upload model

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "/staging/jzhang2427/checkpoints/llava-v1.5-13b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "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": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c2c515dde5df5a782dd4fad7e88e3ad52d957a7b4e78cd92c5d5a936d440be
+size 4978265800

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312f001543fc3c0bb5ff2183c5e83975b522dc08c65c9323927236e761a3fd9d
+size 4970422232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c124852df7b019a91e5c071a6aa9a8c401972f96d5d3763f4de4c39415570a4
+size 4970422256

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc127c2b3900357d4754c8fbfbe1b4cb4ba311f7c656d1d20ab9d68bc1634f5
+size 4933701504

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8ad096a6c2a434e361cd0abc229601964df3ac9116c71477ed663c2b0fc0f6
+size 4933722216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fc20113a564f993db2cdd894a3dc80aaef6556fcaac45093bd39493553172f
+size 1915248664

model.safetensors.index.json

@@ -0,0 +1,765 @@
+{
+  "metadata": {
+    "total_size": 26701678592
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.mm_projector.0.bias": "model-00006-of-00006.safetensors",
+    "model.mm_projector.0.weight": "model-00006-of-00006.safetensors",
+    "model.mm_projector.2.bias": "model-00006-of-00006.safetensors",
+    "model.mm_projector.2.weight": "model-00006-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00006-of-00006.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1908 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 313,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.56e-06,
+      "loss": 0.4214,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.12e-06,
+      "loss": 0.4106,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.68e-06,
+      "loss": 0.4552,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.024e-05,
+      "loss": 0.3365,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.28e-05,
+      "loss": 0.8407,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.536e-05,
+      "loss": 0.3813,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.7919999999999998e-05,
+      "loss": 0.8731,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.048e-05,
+      "loss": 0.3706,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.304e-05,
+      "loss": 0.3535,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.56e-05,
+      "loss": 0.3863,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.5599311996620115e-05,
+      "loss": 0.3584,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.559724806044119e-05,
+      "loss": 0.3363,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.5593808413337446e-05,
+      "loss": 0.3735,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.558899342507277e-05,
+      "loss": 0.3471,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.5582803613260944e-05,
+      "loss": 0.3744,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.5575239643310006e-05,
+      "loss": 0.3509,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.5566302328350718e-05,
+      "loss": 0.345,
+      "step": 17
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5555992629149157e-05,
+      "loss": 0.3466,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5544311654003438e-05,
+      "loss": 0.3652,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.553126065862455e-05,
+      "loss": 0.3544,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.5516841046001392e-05,
+      "loss": 0.3413,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.5501054366249938e-05,
+      "loss": 0.3467,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.5483902316446597e-05,
+      "loss": 0.3449,
+      "step": 23
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.5465386740445777e-05,
+      "loss": 0.3508,
+      "step": 24
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.5445509628681684e-05,
+      "loss": 0.3506,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.5424273117954328e-05,
+      "loss": 0.3426,
+      "step": 26
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.540167949119982e-05,
+      "loss": 0.3294,
+      "step": 27
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.5377731177244976e-05,
+      "loss": 0.3914,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.5352430750546188e-05,
+      "loss": 0.3662,
+      "step": 29
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.532578093091269e-05,
+      "loss": 0.361,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.5297784583214168e-05,
+      "loss": 0.3488,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.5268444717072784e-05,
+      "loss": 0.375,
+      "step": 32
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.523776448653964e-05,
+      "loss": 0.3583,
+      "step": 33
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.5205747189755726e-05,
+      "loss": 0.3491,
+      "step": 34
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.5172396268597348e-05,
+      "loss": 0.3589,
+      "step": 35
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.5137715308306148e-05,
+      "loss": 0.3913,
+      "step": 36
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.5101708037103674e-05,
+      "loss": 0.3482,
+      "step": 37
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.506437832579059e-05,
