Upload folder using huggingface_hub

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250d57032d8c5cf214288fb4718ab42c62b177f193cafd2483f05b5e5e3d724b
+size 9976631486

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53743619301dd9094bb2af4cac48bad290365583fe232b8c90aa9160c44482d3
+size 4149438290

pytorch_model.bin.index.json

@@ -0,0 +1,725 @@
+{
+  "metadata": {
+    "total_size": 14125809664
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.mm_projector.0.bias": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.0.weight": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

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 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 211,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.8875,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.8643,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.8896,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.6971,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 1.5649,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 1.6123,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 1.5796,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999881422898077e-05,
+      "loss": 1.5678,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999525719713366e-05,
+      "loss": 1.5245,
+      "step": 9
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9989329748023728e-05,
+      "loss": 1.5341,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9981033287370443e-05,
+      "loss": 1.4827,
+      "step": 11
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.997036978271433e-05,
+      "loss": 1.4803,
+      "step": 12
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9957341762950346e-05,
+      "loss": 1.4347,
+      "step": 13
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.994195231772815e-05,
+      "loss": 1.4375,
+      "step": 14
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.992420509671936e-05,
+      "loss": 1.4007,
+      "step": 15
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9904104308752053e-05,
+      "loss": 1.416,
+      "step": 16
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9881654720812594e-05,
+      "loss": 1.4114,
+      "step": 17
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.985686165691514e-05,
+      "loss": 1.3866,
+      "step": 18
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 1.3905,
+      "step": 19
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.980026917473432e-05,
+      "loss": 1.3748,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9768483177596008e-05,
+      "loss": 1.3506,
+      "step": 21
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9734380543606932e-05,
+      "loss": 1.3386,
+      "step": 22
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9697969360350098e-05,
+      "loss": 1.375,
+      "step": 23
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 1.3462,
+      "step": 24
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.961825643172819e-05,
+      "loss": 1.3849,
+      "step": 25
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9574973590619243e-05,
+      "loss": 1.3286,
+      "step": 26
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9529420004271568e-05,
+      "loss": 1.3512,
+      "step": 27
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.948160647590966e-05,
+      "loss": 1.3521,
+      "step": 28
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9431544344712776e-05,
+      "loss": 1.3662,
+      "step": 29
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9379245483125783e-05,
+      "loss": 1.3462,
+      "step": 30
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 1.3157,
+      "step": 31
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9267987707869605e-05,
+      "loss": 1.3327,
+      "step": 32
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.920905517944954e-05,
+      "loss": 1.3148,
+      "step": 33
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9147938684880213e-05,
+      "loss": 1.3175,
+      "step": 34
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9084652718195237e-05,
+      "loss": 1.3443,
+      "step": 35
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9019212287927663e-05,
+      "loss": 1.3115,
+      "step": 36
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8951632913550625e-05,
+      "loss": 1.3248,
+      "step": 37
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.888193062179685e-05,
+      "loss": 1.3468,
+      "step": 38
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8810121942857848e-05,
+      "loss": 1.3053,
+      "step": 39
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8736223906463698e-05,
+      "loss": 1.3432,
+      "step": 40
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 1.3188,
+      "step": 41
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8582230353573628e-05,
+      "loss": 1.3094,
+      "step": 42
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 1.3215,
+      "step": 43
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8420096035339454e-05,
+      "loss": 1.2739,
+      "step": 44
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8336023852211197e-05,
+      "loss": 1.3058,
+      "step": 45
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8249974745983023e-05,
+      "loss": 1.2857,
+      "step": 46
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.816196912356222e-05,
+      "loss": 1.2839,
+      "step": 47
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8072027855852098e-05,
+      "loss": 1.2899,
+      "step": 48
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7980172272802398e-05,
+      "loss": 1.2953,
+      "step": 49
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7886424158350784e-05,
+      "loss": 1.2847,
+      "step": 50
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7790805745256703e-05,
+      "loss": 1.3089,
+      "step": 51
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.769333970982879e-05,
