Upload 11 files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "/scratch/r929a01/work/pretrained-model/Synatra-7B-v0.3-dpo",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "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": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 4096,
+  "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": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.31.0",
+  "use_cache": false
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e88c317d685170687a49c82238d2a7480b0c8707c288e606b686facc9180857
+size 9943055325

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ac0dee001b5594e7ef99038cc5ce7abeae1534cec23152eae34be394c4c79c
+size 5189680379

pytorch_model.bin.index.json

@@ -0,0 +1,725 @@
+{
+  "metadata": {
+    "total_size": 15132475392
+  },
+  "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-00002-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-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 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,94 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,2719 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9983324068927182,
+  "global_step": 449,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 2.3547,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 2.3748,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 2.02,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.7879,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 1.6861,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.3654,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 1.3584,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.1595,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.2857142857142859e-05,
+      "loss": 1.0781,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 1.0899,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 0.9667,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.9737,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8571428571428575e-05,
+      "loss": 0.9328,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.8672,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999739210952493e-05,
+      "loss": 0.7745,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999895685741216e-05,
+      "loss": 0.7808,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999765298018484e-05,
+      "loss": 0.746,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9995827647277926e-05,
+      "loss": 0.7372,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999348095389677e-05,
+      "loss": 0.6908,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999061302243977e-05,
+      "loss": 0.7155,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998722400249194e-05,
+      "loss": 0.6993,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9983314070817142e-05,
+      "loss": 0.6723,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9978883431348845e-05,
+      "loss": 0.6804,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9973932315179502e-05,
+      "loss": 0.6559,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996846098054848e-05,
+      "loss": 0.6362,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9962469712828613e-05,
+      "loss": 0.6358,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9955958824511302e-05,
+      "loss": 0.6226,
+      "step": 27
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.994892865519022e-05,
+      "loss": 0.6076,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9941379571543597e-05,
+      "loss": 0.5944,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.99333119673151e-05,
+      "loss": 0.5725,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9924726263293297e-05,
+      "loss": 0.6,
+      "step": 31
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9915622907289695e-05,
+      "loss": 0.5822,
+      "step": 32
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.990600237411541e-05,
+      "loss": 0.5779,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9895865165556375e-05,
+      "loss": 0.5828,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9885211810347185e-05,
+      "loss": 0.5725,
+      "step": 35
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.987404286414351e-05,
+      "loss": 0.5688,
+      "step": 36
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9862358909493113e-05,
+      "loss": 0.5756,
+      "step": 37
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9850160555805485e-05,
+      "loss": 0.5606,
+      "step": 38
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9837448439320027e-05,
+      "loss": 0.5675,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9824223223072895e-05,
+      "loss": 0.5619,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.981048559686239e-05,
+      "loss": 0.547,
+      "step": 41
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9796236277213013e-05,
+      "loss": 0.5567,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.5614,
+      "step": 43
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.976620555710087e-05,
+      "loss": 0.5319,
+      "step": 44
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.975042572297468e-05,
+      "loss": 0.5288,
+      "step": 45
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9734137328001077e-05,
+      "loss": 0.5394,
+      "step": 46
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9717341221747056e-05,
+      "loss": 0.5469,
+      "step": 47
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9700038280260734e-05,
+      "loss": 0.5392,
+      "step": 48
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9682229406025635e-05,
+      "loss": 0.5416,
+      "step": 49
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9663915527913628e-05,
+      "loss": 0.5413,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9645097601136475e-05,
+      "loss": 0.5191,
+      "step": 51
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9625776607196024e-05,
+      "loss": 0.5075,
+      "step": 52
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9605953553832987e-05,
+      "loss": 0.5249,
+      "step": 53
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9585629474974413e-05,