+      "loss": 0.3478,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.502573018733058e-05,
+      "loss": 0.3416,
+      "step": 39
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.498576777641894e-05,
+      "loss": 0.3578,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.494449538903595e-05,
+      "loss": 0.3771,
+      "step": 41
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.4901917461985037e-05,
+      "loss": 0.3556,
+      "step": 42
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.485803857241586e-05,
+      "loss": 0.3466,
+      "step": 43
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.4812863437332214e-05,
+      "loss": 0.3456,
+      "step": 44
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.4766396913084973e-05,
+      "loss": 0.3417,
+      "step": 45
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.471864399485004e-05,
+      "loss": 0.3613,
+      "step": 46
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.466960981609134e-05,
+      "loss": 0.3762,
+      "step": 47
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.461929964800899e-05,
+      "loss": 0.3554,
+      "step": 48
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.4567718898972623e-05,
+      "loss": 0.3509,
+      "step": 49
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.4514873113940003e-05,
+      "loss": 0.3962,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.4460767973860926e-05,
+      "loss": 0.3509,
+      "step": 51
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.4405409295066526e-05,
+      "loss": 0.3624,
+      "step": 52
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.434880302864401e-05,
+      "loss": 0.3807,
+      "step": 53
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.4290955259796913e-05,
+      "loss": 0.3182,
+      "step": 54
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.423187220719093e-05,
+      "loss": 0.3609,
+      "step": 55
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.4171560222285425e-05,
+      "loss": 0.3425,
+      "step": 56
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.4110025788650625e-05,
+      "loss": 0.3361,
+      "step": 57
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.404727552127064e-05,
+      "loss": 0.3444,
+      "step": 58
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.3983316165832353e-05,
+      "loss": 0.3416,
+      "step": 59
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.391815459800025e-05,
+      "loss": 0.3519,
+      "step": 60
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.385179782267729e-05,
+      "loss": 0.3586,
+      "step": 61
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.3784252973251862e-05,
+      "loss": 0.3415,
+      "step": 62
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.3715527310830945e-05,
+      "loss": 0.3468,
+      "step": 63
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.364562822345955e-05,
+      "loss": 0.346,
+      "step": 64
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.3574563225326483e-05,
+      "loss": 0.3538,
+      "step": 65
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.3502339955956567e-05,
+      "loss": 0.3451,
+      "step": 66
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.3428966179389407e-05,
+      "loss": 0.3535,
+      "step": 67
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.335444978334473e-05,
+      "loss": 0.3462,
+      "step": 68
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.327879877837447e-05,
+      "loss": 0.3435,
+      "step": 69
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.32020212970016e-05,
+      "loss": 0.3492,
+      "step": 70
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.312412559284593e-05,
+      "loss": 0.3439,
+      "step": 71
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.304512003973678e-05,
+      "loss": 0.3415,
+      "step": 72
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.296501313081284e-05,
+      "loss": 0.3548,
+      "step": 73
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.2883813477609127e-05,
+      "loss": 0.3488,
+      "step": 74
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.280152980913124e-05,
+      "loss": 0.3548,
+      "step": 75
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.2718170970916988e-05,
+      "loss": 0.3469,
+      "step": 76
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.263374592408551e-05,
+      "loss": 0.3517,
+      "step": 77
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.2548263744373924e-05,
+      "loss": 0.3456,
+      "step": 78
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.246173362116169e-05,
+      "loss": 0.3456,
+      "step": 79
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.2374164856482753e-05,
+      "loss": 0.3445,
+      "step": 80
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.228556686402556e-05,
+      "loss": 0.3509,
+      "step": 81
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.219594916812109e-05,
+      "loss": 0.3527,
+      "step": 82
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.210532140271898e-05,
+      "loss": 0.3414,
+      "step": 83
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.2013693310351872e-05,
+      "loss": 0.3366,
+      "step": 84
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.192107474108809e-05,
+      "loss": 0.3385,
+      "step": 85
