Training in progress, epoch 1

config.json

@@ -8,20 +8,20 @@
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 12288,
+  "intermediate_size": 6144,
   "max_position_embeddings": 40960,
-  "max_window_layers": 36,
+  "max_window_layers": 28,
   "model_type": "qwen3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "sliding_window": null,
-  "tie_word_embeddings": false,
+  "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
   "use_cache": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bac6f9e9b2d32aedb1033825e58ed39986360ea26aa557961d950be4dd2884a
+oid sha256:efb2c61fb59ee07aa1b1c925190b0ec0fe0c92f1cc060b4f9221956313e8cd95
 size 4063515640

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7fc1d15fe5d1341c14e5ae02eea1b3db57e3bd90adf2d018894356131d8b0c2
+oid sha256:6bc5d0b8325f505173b18def94bdef6e9b86ab54a16d1d285e3cb59f8e4653f1
 size 7992