Upload folder using huggingface_hub

config.json

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

generation_config.json

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

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f887f785a8e65c00d0cb56172c182fbfcdede29ee2d2f85e555c30983d00965
+size 4978265800

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19c01f5717e50efc8a793520a484a0c12072d3ac23f28791a4cb4c044a0671b
+size 4970422232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13dcefe35b771f6dd7159f5f2dca50b19622689aa2ea5e9a95d5c19aa57bf802
+size 4970422256

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b3632d5a4651bd3a48d3f7d5c5a7cf3f613676723f0b024f29e53dedc22c40
+size 4933701504

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe372d2a7dc323a145eace676b0c1c59077581c4da93446f8f844bd9c5e9a634
+size 4933722216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22c4187c7d2f5f92d8a0c5693003599263c222c54174ee99965b09aae6dd677
+size 1915248664

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,2376 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 391,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.0562,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0408,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 1.0595,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0169,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.9569,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 0.9233,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.8901,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8269,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.9209,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8551,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.8296,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.7975,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999965645087791e-05,
+      "loss": 0.8128,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9998625827116828e-05,
+      "loss": 0.8012,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9996908199530737e-05,
+      "loss": 0.7844,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9994503686137526e-05,
+      "loss": 0.7976,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999141245215089e-05,
+      "loss": 0.7731,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998763470996897e-05,
+      "loss": 0.741,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998317071915977e-05,
+      "loss": 0.7263,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9978020786443314e-05,
+      "loss": 0.767,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9972185265670573e-05,
+      "loss": 0.7379,
+      "step": 21
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9965664557799164e-05,
+      "loss": 0.7155,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9958459110865767e-05,
+      "loss": 0.7516,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.995056941995538e-05,
+      "loss": 0.738,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9941996027167286e-05,
+      "loss": 0.7013,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.993273952157779e-05,
+      "loss": 0.7052,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.992280053919977e-05,
+      "loss": 0.6932,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9912179762938962e-05,
+      "loss": 0.6894,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9900877922547034e-05,
+      "loss": 0.6697,
+      "step": 29
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.988889579457146e-05,
+      "loss": 0.6937,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.987623420230214e-05,
+      "loss": 0.6951,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9862894015714866e-05,
+      "loss": 0.6716,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.984887615141151e-05,
+      "loss": 0.7112,
+      "step": 33
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9834181572557066e-05,
+      "loss": 0.6957,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9818811288813475e-05,
+      "loss": 0.6733,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9802766356270226e-05,
+      "loss": 0.6868,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9786047877371823e-05,
+      "loss": 0.6634,
+      "step": 37
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.976865700084201e-05,
+      "loss": 0.6877,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.975059492160486e-05,
+      "loss": 0.6397,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9731862880702676e-05,
+      "loss": 0.652,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9712462165210687e-05,
+      "loss": 0.6733,
+      "step": 41
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.969239410814865e-05,
+      "loss": 0.6533,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.967166008838925e-05,
+      "loss": 0.6526,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9650261530563336e-05,
+      "loss": 0.6479,
+      "step": 44
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9628199904962063e-05,
+      "loss": 0.644,
+      "step": 45
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9605476727435854e-05,
+      "loss": 0.6563,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9582093559290242e-05,
+      "loss": 0.6518,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9558052007178608e-05,
+      "loss": 0.6222,
+      "step": 48
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9533353722991775e-05,
+      "loss": 0.6639,
+      "step": 49
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9508000403744516e-05,