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.1827475651472734e-05,
+      "loss": 0.3652,
+      "step": 86
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.1732906103457373e-05,
+      "loss": 0.3608,
+      "step": 87
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.1637376263318357e-05,
+      "loss": 0.3499,
+      "step": 88
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.1540896400563956e-05,
+      "loss": 0.3726,
+      "step": 89
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.144347688683037e-05,
+      "loss": 0.3466,
+      "step": 90
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.1345128194766766e-05,
+      "loss": 0.3599,
+      "step": 91
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.1245860896909483e-05,
+      "loss": 0.3582,
+      "step": 92
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.1145685664545464e-05,
+      "loss": 0.3806,
+      "step": 93
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.104461326656509e-05,
+      "loss": 0.3468,
+      "step": 94
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.0942654568304528e-05,
+      "loss": 0.3313,
+      "step": 95
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.0839820530377674e-05,
+      "loss": 0.351,
+      "step": 96
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.0736122207497922e-05,
+      "loss": 0.3768,
+      "step": 97
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.063157074728974e-05,
+      "loss": 0.4054,
+      "step": 98
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.052617738909032e-05,
+      "loss": 0.3371,
+      "step": 99
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.0419953462741325e-05,
+      "loss": 0.3451,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.031291038737093e-05,
+      "loss": 0.3731,
+      "step": 101
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.020505967016628e-05,
+      "loss": 0.3518,
+      "step": 102
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.0096412905136418e-05,
+      "loss": 0.3434,
+      "step": 103
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9986981771865968e-05,
+      "loss": 0.3464,
+      "step": 104
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9876778034259548e-05,
+      "loss": 0.3605,
+      "step": 105
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9765813539277148e-05,
+      "loss": 0.3912,
+      "step": 106
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9654100215660584e-05,
+      "loss": 0.3963,
+      "step": 107
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9541650072651133e-05,
+      "loss": 0.3566,
+      "step": 108
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9428475198698565e-05,
+      "loss": 0.3404,
+      "step": 109
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9314587760161588e-05,
+      "loss": 0.352,
+      "step": 110
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.92e-05,
+      "loss": 0.347,
+      "step": 111
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9084724236458523e-05,
+      "loss": 0.3685,
+      "step": 112
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8968772861742624e-05,
+      "loss": 0.348,
+      "step": 113
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.885215834068631e-05,
+      "loss": 0.3611,
+      "step": 114
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.873489320941219e-05,
+      "loss": 0.369,
+      "step": 115
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8616990073983795e-05,
+      "loss": 0.3493,
+      "step": 116
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8498461609050458e-05,
+      "loss": 0.3451,
+      "step": 117
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.837932055648475e-05,
+      "loss": 0.3702,
+      "step": 118
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.825957972401274e-05,
+      "loss": 0.3294,
+      "step": 119
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8139251983837158e-05,
+      "loss": 0.39,
+      "step": 120
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8018350271253614e-05,
+      "loss": 0.3598,
+      "step": 121
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.789688758326007e-05,
+      "loss": 0.351,
+      "step": 122
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.7774876977159616e-05,
+      "loss": 0.3612,
+      "step": 123
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.7652331569156855e-05,
+      "loss": 0.3559,
+      "step": 124
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.752926453294786e-05,
+      "loss": 0.3637,
+      "step": 125
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.740568909830401e-05,
+      "loss": 0.3374,
+      "step": 126
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.72816185496498e-05,
+      "loss": 0.3318,
+      "step": 127
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.715706622463473e-05,
+      "loss": 0.3552,
+      "step": 128
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.703204551269951e-05,
+      "loss": 0.3614,
+      "step": 129
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.6906569853636704e-05,
+      "loss": 0.3511,
+      "step": 130
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.6780652736145928e-05,
+      "loss": 0.3472,
+      "step": 131
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.66543076963838e-05,
+      "loss": 0.3504,