+      "loss": 0.5356,
+      "step": 54
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9564805430679733e-05,
+      "loss": 0.5181,
+      "step": 55
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9543482507085484e-05,
+      "loss": 0.5144,
+      "step": 56
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9521661816348647e-05,
+      "loss": 0.53,
+      "step": 57
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9499344496588656e-05,
+      "loss": 0.5214,
+      "step": 58
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 0.5227,
+      "step": 59
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9453224651931638e-05,
+      "loss": 0.5198,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9429424532544677e-05,
+      "loss": 0.5423,
+      "step": 61
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.940513259502924e-05,
+      "loss": 0.5192,
+      "step": 62
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9380350106399578e-05,
+      "loss": 0.5198,
+      "step": 63
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.935507835925601e-05,
+      "loss": 0.5071,
+      "step": 64
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.932931867171751e-05,
+      "loss": 0.5119,
+      "step": 65
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9303072387352952e-05,
+      "loss": 0.5291,
+      "step": 66
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.927634087511104e-05,
+      "loss": 0.5031,
+      "step": 67
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.924912552924889e-05,
+      "loss": 0.5184,
+      "step": 68
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9221427769259333e-05,
+      "loss": 0.5138,
+      "step": 69
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9193249039796856e-05,
+      "loss": 0.516,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9164590810602262e-05,
+      "loss": 0.4795,
+      "step": 71
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.4943,
+      "step": 72
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9105841856950254e-05,
+      "loss": 0.4881,
+      "step": 73
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 0.4875,
+      "step": 74
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9045193165010417e-05,
+      "loss": 0.4936,
+      "step": 75
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.901416035584926e-05,
+      "loss": 0.5009,
+      "step": 76
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8982657387829447e-05,
+      "loss": 0.4853,
+      "step": 77
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.895068590407678e-05,
+      "loss": 0.4901,
+      "step": 78
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8918247572153822e-05,
+      "loss": 0.4854,
+      "step": 79
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8885344083972912e-05,
+      "loss": 0.4974,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8851977155707917e-05,
+      "loss": 0.4918,
+      "step": 81
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.881814852770472e-05,
+      "loss": 0.4795,
+      "step": 82
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8783859964390466e-05,
+      "loss": 0.5025,
+      "step": 83
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8749113254181498e-05,
+      "loss": 0.4997,
+      "step": 84
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8713910209390113e-05,
+      "loss": 0.4936,
+      "step": 85
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8678252666130016e-05,
+      "loss": 0.484,
+      "step": 86
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.864214248422055e-05,
+      "loss": 0.4882,
+      "step": 87
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8605581547089715e-05,
+      "loss": 0.4898,
+      "step": 88
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 0.4993,
+      "step": 89
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.853111505832843e-05,
+      "loss": 0.4884,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.849321339070692e-05,
+      "loss": 0.4789,
+      "step": 91
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.845486873567932e-05,
+      "loss": 0.4909,
+      "step": 92
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8416083093218847e-05,
+      "loss": 0.4788,
+      "step": 93
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.837685848629965e-05,
+      "loss": 0.4972,
+      "step": 94
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8337196960791305e-05,
+      "loss": 0.4876,
+      "step": 95
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.82971005853521e-05,
+      "loss": 0.4774,
+      "step": 96
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8256571451321155e-05,
+      "loss": 0.4822,
+      "step": 97
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8215611672609316e-05,
+      "loss": 0.4884,
+      "step": 98
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.817422338558892e-05,
+      "loss": 0.477,
+      "step": 99
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8132408748982356e-05,
+      "loss": 0.4848,
+      "step": 100
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.4661,
+      "step": 101
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8047509172973832e-05,
+      "loss": 0.4822,
+      "step": 102
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.800442866174779e-05,
+      "loss": 0.4787,
+      "step": 103
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.796093065705644e-05,
+      "loss": 0.4879,
+      "step": 104
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7917017427660424e-05,
+      "loss": 0.4858,
+      "step": 105
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.78726912639776e-05,
+      "loss": 0.4865,
+      "step": 106
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.782795447796356e-05,
+      "loss": 0.4758,
+      "step": 107
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7782809402991076e-05,
+      "loss": 0.4919,
+      "step": 108
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7737258393728363e-05,
+      "loss": 0.4807,
+      "step": 109
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.769130382601629e-05,
