Training completed: lora mode

config.json

@@ -64,5 +64,5 @@
   "transformers_version": "4.57.3",
   "use_cache": true,
   "use_sliding_window": false,
-  "vocab_size": 192629
+  "vocab_size": 172149
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3c45ba437b6059fe3b3ae0881fa318194fc31d1c5f8e271416609efbe67dc4
-size 4903452008
+oid sha256:ceccc0f70ecdf4be84652f8bdf024f49f1f1e9c1332d0b0cddcd424d377cdf22
+size 4992602008

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6bd63fc9fe553a8392ad937054d5e85bc2d35c6420e7bac4f952393f2e65e5
-size 4944309080
+oid sha256:0a786e48e6e4d5709b557e09a2f8acec5a5ab8af0c5a136de14e3cb7947788ef
+size 4949553568

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300fe8091ba3b8c7b3e165ccc304fe82878c58690c104d088dfe537178f420e1
-size 4944309104
+oid sha256:fd0f2a39ba7bead2a97a64a8738f31e3bf3db155e7a65667a3b21fa7b1634853
+size 4944309120

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be393e0bc602cf6cfa7ab22c76247e4c57085484f43a894b33b6d967e6a74875
-size 1714543944
+oid sha256:c22e721da22b0b2fc0c3f1dc47e44fd4523738a999b7802259caf46f28ee21d7
+size 1410434256

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 4126642176,
-    "total_size": 16506568704
+    "total_parameters": 4074213376,
+    "total_size": 16296853504
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
@@ -126,11 +126,11 @@
     "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
@@ -153,12 +153,12 @@
     "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -280,11 +280,11 @@
     "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
@@ -293,15 +293,15 @@
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
@@ -368,11 +368,11 @@
     "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",