commit from jcy

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/jcy/ckpt/llama3-8b-instruct",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "anyres",
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "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": "/data/jcy/ckpt/clip-vit-large-patch14-336",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128256,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 1000000000000000019884624838656,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 128257
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55a4d6c9f568884b0ee766216c16cde33bd689bf3fc9b7c081a7d1953d255ad
+size 4976715144

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1155d2f04d05323700de70fba0d6384ce2efd082f88d7d40a9c6b5f4bfc64c7
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036352178aa5473368de4adf1dc874908d19ff4ac721703d5acdde314e231446
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3139034a954659376b9cb8d140158d9d5bc3ab324edfc44f3b26e2fd345cbaa7
+size 1817183128

model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 16709521408
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.image_newline": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2072 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,4056 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9986976744186047,
+  "eval_steps": 500,
+  "global_step": 671,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 1.9835,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 1.9424,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.9622,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 1.8711,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 1.856,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.7429,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.7233,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 1.8379,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.7302,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 1.7233,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0476190476190477e-05,
+      "loss": 1.7449,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.6604,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.2380952380952383e-05,
+      "loss": 1.659,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.5993,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 1.6294,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.523809523809524e-05,
+      "loss": 1.6448,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 1.646,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 1.6029,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8095238095238097e-05,
+      "loss": 1.5918,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 1.5732,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 1.5891,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999883200175286e-05,
+      "loss": 1.5999,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999953280342959e-05,
+      "loss": 1.6173,
+      "step": 23
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9998948817948157e-05,
+      "loss": 1.5544,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9998131257372878e-05,
+      "loss": 1.5308,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9997080140801932e-05,
+      "loss": 1.6077,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9995795492789368e-05,
+      "loss": 1.5175,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999427734334452e-05,
+      "loss": 1.4982,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9992525727931303e-05,
+      "loss": 1.4936,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9990540687467394e-05,
+      "loss": 1.4676,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998832226832327e-05,
+      "loss": 1.5268,
+      "step": 31
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9985870522321118e-05,
+      "loss": 1.4486,
+      "step": 32
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9983185506733643e-05,
+      "loss": 1.5313,
+      "step": 33
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9980267284282718e-05,
+      "loss": 1.4926,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9977115923137912e-05,
+      "loss": 1.4406,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9973731496914914e-05,
+      "loss": 1.4931,
+      "step": 36
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9970114084673796e-05,
+      "loss": 1.5088,
+      "step": 37
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9966263770917192e-05,
+      "loss": 1.5093,
+      "step": 38
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996218064558829e-05,
+      "loss": 1.5074,
+      "step": 39
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9957864804068752e-05,
+      "loss": 1.4461,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.995331634717649e-05,
+      "loss": 1.4537,
+      "step": 41
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.994853538116329e-05,
+      "loss": 1.4572,
+      "step": 42
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.994352201771236e-05,
+      "loss": 1.4689,
+      "step": 43
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9938276373935688e-05,
+      "loss": 1.4414,
+      "step": 44
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.993279857237133e-05,
+      "loss": 1.4722,
+      "step": 45
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.992708874098054e-05,
+      "loss": 1.4739,
+      "step": 46
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 1.4743,
+      "step": 47
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.99149735276626e-05,
+      "loss": 1.5054,
+      "step": 48
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9908568428746408e-05,
+      "loss": 1.4858,
+      "step": 49
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9901931866019087e-05,
+      "loss": 1.3958,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9895063994510512e-05,
+      "loss": 1.4096,
+      "step": 51
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.988796497465392e-05,
+      "loss": 1.3925,
+      "step": 52
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9880634972282168e-05,
+      "loss": 1.4134,
+      "step": 53
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.987307415862385e-05,
+      "loss": 1.4232,
+      "step": 54
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.986528271029931e-05,
+      "loss": 1.4263,
+      "step": 55
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.985726080931651e-05,
+      "loss": 1.4345,
+      "step": 56
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9849008643066774e-05,
+      "loss": 1.4655,
+      "step": 57
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9840526404320415e-05,
+      "loss": 1.4758,
+      "step": 58
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9831814291222233e-05,
+      "loss": 1.4192,
+      "step": 59
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.982287250728689e-05,
+      "loss": 1.5018,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9813701261394136e-05,
+      "loss": 1.4578,
+      "step": 61
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9804300767783958e-05,
+      "loss": 1.4346,
+      "step": 62
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.979467124605156e-05,
+      "loss": 1.4475,
+      "step": 63
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9784812921142232e-05,
+      "loss": 1.4009,
+      "step": 64
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.977472602334609e-05,
+      "loss": 1.4464,
+      "step": 65
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9764410788292724e-05,
+      "loss": 1.3768,
+      "step": 66
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9753867456945653e-05,
+      "loss": 1.3851,
+      "step": 67
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9743096275596735e-05,
+      "loss": 1.4259,
+      "step": 68
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9732097495860388e-05,
+      "loss": 1.4571,
+      "step": 69
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9720871374667714e-05,
+      "loss": 1.4097,
+      "step": 70
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 1.536,
+      "step": 71
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9697738162185163e-05,
+      "loss": 1.4237,
+      "step": 72
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 1.3861,
+      "step": 73
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9673698799700582e-05,
+      "loss": 1.4183,
+      "step": 74
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9661340010850025e-05,
+      "loss": 1.4255,
+      "step": 75
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9648755533435517e-05,
+      "loss": 1.4681,
+      "step": 76
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9635945661430006e-05,
+      "loss": 1.4336,
+      "step": 77
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9622910694071654e-05,
+      "loss": 1.4406,
+      "step": 78
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9609650935856847e-05,
+      "loss": 1.4647,
+      "step": 79
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9596166696533062e-05,
+      "loss": 1.4086,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9582458291091664e-05,
+      "loss": 1.3972,
+      "step": 81
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.956852603976052e-05,
+      "loss": 1.4239,
+      "step": 82
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9554370267996537e-05,
+      "loss": 1.433,
+      "step": 83
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9539991306478046e-05,
+      "loss": 1.4477,