+      "loss": 1.2763,
+      "step": 52
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7594049166547073e-05,
+      "loss": 1.3226,
+      "step": 53
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7492957662581297e-05,
+      "loss": 1.2884,
+      "step": 54
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 1.326,
+      "step": 55
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7285468091117904e-05,
+      "loss": 1.2741,
+      "step": 56
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.717911923064442e-05,
+      "loss": 1.3115,
+      "step": 57
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.2578,
+      "step": 58
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.696133945962927e-05,
+      "loss": 1.2754,
+      "step": 59
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6849960196475808e-05,
+      "loss": 1.3098,
+      "step": 60
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6736956436465573e-05,
+      "loss": 1.2831,
+      "step": 61
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6622354978915306e-05,
+      "loss": 1.2863,
+      "step": 62
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.650618300204242e-05,
+      "loss": 1.3345,
+      "step": 63
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.638846805651961e-05,
+      "loss": 1.2951,
+      "step": 64
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.626923805894107e-05,
+      "loss": 1.2884,
+      "step": 65
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6148521285201926e-05,
+      "loss": 1.2866,
+      "step": 66
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 1.2499,
+      "step": 67
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5902742269009198e-05,
+      "loss": 1.277,
+      "step": 68
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5777738314082514e-05,
+      "loss": 1.2836,
+      "step": 69
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.565136414422592e-05,
+      "loss": 1.28,
+      "step": 70
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.552364972960506e-05,
+      "loss": 1.2747,
+      "step": 71
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5394625358230252e-05,
+      "loss": 1.2783,
+      "step": 72
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.526432162877356e-05,
+      "loss": 1.2536,
+      "step": 73
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5132769443312207e-05,
+      "loss": 1.2757,
+      "step": 74
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.2785,
+      "step": 75
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4866044785668563e-05,
+      "loss": 1.239,
+      "step": 76
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4730935568360103e-05,
+      "loss": 1.2783,
+      "step": 77
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4594704389793477e-05,
+      "loss": 1.2945,
+      "step": 78
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 1.3282,
+      "step": 79
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4319005638488413e-05,
+      "loss": 1.2503,
+      "step": 80
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4179603448867836e-05,
+      "loss": 1.2563,
+      "step": 81
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.403921004871895e-05,
+      "loss": 1.2832,
+      "step": 82
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3897858732926794e-05,
+      "loss": 1.2885,
+      "step": 83
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3755583023550128e-05,
+      "loss": 1.2307,
+      "step": 84
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3612416661871532e-05,
+      "loss": 1.2627,
+      "step": 85
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3468393600395526e-05,
+      "loss": 1.2693,
+      "step": 86
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3323547994796597e-05,
+      "loss": 1.2647,
+      "step": 87
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3177914195819018e-05,
+      "loss": 1.2946,
+      "step": 88
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3031526741130435e-05,
+      "loss": 1.2575,
+      "step": 89
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2884420347131123e-05,
+      "loss": 1.2744,
+      "step": 90
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 1.2949,
+      "step": 91
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 1.2619,
+      "step": 92
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2439137201083772e-05,
+      "loss": 1.2577,
+      "step": 93
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2289505499501341e-05,
+      "loss": 1.2875,
+      "step": 94
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2139330832064975e-05,
+      "loss": 1.2539,
+      "step": 95
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1988648813328368e-05,
+      "loss": 1.2455,
+      "step": 96
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1837495178165706e-05,
+      "loss": 1.278,
+      "step": 97
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1685905773296992e-05,
+      "loss": 1.19,
+      "step": 98
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1533916548786856e-05,
+      "loss": 1.2884,
+      "step": 99
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1381563549518823e-05,
+      "loss": 1.2803,
+      "step": 100
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1228882906647142e-05,
+      "loss": 1.2633,
+      "step": 101
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1075910829028116e-05,
+      "loss": 1.2803,
+      "step": 102
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 1.2648,
+      "step": 103
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0769237541944639e-05,
+      "loss": 1.2875,
+      "step": 104
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0615609061339431e-05,
+      "loss": 1.296,
+      "step": 105
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0461834586457398e-05,
+      "loss": 1.2473,
+      "step": 106
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0307950585561705e-05,
