Upload continuous evaluation checkpoints, batch 14

.gitattributes

@@ -140,3 +140,5 @@ continuous/qwen3/mc2_b16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=l
 continuous/qwen3/mc2_b32_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 continuous/qwen3/mc2_b32_224_mt5/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 continuous/qwen3/mc2_b32_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+continuous/qwen3/mc2_g14_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+continuous/qwen3/mc2_g14_378/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text

continuous/qwen3/mc2_g14_224/finetune/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda72ea18dd04f12511e6e05d7ef19eedf9ddd4539e79dfcc5c8d087482e1687
+size 4999403240

continuous/qwen3/mc2_g14_224/finetune/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e14a05b6c167a1a8ad4a8178cf89e26f866061d27a6cbbd889cc0843bb866fd
+size 2784437848

continuous/qwen3/mc2_g14_224/finetune/model.safetensors.index.json

@@ -0,0 +1,906 @@
+{
+  "metadata": {
+    "total_size": 7783719424
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.class_embedding": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_post.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_post.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_pre.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_pre.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.positional_embedding": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.proj": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

continuous/qwen3/mc2_g14_224/finetune/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

continuous/qwen3/mc2_g14_224/finetune/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

continuous/qwen3/mc2_g14_224/finetune/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

continuous/qwen3/mc2_g14_224/finetune/trainer_state.json

@@ -0,0 +1,1856 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999037443449803,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850226200789296,
+      "grad_norm": 19.635221481323242,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 2.6271,
+      "step": 10
+    },
+    {
+      "epoch": 0.007700452401578592,
+      "grad_norm": 7.1385273933410645,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.9523,
+      "step": 20
+    },
+    {
+      "epoch": 0.01155067860236789,
+      "grad_norm": 4.291745662689209,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.4808,
+      "step": 30
+    },
+    {
+      "epoch": 0.015400904803157185,
+      "grad_norm": 1.2537659406661987,
+      "learning_rate": 5e-06,
+      "loss": 1.163,
+      "step": 40
+    },
+    {
+      "epoch": 0.019251131003946483,
+      "grad_norm": 0.8146989345550537,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 1.0567,
+      "step": 50
+    },
+    {
+      "epoch": 0.02310135720473578,
+      "grad_norm": 0.4013882279396057,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.9701,
+      "step": 60
+    },
+    {
+      "epoch": 0.026951583405525073,
+      "grad_norm": 0.3049355149269104,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.9216,
+      "step": 70
+    },
+    {
+      "epoch": 0.03080180960631437,
+      "grad_norm": 0.2979246973991394,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.9163,
+      "step": 80
+    },
+    {
+      "epoch": 0.034652035807103666,
+      "grad_norm": 0.27478092908859253,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.884,
+      "step": 90
+    },
+    {
+      "epoch": 0.038502262007892966,
+      "grad_norm": 0.25521355867385864,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.8653,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235248820868226,
+      "grad_norm": 0.26194027066230774,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.8468,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620271440947156,
+      "grad_norm": 0.2672634422779083,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8566,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005294061026085,
+      "grad_norm": 0.25442078709602356,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.8513,
+      "step": 130
+    },
+    {
+      "epoch": 0.053903166811050146,
+      "grad_norm": 0.2796657383441925,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.8466,
+      "step": 140
+    },
+    {
+      "epoch": 0.057753393011839446,
+      "grad_norm": 0.2887614369392395,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.8308,
+      "step": 150
+    },
+    {
+      "epoch": 0.06160361921262874,
+      "grad_norm": 0.2587645351886749,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.8365,
+      "step": 160
+    },
+    {
+      "epoch": 0.06545384541341803,
+      "grad_norm": 0.2239449918270111,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.8366,
+      "step": 170
+    },
+    {
+      "epoch": 0.06930407161420733,
+      "grad_norm": 0.2578524053096771,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.8641,
+      "step": 180
+    },
+    {
+      "epoch": 0.07315429781499663,
+      "grad_norm": 0.2639698386192322,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.853,
+      "step": 190
+    },
+    {
+      "epoch": 0.07700452401578593,
+      "grad_norm": 0.27230578660964966,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.8426,
+      "step": 200
+    },
+    {
+      "epoch": 0.08085475021657522,
+      "grad_norm": 0.25428929924964905,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.8377,
+      "step": 210
+    },
+    {
+      "epoch": 0.08470497641736452,
+      "grad_norm": 0.25386059284210205,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.8231,
+      "step": 220
+    },
+    {
+      "epoch": 0.08855520261815382,
+      "grad_norm": 0.2505797743797302,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.8247,
+      "step": 230
+    },
+    {
+      "epoch": 0.09240542881894312,
+      "grad_norm": 0.2551997900009155,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.819,
+      "step": 240
+    },
+    {
+      "epoch": 0.0962556550197324,
+      "grad_norm": 0.2871937155723572,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.8361,
+      "step": 250
+    },
+    {
+      "epoch": 0.1001058812205217,
+      "grad_norm": 0.24424192309379578,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.8307,
+      "step": 260
+    },
+    {
+      "epoch": 0.103956107421311,
+      "grad_norm": 0.24709659814834595,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.8191,
+      "step": 270
+    },
+    {
+      "epoch": 0.10780633362210029,
+      "grad_norm": 0.24536557495594025,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.8169,
+      "step": 280
+    },
+    {
+      "epoch": 0.11165655982288959,
+      "grad_norm": 0.24705995619297028,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.8358,
+      "step": 290
+    },
+    {
+      "epoch": 0.11550678602367889,
+      "grad_norm": 0.23462027311325073,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.7969,
+      "step": 300
+    },
+    {
+      "epoch": 0.11935701222446819,
+      "grad_norm": 0.24313302338123322,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.8096,
+      "step": 310
+    },
+    {
+      "epoch": 0.12320723842525748,
+      "grad_norm": 0.24251189827919006,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.8091,
+      "step": 320
+    },
+    {
+      "epoch": 0.12705746462604678,
+      "grad_norm": 0.25933805108070374,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.8074,
+      "step": 330
+    },
+    {
+      "epoch": 0.13090769082683607,
+      "grad_norm": 0.24107322096824646,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.8191,
+      "step": 340
+    },
+    {
+      "epoch": 0.13475791702762538,
+      "grad_norm": 0.256486713886261,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.8192,
+      "step": 350
+    },
+    {
+      "epoch": 0.13860814322841467,
+      "grad_norm": 0.2413967251777649,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.8052,
+      "step": 360
+    },
+    {
+      "epoch": 0.14245836942920398,
+      "grad_norm": 0.24443666636943817,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.8305,
+      "step": 370
+    },
+    {
+      "epoch": 0.14630859562999327,
+      "grad_norm": 0.24549005925655365,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.7904,
+      "step": 380
+    },
+    {
+      "epoch": 0.15015882183078255,
+      "grad_norm": 0.24988967180252075,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.795,
+      "step": 390
+    },
+    {
+      "epoch": 0.15400904803157187,
+      "grad_norm": 0.23765647411346436,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.7959,
+      "step": 400
+    },
+    {
+      "epoch": 0.15785927423236115,
+      "grad_norm": 0.24149486422538757,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.7842,
+      "step": 410
+    },
+    {
+      "epoch": 0.16170950043315044,
+      "grad_norm": 0.2566930055618286,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.8017,
+      "step": 420
+    },
+    {
+      "epoch": 0.16555972663393975,
+      "grad_norm": 0.24500906467437744,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.792,
+      "step": 430
+    },
+    {
+      "epoch": 0.16940995283472904,
+      "grad_norm": 0.24452614784240723,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.7864,
+      "step": 440
+    },
+    {
+      "epoch": 0.17326017903551832,
+      "grad_norm": 0.24844875931739807,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.7758,
+      "step": 450
+    },
+    {
+      "epoch": 0.17711040523630764,
+      "grad_norm": 0.23634256422519684,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.7821,
+      "step": 460
+    },
+    {
+      "epoch": 0.18096063143709692,
+      "grad_norm": 0.23875758051872253,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.7872,
+      "step": 470
+    },
+    {
+      "epoch": 0.18481085763788624,
+      "grad_norm": 0.2569423019886017,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.7847,
+      "step": 480
+    },
+    {
+      "epoch": 0.18866108383867553,
+      "grad_norm": 0.22347091138362885,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.7715,
+      "step": 490
+    },
+    {
+      "epoch": 0.1925113100394648,
+      "grad_norm": 0.2286008894443512,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.7799,
+      "step": 500
+    },
+    {
+      "epoch": 0.19636153624025413,
+      "grad_norm": 0.2413949817419052,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.7723,
+      "step": 510
+    },
+    {
+      "epoch": 0.2002117624410434,
+      "grad_norm": 0.2387804090976715,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.8022,
+      "step": 520
+    },
+    {
+      "epoch": 0.2040619886418327,
+      "grad_norm": 0.24583588540554047,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.7728,
+      "step": 530
+    },
+    {
+      "epoch": 0.207912214842622,
+      "grad_norm": 0.25096479058265686,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.7868,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117624410434113,
+      "grad_norm": 0.23305988311767578,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.7913,
+      "step": 550
+    },
+    {
+      "epoch": 0.21561266724420058,
+      "grad_norm": 0.2326512485742569,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.7923,
+      "step": 560
+    },
+    {
+      "epoch": 0.2194628934449899,
+      "grad_norm": 0.25948092341423035,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.7965,
+      "step": 570
+    },
+    {
+      "epoch": 0.22331311964577918,
+      "grad_norm": 0.24989984929561615,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.7811,
+      "step": 580
+    },
+    {
+      "epoch": 0.2271633458465685,
+      "grad_norm": 0.2502538859844208,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.7879,
+      "step": 590
+    },
+    {
+      "epoch": 0.23101357204735778,
+      "grad_norm": 0.2289857566356659,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.7799,
+      "step": 600
+    },
+    {
+      "epoch": 0.23486379824814707,
+      "grad_norm": 0.24947670102119446,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.7999,
+      "step": 610
+    },
+    {
+      "epoch": 0.23871402444893638,
+      "grad_norm": 0.2298833280801773,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.7854,
+      "step": 620
+    },
+    {
+      "epoch": 0.24256425064972567,
+      "grad_norm": 0.2408597469329834,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.8005,
+      "step": 630
+    },
+    {
+      "epoch": 0.24641447685051496,
+      "grad_norm": 0.22736148536205292,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.7934,
+      "step": 640
+    },
+    {
+      "epoch": 0.25026470305130427,
+      "grad_norm": 0.21721486747264862,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.7487,
+      "step": 650
+    },
+    {
+      "epoch": 0.25411492925209356,
+      "grad_norm": 0.24846772849559784,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.7803,
+      "step": 660
+    },
+    {
+      "epoch": 0.25796515545288284,
+      "grad_norm": 0.26426631212234497,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.7906,
+      "step": 670
+    },
+    {
+      "epoch": 0.26181538165367213,
+      "grad_norm": 0.23222801089286804,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7582,
+      "step": 680
+    },
+    {
+      "epoch": 0.26566560785446147,
+      "grad_norm": 0.234327495098114,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.7811,
+      "step": 690
+    },
+    {
+      "epoch": 0.26951583405525076,
+      "grad_norm": 0.23296283185482025,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.7884,
+      "step": 700
+    },
+    {
+      "epoch": 0.27336606025604004,
+      "grad_norm": 0.2282010316848755,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.7697,
+      "step": 710
+    },
+    {
+      "epoch": 0.27721628645682933,
+      "grad_norm": 0.21689842641353607,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.7729,
+      "step": 720
+    },
+    {
+      "epoch": 0.2810665126576186,
+      "grad_norm": 0.23348668217658997,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.7759,
+      "step": 730
+    },
+    {
+      "epoch": 0.28491673885840796,
+      "grad_norm": 0.237444669008255,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.7637,
+      "step": 740
+    },
+    {
+      "epoch": 0.28876696505919724,
+      "grad_norm": 0.22143065929412842,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.7669,
+      "step": 750
+    },
+    {
+      "epoch": 0.29261719125998653,
+      "grad_norm": 0.2264387458562851,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.757,
+      "step": 760
+    },
+    {
+      "epoch": 0.2964674174607758,
+      "grad_norm": 0.2230641394853592,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.7758,
+      "step": 770
+    },
+    {
+      "epoch": 0.3003176436615651,
+      "grad_norm": 0.22873511910438538,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.7726,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041678698623544,
+      "grad_norm": 0.24240389466285706,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.7555,
+      "step": 790
+    },
+    {
+      "epoch": 0.30801809606314373,
