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:e25a7f3c76b73098e4da6c762c26503c9b529aa986bc8537042151e29440f18f
-size 4903452008
+oid sha256:ac441a8c341009c2c2e7303b60809e021b4a4c85883d2883ec2cbc93bfba9c10
+size 4992602008

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8cacd63923186bf64ba25c12a70e42d78633857f0d1090d8299b4a3d0b6303
-size 4944309080
+oid sha256:95df3569d118243abac6a310ecac2a331f50831cb90bd0dd32c2842ca4078058
+size 4949553568

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea94940cc0f1d460ae8c6c5adf26cbea07225d8ecb1d52364319b361be59802
-size 4944309104
+oid sha256:9e4e1a18759efa122b503668d40c6506dd7edd37f92122f5023e26ee074fbc71
+size 4944309120

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f2092845a9dfbdca8ecf3ceefb424e0ed9e5ca0cfe71b35bc6997e02e94aca
-size 1714543944
+oid sha256:9df5b8499787780210223204855f70581c850bc707daf6a9b0c679a14f434f08
+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",