+      "loss": 1.2367,
+      "step": 107
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0153993552890069e-05,
+      "loss": 1.2594,
+      "step": 108
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 1.2455,
+      "step": 109
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.846006447109934e-06,
+      "loss": 1.2389,
+      "step": 110
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.692049414438298e-06,
+      "loss": 1.2345,
+      "step": 111
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.538165413542607e-06,
+      "loss": 1.2333,
+      "step": 112
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.384390938660572e-06,
+      "loss": 1.2659,
+      "step": 113
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.230762458055363e-06,
+      "loss": 1.255,
+      "step": 114
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 1.2748,
+      "step": 115
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.924089170971887e-06,
+      "loss": 1.236,
+      "step": 116
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.771117093352861e-06,
+      "loss": 1.2205,
+      "step": 117
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.618436450481182e-06,
+      "loss": 1.2642,
+      "step": 118
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.466083451213145e-06,
+      "loss": 1.2446,
+      "step": 119
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.314094226703007e-06,
+      "loss": 1.2335,
+      "step": 120
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.162504821834296e-06,
+      "loss": 1.2341,
+      "step": 121
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.011351186671637e-06,
+      "loss": 1.2627,
+      "step": 122
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.860669167935028e-06,
+      "loss": 1.2627,
+      "step": 123
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.710494500498662e-06,
+      "loss": 1.2629,
+      "step": 124
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.560862798916229e-06,
+      "loss": 1.2712,
+      "step": 125
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 1.2291,
+      "step": 126
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 1.2256,
+      "step": 127
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.115579652868878e-06,
+      "loss": 1.2618,
+      "step": 128
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.968473258869566e-06,
+      "loss": 1.2276,
+      "step": 129
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.822085804180985e-06,
+      "loss": 1.2346,
+      "step": 130
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.6764520052034054e-06,
+      "loss": 1.2408,
+      "step": 131
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.5316063996044735e-06,
+      "loss": 1.2374,
+      "step": 132
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.387583338128471e-06,
+      "loss": 1.2408,
+      "step": 133
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.244416976449875e-06,
+      "loss": 1.2408,
+      "step": 134
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.102141267073207e-06,
+      "loss": 1.2389,
+      "step": 135
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.960789951281052e-06,
+      "loss": 1.264,
+      "step": 136
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.82039655113217e-06,
+      "loss": 1.2144,
+      "step": 137
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.6809943615115915e-06,
+      "loss": 1.2186,
+      "step": 138
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 1.2578,
+      "step": 139
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.405295610206525e-06,
+      "loss": 1.2285,
+      "step": 140
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.269064431639901e-06,
+      "loss": 1.2604,
+      "step": 141
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.133955214331439e-06,
+      "loss": 1.2013,
+      "step": 142
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.248,
+      "step": 143
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.867230556687797e-06,
+      "loss": 1.2354,
+      "step": 144
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.7356783712264405e-06,
+      "loss": 1.2128,
+      "step": 145
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.605374641769752e-06,
+      "loss": 1.2409,
+      "step": 146
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.476350270394942e-06,
+      "loss": 1.2855,
+      "step": 147
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.348635855774082e-06,
+      "loss": 1.2478,
+      "step": 148
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.222261685917489e-06,
+      "loss": 1.2466,
+      "step": 149
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.097257730990806e-06,
+      "loss": 1.2434,
+      "step": 150
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 1.2537,
+      "step": 151
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.851478714798076e-06,
+      "loss": 1.2391,
+      "step": 152
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.730761941058938e-06,
+      "loss": 1.2721,
+      "step": 153
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6115319434803897e-06,
+      "loss": 1.2237,
+      "step": 154
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.493816997957582e-06,
+      "loss": 1.2108,
+      "step": 155
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.377645021084701e-06,
+      "loss": 1.2401,
+      "step": 156
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2630435635344283e-06,
+      "loss": 1.176,
+      "step": 157
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.150039803524194e-06,
+      "loss": 1.2525,
+      "step": 158
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0386605403707347e-06,
+      "loss": 1.2273,
+      "step": 159
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 1.2215,
+      "step": 160
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.820880769355582e-06,
+      "loss": 1.2344,
+      "step": 161