+      "loss": 0.6504,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.948199379145894e-05,
+      "loss": 0.6556,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9455335673044817e-05,
+      "loss": 0.6246,
+      "step": 52
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9428027880176775e-05,
+      "loss": 0.6463,
+      "step": 53
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9400072289168474e-05,
+      "loss": 0.667,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.937147082084366e-05,
+      "loss": 0.668,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.93422254404042e-05,
+      "loss": 0.6313,
+      "step": 56
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.931233815729505e-05,
+      "loss": 0.6484,
+      "step": 57
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9281811025066184e-05,
+      "loss": 0.6607,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9250646141231503e-05,
+      "loss": 0.6319,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.921884564712469e-05,
+      "loss": 0.6335,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9186411727752124e-05,
+      "loss": 0.6299,
+      "step": 61
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9153346611642706e-05,
+      "loss": 0.6344,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.911965257069476e-05,
+      "loss": 0.6491,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.908533192001992e-05,
+      "loss": 0.6734,
+      "step": 64
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9050387017784067e-05,
+      "loss": 0.6224,
+      "step": 65
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9014820265045304e-05,
+      "loss": 0.6249,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8978634105588963e-05,
+      "loss": 0.6038,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8941831025759705e-05,
+      "loss": 0.6493,
+      "step": 68
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8904413554290687e-05,
+      "loss": 0.6463,
+      "step": 69
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.88663842621298e-05,
+      "loss": 0.5849,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8827745762263038e-05,
+      "loss": 0.628,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8788500709534934e-05,
+      "loss": 0.6383,
+      "step": 72
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8748651800466174e-05,
+      "loss": 0.6498,
+      "step": 73
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8708201773068303e-05,
+      "loss": 0.6196,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8667153406655606e-05,
+      "loss": 0.6178,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8625509521654122e-05,
+      "loss": 0.6199,
+      "step": 76
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8583272979407885e-05,
+      "loss": 0.6522,
+      "step": 77
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8540446681982295e-05,
+      "loss": 0.6288,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.849703357196473e-05,
+      "loss": 0.6311,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8453036632262352e-05,
+      "loss": 0.6396,
+      "step": 80
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.840845888589717e-05,
+      "loss": 0.6056,
+      "step": 81
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8363303395798305e-05,
+      "loss": 0.6279,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8317573264591553e-05,
+      "loss": 0.6233,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.82712716343862e-05,
+      "loss": 0.6184,
+      "step": 84
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.822440168655913e-05,
+      "loss": 0.613,
+      "step": 85
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8176966641536228e-05,
+      "loss": 0.6283,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.812896975857111e-05,
+      "loss": 0.6438,
+      "step": 87
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8080414335521174e-05,
+      "loss": 0.6304,
+      "step": 88
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.803130370862101e-05,
+      "loss": 0.6014,
+      "step": 89
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.798164125225318e-05,
+      "loss": 0.6188,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.793143037871633e-05,
+      "loss": 0.5997,
+      "step": 91
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.788067453799077e-05,
+      "loss": 0.6067,
+      "step": 92
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.78293772175014e-05,
+      "loss": 0.6401,
+      "step": 93
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7777541941878116e-05,
+      "loss": 0.6533,
+      "step": 94
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.772517227271359e-05,
+      "loss": 0.6286,
+      "step": 95
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7672271808318603e-05,
+      "loss": 0.6238,
+      "step": 96
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7618844183474775e-05,
+      "loss": 0.57,
+      "step": 97
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7564893069184824e-05,
+      "loss": 0.6344,
+      "step": 98
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7510422172420344e-05,
+      "loss": 0.6451,
+      "step": 99
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.745543523586709e-05,
+      "loss": 0.6178,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7399936037667807e-05,
+      "loss": 0.6071,
+      "step": 101
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7343928391162673e-05,
+      "loss": 0.6222,
+      "step": 102
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7287416144627237e-05,