+      "loss": 0.4928,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.764494809674444e-05,
+      "loss": 0.4828,
+      "step": 111
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7598193623726115e-05,
+      "loss": 0.4865,
+      "step": 112
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.755104284557221e-05,
+      "loss": 0.464,
+      "step": 113
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7503498221564026e-05,
+      "loss": 0.4775,
+      "step": 114
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7455562231525006e-05,
+      "loss": 0.4882,
+      "step": 115
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7407237375691394e-05,
+      "loss": 0.484,
+      "step": 116
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7358526174581806e-05,
+      "loss": 0.4686,
+      "step": 117
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.730943116886579e-05,
+      "loss": 0.4877,
+      "step": 118
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.725995491923131e-05,
+      "loss": 0.455,
+      "step": 119
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7210100006251164e-05,
+      "loss": 0.47,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7159869030248404e-05,
+      "loss": 0.4756,
+      "step": 121
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.710926461116071e-05,
+      "loss": 0.4808,
+      "step": 122
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.705828938840373e-05,
+      "loss": 0.4687,
+      "step": 123
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7006946020733426e-05,
+      "loss": 0.4707,
+      "step": 124
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6955237186107387e-05,
+      "loss": 0.4551,
+      "step": 125
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.690316558154516e-05,
+      "loss": 0.4769,
+      "step": 126
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.685073392298757e-05,
+      "loss": 0.4799,
+      "step": 127
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.679794494515508e-05,
+      "loss": 0.4704,
+      "step": 128
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6744801401405138e-05,
+      "loss": 0.4617,
+      "step": 129
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.4573,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6637461721905047e-05,
+      "loss": 0.4624,
+      "step": 131
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6583271184757444e-05,
+      "loss": 0.4789,
+      "step": 132
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6528737278605492e-05,
+      "loss": 0.4785,
+      "step": 133
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.647386284781828e-05,
+      "loss": 0.4682,
+      "step": 134
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.641865075452591e-05,
+      "loss": 0.4771,
+      "step": 135
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.636310387847023e-05,
+      "loss": 0.4762,
+      "step": 136
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6307225116854623e-05,
+      "loss": 0.4633,
+      "step": 137
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6251017384192885e-05,
+      "loss": 0.4565,
+      "step": 138
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6194483612157232e-05,
+      "loss": 0.4594,
+      "step": 139
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6137626749425377e-05,
+      "loss": 0.4749,
+      "step": 140
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6080449761526737e-05,
+      "loss": 0.4785,
+      "step": 141
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6022955630687752e-05,
+      "loss": 0.4574,
+      "step": 142
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5965147355676344e-05,
+      "loss": 0.4739,
+      "step": 143
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.590702795164551e-05,
+      "loss": 0.4498,
+      "step": 144
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.584860044997606e-05,
+      "loss": 0.4631,
+      "step": 145
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.578986789811849e-05,
+      "loss": 0.4617,
+      "step": 146
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.573083335943405e-05,
+      "loss": 0.4593,
+      "step": 147
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5671499913034962e-05,
+      "loss": 0.4835,
+      "step": 148
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5611870653623826e-05,
+      "loss": 0.4776,
+      "step": 149
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5551948691332192e-05,
+      "loss": 0.4684,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5491737151558352e-05,
+      "loss": 0.4572,
+      "step": 151
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.543123917480433e-05,
+      "loss": 0.4719,
+      "step": 152
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5370457916512072e-05,
+      "loss": 0.4771,
+      "step": 153
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.530939654689887e-05,
+      "loss": 0.4735,
+      "step": 154
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5248058250792008e-05,
+      "loss": 0.4508,
+      "step": 155
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5186446227462646e-05,
+      "loss": 0.4604,
+      "step": 156
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5124563690458966e-05,
+      "loss": 0.458,
+      "step": 157
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.506241386743854e-05,
+      "loss": 0.4482,
+      "step": 158
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4643,
+      "step": 159
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4937325343513953e-05,
+      "loss": 0.4576,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4874393166953194e-05,
+      "loss": 0.4678,
+      "step": 161
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4811206752722196e-05,
+      "loss": 0.4593,
+      "step": 162
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4747769396485917e-05,
+      "loss": 0.4643,
+      "step": 163
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 0.4518,
+      "step": 164
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4620155105927699e-05,
+      "loss": 0.441,
