Training in progress, step 1

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f34b1c379adacc89864a9b7e338ad9ec47e2271c51d0bcd09354da301e8b61ef
-size 4985016320
+oid sha256:3869398fc48ad3f74d778aabfd9e5b83f093f09cdfa96e088eec70f6fe1b9e52
+size 4984643440

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7430ff52c6ddca21b8e9fa637ddee73a70bd574346a32a005a1b417e7b999c0b
-size 3447619392
+oid sha256:a140195f6364acf6031a60385b4e2bf3ed621c73e59eba31d44c0ec8f03623f8
+size 3351496424

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8432513024
+    "total_size": 8336017408
   },
   "weight_map": {
     "language_model.base_model.model.lm_head.weight": "model-00002-of-00002.safetensors",
@@ -101,11 +101,11 @@
     "language_model.base_model.model.model.layers.13.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -122,17 +122,17 @@
     "language_model.base_model.model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.base_model.model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.base_model.model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.q_proj.base_layer.bias": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.v_proj.base_layer.bias": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.q_proj.base_layer.bias": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.v_proj.base_layer.bias": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.base_model.model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.base_model.model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
@@ -454,10 +454,8 @@
     "language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "language_model.base_model.model.model.norm.weight": "model-00002-of-00002.safetensors",
-    "multi_modal_projector.linear_1.bias": "model-00001-of-00002.safetensors",
-    "multi_modal_projector.linear_1.weight": "model-00001-of-00002.safetensors",
-    "multi_modal_projector.linear_2.bias": "model-00001-of-00002.safetensors",
-    "multi_modal_projector.linear_2.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.bias": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.weight": "model-00001-of-00002.safetensors",
     "vision_projection.bias": "model-00002-of-00002.safetensors",
     "vision_projection.weight": "model-00002-of-00002.safetensors",
     "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e27a6bde262bc1c2d37f310e8df0005d3e473944cd31eef9c1e248cbc7f401a
+oid sha256:085b5fd0a60d0c9056adb9c5af1cc4306315bd51e59b6f7b7494b33cebac1737
 size 5624