+oid sha256:49f5521bef719ed8b7180d40a08d81104ab759329e440b32c1a185fedcba621a
 size 3087467144

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2498b8175f69bd3130933948a179dab1bf7ee7289114284e14c9c58dd6c9cb6
+oid sha256:4b096d93940dc9d46aa0236becc9adceb8294528db82759afbbb2ee92bf70951
 size 9336