+      "loss": 0.6109,
+      "step": 103
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7230403181008032e-05,
+      "loss": 0.6213,
+      "step": 104
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7172893417655792e-05,
+      "loss": 0.6131,
+      "step": 105
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7114890806056245e-05,
+      "loss": 0.5886,
+      "step": 106
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.705639933155866e-05,
+      "loss": 0.6415,
+      "step": 107
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6997423013101967e-05,
+      "loss": 0.6233,
+      "step": 108
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6937965902938667e-05,
+      "loss": 0.6242,
+      "step": 109
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.687803208635635e-05,
+      "loss": 0.6156,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6817625681397035e-05,
+      "loss": 0.6204,
+      "step": 111
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6756750838574197e-05,
+      "loss": 0.6042,
+      "step": 112
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.66954117405876e-05,
+      "loss": 0.64,
+      "step": 113
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.66336126020359e-05,
+      "loss": 0.608,
+      "step": 114
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6571357669127047e-05,
+      "loss": 0.5809,
+      "step": 115
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.650865121938656e-05,
+      "loss": 0.6379,
+      "step": 116
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.644549756136358e-05,
+      "loss": 0.5943,
+      "step": 117
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6381901034334876e-05,
+      "loss": 0.6044,
+      "step": 118
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.631786600800664e-05,
+      "loss": 0.6103,
+      "step": 119
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6253396882214293e-05,
+      "loss": 0.6188,
+      "step": 120
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6188498086620148e-05,
+      "loss": 0.6223,
+      "step": 121
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6123174080409055e-05,
+      "loss": 0.6178,
+      "step": 122
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6057429351982016e-05,
+      "loss": 0.6209,
+      "step": 123
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5991268418647772e-05,
+      "loss": 0.5792,
+      "step": 124
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5924695826312434e-05,
+      "loss": 0.6256,
+      "step": 125
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.585771614916714e-05,
+      "loss": 0.6347,
+      "step": 126
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5790333989373738e-05,
+      "loss": 0.5962,
+      "step": 127
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5722553976748605e-05,
+      "loss": 0.6243,
+      "step": 128
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5654380768444498e-05,
+      "loss": 0.6344,
+      "step": 129
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.55858190486306e-05,
+      "loss": 0.592,
+      "step": 130
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.551687352817063e-05,
+      "loss": 0.5986,
+      "step": 131
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5447548944299203e-05,
+      "loss": 0.6391,
+      "step": 132
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.53778500602963e-05,
+      "loss": 0.591,
+      "step": 133
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5307781665160005e-05,
+      "loss": 0.5903,
+      "step": 134
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.523734857327744e-05,
+      "loss": 0.5969,
+      "step": 135
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5166555624093986e-05,
+      "loss": 0.6014,
+      "step": 136
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5095407681780753e-05,
+      "loss": 0.6323,
+      "step": 137
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5023909634900362e-05,
+      "loss": 0.5849,
+      "step": 138
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4952066396071064e-05,
+      "loss": 0.6258,
+      "step": 139
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4879882901629181e-05,
+      "loss": 0.5823,
+      "step": 140
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4807364111289941e-05,
+      "loss": 0.5914,
+      "step": 141
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4734515007806698e-05,
+      "loss": 0.6113,
+      "step": 142
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4661340596628564e-05,
+      "loss": 0.5948,
+      "step": 143
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4587845905556477e-05,
+      "loss": 0.61,
+      "step": 144
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4514035984397759e-05,
+      "loss": 0.5916,
+      "step": 145
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4439915904619136e-05,
+      "loss": 0.5993,
+      "step": 146
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4365490758998268e-05,
+      "loss": 0.5886,
+      "step": 147
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.429076566127385e-05,
+      "loss": 0.586,
+      "step": 148
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4215745745794224e-05,
+      "loss": 0.6168,
+      "step": 149
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4140436167164611e-05,
+      "loss": 0.6093,
+      "step": 150
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4064842099892934e-05,
+      "loss": 0.6097,
+      "step": 151
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3988968738034285e-05,