+      "grad_norm": 0.2213539034128189,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.7822,
+      "step": 800
+    },
+    {
+      "epoch": 0.311868322263933,
+      "grad_norm": 0.23885473608970642,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.7737,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157185484647223,
+      "grad_norm": 0.22374247014522552,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.7669,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195687746655116,
+      "grad_norm": 0.2295852154493332,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.754,
+      "step": 830
+    },
+    {
+      "epoch": 0.3234190008663009,
+      "grad_norm": 0.22742396593093872,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.7599,
+      "step": 840
+    },
+    {
+      "epoch": 0.3272692270670902,
+      "grad_norm": 0.23195599019527435,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.7738,
+      "step": 850
+    },
+    {
+      "epoch": 0.3311194532678795,
+      "grad_norm": 0.22870472073554993,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.7536,
+      "step": 860
+    },
+    {
+      "epoch": 0.3349696794686688,
+      "grad_norm": 0.22946125268936157,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.7648,
+      "step": 870
+    },
+    {
+      "epoch": 0.3388199056694581,
+      "grad_norm": 0.22306060791015625,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.7609,
+      "step": 880
+    },
+    {
+      "epoch": 0.34267013187024736,
+      "grad_norm": 0.22692959010601044,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7616,
+      "step": 890
+    },
+    {
+      "epoch": 0.34652035807103665,
+      "grad_norm": 0.21292544901371002,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.7622,
+      "step": 900
+    },
+    {
+      "epoch": 0.350370584271826,
+      "grad_norm": 0.23139427602291107,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.7516,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542208104726153,
+      "grad_norm": 0.24413461983203888,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7541,
+      "step": 920
+    },
+    {
+      "epoch": 0.35807103667340456,
+      "grad_norm": 0.23868894577026367,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7389,
+      "step": 930
+    },
+    {
+      "epoch": 0.36192126287419385,
+      "grad_norm": 0.2586914896965027,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.7749,
+      "step": 940
+    },
+    {
+      "epoch": 0.36577148907498314,
+      "grad_norm": 0.22806251049041748,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.7886,
+      "step": 950
+    },
+    {
+      "epoch": 0.3696217152757725,
+      "grad_norm": 0.24085251986980438,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.7731,
+      "step": 960
+    },
+    {
+      "epoch": 0.37347194147656176,
+      "grad_norm": 0.23462499678134918,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7517,
+      "step": 970
+    },
+    {
+      "epoch": 0.37732216767735105,
+      "grad_norm": 0.22711265087127686,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.7602,
+      "step": 980
+    },
+    {
+      "epoch": 0.38117239387814034,
+      "grad_norm": 0.24012592434883118,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7406,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850226200789296,
+      "grad_norm": 0.23794637620449066,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.7621,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3888728462797189,
+      "grad_norm": 0.23063179850578308,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.7845,
+      "step": 1010
+    },
+    {
+      "epoch": 0.39272307248050825,
+      "grad_norm": 0.256242960691452,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.774,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39657329868129754,
+      "grad_norm": 0.23388072848320007,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.7715,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4004235248820868,
+      "grad_norm": 0.23357291519641876,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.7612,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4042737510828761,
+      "grad_norm": 0.21466144919395447,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.756,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4081239772836654,
+      "grad_norm": 0.21567749977111816,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.763,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41197420348445474,
+      "grad_norm": 0.23145708441734314,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.7551,
+      "step": 1070
+    },
+    {
+      "epoch": 0.415824429685244,
+      "grad_norm": 0.2153475433588028,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.779,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4196746558860333,
+      "grad_norm": 0.2532651722431183,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7615,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235248820868226,
+      "grad_norm": 0.23626495897769928,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.775,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4273751082876119,
+      "grad_norm": 0.23218466341495514,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.7693,
+      "step": 1110
+    },
+    {
+      "epoch": 0.43122533448840117,
+      "grad_norm": 0.24860821664333344,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.7659,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4350755606891905,
+      "grad_norm": 0.23905062675476074,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7449,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4389257868899798,
+      "grad_norm": 0.23672519624233246,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.7677,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4427760130907691,
+      "grad_norm": 0.21548010408878326,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7544,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44662623929155837,
+      "grad_norm": 0.25654518604278564,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.7796,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45047646549234766,
+      "grad_norm": 0.22696617245674133,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.7905,
+      "step": 1170
+    },
+    {
+      "epoch": 0.454326691693137,
+      "grad_norm": 0.2223900705575943,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.7661,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4581769178939263,
+      "grad_norm": 0.23573753237724304,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.7419,
+      "step": 1190
+    },
+    {
+      "epoch": 0.46202714409471557,
+      "grad_norm": 0.23894119262695312,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.756,
+      "step": 1200
+    },
+    {
+      "epoch": 0.46587737029550486,
+      "grad_norm": 0.23804804682731628,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.7605,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46972759649629414,
+      "grad_norm": 0.2268250733613968,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.7758,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47357782269708343,
+      "grad_norm": 0.23040036857128143,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.7794,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47742804889787277,
+      "grad_norm": 0.22629646956920624,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.7495,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48127827509866206,
+      "grad_norm": 0.2150408774614334,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7461,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48512850129945134,
+      "grad_norm": 0.24346598982810974,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7537,
+      "step": 1260
+    },
+    {
+      "epoch": 0.48897872750024063,
+      "grad_norm": 0.25205615162849426,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7366,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928289537010299,
+      "grad_norm": 0.24028243124485016,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7488,
+      "step": 1280
+    },
+    {
+      "epoch": 0.49667917990181926,
+      "grad_norm": 0.22735239565372467,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.757,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005294061026085,
+      "grad_norm": 0.21869350969791412,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7575,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5043796323033978,
+      "grad_norm": 0.22685693204402924,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.775,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082298585041871,
+      "grad_norm": 0.23667573928833008,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7391,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5120800847049765,
+      "grad_norm": 0.2562355101108551,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.7504,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5159303109057657,
+      "grad_norm": 0.22640971839427948,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.7593,
+      "step": 1340
+    },
+    {
+      "epoch": 0.519780537106555,
+      "grad_norm": 0.23093834519386292,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.7534,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236307633073443,
+      "grad_norm": 0.25133779644966125,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.767,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5274809895081336,
+      "grad_norm": 0.2360536903142929,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.7644,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313312157089229,
+      "grad_norm": 0.2185036838054657,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.7715,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5351814419097122,
+      "grad_norm": 0.23983286321163177,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.751,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390316681105015,
+      "grad_norm": 0.2260584682226181,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.7521,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5428818943112907,
+      "grad_norm": 0.23372486233711243,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.7663,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467321205120801,
+      "grad_norm": 0.24965152144432068,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7493,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5505823467128694,
+      "grad_norm": 0.2714933156967163,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.765,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544325729136587,
+      "grad_norm": 0.2552967965602875,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.7707,
+      "step": 1440
+    },
+    {
+      "epoch": 0.558282799114448,
+      "grad_norm": 0.24735282361507416,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.754,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5621330253152372,
+      "grad_norm": 0.2339288592338562,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7558,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5659832515160266,
+      "grad_norm": 0.22078652679920197,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7517,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698334777168159,
+      "grad_norm": 0.22677497565746307,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.7517,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5736837039176051,
+      "grad_norm": 0.22201400995254517,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7544,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775339301183945,
+      "grad_norm": 0.22677037119865417,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.7658,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5813841563191837,
+      "grad_norm": 0.23100300133228302,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7575,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852343825199731,
+      "grad_norm": 0.22671516239643097,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.7643,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5890846087207623,
+      "grad_norm": 0.23117835819721222,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.7658,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929348349215516,
+      "grad_norm": 0.23447252810001373,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.7718,
+      "step": 1540
+    },
+    {
+      "epoch": 0.596785061122341,
+      "grad_norm": 0.22705359756946564,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.7572,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006352873231302,
+      "grad_norm": 0.22066965699195862,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.7725,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6044855135239195,
+      "grad_norm": 0.2384282797574997,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.7698,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6083357397247088,
+      "grad_norm": 0.23802250623703003,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.7581,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6121859659254981,
+      "grad_norm": 0.2081289291381836,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.7624,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160361921262875,
+      "grad_norm": 0.21764948964118958,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7488,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6198864183270767,
+      "grad_norm": 0.2137974202632904,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.731,
+      "step": 1610
+    },
+    {
+      "epoch": 0.623736644527866,
+      "grad_norm": 0.23348702490329742,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7294,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6275868707286553,
+      "grad_norm": 0.22613590955734253,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.7614,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314370969294446,
+      "grad_norm": 0.21876026690006256,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7517,
+      "step": 1640
+    },
+    {
+      "epoch": 0.635287323130234,
+      "grad_norm": 0.23423820734024048,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7612,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391375493310232,
+      "grad_norm": 0.24148111045360565,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7416,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6429877755318125,
+      "grad_norm": 0.2457371950149536,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.7652,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6468380017326018,
+      "grad_norm": 0.2358461320400238,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7582,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6506882279333911,
+      "grad_norm": 0.24494923651218414,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7491,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6545384541341804,
+      "grad_norm": 0.20545527338981628,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7465,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6583886803349697,
+      "grad_norm": 0.24299223721027374,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7633,