+      "step": 132
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.6527548316508828e-05,
+      "loss": 0.367,
+      "step": 133
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.6400388223221283e-05,
+      "loss": 0.3452,
+      "step": 134
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.6272841086298353e-05,
+      "loss": 0.3458,
+      "step": 135
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.6144920617124617e-05,
+      "loss": 0.3608,
+      "step": 136
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.601664056721806e-05,
+      "loss": 0.3453,
+      "step": 137
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.5888014726751798e-05,
+      "loss": 0.3504,
+      "step": 138
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.5759056923071613e-05,
+      "loss": 0.3463,
+      "step": 139
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.5629781019209496e-05,
+      "loss": 0.3493,
+      "step": 140
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.5500200912393385e-05,
+      "loss": 0.352,
+      "step": 141
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.5370330532553195e-05,
+      "loss": 0.3419,
+      "step": 142
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.524018384082335e-05,
+      "loss": 0.3366,
+      "step": 143
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.5109774828041934e-05,
+      "loss": 0.3478,
+      "step": 144
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.4979117513246702e-05,
+      "loss": 0.3576,
+      "step": 145
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4848225942167988e-05,
+      "loss": 0.3469,
+      "step": 146
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4717114185718804e-05,
+      "loss": 0.3589,
+      "step": 147
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4585796338482217e-05,
+      "loss": 0.3383,
+      "step": 148
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.4454286517196146e-05,
+      "loss": 0.3512,
+      "step": 149
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.4322598859235845e-05,
+      "loss": 0.3432,
+      "step": 150
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.4190747521094073e-05,
+      "loss": 0.3496,
+      "step": 151
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.4058746676859326e-05,
+      "loss": 0.3482,
+      "step": 152
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.3926610516692062e-05,
+      "loss": 0.3478,
+      "step": 153
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.3794353245299282e-05,
+      "loss": 0.3496,
+      "step": 154
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.3661989080407505e-05,
+      "loss": 0.3472,
+      "step": 155
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.3529532251234362e-05,
+      "loss": 0.3486,
+      "step": 156
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.3396996996958944e-05,
+      "loss": 0.3487,
+      "step": 157
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.3264397565191072e-05,
+      "loss": 0.346,
+      "step": 158
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.3131748210439692e-05,
+      "loss": 0.3458,
+      "step": 159
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.2999063192580492e-05,
+      "loss": 0.3417,
+      "step": 160
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.286635677532296e-05,
+      "loss": 0.3639,
+      "step": 161
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.2733643224677042e-05,
+      "loss": 0.3511,
+      "step": 162
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.2600936807419507e-05,
+      "loss": 0.3461,
+      "step": 163
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.2468251789560305e-05,
+      "loss": 0.3533,
+      "step": 164
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.2335602434808929e-05,
+      "loss": 0.3446,
+      "step": 165
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.2203003003041055e-05,
+      "loss": 0.3476,
+      "step": 166
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.2070467748765635e-05,
+      "loss": 0.3434,
+      "step": 167
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.1938010919592494e-05,
+      "loss": 0.3499,
+      "step": 168
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.1805646754700718e-05,
+      "loss": 0.3483,
+      "step": 169
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.1673389483307942e-05,
+      "loss": 0.3457,
+      "step": 170
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.1541253323140676e-05,
+      "loss": 0.3439,
+      "step": 171
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.1409252478905925e-05,
+      "loss": 0.341,
+      "step": 172
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.1277401140764161e-05,
+      "loss": 0.3653,
+      "step": 173
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.1145713482803853e-05,
+      "loss": 0.3601,
+      "step": 174
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.1014203661517785e-05,
+      "loss": 0.3495,
+      "step": 175
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.0882885814281198e-05,
+      "loss": 0.3509,
+      "step": 176
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.0751774057832015e-05,
+      "loss": 0.3471,
+      "step": 177
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.0620882486753296e-05,
+      "loss": 0.3491,