+      "step": 165
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4555984827687613e-05,
+      "loss": 0.4595,
+      "step": 166
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4491576919258794e-05,
+      "loss": 0.4751,
+      "step": 167
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4426934740016655e-05,
+      "loss": 0.4455,
+      "step": 168
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4362061661555675e-05,
+      "loss": 0.4608,
+      "step": 169
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4296961067513519e-05,
+      "loss": 0.4593,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.423163635339457e-05,
+      "loss": 0.4504,
+      "step": 171
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4166090926392815e-05,
+      "loss": 0.4559,
+      "step": 172
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4100328205214161e-05,
+      "loss": 0.4445,
+      "step": 173
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4034351619898088e-05,
+      "loss": 0.4695,
+      "step": 174
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3968164611638759e-05,
+      "loss": 0.4492,
+      "step": 175
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3901770632605546e-05,
+      "loss": 0.4543,
+      "step": 176
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3835173145762961e-05,
+      "loss": 0.4536,
+      "step": 177
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3768375624690033e-05,
+      "loss": 0.4457,
+      "step": 178
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3701381553399147e-05,
+      "loss": 0.4567,
+      "step": 179
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3634194426154301e-05,
+      "loss": 0.4388,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3566817747288887e-05,
+      "loss": 0.4463,
+      "step": 181
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3499255031022887e-05,
+      "loss": 0.4688,
+      "step": 182
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3431509801279578e-05,
+      "loss": 0.4448,
+      "step": 183
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3363585591501751e-05,
+      "loss": 0.4417,
+      "step": 184
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3295485944467405e-05,
+      "loss": 0.4583,
+      "step": 185
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3227214412104952e-05,
+      "loss": 0.44,
+      "step": 186
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3158774555307972e-05,
+      "loss": 0.4529,
+      "step": 187
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.4528,
+      "step": 188
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3021404155695728e-05,
+      "loss": 0.4357,
+      "step": 189
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.29524807778196e-05,
+      "loss": 0.4418,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.288340340501351e-05,
+      "loss": 0.4379,
+      "step": 191
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.28141756402019e-05,
+      "loss": 0.4468,
+      "step": 192
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.274480109415335e-05,
+      "loss": 0.4521,
+      "step": 193
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 0.4467,
+      "step": 194
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2605626139509899e-05,
+      "loss": 0.4393,
+      "step": 195
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2535832989975766e-05,
+      "loss": 0.4616,
+      "step": 196
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2465907576947623e-05,
+      "loss": 0.4447,
+      "step": 197
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2395853547581829e-05,
+      "loss": 0.4503,
+      "step": 198
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2325674555743106e-05,
+      "loss": 0.4336,
+      "step": 199
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2255374261813944e-05,
+      "loss": 0.4443,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2184956332503679e-05,
+      "loss": 0.4567,
+      "step": 201
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2114424440657255e-05,
+      "loss": 0.4566,
+      "step": 202
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.204378226506365e-05,
+      "loss": 0.4453,
+      "step": 203
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1973033490264e-05,
+      "loss": 0.4476,
+      "step": 204
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1902181806359427e-05,
+      "loss": 0.4344,
+      "step": 205
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1831230908818563e-05,
+      "loss": 0.4345,
+      "step": 206
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1760184498284801e-05,
+      "loss": 0.4415,
+      "step": 207
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.168904628038329e-05,
+      "loss": 0.4574,
+      "step": 208
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.161781996552765e-05,
+      "loss": 0.4484,
+      "step": 209
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1546509268726437e-05,
+      "loss": 0.4485,
+      "step": 210
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1475117909389396e-05,
+      "loss": 0.4389,
+      "step": 211
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1403649611133444e-05,
+      "loss": 0.4539,
+      "step": 212
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1332108101588468e-05,
+      "loss": 0.4509,
+      "step": 213
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1260497112202895e-05,
+      "loss": 0.4334,
+      "step": 214
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1188820378049066e-05,
+      "loss": 0.4513,
+      "step": 215
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1117081637628426e-05,
+      "loss": 0.4568,
+      "step": 216
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.4334,
+      "step": 217
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0973433107967901e-05,
+      "loss": 0.4422,
+      "step": 218
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0901530811120655e-05,
+      "loss": 0.4436,
+      "step": 219
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0829581492401103e-05,
+      "loss": 0.4279,