+      "step": 84
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.952538949109708e-05,
+      "loss": 1.4227,
+      "step": 85
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 1.4291,
+      "step": 86
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9495518668337204e-05,
+      "loss": 1.3841,
+      "step": 87
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9480250358739667e-05,
+      "loss": 1.3668,
+      "step": 88
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.94647605908261e-05,
+      "loss": 1.4258,
+      "step": 89
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.944904972643694e-05,
+      "loss": 1.4438,
+      "step": 90
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9433118132577432e-05,
+      "loss": 1.4337,
+      "step": 91
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9416966181409047e-05,
+      "loss": 1.4111,
+      "step": 92
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.94005942502408e-05,
+      "loss": 1.4473,
+      "step": 93
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9384002721520423e-05,
+      "loss": 1.3321,
+      "step": 94
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.936719198282545e-05,
+      "loss": 1.3896,
+      "step": 95
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 1.3459,
+      "step": 96
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.933291445141635e-05,
+      "loss": 1.4044,
+      "step": 97
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.931544845942415e-05,
+      "loss": 1.4181,
+      "step": 98
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 1.4039,
+      "step": 99
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.927986406287973e-05,
+      "loss": 1.3454,
+      "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9261746489577767e-05,
+      "loss": 1.406,
+      "step": 101
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.92434125622025e-05,
+      "loss": 1.431,
+      "step": 102
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9224862709033823e-05,
+      "loss": 1.3683,
+      "step": 103
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9206097363395668e-05,
+      "loss": 1.3528,
+      "step": 104
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9187116963645845e-05,
+      "loss": 1.4111,
+      "step": 105
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9167921953165827e-05,
+      "loss": 1.3924,
+      "step": 106
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9148512780350384e-05,
+      "loss": 1.3701,
+      "step": 107
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9128889898597117e-05,
+      "loss": 1.327,
+      "step": 108
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.910905376629585e-05,
+      "loss": 1.3746,
+      "step": 109
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9089004846817947e-05,
+      "loss": 1.3469,
+      "step": 110
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9068743608505454e-05,
+      "loss": 1.3765,
+      "step": 111
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9048270524660197e-05,
+      "loss": 1.4148,
+      "step": 112
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.902758607353269e-05,
+      "loss": 1.4208,
+      "step": 113
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9006690738310988e-05,
+      "loss": 1.3988,
+      "step": 114
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.898558500710939e-05,
+      "loss": 1.3937,
+      "step": 115
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.896426937295704e-05,
+      "loss": 1.4248,
+      "step": 116
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.89427443337864e-05,
+      "loss": 1.3625,
+      "step": 117
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8921010392421628e-05,
+      "loss": 1.3566,
+      "step": 118
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.889906805656684e-05,
+      "loss": 1.3763,
+      "step": 119
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8876917838794226e-05,
+      "loss": 1.4015,
+      "step": 120
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 1.3169,
+      "step": 121
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8831995832052802e-05,
+      "loss": 1.4215,
+      "step": 122
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8809225092460488e-05,
+      "loss": 1.4371,
+      "step": 123
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8786248569678847e-05,
+      "loss": 1.4199,
+      "step": 124
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8763066800438638e-05,
+      "loss": 1.3484,
+      "step": 125
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.873968032626518e-05,
+      "loss": 1.3701,
+      "step": 126
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8716089693465696e-05,
+      "loss": 1.359,
+      "step": 127
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.869229545311653e-05,
+      "loss": 1.3674,
+      "step": 128
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8668298161050308e-05,
+      "loss": 1.3531,
+      "step": 129
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8644098377842934e-05,
+      "loss": 1.3539,
+      "step": 130
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8619696668800494e-05,
+      "loss": 1.351,
+      "step": 131
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8595093603946053e-05,
+      "loss": 1.4147,
+      "step": 132
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8570289758006346e-05,
+      "loss": 1.4284,
+      "step": 133
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8545285710398343e-05,
+      "loss": 1.3313,
+      "step": 134
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.852008204521572e-05,
+      "loss": 1.3986,
+      "step": 135
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8494679351215212e-05,
+      "loss": 1.3815,
+      "step": 136
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.846907822180286e-05,
+      "loss": 1.4004,
+      "step": 137
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8443279255020153e-05,
+      "loss": 1.3541,
+      "step": 138
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8417283053530047e-05,
+      "loss": 1.3502,
+      "step": 139
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8391090224602895e-05,
+      "loss": 1.4261,
+      "step": 140
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8364701380102267e-05,
+      "loss": 1.3425,
+      "step": 141
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8338117136470648e-05,
+      "loss": 1.3581,
+      "step": 142
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.831133811471503e-05,
+      "loss": 1.3936,
+      "step": 143
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8284364940392426e-05,
+      "loss": 1.2922,
+      "step": 144
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.825719824359524e-05,
+      "loss": 1.4399,
+      "step": 145
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 1.425,
+      "step": 146
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.820228682553533e-05,
+      "loss": 1.376,
+      "step": 147
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8174543387001403e-05,
+      "loss": 1.3611,
+      "step": 148
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8146608991420533e-05,
+      "loss": 1.2964,
+      "step": 149
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.811848429133922e-05,
+      "loss": 1.3837,
+      "step": 150
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.3623,
+      "step": 151
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8061666610073465e-05,
+      "loss": 1.417,
+      "step": 152
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8032974956148064e-05,
+      "loss": 1.3424,
+      "step": 153
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8004095652209304e-05,
+      "loss": 1.3589,
+      "step": 154
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7975029372876706e-05,
+      "loss": 1.3266,
+      "step": 155
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7945776797137544e-05,
+      "loss": 1.412,
+      "step": 156
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.791633860833096e-05,
+      "loss": 1.3824,
+      "step": 157
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7886715494132008e-05,
+      "loss": 1.331,
+      "step": 158
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7856908146535602e-05,
+      "loss": 1.3412,
+      "step": 159
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7826917261840337e-05,
+      "loss": 1.3855,
+      "step": 160
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7796743540632226e-05,
+      "loss": 1.3392,
+      "step": 161
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7766387687768338e-05,
+      "loss": 1.3154,
+      "step": 162
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7735850412360332e-05,
+      "loss": 1.4047,
+      "step": 163
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7705132427757895e-05,
+      "loss": 1.3719,
+      "step": 164
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7674234451532065e-05,
+      "loss": 1.3858,
+      "step": 165
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7643157205458483e-05,
+      "loss": 1.372,
+      "step": 166
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7611901415500536e-05,
+      "loss": 1.3725,
+      "step": 167
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7580467811792374e-05,
+      "loss": 1.3229,
+      "step": 168
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7548857128621878e-05,
+      "loss": 1.3614,
+      "step": 169