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7145319088820986e-06,
+      "loss": 1.2307,
+      "step": 162
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 1.2581,
+      "step": 163
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.507042337418707e-06,
+      "loss": 1.2203,
+      "step": 164
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.405950833452928e-06,
+      "loss": 1.2539,
+      "step": 165
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.306660290171211e-06,
+      "loss": 1.2341,
+      "step": 166
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.209194254743295e-06,
+      "loss": 1.2397,
+      "step": 167
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.1135758416492168e-06,
+      "loss": 1.2131,
+      "step": 168
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.019827727197605e-06,
+      "loss": 1.2319,
+      "step": 169
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.927972144147905e-06,
+      "loss": 1.2468,
+      "step": 170
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8380308764377841e-06,
+      "loss": 1.217,
+      "step": 171
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7500252540169782e-06,
+      "loss": 1.2254,
+      "step": 172
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.663976147788806e-06,
+      "loss": 1.211,
+      "step": 173
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5799039646605486e-06,
+      "loss": 1.2048,
+      "step": 174
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 1.2243,
+      "step": 175
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4177696464263725e-06,
+      "loss": 1.1779,
+      "step": 176
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 1.2447,
+      "step": 177
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2637760935363053e-06,
+      "loss": 1.2624,
+      "step": 178
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1898780571421554e-06,
+      "loss": 1.2074,
+      "step": 179
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1180693782031516e-06,
+      "loss": 1.2285,
+      "step": 180
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0483670864493777e-06,
+      "loss": 1.2529,
+      "step": 181
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.807877120723397e-07,
+      "loss": 1.2407,
+      "step": 182
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.153472818047627e-07,
+      "loss": 1.2512,
+      "step": 183
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.520613151197899e-07,
+      "loss": 1.2288,
+      "step": 184
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.909448205504633e-07,
+      "loss": 1.2128,
+      "step": 185
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.320122921303962e-07,
+      "loss": 1.2383,
+      "step": 186
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 1.2692,
+      "step": 187
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.207545168742212e-07,
+      "loss": 1.2128,
+      "step": 188
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.684556552872256e-07,
+      "loss": 1.2152,
+      "step": 189
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.183935240903415e-07,
+      "loss": 1.2494,
+      "step": 190
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.7057999572843516e-07,
+      "loss": 1.2492,
+      "step": 191
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.2502640938075654e-07,
+      "loss": 1.2599,
+      "step": 192
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.817435682718096e-07,
+      "loss": 1.2451,
+      "step": 193
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 1.2468,
+      "step": 194
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.020306396499062e-07,
+      "loss": 1.2331,
+      "step": 195
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.656194563930714e-07,
+      "loss": 1.2034,
+      "step": 196
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.315168224039932e-07,
+      "loss": 1.2083,
+      "step": 197
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9973082526568155e-07,
+      "loss": 1.2145,
+      "step": 198
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 1.1815,
+      "step": 199
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4313834308486097e-07,
+      "loss": 1.2388,
+      "step": 200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1834527918740624e-07,
+      "loss": 1.2485,
+      "step": 201
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.589569124794918e-08,
+      "loss": 1.2527,
+      "step": 202
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.579490328064265e-08,
+      "loss": 1.2448,
+      "step": 203
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.8047682271855644e-08,
+      "loss": 1.2123,
+      "step": 204
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.2658237049655325e-08,
+      "loss": 1.259,
+      "step": 205
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.963021728567106e-08,
+      "loss": 1.2348,
+      "step": 206
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.896671262955896e-08,
+      "loss": 1.2254,
+      "step": 207
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0670251976275803e-08,
+      "loss": 1.2404,
+      "step": 208
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.74280286634099e-09,
+      "loss": 1.2435,
+      "step": 209
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.185771019230897e-09,
+      "loss": 1.2122,
+      "step": 210
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 1.2199,
+      "step": 211
+    },
+    {
+      "epoch": 1.0,
+      "step": 211,
+      "total_flos": 167544146296832.0,
+      "train_loss": 1.289455922294002,
+      "train_runtime": 2388.2192,
+      "train_samples_per_second": 9.884,
+      "train_steps_per_second": 0.088
+    }
+  ],
+  "max_steps": 211,
+  "num_train_epochs": 1,
+  "total_flos": 167544146296832.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e579a9a4a2cfef940a49d89c9a220dc0498135355d7fbfdc9cf705e70fcb8943
+size 5947