+      "step": 178
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.0490225171958064e-05,
+      "loss": 0.3491,
+      "step": 179
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.0359816159176651e-05,
+      "loss": 0.3485,
+      "step": 180
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.0229669467446806e-05,
+      "loss": 0.346,
+      "step": 181
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.0099799087606617e-05,
+      "loss": 0.3487,
+      "step": 182
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.970218980790506e-06,
+      "loss": 0.3534,
+      "step": 183
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.840943076928391e-06,
+      "loss": 0.3484,
+      "step": 184
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.711985273248199e-06,
+      "loss": 0.353,
+      "step": 185
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.583359432781938e-06,
+      "loss": 0.3501,
+      "step": 186
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.455079382875387e-06,
+      "loss": 0.3483,
+      "step": 187
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.327158913701648e-06,
+      "loss": 0.351,
+      "step": 188
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.199611776778716e-06,
+      "loss": 0.347,
+      "step": 189
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.072451683491174e-06,
+      "loss": 0.348,
+      "step": 190
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.9456923036162e-06,
+      "loss": 0.349,
+      "step": 191
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.819347263854072e-06,
+      "loss": 0.3492,
+      "step": 192
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.693430146363296e-06,
+      "loss": 0.3521,
+      "step": 193
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.567954487300488e-06,
+      "loss": 0.348,
+      "step": 194
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.442933775365273e-06,
+      "loss": 0.3464,
+      "step": 195
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.318381450350199e-06,
+      "loss": 0.35,
+      "step": 196
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.194310901695986e-06,
+      "loss": 0.3531,
+      "step": 197
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.070735467052144e-06,
+      "loss": 0.3466,
+      "step": 198
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.947668430843145e-06,
+      "loss": 0.3541,
+      "step": 199
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.825123022840381e-06,
+      "loss": 0.3469,
+      "step": 200
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.703112416739936e-06,
+      "loss": 0.3471,
+      "step": 201
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.581649728746385e-06,
+      "loss": 0.3455,
+      "step": 202
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.460748016162839e-06,
+      "loss": 0.3433,
+      "step": 203
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.340420275987263e-06,
+      "loss": 0.351,
+      "step": 204
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.2206794435152495e-06,
+      "loss": 0.3432,
+      "step": 205
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.101538390949542e-06,
+      "loss": 0.3496,
+      "step": 206
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.983009926016205e-06,
+      "loss": 0.3456,
+      "step": 207
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.865106790587808e-06,
+      "loss": 0.3499,
+      "step": 208
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.747841659313692e-06,
+      "loss": 0.3509,
+      "step": 209
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.631227138257378e-06,
+      "loss": 0.3432,
+      "step": 210
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.515275763541477e-06,
+      "loss": 0.3468,
+      "step": 211
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.400000000000002e-06,
+      "loss": 0.3435,
+      "step": 212
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.285412239838408e-06,
+      "loss": 0.3431,
+      "step": 213
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.171524801301434e-06,
+      "loss": 0.3454,
+      "step": 214
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.058349927348865e-06,
+      "loss": 0.3436,
+      "step": 215
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.945899784339418e-06,
+      "loss": 0.3458,
+      "step": 216
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.834186460722848e-06,
+      "loss": 0.3472,
+      "step": 217
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.7232219657404555e-06,
+      "loss": 0.3468,
+      "step": 218
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.613018228134031e-06,
+      "loss": 0.3461,
+      "step": 219
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.5035870948635815e-06,
+      "loss": 0.3391,
+      "step": 220
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.3949403298337225e-06,
+      "loss": 0.351,
+      "step": 221
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.287089612629064e-06,
+      "loss": 0.3506,
+      "step": 222
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.180046537258678e-06,
+      "loss": 0.3581,
+      "step": 223
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.073822610909679e-06,
+      "loss": 0.3335,
+      "step": 224