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7517070104413497e-05,
+      "loss": 1.3202,
+      "step": 170
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 1.328,
+      "step": 171
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.745297000716016e-05,
+      "loss": 1.4035,
+      "step": 172
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7420658431491224e-05,
+      "loss": 1.3921,
+      "step": 173
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7388173509501475e-05,
+      "loss": 1.3991,
+      "step": 174
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7355516000037555e-05,
+      "loss": 1.3446,
+      "step": 175
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7322686665977738e-05,
+      "loss": 1.3412,
+      "step": 176
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7289686274214116e-05,
+      "loss": 1.3459,
+      "step": 177
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7256515595634688e-05,
+      "loss": 1.3381,
+      "step": 178
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.722317540510534e-05,
+      "loss": 1.3947,
+      "step": 179
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7189666481451755e-05,
+      "loss": 1.3186,
+      "step": 180
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.715598960744121e-05,
+      "loss": 1.3873,
+      "step": 181
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.712214556976431e-05,
+      "loss": 1.2937,
+      "step": 182
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7088135159016584e-05,
+      "loss": 1.3279,
+      "step": 183
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7053959169680033e-05,
+      "loss": 1.4129,
+      "step": 184
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7019618400104572e-05,
+      "loss": 1.2923,
+      "step": 185
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6985113652489374e-05,
+      "loss": 1.3812,
+      "step": 186
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.695044573286413e-05,
+      "loss": 1.3207,
+      "step": 187
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6915615451070234e-05,
+      "loss": 1.3297,
+      "step": 188
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6880623620741843e-05,
+      "loss": 1.3116,
+      "step": 189
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.684547105928689e-05,
+      "loss": 1.3302,
+      "step": 190
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6810158587867973e-05,
+      "loss": 1.3288,
+      "step": 191
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.677468703138319e-05,
+      "loss": 1.3685,
+      "step": 192
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.673905721844686e-05,
+      "loss": 1.3432,
+      "step": 193
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.670326998137016e-05,
+      "loss": 1.3562,
+      "step": 194
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.666732615614169e-05,
+      "loss": 1.2824,
+      "step": 195
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 1.3672,
+      "step": 196
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6594972103453727e-05,
+      "loss": 1.3745,
+      "step": 197
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6558563566182365e-05,
+      "loss": 1.3037,
+      "step": 198
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.652200182109602e-05,
+      "loss": 1.3838,
+      "step": 199
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6485287722275783e-05,
+      "loss": 1.2685,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6448422127361707e-05,
+      "loss": 1.3409,
+      "step": 201
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.64114058975328e-05,
+      "loss": 1.2576,
+      "step": 202
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 1.336,
+      "step": 203
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6336924995420453e-05,
+      "loss": 1.3551,
+      "step": 204
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6299462063008272e-05,
+      "loss": 1.2506,
+      "step": 205
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.626185197538314e-05,
+      "loss": 1.3776,
+      "step": 206
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6224095611115385e-05,
+      "loss": 1.3258,
+      "step": 207
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6186193852192356e-05,
+      "loss": 1.3096,
+      "step": 208
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6148147583997813e-05,
+      "loss": 1.3984,
+      "step": 209
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6109957695291246e-05,
+      "loss": 1.3572,
+      "step": 210
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6071625078187113e-05,
+      "loss": 1.2951,
+      "step": 211
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.603315062813401e-05,
+      "loss": 1.3418,
+      "step": 212
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5994535243893742e-05,
+      "loss": 1.3248,
+      "step": 213
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5955779827520327e-05,
+      "loss": 1.3535,
+      "step": 214
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5916885284338937e-05,
+      "loss": 1.3711,
+      "step": 215
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 1.3681,
+      "step": 216
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5838682455081657e-05,
+      "loss": 1.3347,
+      "step": 217
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5799375995821116e-05,
+      "loss": 1.3638,
+      "step": 218
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5759934063340627e-05,
+      "loss": 1.31,
+      "step": 219
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5720357579002346e-05,
+      "loss": 1.3567,
+      "step": 220
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 1.3835,
+      "step": 221
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5640804655895086e-05,
+      "loss": 1.291,
+      "step": 222
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5600830075479604e-05,
+      "loss": 1.3224,
+      "step": 223
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5560724659869905e-05,
+      "loss": 1.3499,
+      "step": 224
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5520489345927095e-05,
+      "loss": 1.3619,
+      "step": 225
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5480125073546705e-05,
+      "loss": 1.2996,
+      "step": 226
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5439632785636707e-05,
+      "loss": 1.3226,
+      "step": 227
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.539901342809554e-05,
+      "loss": 1.3902,
+      "step": 228
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5358267949789968e-05,
+      "loss": 1.3496,
+      "step": 229
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5317397302532933e-05,
+      "loss": 1.311,
+      "step": 230
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.527640244106133e-05,
+      "loss": 1.3254,
+      "step": 231
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5235284323013674e-05,
+      "loss": 1.3453,
+      "step": 232
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5194043908907774e-05,
+      "loss": 1.3137,
+      "step": 233
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.515268216211825e-05,
+      "loss": 1.3203,
+      "step": 234
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5111200048854055e-05,
+      "loss": 1.3282,
+      "step": 235
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5069598538135905e-05,
+      "loss": 1.3457,
+      "step": 236
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5027878601773633e-05,
+      "loss": 1.2971,
+      "step": 237
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4986041214343487e-05,
+      "loss": 1.3374,
+      "step": 238
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.494408735316537e-05,
+      "loss": 1.3082,
+      "step": 239
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.490201799828001e-05,
+      "loss": 1.3323,
+      "step": 240
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.485983413242606e-05,
+      "loss": 1.3553,
+      "step": 241
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4817536741017153e-05,
+      "loss": 1.3666,
+      "step": 242
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4775126812118865e-05,
+      "loss": 1.3257,
+      "step": 243
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4732605336425651e-05,
+      "loss": 1.3477,
+      "step": 244
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4689973307237687e-05,
+      "loss": 1.3321,
+      "step": 245
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4647231720437687e-05,
+      "loss": 1.363,
+      "step": 246
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4604381574467616e-05,
+      "loss": 1.35,
+      "step": 247
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4561423870305383e-05,
+      "loss": 1.3416,
+      "step": 248
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4518359611441452e-05,
+      "loss": 1.3453,
+      "step": 249
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4475189803855399e-05,
+      "loss": 1.3792,
+      "step": 250
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4431915455992416e-05,
+      "loss": 1.291,
+      "step": 251
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.438853757873975e-05,
+      "loss": 1.3631,
+      "step": 252
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.43450571854031e-05,
+      "loss": 1.299,
+      "step": 253
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.430147529168292e-05,
+      "loss": 1.2753,
+      "step": 254