+      "step": 220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0757588904528106e-05,
+      "loss": 0.4404,
+      "step": 221
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0685556802477347e-05,
+      "loss": 0.4651,
+      "step": 222
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.061348894328548e-05,
+      "loss": 0.4459,
+      "step": 223
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0541389085854177e-05,
+      "loss": 0.4486,
+      "step": 224
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.046926099075407e-05,
+      "loss": 0.4319,
+      "step": 225
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0397108420028598e-05,
+      "loss": 0.4423,
+      "step": 226
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0324935136997807e-05,
+      "loss": 0.4361,
+      "step": 227
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0252744906062038e-05,
+      "loss": 0.4481,
+      "step": 228
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0180541492505605e-05,
+      "loss": 0.4315,
+      "step": 229
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0108328662300399e-05,
+      "loss": 0.417,
+      "step": 230
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0036110181909466e-05,
+      "loss": 0.4413,
+      "step": 231
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.963889818090539e-06,
+      "loss": 0.4419,
+      "step": 232
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.891671337699603e-06,
+      "loss": 0.4461,
+      "step": 233
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.819458507494395e-06,
+      "loss": 0.4484,
+      "step": 234
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.747255093937966e-06,
+      "loss": 0.4283,
+      "step": 235
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.675064863002196e-06,
+      "loss": 0.4429,
+      "step": 236
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.602891579971405e-06,
+      "loss": 0.4467,
+      "step": 237
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.530739009245934e-06,
+      "loss": 0.4391,
+      "step": 238
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.458610914145826e-06,
+      "loss": 0.4527,
+      "step": 239
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.386511056714527e-06,
+      "loss": 0.4406,
+      "step": 240
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.314443197522658e-06,
+      "loss": 0.4375,
+      "step": 241
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.242411095471897e-06,
+      "loss": 0.4423,
+      "step": 242
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.170418507598902e-06,
+      "loss": 0.4391,
+      "step": 243
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.098469188879348e-06,
+      "loss": 0.4376,
+      "step": 244
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.026566892032104e-06,
+      "loss": 0.4478,
+      "step": 245
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.4252,
+      "step": 246
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.882918362371573e-06,
+      "loss": 0.4227,
+      "step": 247
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.811179621950937e-06,
+      "loss": 0.4421,
+      "step": 248
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.739502887797108e-06,
+      "loss": 0.438,
+      "step": 249
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.66789189841153e-06,
+      "loss": 0.4273,
+      "step": 250
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.596350388866557e-06,
+      "loss": 0.4364,
+      "step": 251
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.524882090610607e-06,
+      "loss": 0.4443,
+      "step": 252
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.453490731273566e-06,
+      "loss": 0.4254,
+      "step": 253
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.382180034472353e-06,
+      "loss": 0.4182,
+      "step": 254
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.31095371961671e-06,
+      "loss": 0.4332,
+      "step": 255
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.239815501715202e-06,
+      "loss": 0.4335,
+      "step": 256
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.168769091181439e-06,
+      "loss": 0.4299,
+      "step": 257
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.097818193640571e-06,
+      "loss": 0.4347,
+      "step": 258
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.026966509736001e-06,
+      "loss": 0.4326,
+      "step": 259
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.956217734936353e-06,
+      "loss": 0.4328,
+      "step": 260
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.885575559342751e-06,
+      "loss": 0.4397,
+      "step": 261
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.815043667496323e-06,
+      "loss": 0.4483,
+      "step": 262
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.74462573818606e-06,
+      "loss": 0.4316,
+      "step": 263
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.674325444256899e-06,
+      "loss": 0.4428,
+      "step": 264
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.604146452418175e-06,
+      "loss": 0.4342,
+      "step": 265
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.534092423052382e-06,
+      "loss": 0.425,
+      "step": 266
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.464167010024236e-06,
+      "loss": 0.4316,
+      "step": 267
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.394373860490105e-06,
+      "loss": 0.4375,
+      "step": 268
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.324716614707794e-06,
+      "loss": 0.4235,
+      "step": 269
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.2551989058466545e-06,
+      "loss": 0.4259,
+      "step": 270
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.185824359798099e-06,
+      "loss": 0.4297,
+      "step": 271
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.1165965949864934e-06,
+      "loss": 0.4303,
+      "step": 272
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.0475192221804014e-06,
+      "loss": 0.441,
+      "step": 273
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.978595844304272e-06,