+      "loss": 0.5866,
+      "step": 152
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3912821294834033e-05,
+      "loss": 0.5959,
+      "step": 153
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3836405002369631e-05,
+      "loss": 0.6317,
+      "step": 154
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3759725111191118e-05,
+      "loss": 0.5843,
+      "step": 155
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3682786889960354e-05,
+      "loss": 0.6113,
+      "step": 156
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3605595625089006e-05,
+      "loss": 0.5724,
+      "step": 157
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3528156620375335e-05,
+      "loss": 0.5863,
+      "step": 158
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3450475196639753e-05,
+      "loss": 0.5539,
+      "step": 159
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3372556691359251e-05,
+      "loss": 0.6015,
+      "step": 160
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3294406458300646e-05,
+      "loss": 0.5777,
+      "step": 161
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3216029867152724e-05,
+      "loss": 0.5923,
+      "step": 162
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3137432303157306e-05,
+      "loss": 0.5966,
+      "step": 163
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3058619166739212e-05,
+      "loss": 0.5777,
+      "step": 164
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2979595873135208e-05,
+      "loss": 0.6055,
+      "step": 165
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.290036785202192e-05,
+      "loss": 0.6007,
+      "step": 166
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2820940547142773e-05,
+      "loss": 0.5675,
+      "step": 167
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2741319415933934e-05,
+      "loss": 0.5802,
+      "step": 168
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2661509929149351e-05,
+      "loss": 0.6081,
+      "step": 169
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.258151757048485e-05,
+      "loss": 0.6099,
+      "step": 170
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2501347836201343e-05,
+      "loss": 0.5731,
+      "step": 171
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2421006234747202e-05,
+      "loss": 0.5934,
+      "step": 172
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2340498286379757e-05,
+      "loss": 0.5729,
+      "step": 173
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2259829522786003e-05,
+      "loss": 0.5663,
+      "step": 174
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2179005486702518e-05,
+      "loss": 0.61,
+      "step": 175
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2098031731534636e-05,
+      "loss": 0.5584,
+      "step": 176
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2016913820974855e-05,
+      "loss": 0.5627,
+      "step": 177
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1935657328620566e-05,
+      "loss": 0.5784,
+      "step": 178
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1854267837591095e-05,
+      "loss": 0.5694,
+      "step": 179
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1772750940144079e-05,
+      "loss": 0.5746,
+      "step": 180
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1691112237291225e-05,
+      "loss": 0.5434,
+      "step": 181
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1609357338413476e-05,
+      "loss": 0.6047,
+      "step": 182
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1527491860875574e-05,
+      "loss": 0.5928,
+      "step": 183
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1445521429640113e-05,
+      "loss": 0.6071,
+      "step": 184
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.136345167688103e-05,
+      "loss": 0.5703,
+      "step": 185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1281288241596624e-05,
+      "loss": 0.5721,
+      "step": 186
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1199036769222104e-05,
+      "loss": 0.5927,
+      "step": 187
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1116702911241704e-05,
+      "loss": 0.598,
+      "step": 188
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1034292324800342e-05,
+      "loss": 0.568,
+      "step": 189
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0951810672314946e-05,
+      "loss": 0.5713,
+      "step": 190
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0869263621085375e-05,
+      "loss": 0.6065,
+      "step": 191
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0786656842905028e-05,
+      "loss": 0.6135,
+      "step": 192
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0703996013671126e-05,
+      "loss": 0.5669,
+      "step": 193
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0621286812994733e-05,
+      "loss": 0.5807,
+      "step": 194
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0538534923810506e-05,
+      "loss": 0.5611,
+      "step": 195
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0455746031986215e-05,
+      "loss": 0.5919,
+      "step": 196
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0372925825932095e-05,
+      "loss": 0.6038,
+      "step": 197
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.029007999620995e-05,
+      "loss": 0.5762,
+      "step": 198
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0207214235142197e-05,
+      "loss": 0.5842,
+      "step": 199
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0124334236420735e-05,
+      "loss": 0.5463,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0041445694715717e-05,