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 1.3002,
+      "step": 255
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4214011077725293e-05,
+      "loss": 1.3069,
+      "step": 256
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4170130800648814e-05,
+      "loss": 1.3388,
+      "step": 257
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4126153109463025e-05,
+      "loss": 1.3223,
+      "step": 258
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4082079031485253e-05,
+      "loss": 1.3053,
+      "step": 259
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.403790959628441e-05,
+      "loss": 1.3334,
+      "step": 260
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3993645835656955e-05,
+      "loss": 1.2915,
+      "step": 261
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.394928878360279e-05,
+      "loss": 1.3546,
+      "step": 262
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3904839476301091e-05,
+      "loss": 1.3055,
+      "step": 263
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3860298952086118e-05,
+      "loss": 1.3464,
+      "step": 264
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3815668251422953e-05,
+      "loss": 1.3684,
+      "step": 265
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3770948416883205e-05,
+      "loss": 1.3457,
+      "step": 266
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3726140493120639e-05,
+      "loss": 1.373,
+      "step": 267
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3681245526846782e-05,
+      "loss": 1.2898,
+      "step": 268
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3636264566806473e-05,
+      "loss": 1.3207,
+      "step": 269
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3591198663753358e-05,
+      "loss": 1.3466,
+      "step": 270
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 1.3006,
+      "step": 271
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3500816241520059e-05,
+      "loss": 1.3772,
+      "step": 272
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3455501833670089e-05,
+      "loss": 1.3406,
+      "step": 273
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3410106705418424e-05,
+      "loss": 1.2943,
+      "step": 274
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3364631917193671e-05,
+      "loss": 1.2715,
+      "step": 275
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3319078531285286e-05,
+      "loss": 1.2483,
+      "step": 276
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3273447611818768e-05,
+      "loss": 1.3117,
+      "step": 277
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3227740224730799e-05,
+      "loss": 1.2942,
+      "step": 278
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3181957437744333e-05,
+      "loss": 1.303,
+      "step": 279
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3136100320343674e-05,
+      "loss": 1.3261,
+      "step": 280
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 1.2932,
+      "step": 281
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3044167380893726e-05,
+      "loss": 1.2304,
+      "step": 282
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2998093706394676e-05,
+      "loss": 1.3353,
+      "step": 283
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.295194999653175e-05,
+      "loss": 1.2972,
+      "step": 284
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2905737329220394e-05,
+      "loss": 1.2799,
+      "step": 285
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2859456783986892e-05,
+      "loss": 1.3691,
+      "step": 286
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2813109441943166e-05,
+      "loss": 1.2723,
+      "step": 287
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2766696385761494e-05,
+      "loss": 1.2673,
+      "step": 288
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2720218699649243e-05,
+      "loss": 1.3167,
+      "step": 289
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2673677469323532e-05,
+      "loss": 1.3344,
+      "step": 290
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.262707378198587e-05,
+      "loss": 1.2612,
+      "step": 291
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.258040872629676e-05,
+      "loss": 1.3137,
+      "step": 292
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2533683392350264e-05,
+      "loss": 1.3172,
+      "step": 293
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2486898871648552e-05,
+      "loss": 1.3587,
+      "step": 294
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2440056257076376e-05,
+      "loss": 1.3483,
+      "step": 295
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2393156642875579e-05,
+      "loss": 1.333,
+      "step": 296
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2346201124619502e-05,
+      "loss": 1.3102,
+      "step": 297
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2299190799187405e-05,
+      "loss": 1.3282,
+      "step": 298
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2252126764738845e-05,
+      "loss": 1.3333,
+      "step": 299
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2205010120688012e-05,
+      "loss": 1.2662,
+      "step": 300
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2157841967678064e-05,
+      "loss": 1.3086,
+      "step": 301
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2110623407555398e-05,
+      "loss": 1.2812,
+      "step": 302
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2063355543343925e-05,
+      "loss": 1.3071,
+      "step": 303
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2016039479219293e-05,
+      "loss": 1.2932,
+      "step": 304
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1968676320483103e-05,
+      "loss": 1.3059,
+      "step": 305
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1921267173537085e-05,
+      "loss": 1.2301,
+      "step": 306
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 1.3119,
+      "step": 307
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1826315345968014e-05,
+      "loss": 1.3146,
+      "step": 308
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1778774883416325e-05,
+      "loss": 1.3019,
+      "step": 309
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1731192868745716e-05,
+      "loss": 1.3268,
+      "step": 310
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1683570413470384e-05,
+      "loss": 1.3823,
+      "step": 311
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.163590863004922e-05,
+      "loss": 1.2614,
+      "step": 312
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1588208631859808e-05,
+      "loss": 1.3186,
+      "step": 313
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.154047153317243e-05,
+      "loss": 1.3654,
+      "step": 314
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1492698449124042e-05,
+      "loss": 1.2827,
+      "step": 315
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1444890495692214e-05,
+      "loss": 1.3103,
+      "step": 316
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1397048789669061e-05,
+      "loss": 1.2942,
+      "step": 317
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1349174448635158e-05,
+      "loss": 1.3167,
+      "step": 318
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1301268590933434e-05,
+      "loss": 1.2643,
+      "step": 319
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1253332335643043e-05,
+      "loss": 1.3429,
+      "step": 320
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 1.2444,
+      "step": 321
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1157373112137171e-05,
+      "loss": 1.2624,
+      "step": 322
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1109352385525782e-05,
+      "loss": 1.2937,
+      "step": 323
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.106130574448156e-05,
+      "loss": 1.2665,
+      "step": 324
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1013234311372353e-05,
+      "loss": 1.2902,
+      "step": 325
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0965139209145153e-05,
+      "loss": 1.2627,
+      "step": 326
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0917021561299864e-05,
+      "loss": 1.2962,
+      "step": 327
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0868882491863048e-05,
+      "loss": 1.304,
+      "step": 328
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0820723125361685e-05,
+      "loss": 1.35,
+      "step": 329
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.077254458679689e-05,
+      "loss": 1.3037,
+      "step": 330
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0724348001617626e-05,
+      "loss": 1.3405,
+      "step": 331
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0676134495694439e-05,
+      "loss": 1.3029,
+      "step": 332
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 1.3236,
+      "step": 333
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0579661227048484e-05,
+      "loss": 1.3413,
+      "step": 334
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0531403717937888e-05,
+      "loss": 1.2775,
+      "step": 335
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0483133795255072e-05,
+      "loss": 1.2882,
+      "step": 336
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0434852586583737e-05,
+      "loss": 1.2673,
+      "step": 337
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0386561219771222e-05,
+      "loss": 1.261,
+      "step": 338
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0338260822902166e-05,
+      "loss": 1.2897,
+      "step": 339