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.9684292527102595e-06,
+      "loss": 0.3438,
+      "step": 225
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.8638777925020805e-06,
+      "loss": 0.3422,
+      "step": 226
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.760179469622325e-06,
+      "loss": 0.3425,
+      "step": 227
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.657345431695474e-06,
+      "loss": 0.3496,
+      "step": 228
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.555386733434909e-06,
+      "loss": 0.3459,
+      "step": 229
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.454314335454537e-06,
+      "loss": 0.3469,
+      "step": 230
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.35413910309052e-06,
+      "loss": 0.3424,
+      "step": 231
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.254871805233233e-06,
+      "loss": 0.3441,
+      "step": 232
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.1565231131696304e-06,
+      "loss": 0.3412,
+      "step": 233
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.059103599436042e-06,
+      "loss": 0.3396,
+      "step": 234
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.962623736681643e-06,
+      "loss": 0.3466,
+      "step": 235
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.867093896542628e-06,
+      "loss": 0.3468,
+      "step": 236
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.7725243485272696e-06,
+      "loss": 0.3489,
+      "step": 237
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.6789252589119114e-06,
+      "loss": 0.3416,
+      "step": 238
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.586306689648127e-06,
+      "loss": 0.3372,
+      "step": 239
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.4946785972810218e-06,
+      "loss": 0.3433,
+      "step": 240
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.404050831878909e-06,
+      "loss": 0.3429,
+      "step": 241
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.314433135974441e-06,
+      "loss": 0.3397,
+      "step": 242
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.2258351435172485e-06,
+      "loss": 0.3428,
+      "step": 243
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.1382663788383126e-06,
+      "loss": 0.3431,
+      "step": 244
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.051736255626079e-06,
+      "loss": 0.3405,
+      "step": 245
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.9662540759144888e-06,
+      "loss": 0.3366,
+      "step": 246
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.8818290290830103e-06,
+      "loss": 0.3438,
+      "step": 247
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.7984701908687624e-06,
+      "loss": 0.3378,
+      "step": 248
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.7161865223908718e-06,
+      "loss": 0.3405,
+      "step": 249
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.6349868691871548e-06,
+      "loss": 0.3347,
+      "step": 250
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.55487996026322e-06,
+      "loss": 0.3341,
+      "step": 251
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.47587440715407e-06,
+      "loss": 0.3353,
+      "step": 252
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.397978702998398e-06,
+      "loss": 0.34,
+      "step": 253
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.321201221625533e-06,
+      "loss": 0.3338,
+      "step": 254
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.245550216655266e-06,
+      "loss": 0.3394,
+      "step": 255
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.1710338206105917e-06,
+      "loss": 0.3364,
+      "step": 256
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.097660044043432e-06,
+      "loss": 0.3341,
+      "step": 257
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.025436774673518e-06,
+      "loss": 0.3343,
+      "step": 258
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.9543717765404494e-06,
+      "loss": 0.3319,
+      "step": 259
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.8844726891690513e-06,
+      "loss": 0.3338,
+      "step": 260
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.8157470267481371e-06,
+      "loss": 0.3366,
+      "step": 261
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7482021773227075e-06,
+      "loss": 0.3345,
+      "step": 262
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6818454019997475e-06,
+      "loss": 0.3395,
+      "step": 263
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6166838341676451e-06,
+      "loss": 0.3273,
+      "step": 264
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.5527244787293625e-06,
+      "loss": 0.3198,
+      "step": 265
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4899742113493743e-06,
+      "loss": 0.3208,
+      "step": 266
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.428439777714574e-06,
+      "loss": 0.3279,
+      "step": 267
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.3681277928090692e-06,
+      "loss": 0.3056,
+      "step": 268
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.309044740203086e-06,
+      "loss": 0.3178,
+      "step": 269
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2511969713559907e-06,
+      "loss": 0.3208,
+      "step": 270
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1945907049334721e-06,