+      "step": 1710
+    },
+    {
+      "epoch": 0.662238906535759,
+      "grad_norm": 0.23373675346374512,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7521,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6660891327365482,
+      "grad_norm": 0.23137982189655304,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.7544,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6699393589373376,
+      "grad_norm": 0.22511033713817596,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7547,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6737895851381268,
+      "grad_norm": 0.2299818992614746,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.753,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6776398113389162,
+      "grad_norm": 0.2193373590707779,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7384,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6814900375397055,
+      "grad_norm": 0.23886582255363464,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.785,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6853402637404947,
+      "grad_norm": 0.23261868953704834,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.7685,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6891904899412841,
+      "grad_norm": 0.22462151944637299,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.7789,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6930407161420733,
+      "grad_norm": 0.23457060754299164,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7445,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6968909423428626,
+      "grad_norm": 0.22927717864513397,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7352,
+      "step": 1810
+    },
+    {
+      "epoch": 0.700741168543652,
+      "grad_norm": 0.2231900542974472,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.7583,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7045913947444412,
+      "grad_norm": 0.22120468318462372,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7483,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7084416209452306,
+      "grad_norm": 0.2372419238090515,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.7521,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7122918471460198,
+      "grad_norm": 0.23697586357593536,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.767,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7161420733468091,
+      "grad_norm": 0.22540521621704102,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7584,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7199922995475985,
+      "grad_norm": 0.23666207492351532,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.755,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7238425257483877,
+      "grad_norm": 0.21609367430210114,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.7631,
+      "step": 1880
+    },
+    {
+      "epoch": 0.727692751949177,
+      "grad_norm": 0.23396433889865875,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7466,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7315429781499663,
+      "grad_norm": 0.2327294945716858,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7542,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7353932043507556,
+      "grad_norm": 0.220290869474411,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7503,
+      "step": 1910
+    },
+    {
+      "epoch": 0.739243430551545,
+      "grad_norm": 0.22423042356967926,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.745,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7430936567523342,
+      "grad_norm": 0.2335342913866043,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.7617,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7469438829531235,
+      "grad_norm": 0.23710191249847412,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.7717,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7507941091539128,
+      "grad_norm": 0.2376398891210556,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.7599,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7546443353547021,
+      "grad_norm": 0.24277731776237488,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.7748,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7584945615554913,
+      "grad_norm": 0.22401562333106995,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.7655,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7623447877562807,
+      "grad_norm": 0.243958979845047,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.7613,
+      "step": 1980
+    },
+    {
+      "epoch": 0.76619501395707,
+      "grad_norm": 0.2435867041349411,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.7589,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7700452401578592,
+      "grad_norm": 0.22393876314163208,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7497,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7738954663586486,
+      "grad_norm": 0.22129637002944946,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.759,
+      "step": 2010
+    },
+    {
+      "epoch": 0.7777456925594378,
+      "grad_norm": 0.21528831124305725,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.7447,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7815959187602272,
+      "grad_norm": 0.22291061282157898,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7294,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7854461449610165,
+      "grad_norm": 0.21873147785663605,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.7467,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7892963711618057,
+      "grad_norm": 0.2135474681854248,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.7509,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7931465973625951,
+      "grad_norm": 0.21712909638881683,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7354,
+      "step": 2060
+    },
+    {
+      "epoch": 0.7969968235633843,
+      "grad_norm": 0.23033863306045532,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.756,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8008470497641736,
+      "grad_norm": 0.22600997984409332,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.738,
+      "step": 2080
+    },
+    {
+      "epoch": 0.804697275964963,
+      "grad_norm": 0.22095747292041779,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7608,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8085475021657522,
+      "grad_norm": 0.21907904744148254,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.749,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8123977283665416,
+      "grad_norm": 0.22485078871250153,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.7604,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8162479545673308,
+      "grad_norm": 0.23080846667289734,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.7626,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8200981807681201,
+      "grad_norm": 0.23355552554130554,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7502,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8239484069689095,
+      "grad_norm": 0.22718556225299835,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7511,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8277986331696987,
+      "grad_norm": 0.23830071091651917,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7449,
+      "step": 2150
+    },
+    {
+      "epoch": 0.831648859370488,
+      "grad_norm": 0.21260781586170197,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.7614,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8354990855712773,
+      "grad_norm": 0.22247038781642914,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.7595,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8393493117720666,
+      "grad_norm": 0.22786065936088562,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7529,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8431995379728559,
+      "grad_norm": 0.2161143720149994,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.757,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8470497641736452,
+      "grad_norm": 0.24214477837085724,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.7533,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8508999903744345,
+      "grad_norm": 0.22540532052516937,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7268,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8547502165752238,
+      "grad_norm": 0.21454910933971405,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.7587,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586004427760131,
+      "grad_norm": 0.23270556330680847,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7534,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8624506689768023,
+      "grad_norm": 0.22169017791748047,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.7656,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663008951775917,
+      "grad_norm": 0.2299358993768692,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7472,
+      "step": 2250
+    },
+    {
+      "epoch": 0.870151121378381,
+      "grad_norm": 0.2280275821685791,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7371,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740013475791703,
+      "grad_norm": 0.23288962244987488,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.746,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8778515737799596,
+      "grad_norm": 0.22268931567668915,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.7603,
+      "step": 2280
+    },
+    {
+      "epoch": 0.8817017999807488,
+      "grad_norm": 0.2283535897731781,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.76,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8855520261815382,
+      "grad_norm": 0.2187565416097641,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.739,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8894022523823275,
+      "grad_norm": 0.2090836614370346,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.749,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8932524785831167,
+      "grad_norm": 0.21840369701385498,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7551,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971027047839061,
+      "grad_norm": 0.2209567278623581,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.7606,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9009529309846953,
+      "grad_norm": 0.2336592823266983,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7546,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048031571854847,
+      "grad_norm": 0.2197485715150833,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.7364,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908653383386274,
+      "grad_norm": 0.22094276547431946,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7496,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125036095870632,
+      "grad_norm": 0.2445399910211563,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7412,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9163538357878526,
+      "grad_norm": 0.2259821742773056,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7509,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202040619886418,
+      "grad_norm": 0.22295519709587097,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.764,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9240542881894311,
+      "grad_norm": 0.24394533038139343,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.7638,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9279045143902205,
+      "grad_norm": 0.2207798808813095,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7475,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9317547405910097,
+      "grad_norm": 0.2175796926021576,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.7662,
+      "step": 2420
+    },
+    {
+      "epoch": 0.935604966791799,
+      "grad_norm": 0.22898642718791962,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.7657,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9394551929925883,
+      "grad_norm": 0.23105816543102264,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7513,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433054191933776,
+      "grad_norm": 0.23494254052639008,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.7483,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9471556453941669,
+      "grad_norm": 0.22617314755916595,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.7688,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510058715949562,
+      "grad_norm": 0.23526957631111145,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.763,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9548560977957455,
+      "grad_norm": 0.22287999093532562,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.7473,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587063239965348,
+      "grad_norm": 0.27098900079727173,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.7515,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9625565501973241,
+      "grad_norm": 0.22189810872077942,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7475,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664067763981133,
+      "grad_norm": 0.22601208090782166,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7416,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9702570025989027,
+      "grad_norm": 0.23159193992614746,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.7652,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974107228799692,
+      "grad_norm": 0.220316544175148,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.745,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9779574550004813,
+      "grad_norm": 0.21388310194015503,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7495,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9818076812012706,
+      "grad_norm": 0.21442057192325592,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7565,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9856579074020598,
+      "grad_norm": 0.23231899738311768,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.7499,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9895081336028492,
+      "grad_norm": 0.22499951720237732,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7392,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9933583598036385,
+      "grad_norm": 0.2044905424118042,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7321,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9972085860044277,
+      "grad_norm": 0.24755574762821198,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7664,
+      "step": 2590
+    },
+    {
+      "epoch": 0.9999037443449803,
+      "step": 2597,
+      "total_flos": 8.19764490638721e+18,
+      "train_loss": 0.7886566456621042,
+      "train_runtime": 11780.2722,
+      "train_samples_per_second": 56.442,
+      "train_steps_per_second": 0.22
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.19764490638721e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/mc2_g14_224/finetune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673eb30ae506da66f7c3c49275c71a15618ba55bd8e453bc3909a7ecb33685e3
+size 6136