+      "loss": 0.5796,
+      "step": 201
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.95855430528429e-06,
+      "loss": 0.5384,
+      "step": 202
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.87566576357927e-06,
+      "loss": 0.5753,
+      "step": 203
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.792785764857803e-06,
+      "loss": 0.5774,
+      "step": 204
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.709920003790054e-06,
+      "loss": 0.5981,
+      "step": 205
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.627074174067909e-06,
+      "loss": 0.57,
+      "step": 206
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.544253968013785e-06,
+      "loss": 0.5757,
+      "step": 207
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.461465076189499e-06,
+      "loss": 0.5564,
+      "step": 208
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.37871318700527e-06,
+      "loss": 0.58,
+      "step": 209
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.296003986328876e-06,
+      "loss": 0.5899,
+      "step": 210
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.213343157094975e-06,
+      "loss": 0.5889,
+      "step": 211
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.130736378914626e-06,
+      "loss": 0.5573,
+      "step": 212
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.048189327685056e-06,
+      "loss": 0.5847,
+      "step": 213
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.965707675199661e-06,
+      "loss": 0.5712,
+      "step": 214
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.883297088758298e-06,
+      "loss": 0.5902,
+      "step": 215
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.800963230777895e-06,
+      "loss": 0.5692,
+      "step": 216
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.718711758403382e-06,
+      "loss": 0.5597,
+      "step": 217
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.636548323118974e-06,
+      "loss": 0.5537,
+      "step": 218
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.554478570359888e-06,
+      "loss": 0.5982,
+      "step": 219
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.472508139124427e-06,
+      "loss": 0.574,
+      "step": 220
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.390642661586527e-06,
+      "loss": 0.576,
+      "step": 221
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.308887762708776e-06,
+      "loss": 0.6015,
+      "step": 222
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.227249059855926e-06,
+      "loss": 0.5857,
+      "step": 223
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.145732162408906e-06,
+      "loss": 0.5879,
+      "step": 224
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.064342671379436e-06,
+      "loss": 0.5467,
+      "step": 225
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.983086179025148e-06,
+      "loss": 0.5673,
+      "step": 226
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.901968268465367e-06,
+      "loss": 0.5437,
+      "step": 227
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.820994513297484e-06,
+      "loss": 0.5599,
+      "step": 228
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.740170477214004e-06,
+      "loss": 0.5888,
+      "step": 229
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.659501713620247e-06,
+      "loss": 0.5646,
+      "step": 230
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.578993765252799e-06,
+      "loss": 0.5681,
+      "step": 231
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.498652163798659e-06,
+      "loss": 0.5471,
+      "step": 232
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.418482429515153e-06,
+      "loss": 0.6253,
+      "step": 233
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.338490070850649e-06,
+      "loss": 0.568,
+      "step": 234
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.258680584066069e-06,
+      "loss": 0.5617,
+      "step": 235
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.17905945285723e-06,
+      "loss": 0.6007,
+      "step": 236
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.09963214797808e-06,
+      "loss": 0.5709,
+      "step": 237
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.020404126864795e-06,
+      "loss": 0.5577,
+      "step": 238
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.94138083326079e-06,
+      "loss": 0.5939,
+      "step": 239
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.862567696842694e-06,
+      "loss": 0.5742,
+      "step": 240
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.78397013284728e-06,
+      "loss": 0.5783,
+      "step": 241
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.705593541699358e-06,
+      "loss": 0.5807,
+      "step": 242
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.627443308640749e-06,
+      "loss": 0.5866,
+      "step": 243
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.549524803360249e-06,
+      "loss": 0.5783,
+      "step": 244
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.4718433796246685e-06,
+      "loss": 0.5716,
+      "step": 245
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.394404374910996e-06,
+      "loss": 0.559,
+      "step": 246
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.317213110039652e-06,
+      "loss": 0.57,
+      "step": 247
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.240274888808884e-06,
+      "loss": 0.5562,
+      "step": 248
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.16359499763037e-06,
+      "loss": 0.5561,
+      "step": 249
