Training in progress, step 100

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "up_proj",
+    "v_proj",
     "o_proj",
-    "q_proj",
     "down_proj",
     "k_proj",
-    "v_proj"
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5c1efe03debfab4d72231305a8225462c3ba6f0ac4fbc937a16eea53eb773e
+oid sha256:a062a62b2c1d0d0733416ec3db7dbc139d5a0f7241a41ac0b548e778aec21f9c
 size 80792456

config.json

@@ -1,36 +1,31 @@
 {
   "architectures": [
-    "Phi3ForCausalLM"
+    "Qwen3ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
-    "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
-  },
-  "bos_token_id": 1,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 32000,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 3072,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 4096,
-  "model_type": "phi3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "original_max_position_embeddings": 4096,
-  "pad_token_id": 32000,
-  "partial_rotary_factor": 1.0,
-  "resid_pdrop": 0.0,
-  "rms_norm_eps": 1e-05,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "sliding_window": 2047,
-  "tie_word_embeddings": false,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "use_cache": true,
-  "vocab_size": 32064
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185aaed5b2c443acb22ff89d1c8491be5a70912edeef68cf3222edf1609e59dc
+oid sha256:83936892210c3f2bb5d1c76118aa98f6c70c255f9c72f434924b1450a905a558
 size 2384234968

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945bb08df17e6c8cf21b4a4c6fa73fdff9ad0bd27cd2aef359c91f2caea5514f
+oid sha256:cc947399dcd680bf8b06b3d76a5c6a23f124141676353a0c105919a191a2a220
 size 6033