+      "loss": 0.3188,
+      "step": 271
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1392320261390737e-06,
+      "loss": 0.3105,
+      "step": 272
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.0851268860599972e-06,
+      "loss": 0.328,
+      "step": 273
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.0322811010273738e-06,
+      "loss": 0.3209,
+      "step": 274
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.807003519910083e-07,
+      "loss": 0.3069,
+      "step": 275
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.303901839086563e-07,
+      "loss": 0.3184,
+      "step": 276
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.813560051499593e-07,
+      "loss": 0.3087,
+      "step": 277
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.336030869150249e-07,
+      "loss": 0.3141,
+      "step": 278
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.871365626677871e-07,
+      "loss": 0.3053,
+      "step": 279
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.419614275841396e-07,
+      "loss": 0.3029,
+      "step": 280
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.980825380149597e-07,
+      "loss": 0.306,
+      "step": 281
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.555046109640528e-07,
+      "loss": 0.3109,
+      "step": 282
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.142322235810567e-07,
+      "loss": 0.3052,
+      "step": 283
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.742698126694194e-07,
+      "loss": 0.2874,
+      "step": 284
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.356216742094091e-07,
+      "loss": 0.2873,
+      "step": 285
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.982919628963258e-07,
+      "loss": 0.2942,
+      "step": 286
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.6228469169385133e-07,
+      "loss": 0.2929,
+      "step": 287
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.276037314026496e-07,
+      "loss": 0.2817,
+      "step": 288
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.942528102442736e-07,
+      "loss": 0.2911,
+      "step": 289
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.6223551346035803e-07,
+      "loss": 0.2913,
+      "step": 290
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.3155528292721496e-07,
+      "loss": 0.2838,
+      "step": 291
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.022154167858304e-07,
+      "loss": 0.277,
+      "step": 292
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.742190690873073e-07,
+      "loss": 0.2717,
+      "step": 293
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.4756924945381226e-07,
+      "loss": 0.285,
+      "step": 294
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.2226882275502503e-07,
+      "loss": 0.2896,
+      "step": 295
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.983205088001796e-07,
+      "loss": 0.311,
+      "step": 296
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.75726882045673e-07,
+      "loss": 0.2688,
+      "step": 297
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5449037131831458e-07,
+      "loss": 0.2615,
+      "step": 298
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.3461325955422012e-07,
+      "loss": 0.2638,
+      "step": 299
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1609768355340293e-07,
+      "loss": 0.2819,
+      "step": 300
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.894563375006129e-08,
+      "loss": 0.2903,
+      "step": 301
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.315895399860551e-08,
+      "loss": 0.2848,
+      "step": 302
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.873934137544922e-08,
+      "loss": 0.2776,
+      "step": 303
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.568834599656185e-08,
+      "loss": 0.2674,
+      "step": 304
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.400737085084074e-08,
+      "loss": 0.2691,
+      "step": 305
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.3697671649281346e-08,
+      "loss": 0.292,
+      "step": 306
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.476035668999259e-08,
+      "loss": 0.2719,
+      "step": 307
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.7196386739053082e-08,
+      "loss": 0.2706,
+      "step": 308
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.100657492722661e-08,
+      "loss": 0.2676,
+      "step": 309
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.191586662552595e-09,
+      "loss": 0.2799,
+      "step": 310
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.7519395588115003e-09,
+      "loss": 0.2465,
+      "step": 311
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.880033798850604e-10,
+      "loss": 0.2624,
+      "step": 312
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.2778,
+      "step": 313
+    },
+    {
+      "epoch": 1.0,
+      "step": 313,
+      "total_flos": 10177814200320.0,
+      "train_loss": 0.3452488072097492,
+      "train_runtime": 2002.2939,
+      "train_samples_per_second": 9.999,
+      "train_steps_per_second": 0.156
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 313,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 10177814200320.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7245e2b0d2ebc131be5bc09052cde2b4ca2bff1cc10ba7778cc3dec8ecf17a
+size 6776