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.087178705165969e-06,
+      "loss": 0.5689,
+      "step": 250
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.011031261965716e-06,
+      "loss": 0.5508,
+      "step": 251
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.9351579001070655e-06,
+      "loss": 0.5733,
+      "step": 252
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.859563832835393e-06,
+      "loss": 0.5736,
+      "step": 253
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.784254254205779e-06,
+      "loss": 0.5737,
+      "step": 254
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.70923433872615e-06,
+      "loss": 0.5547,
+      "step": 255
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.634509241001736e-06,
+      "loss": 0.5547,
+      "step": 256
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5600840953808675e-06,
+      "loss": 0.5337,
+      "step": 257
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.485964015602243e-06,
+      "loss": 0.579,
+      "step": 258
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.412154094443527e-06,
+      "loss": 0.5794,
+      "step": 259
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.338659403371438e-06,
+      "loss": 0.5722,
+      "step": 260
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.265484992193302e-06,
+      "loss": 0.5747,
+      "step": 261
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.19263588871006e-06,
+      "loss": 0.5748,
+      "step": 262
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.120117098370824e-06,
+      "loss": 0.5388,
+      "step": 263
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.047933603928936e-06,
+      "loss": 0.5451,
+      "step": 264
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.976090365099638e-06,
+      "loss": 0.5407,
+      "step": 265
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.904592318219249e-06,
+      "loss": 0.5425,
+      "step": 266
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.833444375906013e-06,
+      "loss": 0.5908,
+      "step": 267
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.762651426722566e-06,
+      "loss": 0.5359,
+      "step": 268
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.6922183348399996e-06,
+      "loss": 0.5771,
+      "step": 269
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.622149939703704e-06,
+      "loss": 0.5429,
+      "step": 270
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.552451055700802e-06,
+      "loss": 0.5683,
+      "step": 271
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.483126471829371e-06,
+      "loss": 0.5695,
+      "step": 272
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.414180951369405e-06,
+      "loss": 0.5244,
+      "step": 273
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.345619231555503e-06,
+      "loss": 0.568,
+      "step": 274
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.277446023251401e-06,
+      "loss": 0.5645,
+      "step": 275
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.209666010626262e-06,
+      "loss": 0.5919,
+      "step": 276
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.142283850832862e-06,
+      "loss": 0.6071,
+      "step": 277
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.0753041736875675e-06,
+      "loss": 0.5503,
+      "step": 278
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.008731581352229e-06,
+      "loss": 0.5646,
+      "step": 279
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.942570648017988e-06,
+      "loss": 0.5996,
+      "step": 280
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.876825919590944e-06,
+      "loss": 0.5617,
+      "step": 281
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8115019133798535e-06,
+      "loss": 0.5673,
+      "step": 282
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.74660311778571e-06,
+      "loss": 0.5728,
+      "step": 283
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.682133991993361e-06,
+      "loss": 0.5575,
+      "step": 284
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6180989656651268e-06,
+      "loss": 0.5562,
+      "step": 285
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5545024386364192e-06,
+      "loss": 0.5252,
+      "step": 286
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.491348780613444e-06,
+      "loss": 0.5533,
+      "step": 287
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4286423308729523e-06,
+      "loss": 0.5371,
+      "step": 288
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3663873979641014e-06,
+      "loss": 0.5707,
+      "step": 289
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.304588259412399e-06,
+      "loss": 0.571,
+      "step": 290
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.243249161425801e-06,
+      "loss": 0.562,
+      "step": 291
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1823743186029676e-06,
+      "loss": 0.5788,
+      "step": 292
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1219679136436496e-06,
+      "loss": 0.6038,
+      "step": 293
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.062034097061335e-06,
+      "loss": 0.5513,
+      "step": 294
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0025769868980337e-06,
+      "loss": 0.5305,
+      "step": 295
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9436006684413444e-06,
+      "loss": 0.5573,
+      "step": 296
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.88510919394376e-06,
+      "loss": 0.5585,
+      "step": 297
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.827106582344212e-06,