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0289952524272147e-05,
+      "loss": 1.2824,
+      "step": 340
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0241637452361323e-05,
+      "loss": 1.2769,
+      "step": 341
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0193316735808085e-05,
+      "loss": 1.3164,
+      "step": 342
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0144991503382676e-05,
+      "loss": 1.3313,
+      "step": 343
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0096662883960833e-05,
+      "loss": 1.3318,
+      "step": 344
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0048332006497406e-05,
+      "loss": 1.2491,
+      "step": 345
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 1.271,
+      "step": 346
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.951667993502599e-06,
+      "loss": 1.2924,
+      "step": 347
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.903337116039172e-06,
+      "loss": 1.307,
+      "step": 348
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.855008496617326e-06,
+      "loss": 1.297,
+      "step": 349
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.806683264191916e-06,
+      "loss": 1.2918,
+      "step": 350
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.75836254763868e-06,
+      "loss": 1.3302,
+      "step": 351
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.710047475727854e-06,
+      "loss": 1.2808,
+      "step": 352
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.661739177097836e-06,
+      "loss": 1.2293,
+      "step": 353
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.613438780228777e-06,
+      "loss": 1.2635,
+      "step": 354
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.565147413416266e-06,
+      "loss": 1.3211,
+      "step": 355
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.516866204744932e-06,
+      "loss": 1.3137,
+      "step": 356
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.468596282062114e-06,
+      "loss": 1.3195,
+      "step": 357
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.420338772951521e-06,
+      "loss": 1.2673,
+      "step": 358
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 1.2974,
+      "step": 359
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.323865504305566e-06,
+      "loss": 1.2973,
+      "step": 360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.275651998382377e-06,
+      "loss": 1.3248,
+      "step": 361
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.227455413203115e-06,
+      "loss": 1.2908,
+      "step": 362
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.179276874638315e-06,
+      "loss": 1.2986,
+      "step": 363
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.131117508136953e-06,
+      "loss": 1.267,
+      "step": 364
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.082978438700138e-06,
+      "loss": 1.2513,
+      "step": 365
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.034860790854848e-06,
+      "loss": 1.3122,
+      "step": 366
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.986765688627652e-06,
+      "loss": 1.2326,
+      "step": 367
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.938694255518444e-06,
+      "loss": 1.3432,
+      "step": 368
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.890647614474223e-06,
+      "loss": 1.245,
+      "step": 369
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.842626887862832e-06,
+      "loss": 1.2181,
+      "step": 370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 1.2605,
+      "step": 371
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.746667664356957e-06,
+      "loss": 1.2901,
+      "step": 372
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.69873140906657e-06,
+      "loss": 1.2793,
+      "step": 373
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.650825551364844e-06,
+      "loss": 1.2719,
+      "step": 374
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.602951210330942e-06,
+      "loss": 1.1598,
+      "step": 375
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.55510950430779e-06,
+      "loss": 1.3019,
+      "step": 376
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.50730155087596e-06,
+      "loss": 1.2954,
+      "step": 377
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.459528466827576e-06,
+      "loss": 1.28,
+      "step": 378
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.411791368140197e-06,
+      "loss": 1.2873,
+      "step": 379
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.364091369950783e-06,
+      "loss": 1.3165,
+      "step": 380
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.316429586529616e-06,
+      "loss": 1.2493,
+      "step": 381
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.268807131254288e-06,
+      "loss": 1.3167,
+      "step": 382
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.221225116583677e-06,
+      "loss": 1.264,
+      "step": 383
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.17368465403199e-06,
+      "loss": 1.2593,
+      "step": 384
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.126186854142752e-06,
+      "loss": 1.303,
+      "step": 385
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.078732826462917e-06,
+      "loss": 1.2191,
+      "step": 386
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.0313236795169e-06,
+      "loss": 1.2881,
+      "step": 387
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.983960520780712e-06,
+      "loss": 1.2278,
+      "step": 388
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.936644456656082e-06,
+      "loss": 1.2647,
+      "step": 389
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.889376592444605e-06,
+      "loss": 1.2423,
+      "step": 390
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.84215803232194e-06,
+      "loss": 1.2385,
+      "step": 391
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.794989879311991e-06,
+      "loss": 1.288,
+      "step": 392
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.747873235261157e-06,
+      "loss": 1.1935,
+      "step": 393
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.700809200812596e-06,
+      "loss": 1.2566,
+      "step": 394
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.6537988753805e-06,
+      "loss": 1.2961,
+      "step": 395
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.606843357124426e-06,
+      "loss": 1.2606,
+      "step": 396
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.559943742923626e-06,
+      "loss": 1.279,
+      "step": 397
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.513101128351454e-06,
+      "loss": 1.2082,
+      "step": 398
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.4663166076497376e-06,
+      "loss": 1.2393,
+      "step": 399
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.419591273703245e-06,
+      "loss": 1.2876,
+      "step": 400
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.372926218014131e-06,
+      "loss": 1.2556,
+      "step": 401
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.326322530676471e-06,
+      "loss": 1.2951,
+      "step": 402
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.279781300350758e-06,
+      "loss": 1.2807,
+      "step": 403
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.23330361423851e-06,
+      "loss": 1.1951,
+      "step": 404
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.186890558056836e-06,
+      "loss": 1.2544,
+      "step": 405
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.140543216013109e-06,
+      "loss": 1.3186,
+      "step": 406
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.094262670779611e-06,
+      "loss": 1.2609,
+      "step": 407
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.048050003468252e-06,
+      "loss": 1.2355,
+      "step": 408
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.001906293605329e-06,
+      "loss": 1.3441,
+      "step": 409
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.9558326191062775e-06,
+      "loss": 1.2555,
+      "step": 410
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.2804,
+      "step": 411
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.8638996796563275e-06,
+      "loss": 1.2558,
+      "step": 412
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.81804256225567e-06,
+      "loss": 1.2442,
+      "step": 413
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.772259775269203e-06,
+      "loss": 1.3093,
+      "step": 414
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.7265523881812335e-06,
+      "loss": 1.2746,
+      "step": 415
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.680921468714718e-06,
+      "loss": 1.2415,
+      "step": 416
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.6353680828063306e-06,
+      "loss": 1.2565,
+      "step": 417
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.589893294581579e-06,
+      "loss": 1.2718,
+      "step": 418
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.5444981663299135e-06,
+      "loss": 1.2559,
+      "step": 419
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.499183758479944e-06,
+      "loss": 1.2666,
+      "step": 420
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 1.2722,
+      "step": 421
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.408801336246645e-06,
+      "loss": 1.2676,
+      "step": 422
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.36373543319353e-06,
+      "loss": 1.3094,
+      "step": 423
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.318754473153221e-06,
+      "loss": 1.2831,