continuous/qwen3/mc2_g14_224/pretrain/config.json

@@ -0,0 +1,60 @@
+{
+  "_attn_implementation_autoset": true,
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1664,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-bigG-14-worldwide",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_g14_224.pt",
+  "vocab_size": 151936
+}

continuous/qwen3/mc2_g14_224/pretrain/mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7621b9a9bb0a1f61a23d60bd546921e0bee790d6ac5c153383217ead724e161
+size 30427192

continuous/qwen3/mc2_g14_224/pretrain/trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 3.2847161293029785,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 7.9448,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.25671184062957764,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 4.9958,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.09981844574213028,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 4.7279,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.11183159798383713,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 4.6339,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.08197896927595139,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 4.5843,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.1556626409292221,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 4.5466,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.1578698605298996,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 4.4961,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.2087523490190506,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 4.4599,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.11541873216629028,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 4.4136,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.1189516931772232,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 4.3779,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.20226018130779266,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 4.3407,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.1711764931678772,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 4.3177,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.19171778857707977,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 4.287,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.14297756552696228,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 4.2665,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.19034050405025482,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 4.259,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.18314889073371887,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 4.2399,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.17884770035743713,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 4.2241,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.1656494438648224,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 4.2089,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.1918845921754837,
+      "learning_rate": 0.000779204504653894,
+      "loss": 4.202,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.159458190202713,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 4.1768,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.16268505156040192,
+      "learning_rate": 0.00072685988254984,
+      "loss": 4.1647,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.13007701933383942,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 4.177,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.12788698077201843,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 4.1665,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.14641211926937103,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 4.1507,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.1290542185306549,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 4.1308,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.13143061101436615,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 4.14,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.17457382380962372,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 4.1157,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.13049037754535675,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 4.1122,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.144669771194458,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 4.1006,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.13269592821598053,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 4.0944,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.15013398230075836,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 4.1038,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.13268427550792694,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 4.0913,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.14053121209144592,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 4.0749,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.15692873299121857,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 4.0706,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.1291613131761551,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 4.0705,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.1269434690475464,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 4.0764,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.13910026848316193,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 4.0583,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.1391800045967102,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 4.0712,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.12745226919651031,
+      "learning_rate": 0.000208323983828828,
+      "loss": 4.0489,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.13378918170928955,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 4.0503,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.10965994745492935,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 4.0485,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.12456592172384262,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 4.0387,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.1315688043832779,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 4.0402,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.1401291787624359,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 4.0477,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.13060836493968964,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 4.0346,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.12157066911458969,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 4.0253,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.12145059555768967,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 4.0129,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.11877547204494476,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 4.0218,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.10939238965511322,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 4.0227,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.11362124979496002,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 4.0348,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.10941842943429947,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 4.0239,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.1094382032752037,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 4.0142,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.11420857161283493,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 4.0178,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.11205973476171494,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 4.0251,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 6.486578758701548e+17,
+      "train_loss": 4.260806120426283,
+      "train_runtime": 5522.1056,
+      "train_samples_per_second": 101.072,
+      "train_steps_per_second": 0.099
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.486578758701548e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/mc2_g14_378/finetune/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