+      "loss": 0.6035,
+      "step": 298
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7695968189919686e-06,
+      "loss": 0.5948,
+      "step": 299
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.712583855372769e-06,
+      "loss": 0.5292,
+      "step": 300
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6560716088373295e-06,
+      "loss": 0.5685,
+      "step": 301
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6000639623321934e-06,
+      "loss": 0.549,
+      "step": 302
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5445647641329154e-06,
+      "loss": 0.5785,
+      "step": 303
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.489577827579659e-06,
+      "loss": 0.6097,
+      "step": 304
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4351069308151774e-06,
+      "loss": 0.5464,
+      "step": 305
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.381155816525228e-06,
+      "loss": 0.5765,
+      "step": 306
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.3277281916814e-06,
+      "loss": 0.5528,
+      "step": 307
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2748277272864108e-06,
+      "loss": 0.5587,
+      "step": 308
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.222458058121889e-06,
+      "loss": 0.5342,
+      "step": 309
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.170622782498598e-06,
+      "loss": 0.538,
+      "step": 310
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.119325462009233e-06,
+      "loss": 0.5665,
+      "step": 311
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0685696212836737e-06,
+      "loss": 0.5527,
+      "step": 312
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0183587477468226e-06,
+      "loss": 0.5514,
+      "step": 313
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9686962913789897e-06,
+      "loss": 0.5289,
+      "step": 314
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.91958566447883e-06,
+      "loss": 0.5796,
+      "step": 315
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.871030241428894e-06,
+      "loss": 0.5477,
+      "step": 316
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8230333584637715e-06,
+      "loss": 0.5773,
+      "step": 317
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7755983134408706e-06,
+      "loss": 0.5297,
+      "step": 318
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7287283656138009e-06,
+      "loss": 0.5628,
+      "step": 319
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6824267354084478e-06,
+      "loss": 0.5604,
+      "step": 320
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6366966042016996e-06,
+      "loss": 0.5333,
+      "step": 321
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5915411141028325e-06,
+      "loss": 0.5227,
+      "step": 322
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5469633677376494e-06,
+      "loss": 0.5521,
+      "step": 323
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.502966428035274e-06,
+      "loss": 0.581,
+      "step": 324
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4595533180177058e-06,
+      "loss": 0.5473,
+      "step": 325
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4167270205921168e-06,
+      "loss": 0.5599,
+      "step": 326
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.37449047834588e-06,
+      "loss": 0.5904,
+      "step": 327
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.332846593344399e-06,
+      "loss": 0.5447,
+      "step": 328
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2917982269316975e-06,
+      "loss": 0.5723,
+      "step": 329
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2513481995338284e-06,
+      "loss": 0.5628,
+      "step": 330
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.211499290465069e-06,
+      "loss": 0.5777,
+      "step": 331
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1722542377369639e-06,
+      "loss": 0.5339,
+      "step": 332
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1336157378702017e-06,
+      "loss": 0.5403,
+      "step": 333
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0955864457093147e-06,
+      "loss": 0.5726,
+      "step": 334
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0581689742402967e-06,
+      "loss": 0.5591,
+      "step": 335
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0213658944110406e-06,
+      "loss": 0.5503,
+      "step": 336
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.851797349546977e-07,
+      "loss": 0.5903,
+      "step": 337
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.496129822159339e-07,
+      "loss": 0.5415,
+      "step": 338
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.146680799800833e-07,
+      "loss": 0.5683,
+      "step": 339
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.803474293052438e-07,
+      "loss": 0.5324,
+      "step": 340
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.466533883572947e-07,
+      "loss": 0.5605,
+      "step": 341
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.135882722478772e-07,
+      "loss": 0.5198,
+      "step": 342
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.811543528753108e-07,
+      "loss": 0.519,
+      "step": 343
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.493538587685012e-07,
+      "loss": 0.5636,
+      "step": 344
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.181889749338178e-07,
+      "loss": 0.566,
+      "step": 345
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.876618427049509e-07,
+      "loss": 0.5921,
+      "step": 346
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.577745595958018e-07,
