Training in progress, step 500

config.json

@@ -32,5 +32,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "use_cache": false,
-  "vocab_size": 129256
+  "vocab_size": 128256
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3e156ab72ce7d30ea6ff6e4f8334d51e05aa4d1285282095c474e052f76ee13
-size 4910391944
+oid sha256:c665ff6523d999ffd5396662b7b597e3caa3d3f8e448c87deb81efa0b0e4d73c
+size 4998767360

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c003aeaa77c3723f41add5ef3fafa45613336564580b27d39688544ef85fb589
+oid sha256:5cdf270300c32b98c2d23a9388d15b8945d176f11c5f354a32d20f19a1f8aee8
 size 4932808968

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f59bbb08c100c327ead33f8315bcf2a8c9d996c4dd3a684730e421f0ceba41d
-size 3020115584
+oid sha256:a12b72a109826ec19f41ea8045d7056c13067fed6d9537840d265c49746f2a82
+size 2919452168

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 12863287296
+    "total_size": 12850999296
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
@@ -124,7 +124,7 @@
     "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -240,7 +240,7 @@
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b2afbd0d4209cab99d1ef597fbfeb8596a726dbd4582c3d86056c0b76e0cef
-size 17393973
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42751b7fb5158167ea3bdff0c22b42c1500fbc84c3a8f5a1122ac3813b7bfb6
+oid sha256:e545a7ac38c3f3035905dd39cb53236f249d8df9c1454b040da5bd58c8b808a4
 size 5752