continuous/qwen3/mc2_g14_378/finetune/config.json

@@ -0,0 +1,59 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1664,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-bigG-14-worldwide-378",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_g14_378.pt",
+  "vocab_size": 151936
+}

continuous/qwen3/mc2_g14_378/finetune/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

continuous/qwen3/mc2_g14_378/finetune/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d526ddbb00bb54ed6d51b31323f591ca0d9efa906fb8dfea44fd27ab128266e
+size 4984353720

continuous/qwen3/mc2_g14_378/finetune/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad09d0b866eeba4a558517094429100412bdfac06e4c36b9b8de6d508b7e279
+size 2801061512

continuous/qwen3/mc2_g14_378/finetune/model.safetensors.index.json

@@ -0,0 +1,906 @@
+{
+  "metadata": {
+    "total_size": 7785293568
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.class_embedding": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_post.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_post.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_pre.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.ln_pre.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.positional_embedding": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.proj": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

continuous/qwen3/mc2_g14_378/finetune/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

continuous/qwen3/mc2_g14_378/finetune/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

continuous/qwen3/mc2_g14_378/finetune/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

continuous/qwen3/mc2_g14_378/finetune/trainer_state.json

@@ -0,0 +1,1856 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999037443449803,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850226200789296,
+      "grad_norm": 11.50015640258789,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 2.8301,
+      "step": 10
+    },
+    {
+      "epoch": 0.007700452401578592,
+      "grad_norm": 4.228683948516846,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 2.1906,
+      "step": 20
+    },
+    {
+      "epoch": 0.01155067860236789,
+      "grad_norm": 2.333322286605835,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.635,
+      "step": 30
+    },
+    {
+      "epoch": 0.015400904803157185,
+      "grad_norm": 0.7907997965812683,
+      "learning_rate": 5e-06,
+      "loss": 1.2461,
+      "step": 40
+    },
+    {
+      "epoch": 0.019251131003946483,
+      "grad_norm": 0.4687734544277191,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 1.0968,
+      "step": 50
+    },
+    {
+      "epoch": 0.02310135720473578,
+      "grad_norm": 0.25824451446533203,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 1.0064,
+      "step": 60
+    },
+    {
+      "epoch": 0.026951583405525073,
+      "grad_norm": 0.19828538596630096,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.9588,
+      "step": 70
+    },
+    {
+      "epoch": 0.03080180960631437,
+      "grad_norm": 0.1759665161371231,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.9525,
+      "step": 80
+    },
+    {
+      "epoch": 0.034652035807103666,
+      "grad_norm": 0.17692992091178894,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.9245,
+      "step": 90
+    },
+    {
+      "epoch": 0.038502262007892966,
+      "grad_norm": 0.14423266053199768,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.898,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235248820868226,
+      "grad_norm": 0.15189839899539948,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.8733,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620271440947156,
+      "grad_norm": 0.14648203551769257,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8799,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005294061026085,
+      "grad_norm": 0.14558018743991852,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.8707,
+      "step": 130
+    },
+    {
+      "epoch": 0.053903166811050146,
+      "grad_norm": 0.15695302188396454,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.8664,
+      "step": 140
+    },
+    {
+      "epoch": 0.057753393011839446,
+      "grad_norm": 0.17507246136665344,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.8623,
+      "step": 150
+    },
+    {
+      "epoch": 0.06160361921262874,
+      "grad_norm": 0.14720788598060608,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.8556,
+      "step": 160
+    },
+    {
+      "epoch": 0.06545384541341803,
+      "grad_norm": 0.12232600152492523,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.853,
+      "step": 170
+    },
+    {
+      "epoch": 0.06930407161420733,
+      "grad_norm": 0.145388662815094,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.8767,
+      "step": 180
+    },
+    {
+      "epoch": 0.07315429781499663,
+      "grad_norm": 0.14347794651985168,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.8761,
+      "step": 190
+    },
+    {
+      "epoch": 0.07700452401578593,
+      "grad_norm": 0.15319544076919556,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.8554,
+      "step": 200
+    },
+    {
+      "epoch": 0.08085475021657522,
+      "grad_norm": 0.13261152803897858,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.8604,
+      "step": 210
+    },
+    {
+      "epoch": 0.08470497641736452,
+      "grad_norm": 0.13263416290283203,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.8378,
+      "step": 220
+    },
+    {
+      "epoch": 0.08855520261815382,
+      "grad_norm": 0.1429535299539566,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.8441,
+      "step": 230
+    },
+    {
+      "epoch": 0.09240542881894312,
+      "grad_norm": 0.13727238774299622,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.831,
+      "step": 240
+    },
+    {
+      "epoch": 0.0962556550197324,
+      "grad_norm": 0.1392630785703659,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.846,
+      "step": 250
+    },
+    {
+      "epoch": 0.1001058812205217,
+      "grad_norm": 0.13507844507694244,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.8504,
+      "step": 260
+    },
+    {
+      "epoch": 0.103956107421311,
+      "grad_norm": 0.1369665116071701,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.8349,
+      "step": 270
+    },
+    {
+      "epoch": 0.10780633362210029,
+      "grad_norm": 0.12714837491512299,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.8385,
+      "step": 280
+    },
+    {
+      "epoch": 0.11165655982288959,
+      "grad_norm": 0.1387113481760025,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.85,
+      "step": 290
+    },
+    {
+      "epoch": 0.11550678602367889,
+      "grad_norm": 0.11898576468229294,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.8125,
+      "step": 300
+    },
+    {
+      "epoch": 0.11935701222446819,
+      "grad_norm": 0.13273321092128754,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.8277,
+      "step": 310
+    },
+    {
+      "epoch": 0.12320723842525748,
+      "grad_norm": 0.1499527245759964,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.8231,
+      "step": 320
+    },
+    {
+      "epoch": 0.12705746462604678,
+      "grad_norm": 0.12848375737667084,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.8251,
+      "step": 330
+    },
+    {
+      "epoch": 0.13090769082683607,
+      "grad_norm": 0.1255291998386383,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.8351,
+      "step": 340
+    },
+    {
+      "epoch": 0.13475791702762538,
+      "grad_norm": 0.14456123113632202,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.84,
+      "step": 350
+    },
+    {
+      "epoch": 0.13860814322841467,
+      "grad_norm": 0.13291427493095398,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.8242,
+      "step": 360
+    },
+    {
+      "epoch": 0.14245836942920398,
+      "grad_norm": 0.12927617132663727,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.8487,
+      "step": 370
+    },
+    {
+      "epoch": 0.14630859562999327,
+      "grad_norm": 0.12031753361225128,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.8165,
+      "step": 380
+    },
+    {
+      "epoch": 0.15015882183078255,
+      "grad_norm": 0.16032083332538605,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.8228,
+      "step": 390
+    },
+    {
+      "epoch": 0.15400904803157187,
+      "grad_norm": 0.1210477203130722,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.8242,
+      "step": 400
+    },
+    {
+      "epoch": 0.15785927423236115,
+      "grad_norm": 0.12737008929252625,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.8045,
+      "step": 410
+    },
+    {
+      "epoch": 0.16170950043315044,
+      "grad_norm": 0.1251932680606842,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.8199,
+      "step": 420
+    },
+    {
+      "epoch": 0.16555972663393975,
+      "grad_norm": 0.13748818635940552,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.8124,
+      "step": 430
+    },
+    {
+      "epoch": 0.16940995283472904,
+      "grad_norm": 0.14572684466838837,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.8128,
+      "step": 440
+    },
+    {
+      "epoch": 0.17326017903551832,
+      "grad_norm": 0.13371258974075317,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.7959,
+      "step": 450
+    },
+    {
+      "epoch": 0.17711040523630764,
+      "grad_norm": 0.12681636214256287,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.8113,
+      "step": 460
+    },
+    {
+      "epoch": 0.18096063143709692,
+      "grad_norm": 0.13152827322483063,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.8167,
+      "step": 470
+    },
+    {
+      "epoch": 0.18481085763788624,
+      "grad_norm": 0.13872100412845612,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.8107,
+      "step": 480
+    },
+    {
+      "epoch": 0.18866108383867553,
+      "grad_norm": 0.12255861610174179,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.8002,
+      "step": 490
+    },
+    {
+      "epoch": 0.1925113100394648,
+      "grad_norm": 0.1315462589263916,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.8028,
+      "step": 500
+    },
+    {
+      "epoch": 0.19636153624025413,
+      "grad_norm": 0.1367127150297165,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.7893,
+      "step": 510
+    },
+    {
+      "epoch": 0.2002117624410434,
+      "grad_norm": 0.12520094215869904,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.8295,
+      "step": 520
+    },
+    {
+      "epoch": 0.2040619886418327,
+      "grad_norm": 0.1458577811717987,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.7961,
+      "step": 530
+    },
+    {
+      "epoch": 0.207912214842622,
+      "grad_norm": 0.14116396009922028,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.8155,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117624410434113,
+      "grad_norm": 0.11544482409954071,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.8201,
+      "step": 550
+    },
+    {
+      "epoch": 0.21561266724420058,
+      "grad_norm": 0.12482374161481857,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.8206,
+      "step": 560
+    },
+    {
+      "epoch": 0.2194628934449899,
+      "grad_norm": 0.14241532981395721,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.829,
+      "step": 570
+    },
+    {
+      "epoch": 0.22331311964577918,
+      "grad_norm": 0.129826620221138,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.8048,
+      "step": 580
+    },
+    {
+      "epoch": 0.2271633458465685,
+      "grad_norm": 0.1317244917154312,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.8217,
+      "step": 590
+    },
+    {
+      "epoch": 0.23101357204735778,
+      "grad_norm": 0.1504894495010376,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.8163,
+      "step": 600
+    },
+    {
+      "epoch": 0.23486379824814707,
+      "grad_norm": 0.13779325783252716,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.8268,
+      "step": 610
+    },
+    {
+      "epoch": 0.23871402444893638,
+      "grad_norm": 0.127375528216362,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.8186,
+      "step": 620
+    },
+    {
+      "epoch": 0.24256425064972567,
+      "grad_norm": 0.13323982059955597,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.8243,
+      "step": 630
+    },
+    {
+      "epoch": 0.24641447685051496,
+      "grad_norm": 0.12178532034158707,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.8176,
+      "step": 640
+    },
+    {
+      "epoch": 0.25026470305130427,
+      "grad_norm": 0.12032730877399445,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.774,
+      "step": 650
+    },
+    {
+      "epoch": 0.25411492925209356,
+      "grad_norm": 0.14112846553325653,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.8022,
+      "step": 660
+    },
+    {
+      "epoch": 0.25796515545288284,
+      "grad_norm": 0.13821765780448914,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.8156,
+      "step": 670
+    },
+    {
+      "epoch": 0.26181538165367213,
+      "grad_norm": 0.1257808655500412,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7918,
+      "step": 680
+    },
+    {
+      "epoch": 0.26566560785446147,
+      "grad_norm": 0.1312248855829239,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.8041,
+      "step": 690
+    },
+    {
+      "epoch": 0.26951583405525076,
+      "grad_norm": 0.12696126103401184,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.8114,
+      "step": 700
+    },
+    {
+      "epoch": 0.27336606025604004,
+      "grad_norm": 0.12357018142938614,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.7965,
+      "step": 710
+    },
+    {
+      "epoch": 0.27721628645682933,
+      "grad_norm": 0.11823710054159164,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.7986,
+      "step": 720
+    },
+    {
+      "epoch": 0.2810665126576186,
+      "grad_norm": 0.12820090353488922,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.8083,
+      "step": 730
+    },
+    {
+      "epoch": 0.28491673885840796,
+      "grad_norm": 0.12548156082630157,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.7901,
+      "step": 740
+    },
+    {
+      "epoch": 0.28876696505919724,
+      "grad_norm": 0.12227360904216766,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.7905,
+      "step": 750
+    },
+    {
+      "epoch": 0.29261719125998653,
+      "grad_norm": 0.12080414593219757,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.7827,
+      "step": 760
+    },
+    {
+      "epoch": 0.2964674174607758,
+      "grad_norm": 0.12107986956834793,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.7997,
+      "step": 770
+    },
+    {
+      "epoch": 0.3003176436615651,
+      "grad_norm": 0.13559994101524353,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.7938,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041678698623544,
+      "grad_norm": 0.13472461700439453,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.7827,
+      "step": 790
+    },
+    {
+      "epoch": 0.30801809606314373,
+      "grad_norm": 0.13287630677223206,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.8076,