+      "loss": 0.5559,
+      "step": 347
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.285291791563431e-07,
+      "loss": 0.5203,
+      "step": 348
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.999277108315272e-07,
+      "loss": 0.5623,
+      "step": 349
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.719721198232254e-07,
+      "loss": 0.5508,
+      "step": 350
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.446643269551854e-07,
+      "loss": 0.5346,
+      "step": 351
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.180062085410609e-07,
+      "loss": 0.5603,
+      "step": 352
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.919995962554846e-07,
+      "loss": 0.575,
+      "step": 353
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.6664627700822475e-07,
+      "loss": 0.5449,
+      "step": 354
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4194799282139324e-07,
+      "loss": 0.5512,
+      "step": 355
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1790644070975884e-07,
+      "loss": 0.5551,
+      "step": 356
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.94523272564149e-07,
+      "loss": 0.5601,
+      "step": 357
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.7180009503793745e-07,
+      "loss": 0.559,
+      "step": 358
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.4973846943666567e-07,
+      "loss": 0.5632,
+      "step": 359
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.283399116107533e-07,
+      "loss": 0.5747,
+      "step": 360
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.076058918513503e-07,
+      "loss": 0.5299,
+      "step": 361
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.875378347893165e-07,
+      "loss": 0.5685,
+      "step": 362
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.681371192973281e-07,
+      "loss": 0.5539,
+      "step": 363
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.494050783951396e-07,
+      "loss": 0.556,
+      "step": 364
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.3134299915799185e-07,
+      "loss": 0.5727,
+      "step": 365
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1395212262817933e-07,
+      "loss": 0.5392,
+      "step": 366
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9723364372977395e-07,
+      "loss": 0.5571,
+      "step": 367
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8118871118652516e-07,
+      "loss": 0.5524,
+      "step": 368
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6581842744293309e-07,
+      "loss": 0.5486,
+      "step": 369
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.511238485884914e-07,
+      "loss": 0.5878,
+      "step": 370
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3710598428513634e-07,
+      "loss": 0.5727,
+      "step": 371
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2376579769786124e-07,
+      "loss": 0.5436,
+      "step": 372
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1110420542854383e-07,
+      "loss": 0.5243,
+      "step": 373
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.912207745296665e-08,
+      "loss": 0.5317,
+      "step": 374
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.782023706103926e-08,
+      "loss": 0.538,
+      "step": 375
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.719946080023022e-08,
+      "loss": 0.5841,
+      "step": 376
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.726047842221083e-08,
+      "loss": 0.5409,
+      "step": 377
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.800397283271753e-08,
+      "loss": 0.5594,
+      "step": 378
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.9430580044620425e-08,
+      "loss": 0.5645,
+      "step": 379
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.154088913423615e-08,
+      "loss": 0.58,
+      "step": 380
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.433544220084017e-08,
+      "loss": 0.5469,
+      "step": 381
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7814734329426607e-08,
+      "loss": 0.5631,
+      "step": 382
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.197921355668875e-08,
+      "loss": 0.5649,
+      "step": 383
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.682928084023261e-08,
+      "loss": 0.5603,
+      "step": 384
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2365290031032261e-08,
+      "loss": 0.5276,
+      "step": 385
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.587547849112643e-09,
+      "loss": 0.5536,
+      "step": 386
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.496313862476399e-09,
+      "loss": 0.5579,
+      "step": 387
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.0918004692648273e-09,
+      "loss": 0.5405,
+      "step": 388
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3741728831750956e-09,
+      "loss": 0.5461,
+      "step": 389
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.435491220937781e-10,
+      "loss": 0.519,
+      "step": 390
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.5772,
+      "step": 391
+    },
+    {
+      "epoch": 1.0,
+      "step": 391,
+      "total_flos": 359714349121536.0,
+      "train_loss": 0.6047002936872985,
+      "train_runtime": 6943.4267,
+      "train_samples_per_second": 7.201,
+      "train_steps_per_second": 0.056
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 391,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 359714349121536.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a1d49d2141d15c48cddfa2fd67ea20ef61f3f2fd478f26d3c44d57d6492d8a
+size 6840