+      "step": 424
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.273859506879365e-06,
+      "loss": 1.2935,
+      "step": 425
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.229051583116796e-06,
+      "loss": 1.2686,
+      "step": 426
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.18433174857705e-06,
+      "loss": 1.3003,
+      "step": 427
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.139701047913885e-06,
+      "loss": 1.2519,
+      "step": 428
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.095160523698913e-06,
+      "loss": 1.2345,
+      "step": 429
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.050711216397212e-06,
+      "loss": 1.2453,
+      "step": 430
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.006354164343047e-06,
+      "loss": 1.2333,
+      "step": 431
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.962090403715592e-06,
+      "loss": 1.297,
+      "step": 432
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.9179209685147525e-06,
+      "loss": 1.2697,
+      "step": 433
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.873846890536976e-06,
+      "loss": 1.1891,
+      "step": 434
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.829869199351188e-06,
+      "loss": 1.2085,
+      "step": 435
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.785988922274711e-06,
+      "loss": 1.2834,
+      "step": 436
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.742207084349274e-06,
+      "loss": 1.2407,
+      "step": 437
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.698524708317082e-06,
+      "loss": 1.2343,
+      "step": 438
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.654942814596902e-06,
+      "loss": 1.2673,
+      "step": 439
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.611462421260251e-06,
+      "loss": 1.2289,
+      "step": 440
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5680845440075885e-06,
+      "loss": 1.1601,
+      "step": 441
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5248101961446065e-06,
+      "loss": 1.1937,
+      "step": 442
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.481640388558551e-06,
+      "loss": 1.287,
+      "step": 443
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.43857612969462e-06,
+      "loss": 1.302,
+      "step": 444
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.39561842553239e-06,
+      "loss": 1.2488,
+      "step": 445
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.352768279562315e-06,
+      "loss": 1.2708,
+      "step": 446
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.310026692762316e-06,
+      "loss": 1.2296,
+      "step": 447
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.267394663574351e-06,
+      "loss": 1.2844,
+      "step": 448
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.224873187881136e-06,
+      "loss": 1.2818,
+      "step": 449
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.1824632589828465e-06,
+      "loss": 1.2913,
+      "step": 450
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.14016586757394e-06,
+      "loss": 1.1986,
+      "step": 451
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.097982001719994e-06,
+      "loss": 1.2389,
+      "step": 452
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.0559126468346354e-06,
+      "loss": 1.2424,
+      "step": 453
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.013958785656516e-06,
+      "loss": 1.2219,
+      "step": 454
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.972121398226371e-06,
+      "loss": 1.3056,
+      "step": 455
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.930401461864099e-06,
+      "loss": 1.2937,
+      "step": 456
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.888799951145948e-06,
+      "loss": 1.2016,
+      "step": 457
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.847317837881757e-06,
+      "loss": 1.2371,
+      "step": 458
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.805956091092228e-06,
+      "loss": 1.2854,
+      "step": 459
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.764715676986327e-06,
+      "loss": 1.2802,
+      "step": 460
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.7235975589386715e-06,
+      "loss": 1.201,
+      "step": 461
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.6826026974670665e-06,
+      "loss": 1.2367,
+      "step": 462
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 1.2973,
+      "step": 463
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.600986571904461e-06,
+      "loss": 1.2414,
+      "step": 464
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.560367214363295e-06,
+      "loss": 1.3178,
+      "step": 465
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.519874926453303e-06,
+      "loss": 1.282,
+      "step": 466
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.479510654072909e-06,
+      "loss": 1.2451,
+      "step": 467
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.439275340130099e-06,
+      "loss": 1.253,
+      "step": 468
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.399169924520403e-06,
+      "loss": 1.2678,
+      "step": 469
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.359195344104916e-06,
+      "loss": 1.2431,
+      "step": 470
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.319352532688444e-06,
+      "loss": 1.2509,
+      "step": 471
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.279642420997655e-06,
+      "loss": 1.2233,
+      "step": 472
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.240065936659374e-06,
+      "loss": 1.2887,
+      "step": 473
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.200624004178883e-06,
+      "loss": 1.2884,
+      "step": 474
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.161317544918345e-06,
+      "loss": 1.2143,
+      "step": 475
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 1.2523,
+      "step": 476
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.083114715661069e-06,
+      "loss": 1.2383,
+      "step": 477
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.044220172479675e-06,
+      "loss": 1.2751,
+      "step": 478
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.0054647561062625e-06,
+      "loss": 1.242,
+      "step": 479
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.9668493718659924e-06,
+      "loss": 1.2541,
+      "step": 480
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.9283749218128885e-06,
+      "loss": 1.2416,
+      "step": 481
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.890042304708758e-06,
+      "loss": 1.3218,
+      "step": 482
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8518524160021876e-06,
+      "loss": 1.2254,
+      "step": 483
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.813806147807645e-06,
+      "loss": 1.2653,
+      "step": 484
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.775904388884618e-06,
+      "loss": 1.2374,
+      "step": 485
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.738148024616863e-06,
+      "loss": 1.2748,
+      "step": 486
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.700537936991733e-06,
+      "loss": 1.2403,
+      "step": 487
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6630750045795472e-06,
+      "loss": 1.2698,
+      "step": 488
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.625760102513103e-06,
+      "loss": 1.2395,
+      "step": 489
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5885941024672e-06,
+      "loss": 1.2069,
+      "step": 490
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5515778726382967e-06,
+      "loss": 1.1868,
+      "step": 491
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5147122777242203e-06,
+      "loss": 1.2782,
+      "step": 492
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.477998178903982e-06,
+      "loss": 1.2558,
+      "step": 493
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.441436433817641e-06,
+      "loss": 1.2606,
+      "step": 494
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.405027896546277e-06,
+      "loss": 1.2529,
+      "step": 495
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3687734175920505e-06,
+      "loss": 1.2769,
+      "step": 496
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3326738438583116e-06,
+      "loss": 1.233,
+      "step": 497
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2967300186298456e-06,
+      "loss": 1.2171,
+      "step": 498
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2609427815531426e-06,
+      "loss": 1.2684,
+      "step": 499
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2253129686168105e-06,
+      "loss": 1.2783,
+      "step": 500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1898414121320277e-06,
+      "loss": 1.2487,
+      "step": 501
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1545289407131128e-06,
+      "loss": 1.2257,
+      "step": 502
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.11937637925816e-06,
+      "loss": 1.2122,
+      "step": 503
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0843845489297698e-06,
+      "loss": 1.239,
+      "step": 504
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0495542671358745e-06,
+      "loss": 1.1959,
+      "step": 505
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0148863475106315e-06,
+      "loss": 1.322,
+      "step": 506
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.9803815998954334e-06,
+      "loss": 1.2692,
+      "step": 507
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9460408303199696e-06,