+      "step": 800
+    },
+    {
+      "epoch": 0.311868322263933,
+      "grad_norm": 0.12479998916387558,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.7951,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157185484647223,
+      "grad_norm": 0.13455930352210999,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.796,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195687746655116,
+      "grad_norm": 0.13059033453464508,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.7853,
+      "step": 830
+    },
+    {
+      "epoch": 0.3234190008663009,
+      "grad_norm": 0.12682785093784332,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.7881,
+      "step": 840
+    },
+    {
+      "epoch": 0.3272692270670902,
+      "grad_norm": 0.1146402508020401,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.7884,
+      "step": 850
+    },
+    {
+      "epoch": 0.3311194532678795,
+      "grad_norm": 0.12451174855232239,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.7815,
+      "step": 860
+    },
+    {
+      "epoch": 0.3349696794686688,
+      "grad_norm": 0.11978106200695038,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.7792,
+      "step": 870
+    },
+    {
+      "epoch": 0.3388199056694581,
+      "grad_norm": 0.1138262003660202,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.7857,
+      "step": 880
+    },
+    {
+      "epoch": 0.34267013187024736,
+      "grad_norm": 0.1324833482503891,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7759,
+      "step": 890
+    },
+    {
+      "epoch": 0.34652035807103665,
+      "grad_norm": 0.11672251671552658,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.7792,
+      "step": 900
+    },
+    {
+      "epoch": 0.350370584271826,
+      "grad_norm": 0.1277104616165161,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.7792,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542208104726153,
+      "grad_norm": 0.12268830090761185,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7681,
+      "step": 920
+    },
+    {
+      "epoch": 0.35807103667340456,
+      "grad_norm": 0.12895998358726501,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7609,
+      "step": 930
+    },
+    {
+      "epoch": 0.36192126287419385,
+      "grad_norm": 0.13424727320671082,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.7979,
+      "step": 940
+    },
+    {
+      "epoch": 0.36577148907498314,
+      "grad_norm": 0.12275192886590958,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.8089,
+      "step": 950
+    },
+    {
+      "epoch": 0.3696217152757725,
+      "grad_norm": 0.1602363884449005,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.7868,
+      "step": 960
+    },
+    {
+      "epoch": 0.37347194147656176,
+      "grad_norm": 0.12531395256519318,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7667,
+      "step": 970
+    },
+    {
+      "epoch": 0.37732216767735105,
+      "grad_norm": 0.11618635803461075,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.7758,
+      "step": 980
+    },
+    {
+      "epoch": 0.38117239387814034,
+      "grad_norm": 0.13537196815013885,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7605,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850226200789296,
+      "grad_norm": 0.1267850399017334,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.7855,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3888728462797189,
+      "grad_norm": 0.1304950714111328,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.8042,
+      "step": 1010
+    },
+    {
+      "epoch": 0.39272307248050825,
+      "grad_norm": 0.1291992962360382,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.7795,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39657329868129754,
+      "grad_norm": 0.12003959715366364,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.7894,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4004235248820868,
+      "grad_norm": 0.12354748696088791,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.7881,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4042737510828761,
+      "grad_norm": 0.1154417172074318,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.776,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4081239772836654,
+      "grad_norm": 0.12984882295131683,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.7812,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41197420348445474,
+      "grad_norm": 0.12552125751972198,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.763,
+      "step": 1070
+    },
+    {
+      "epoch": 0.415824429685244,
+      "grad_norm": 0.12086072564125061,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.7936,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4196746558860333,
+      "grad_norm": 0.13771279156208038,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7682,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235248820868226,
+      "grad_norm": 0.1406165212392807,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.7889,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4273751082876119,
+      "grad_norm": 0.12790493667125702,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.78,
+      "step": 1110
+    },
+    {
+      "epoch": 0.43122533448840117,
+      "grad_norm": 0.13803191483020782,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.7727,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4350755606891905,
+      "grad_norm": 0.12780173122882843,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7617,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4389257868899798,
+      "grad_norm": 0.12104834616184235,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.7656,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4427760130907691,
+      "grad_norm": 0.11252949386835098,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7599,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44662623929155837,
+      "grad_norm": 0.13937969505786896,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.7878,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45047646549234766,
+      "grad_norm": 0.11821415275335312,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.7937,
+      "step": 1170
+    },
+    {
+      "epoch": 0.454326691693137,
+      "grad_norm": 0.1128503829240799,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.7663,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4581769178939263,
+      "grad_norm": 0.1352337747812271,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.7451,
+      "step": 1190
+    },
+    {
+      "epoch": 0.46202714409471557,
+      "grad_norm": 0.1324506402015686,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7551,
+      "step": 1200
+    },
+    {
+      "epoch": 0.46587737029550486,
+      "grad_norm": 0.1262679547071457,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.7595,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46972759649629414,
+      "grad_norm": 0.12286563217639923,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.7725,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47357782269708343,
+      "grad_norm": 0.1196163222193718,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.7755,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47742804889787277,
+      "grad_norm": 0.12125028669834137,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.7523,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48127827509866206,
+      "grad_norm": 0.11524039506912231,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7488,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48512850129945134,
+      "grad_norm": 0.1278262734413147,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7514,
+      "step": 1260
+    },
+    {
+      "epoch": 0.48897872750024063,
+      "grad_norm": 0.13727641105651855,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7386,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928289537010299,
+      "grad_norm": 0.13653966784477234,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.746,
+      "step": 1280
+    },
+    {
+      "epoch": 0.49667917990181926,
+      "grad_norm": 0.1193273589015007,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.7669,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005294061026085,
+      "grad_norm": 0.1273251473903656,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7597,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5043796323033978,
+      "grad_norm": 0.12609454989433289,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.7738,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082298585041871,
+      "grad_norm": 0.137467160820961,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7487,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5120800847049765,
+      "grad_norm": 0.137483149766922,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.75,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5159303109057657,
+      "grad_norm": 0.1272590458393097,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.7593,
+      "step": 1340
+    },
+    {
+      "epoch": 0.519780537106555,
+      "grad_norm": 0.1237141415476799,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.7505,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236307633073443,
+      "grad_norm": 0.1357862502336502,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.7585,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5274809895081336,
+      "grad_norm": 0.12664447724819183,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.7638,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313312157089229,
+      "grad_norm": 0.11405707150697708,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.7691,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5351814419097122,
+      "grad_norm": 0.1333017498254776,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7432,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390316681105015,
+      "grad_norm": 0.11735134571790695,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.7498,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5428818943112907,
+      "grad_norm": 0.12355709075927734,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.7667,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467321205120801,
+      "grad_norm": 0.13408426940441132,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7479,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5505823467128694,
+      "grad_norm": 0.13198229670524597,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.7604,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544325729136587,
+      "grad_norm": 0.1327231526374817,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.7638,
+      "step": 1440
+    },
+    {
+      "epoch": 0.558282799114448,
+      "grad_norm": 0.13439516723155975,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.7468,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5621330253152372,
+      "grad_norm": 0.11935332417488098,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7516,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5659832515160266,
+      "grad_norm": 0.1174820140004158,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7465,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698334777168159,
+      "grad_norm": 0.1196560487151146,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.7466,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5736837039176051,
+      "grad_norm": 0.12211856991052628,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7514,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775339301183945,
+      "grad_norm": 0.12734705209732056,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.7628,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5813841563191837,
+      "grad_norm": 0.1193179190158844,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7503,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852343825199731,
+      "grad_norm": 0.13388259708881378,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.7581,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5890846087207623,
+      "grad_norm": 0.13022971153259277,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.7565,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929348349215516,
+      "grad_norm": 0.12499910593032837,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.7666,
+      "step": 1540
+    },
+    {
+      "epoch": 0.596785061122341,
+      "grad_norm": 0.1213713064789772,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.757,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006352873231302,
+      "grad_norm": 0.12688256800174713,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.7679,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6044855135239195,
+      "grad_norm": 0.12446650117635727,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.758,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6083357397247088,
+      "grad_norm": 0.12659786641597748,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.759,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6121859659254981,
+      "grad_norm": 0.11269046366214752,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.757,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160361921262875,
+      "grad_norm": 0.11462853103876114,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7404,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6198864183270767,
+      "grad_norm": 0.10979299992322922,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7214,
+      "step": 1610
+    },
+    {
+      "epoch": 0.623736644527866,
+      "grad_norm": 0.1237095445394516,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7241,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6275868707286553,
+      "grad_norm": 0.11970501393079758,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.7625,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314370969294446,
+      "grad_norm": 0.11450142413377762,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7449,
+      "step": 1640
+    },
+    {
+      "epoch": 0.635287323130234,
+      "grad_norm": 0.12752479314804077,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7558,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391375493310232,
+      "grad_norm": 0.12224077433347702,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7408,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6429877755318125,
+      "grad_norm": 0.1251411885023117,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.7636,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6468380017326018,
+      "grad_norm": 0.12419106811285019,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7458,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6506882279333911,
+      "grad_norm": 0.1291576623916626,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7364,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6545384541341804,
+      "grad_norm": 0.11209014058113098,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7335,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6583886803349697,
+      "grad_norm": 0.1256975680589676,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7545,
+      "step": 1710
+    },
+    {
+      "epoch": 0.662238906535759,
+      "grad_norm": 0.12187622487545013,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.743,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6660891327365482,
+      "grad_norm": 0.11859733611345291,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.7446,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6699393589373376,
+      "grad_norm": 0.12116556614637375,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7529,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6737895851381268,
+      "grad_norm": 0.12907718122005463,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.7463,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6776398113389162,
+      "grad_norm": 0.1128045991063118,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7336,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6814900375397055,
+      "grad_norm": 0.12408054620027542,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.775,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6853402637404947,
+      "grad_norm": 0.12433405965566635,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.7575,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6891904899412841,
+      "grad_norm": 0.11531848460435867,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.7684,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6930407161420733,
+      "grad_norm": 0.11565843224525452,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7362,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6968909423428626,
+      "grad_norm": 0.12056531757116318,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7301,
+      "step": 1810
+    },
+    {
+      "epoch": 0.700741168543652,
+      "grad_norm": 0.11735653132200241,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.7533,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7045913947444412,
+      "grad_norm": 0.11823755502700806,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7084416209452306,
+      "grad_norm": 0.12966519594192505,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.7471,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7122918471460198,
+      "grad_norm": 0.1241731196641922,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.7571,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7161420733468091,
+      "grad_norm": 0.11643011122941971,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7542,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7199922995475985,
+      "grad_norm": 0.12082838267087936,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.7501,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7238425257483877,
+      "grad_norm": 0.11822610348463058,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.7552,
+      "step": 1880
+    },
+    {
+      "epoch": 0.727692751949177,
+      "grad_norm": 0.1216840073466301,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7428,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7315429781499663,
+      "grad_norm": 0.12785890698432922,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7503,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7353932043507556,
+      "grad_norm": 0.11486434191465378,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7491,
+      "step": 1910
+    },
+    {
+      "epoch": 0.739243430551545,
+      "grad_norm": 0.1169443354010582,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.7405,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7430936567523342,
+      "grad_norm": 0.12183164805173874,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.7555,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7469438829531235,
+      "grad_norm": 0.12354554980993271,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.7661,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7507941091539128,
+      "grad_norm": 0.13574601709842682,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.7533,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7546443353547021,
+      "grad_norm": 0.12556491792201996,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.7685,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7584945615554913,
+      "grad_norm": 0.11821416765451431,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.7658,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7623447877562807,
+      "grad_norm": 0.12234459072351456,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.7482,
+      "step": 1980
+    },
+    {
+      "epoch": 0.76619501395707,
+      "grad_norm": 0.1381792277097702,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.7522,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7700452401578592,
+      "grad_norm": 0.11668307334184647,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.751,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7738954663586486,
+      "grad_norm": 0.1239878311753273,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.7501,
+      "step": 2010
+    },
+    {
+      "epoch": 0.7777456925594378,
+      "grad_norm": 0.12283717095851898,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.737,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7815959187602272,
+      "grad_norm": 0.12468616664409637,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.723,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7854461449610165,
+      "grad_norm": 0.12114488333463669,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.7404,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7892963711618057,
+      "grad_norm": 0.11408759653568268,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.7484,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7931465973625951,
+      "grad_norm": 0.11462920159101486,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7286,
+      "step": 2060
+    },
+    {
+      "epoch": 0.7969968235633843,
+      "grad_norm": 0.12798266112804413,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.7406,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8008470497641736,
+      "grad_norm": 0.12972761690616608,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7272,
+      "step": 2080
+    },
+    {
+      "epoch": 0.804697275964963,
+      "grad_norm": 0.11920693516731262,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7507,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8085475021657522,
+      "grad_norm": 0.11617391556501389,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.7457,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8123977283665416,
+      "grad_norm": 0.1164344921708107,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.757,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8162479545673308,
+      "grad_norm": 0.12267202883958817,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.7559,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8200981807681201,
+      "grad_norm": 0.11937754601240158,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7406,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8239484069689095,
+      "grad_norm": 0.1275489628314972,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7515,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8277986331696987,
+      "grad_norm": 0.12967033684253693,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7365,
+      "step": 2150
+    },
+    {
+      "epoch": 0.831648859370488,
+      "grad_norm": 0.11148153245449066,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.7526,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8354990855712773,
+      "grad_norm": 0.11569025367498398,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.7548,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8393493117720666,
+      "grad_norm": 0.11744970828294754,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7443,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8431995379728559,
+      "grad_norm": 0.11974085867404938,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.7532,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8470497641736452,
+      "grad_norm": 0.1300898641347885,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.7377,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8508999903744345,
+      "grad_norm": 0.1267232745885849,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7276,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8547502165752238,
+      "grad_norm": 0.11501968652009964,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.7484,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586004427760131,
+      "grad_norm": 0.1287970095872879,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.741,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8624506689768023,
+      "grad_norm": 0.11964387446641922,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.761,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663008951775917,
+      "grad_norm": 0.12011078745126724,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7421,
+      "step": 2250
+    },
+    {
+      "epoch": 0.870151121378381,
+      "grad_norm": 0.12343201786279678,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7305,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740013475791703,
+      "grad_norm": 0.11975027620792389,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7331,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8778515737799596,
+      "grad_norm": 0.11683901399374008,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.7533,
+      "step": 2280
+    },
+    {
+      "epoch": 0.8817017999807488,
+      "grad_norm": 0.11742927134037018,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.753,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8855520261815382,
+      "grad_norm": 0.11286367475986481,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.7354,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8894022523823275,
+      "grad_norm": 0.11339740455150604,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.7364,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8932524785831167,
+      "grad_norm": 0.10938482731580734,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7467,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971027047839061,
+      "grad_norm": 0.12313669919967651,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.7579,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9009529309846953,
+      "grad_norm": 0.1241786777973175,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7482,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048031571854847,
+      "grad_norm": 0.11727552860975266,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.7304,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908653383386274,
+      "grad_norm": 0.12073932588100433,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7489,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125036095870632,
+      "grad_norm": 0.1287194788455963,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7352,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9163538357878526,
+      "grad_norm": 0.11950632184743881,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7392,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202040619886418,
+      "grad_norm": 0.11680721491575241,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.7598,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9240542881894311,
+      "grad_norm": 0.12663526833057404,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.749,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9279045143902205,
+      "grad_norm": 0.11780382692813873,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7381,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9317547405910097,
+      "grad_norm": 0.11319594830274582,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.7626,
+      "step": 2420
+    },
+    {
+      "epoch": 0.935604966791799,
+      "grad_norm": 0.12120883911848068,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.757,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9394551929925883,
+      "grad_norm": 0.12162882834672928,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7428,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433054191933776,
+      "grad_norm": 0.1259188950061798,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.7406,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9471556453941669,
+      "grad_norm": 0.12818758189678192,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.7625,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510058715949562,
+      "grad_norm": 0.12184157967567444,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.7468,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9548560977957455,
+      "grad_norm": 0.12966322898864746,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.7431,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587063239965348,
+      "grad_norm": 0.13867227733135223,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.7434,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9625565501973241,
+      "grad_norm": 0.12187886238098145,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7402,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664067763981133,
+      "grad_norm": 0.12048889696598053,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7345,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9702570025989027,
+      "grad_norm": 0.1165175586938858,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.7528,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974107228799692,
+      "grad_norm": 0.1191401332616806,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.7379,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9779574550004813,
+      "grad_norm": 0.11097937822341919,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7441,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9818076812012706,
+      "grad_norm": 0.11391369998455048,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7525,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9856579074020598,
+      "grad_norm": 0.11812368035316467,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.734,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9895081336028492,
+      "grad_norm": 0.1291765421628952,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7365,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9933583598036385,
+      "grad_norm": 0.10907117277383804,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7231,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9972085860044277,
+      "grad_norm": 0.11967071145772934,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7549,
+      "step": 2590
+    },
+    {
+      "epoch": 0.9999037443449803,
+      "step": 2597,
+      "total_flos": 6.502729116708504e+18,
+      "train_loss": 0.7978649394623261,
+      "train_runtime": 18782.2794,
+      "train_samples_per_second": 35.401,
+      "train_steps_per_second": 0.138
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.502729116708504e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/mc2_g14_378/finetune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771780cac8a3c68a05aeaf4aee93c85d7d663085ba7f901c8b0150bb5a5677b0
+size 6136