+      "loss": 1.2184,
+      "step": 508
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9118648409834205e-06,
+      "loss": 1.2474,
+      "step": 509
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8778544302356904e-06,
+      "loss": 1.2498,
+      "step": 510
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8440103925587904e-06,
+      "loss": 1.2443,
+      "step": 511
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.810333518548246e-06,
+      "loss": 1.2884,
+      "step": 512
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7768245948946615e-06,
+      "loss": 1.1899,
+      "step": 513
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.743484404365314e-06,
+      "loss": 1.245,
+      "step": 514
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 1.1911,
+      "step": 515
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6773133340222677e-06,
+      "loss": 1.2697,
+      "step": 516
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6444839999624496e-06,
+      "loss": 1.3149,
+      "step": 517
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.61182649049853e-06,
+      "loss": 1.2549,
+      "step": 518
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5793415685087797e-06,
+      "loss": 1.2726,
+      "step": 519
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5470299928398424e-06,
+      "loss": 1.1909,
+      "step": 520
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 1.1946,
+      "step": 521
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4829298955865022e-06,
+      "loss": 1.2669,
+      "step": 522
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.451142871378124e-06,
+      "loss": 1.2515,
+      "step": 523
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4195321882076295e-06,
+      "loss": 1.2561,
+      "step": 524
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3880985844994674e-06,
+      "loss": 1.2367,
+      "step": 525
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3568427945415163e-06,
+      "loss": 1.2895,
+      "step": 526
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3257655484679376e-06,
+      "loss": 1.2103,
+      "step": 527
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2948675722421086e-06,
+      "loss": 1.2231,
+      "step": 528
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2641495876396713e-06,
+      "loss": 1.2337,
+      "step": 529
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2336123122316642e-06,
+      "loss": 1.2965,
+      "step": 530
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2032564593677773e-06,
+      "loss": 1.1466,
+      "step": 531
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1730827381596643e-06,
+      "loss": 1.2549,
+      "step": 532
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1430918534643996e-06,
+      "loss": 1.2029,
+      "step": 533
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1132845058679942e-06,
+      "loss": 1.2463,
+      "step": 534
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.083661391669043e-06,
+      "loss": 1.1695,
+      "step": 535
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0542232028624585e-06,
+      "loss": 1.2532,
+      "step": 536
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.024970627123295e-06,
+      "loss": 1.2172,
+      "step": 537
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9959043477907e-06,
+      "loss": 1.2227,
+      "step": 538
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.967025043851939e-06,
+      "loss": 1.2273,
+      "step": 539
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9383333899265368e-06,
+      "loss": 1.1965,
+      "step": 540
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.2331,
+      "step": 541
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8815157086607826e-06,
+      "loss": 1.2546,
+      "step": 542
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8533910085794714e-06,
+      "loss": 1.2212,
+      "step": 543
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8254566129985996e-06,
+      "loss": 1.264,
+      "step": 544
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7977131744646724e-06,
+      "loss": 1.1909,
+      "step": 545
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7701613410634367e-06,
+      "loss": 1.2418,
+      "step": 546
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7428017564047594e-06,
+      "loss": 1.2505,
+      "step": 547
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7156350596075743e-06,
+      "loss": 1.2874,
+      "step": 548
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6886618852849723e-06,
+      "loss": 1.2475,
+      "step": 549
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6618828635293538e-06,
+      "loss": 1.2224,
+      "step": 550
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6352986198977327e-06,
+      "loss": 1.1563,
+      "step": 551
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6089097753971061e-06,
+      "loss": 1.2175,
+      "step": 552
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5827169464699576e-06,
+      "loss": 1.1903,
+      "step": 553
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5567207449798517e-06,
+      "loss": 1.2403,
+      "step": 554
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5309217781971419e-06,
+      "loss": 1.205,
+      "step": 555
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5053206487847916e-06,
+      "loss": 1.2447,
+      "step": 556
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4799179547842823e-06,
+      "loss": 1.208,
+      "step": 557
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.454714289601661e-06,
+      "loss": 1.2491,
+      "step": 558
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4297102419936559e-06,
+      "loss": 1.2412,
+      "step": 559
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4049063960539488e-06,
+      "loss": 1.2431,
+      "step": 560
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3803033311995072e-06,
+      "loss": 1.206,
+      "step": 561
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3559016221570663e-06,
+      "loss": 1.2426,
+      "step": 562
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3317018389496927e-06,
+      "loss": 1.2978,
+      "step": 563
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3077045468834714e-06,
+      "loss": 1.2363,
+      "step": 564
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2839103065343084e-06,
+      "loss": 1.2608,
+      "step": 565
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2603196737348211e-06,
+      "loss": 1.1973,
+      "step": 566
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2369331995613664e-06,
+      "loss": 1.2315,
+      "step": 567
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.213751430321156e-06,
+      "loss": 1.2313,
+      "step": 568
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1907749075395147e-06,
+      "loss": 1.2884,
+      "step": 569
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.168004167947202e-06,
+      "loss": 1.1736,
+      "step": 570
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1454397434679022e-06,
+      "loss": 1.2719,
+      "step": 571
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.123082161205775e-06,
+      "loss": 1.2442,
+      "step": 572
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1009319434331623e-06,
+      "loss": 1.1979,
+      "step": 573
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0789896075783734e-06,
+      "loss": 1.2035,
+      "step": 574
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0572556662136036e-06,
+      "loss": 1.1973,
+      "step": 575
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0357306270429623e-06,
+      "loss": 1.2564,
+      "step": 576
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.014414992890611e-06,
+      "loss": 1.2806,
+      "step": 577
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.93309261689015e-07,
+      "loss": 1.2205,
+      "step": 578
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.724139264673116e-07,
+      "loss": 1.2583,
+      "step": 579
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.517294753398066e-07,
+      "loss": 1.1722,
+      "step": 580
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.312563914945461e-07,
+      "loss": 1.2193,
+      "step": 581
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.10995153182056e-07,
+      "loss": 1.212,
+      "step": 582
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.909462337041508e-07,
+      "loss": 1.2481,
+      "step": 583
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.711101014028855e-07,
+      "loss": 1.1747,
+      "step": 584
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.514872196496182e-07,
+      "loss": 1.2399,
+      "step": 585
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.320780468341761e-07,
+      "loss": 1.1957,
+      "step": 586
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.128830363541574e-07,
+      "loss": 1.1571,
+      "step": 587
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.939026366043323e-07,
+      "loss": 1.2122,
+      "step": 588
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.75137290966177e-07,
+      "loss": 1.1939,
+      "step": 589
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.565874377975046e-07,
+      "loss": 1.2378,
+      "step": 590
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.382535104222366e-07,
+      "loss": 1.2314,
+      "step": 591
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.201359371202698e-07,