continuous/qwen3/mc2_g14_378/pretrain/config.json

@@ -0,0 +1,60 @@
+{
+  "_attn_implementation_autoset": true,
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1664,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-bigG-14-worldwide-378",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_g14_378.pt",
+  "vocab_size": 151936
+}

continuous/qwen3/mc2_g14_378/pretrain/mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991909ec70cb22fac924aed1451038a25bdd4eee80370dbc92522a154e0cd628
+size 30427192

continuous/qwen3/mc2_g14_378/pretrain/trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 0.8786392211914062,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 9.981,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.7976408004760742,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 6.5589,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.23954102396965027,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 5.2983,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.07376802712678909,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 4.8738,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.0549912229180336,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 4.7814,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.035330623388290405,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 4.7267,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.07964567095041275,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 4.6786,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.06629026681184769,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 4.6514,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.054001204669475555,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 4.6196,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.06876769661903381,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 4.5999,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.056675273925065994,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 4.5672,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.07686641067266464,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 4.5499,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.06272152066230774,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 4.5201,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.10405425727367401,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 4.4957,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.06566017866134644,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 4.4836,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.07154052704572678,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 4.4602,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.08845120668411255,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 4.438,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.08573576807975769,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 4.4199,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.08035098016262054,
+      "learning_rate": 0.000779204504653894,
+      "loss": 4.4104,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.07816305011510849,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 4.3814,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.08872032910585403,
+      "learning_rate": 0.00072685988254984,
+      "loss": 4.3672,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.08523327857255936,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 4.3713,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.10197874158620834,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 4.3652,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.08248809725046158,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 4.3425,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.07436154782772064,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 4.3207,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.13103219866752625,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 4.3283,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.12502165138721466,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 4.3029,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.07761412113904953,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 4.2907,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.08125612884759903,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 4.2724,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.09936586022377014,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 4.2682,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.09998597204685211,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 4.2755,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.0667056292295456,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 4.2634,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.11155548691749573,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 4.2421,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.09269794821739197,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 4.2386,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.0840400829911232,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 4.2389,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.08362014591693878,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 4.2419,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.08653614670038223,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 4.2203,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.07752811908721924,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 4.2316,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.10045653581619263,
+      "learning_rate": 0.000208323983828828,
+      "loss": 4.2101,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.0918351337313652,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 4.2097,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.07739397138357162,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 4.2039,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.06411351263523102,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 4.1941,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.07283350825309753,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 4.1938,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.07007995247840881,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 4.1999,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.06308047473430634,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 4.1904,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.06272301822900772,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 4.1803,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.06520343571901321,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 4.166,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.06513313949108124,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 4.1758,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.0613534078001976,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 4.175,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.06278136372566223,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 4.19,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.0625012144446373,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 4.1791,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.06260190904140472,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 4.1695,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.06025629863142967,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 4.1723,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.06258535385131836,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 4.1767,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 6.244151627486331e+17,
+      "train_loss": 4.509469107531626,
+      "train_runtime": 6668.5378,
+      "train_samples_per_second": 83.696,
+      "train_steps_per_second": 0.082
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.244151627486331e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/mc2_h14_378/finetune/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

continuous/qwen3/mc2_h14_378/finetune/config.json

@@ -0,0 +1,59 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1280,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-H-14-worldwide-378",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_h14_378.pt",
+  "vocab_size": 151936
+}

continuous/qwen3/mc2_h14_378/finetune/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}