+      "loss": 1.3062,
+      "step": 592
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 1.2114,
+      "step": 593
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.845515405758518e-07,
+      "loss": 1.2199,
+      "step": 594
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.670855485836525e-07,
+      "loss": 1.1837,
+      "step": 595
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.498375731458529e-07,
+      "loss": 1.2768,
+      "step": 596
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.32808017174551e-07,
+      "loss": 1.1881,
+      "step": 597
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.159972784795798e-07,
+      "loss": 1.1876,
+      "step": 598
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.994057497592032e-07,
+      "loss": 1.2634,
+      "step": 599
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.830338185909545e-07,
+      "loss": 1.2416,
+      "step": 600
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.668818674225684e-07,
+      "loss": 1.2112,
+      "step": 601
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.509502735630601e-07,
+      "loss": 1.2512,
+      "step": 602
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.352394091739022e-07,
+      "loss": 1.205,
+      "step": 603
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.197496412603365e-07,
+      "loss": 1.2531,
+      "step": 604
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.044813316627994e-07,
+      "loss": 1.1902,
+      "step": 605
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 1.2178,
+      "step": 606
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.746105089029229e-07,
+      "loss": 1.1809,
+      "step": 607
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.6000869352195607e-07,
+      "loss": 1.2531,
+      "step": 608
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4562973200346413e-07,
+      "loss": 1.2166,
+      "step": 609
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.314739602394791e-07,
+      "loss": 1.2276,
+      "step": 610
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1754170890833777e-07,
+      "loss": 1.2475,
+      "step": 611
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.038333034669406e-07,
+      "loss": 1.2198,
+      "step": 612
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.903490641431573e-07,
+      "loss": 1.2193,
+      "step": 613
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.770893059283465e-07,
+      "loss": 1.2427,
+      "step": 614
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.6405433856999684e-07,
+      "loss": 1.2744,
+      "step": 615
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.5124446656448654e-07,
+      "loss": 1.2709,
+      "step": 616
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.3865998914997645e-07,
+      "loss": 1.2479,
+      "step": 617
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.2630120029942034e-07,
+      "loss": 1.2375,
+      "step": 618
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1416838871368925e-07,
+      "loss": 1.2396,
+      "step": 619
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.0226183781483897e-07,
+      "loss": 1.1764,
+      "step": 620
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.905818257394799e-07,
+      "loss": 1.2325,
+      "step": 621
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.791286253322856e-07,
+      "loss": 1.2208,
+      "step": 622
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.679025041396155e-07,
+      "loss": 1.2567,
+      "step": 623
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.569037244032657e-07,
+      "loss": 1.1698,
+      "step": 624
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.461325430543482e-07,
+      "loss": 1.1624,
+      "step": 625
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.355892117072789e-07,
+      "loss": 1.2314,
+      "step": 626
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.2527397665391026e-07,
+      "loss": 1.2763,
+      "step": 627
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.1518707885777147e-07,
+      "loss": 1.1968,
+      "step": 628
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0532875394844053e-07,
+      "loss": 1.2502,
+      "step": 629
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9569923221604224e-07,
+      "loss": 1.2219,
+      "step": 630
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8629873860586567e-07,
+      "loss": 1.2245,
+      "step": 631
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7712749271311392e-07,
+      "loss": 1.214,
+      "step": 632
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.681857087777672e-07,
+      "loss": 1.1827,
+      "step": 633
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5947359567958677e-07,
+      "loss": 1.2491,
+      "step": 634
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5099135693322776e-07,
+      "loss": 1.2284,
+      "step": 635
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4273919068349184e-07,
+      "loss": 1.1829,
+      "step": 636
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3471728970068986e-07,
+      "loss": 1.2225,
+      "step": 637
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2692584137615205e-07,
+      "loss": 1.2541,
+      "step": 638
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1936502771783488e-07,
+      "loss": 1.2206,
+      "step": 639
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1203502534608113e-07,
+      "loss": 1.2489,
+      "step": 640
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0493600548948879e-07,
+      "loss": 1.2834,
+      "step": 641
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.806813398091419e-08,
+      "loss": 1.191,
+      "step": 642
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.143157125359514e-08,
+      "loss": 1.1584,
+      "step": 643
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.502647233740169e-08,
+      "loss": 1.1973,
+      "step": 644
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.885298685522235e-08,
+      "loss": 1.2084,
+      "step": 645
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.291125901946027e-08,
+      "loss": 1.2765,
+      "step": 646
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.720142762867032e-08,
+      "loss": 1.2335,
+      "step": 647
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.172362606431281e-08,
+      "loss": 1.2119,
+      "step": 648
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.647798228764156e-08,
+      "loss": 1.2392,
+      "step": 649
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.146461883671072e-08,
+      "loss": 1.2353,
+      "step": 650
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.6683652823513725e-08,
+      "loss": 1.2426,
+      "step": 651
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.2135195931249925e-08,
+      "loss": 1.2257,
+      "step": 652
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.7819354411713364e-08,
+      "loss": 1.2124,
+      "step": 653
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.373622908280916e-08,
+      "loss": 1.157,
+      "step": 654
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.988591532620322e-08,
+      "loss": 1.2755,
+      "step": 655
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.6268503085089547e-08,
+      "loss": 1.1833,
+      "step": 656
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.2884076862089712e-08,
+      "loss": 1.2691,
+      "step": 657
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.973271571728441e-08,
+      "loss": 1.2374,
+      "step": 658
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.6814493266357202e-08,
+      "loss": 1.276,
+      "step": 659
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.4129477678884728e-08,
+      "loss": 1.2091,
+      "step": 660
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1677731676733584e-08,
+      "loss": 1.1781,
+      "step": 661
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.459312532608122e-09,
+      "loss": 1.2607,
+      "step": 662
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.474272068698219e-09,
+      "loss": 1.2763,
+      "step": 663
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.722656655482439e-09,
+      "loss": 1.1663,
+      "step": 664
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.204507210633368e-09,
+      "loss": 1.2102,
+      "step": 665
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.9198591980705847e-09,
+      "loss": 1.2141,
+      "step": 666
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.8687426271246646e-09,
+      "loss": 1.2232,
+      "step": 667
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0511820518432915e-09,
+      "loss": 1.2098,
+      "step": 668
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.671965704128312e-10,
+      "loss": 1.2296,
+      "step": 669
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.167998247131319e-10,
+      "loss": 1.2456,
+      "step": 670
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 1.1816,
+      "step": 671
+    },
+    {
+      "epoch": 1.0,
+      "step": 671,
+      "total_flos": 1.6993129412260004e+18,
+      "train_loss": 1.318009591315791,
+      "train_runtime": 13830.2591,
+      "train_samples_per_second": 6.218,
+      "train_steps_per_second": 0.049
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 671,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 7975,
+  "total_flos": 1.6993129412260004e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe23ff97e9205ace406b342623ce2cdef5f09a6d1d8224a81c4ca52f7f788b1
+size 6456