+      "loss": 0.4292,
+      "step": 274
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.431,
+      "step": 275
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.841225444692032e-06,
+      "loss": 0.4192,
+      "step": 276
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.772785587895055e-06,
+      "loss": 0.4349,
+      "step": 277
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.704514055532597e-06,
+      "loss": 0.4362,
+      "step": 278
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.636414408498249e-06,
+      "loss": 0.4332,
+      "step": 279
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.568490198720426e-06,
+      "loss": 0.4339,
+      "step": 280
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.500744968977116e-06,
+      "loss": 0.431,
+      "step": 281
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.433182252711113e-06,
+      "loss": 0.4369,
+      "step": 282
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.365805573845701e-06,
+      "loss": 0.4302,
+      "step": 283
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.298618446600856e-06,
+      "loss": 0.422,
+      "step": 284
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.231624375309971e-06,
+      "loss": 0.4379,
+      "step": 285
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.164826854237042e-06,
+      "loss": 0.4162,
+      "step": 286
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.098229367394455e-06,
+      "loss": 0.4293,
+      "step": 287
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.0318353883612465e-06,
+      "loss": 0.4322,
+      "step": 288
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.965648380101916e-06,
+      "loss": 0.4322,
+      "step": 289
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.8996717947858395e-06,
+      "loss": 0.4126,
+      "step": 290
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.833909073607187e-06,
+      "loss": 0.441,
+      "step": 291
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.768363646605435e-06,
+      "loss": 0.4238,
+      "step": 292
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.7030389324864845e-06,
+      "loss": 0.429,
+      "step": 293
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.637938338444325e-06,
+      "loss": 0.4101,
+      "step": 294
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.573065259983347e-06,
+      "loss": 0.4419,
+      "step": 295
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5084230807412135e-06,
+      "loss": 0.4052,
+      "step": 296
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.444015172312391e-06,
+      "loss": 0.4308,
+      "step": 297
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.379844894072303e-06,
+      "loss": 0.4432,
+      "step": 298
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.3159155930021e-06,
+      "loss": 0.4259,
+      "step": 299
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.252230603514082e-06,
+      "loss": 0.4291,
+      "step": 300
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.1887932472778056e-06,
+      "loss": 0.4202,
+      "step": 301
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.12560683304681e-06,
+      "loss": 0.4274,
+      "step": 302
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.062674656486049e-06,
+      "loss": 0.438,
+      "step": 303
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.4295,
+      "step": 304
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.93758613256146e-06,
+      "loss": 0.4244,
+      "step": 305
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.875436309541033e-06,
+      "loss": 0.4258,
+      "step": 306
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.813553772537354e-06,
+      "loss": 0.4133,
+      "step": 307
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.751941749207996e-06,
+      "loss": 0.4217,
+      "step": 308
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.690603453101134e-06,
+      "loss": 0.43,
+      "step": 309
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.629542083487931e-06,
+      "loss": 0.4314,
+      "step": 310
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.568760825195671e-06,
+      "loss": 0.4178,
+      "step": 311
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.508262848441651e-06,
+      "loss": 0.4175,
+      "step": 312
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.44805130866781e-06,
+      "loss": 0.4189,
+      "step": 313
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.388129346376177e-06,
+      "loss": 0.4351,
+      "step": 314
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.328500086965041e-06,
+      "loss": 0.4259,
+      "step": 315
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.269166640565953e-06,
+      "loss": 0.4104,
+      "step": 316
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.210132101881516e-06,
+      "loss": 0.4136,
+      "step": 317
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.151399550023941e-06,
+      "loss": 0.4232,
+      "step": 318
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.092972048354491e-06,
+      "loss": 0.4296,
+      "step": 319
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.034852644323661e-06,
+      "loss": 0.422,
+      "step": 320
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.977044369312253e-06,
+      "loss": 0.4264,
+      "step": 321
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.919550238473265e-06,
+      "loss": 0.4091,
+      "step": 322
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.862373250574626e-06,
+      "loss": 0.4264,
+      "step": 323
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8055163878427703e-06,
+      "loss": 0.4264,
+      "step": 324
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7489826158071196e-06,
+      "loss": 0.4181,
+      "step": 325
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.6927748831453835e-06,
+      "loss": 0.4072,
+      "step": 326
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6368961215297726e-06,
+      "loss": 0.4268,
+      "step": 327
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.581349245474095e-06,
+      "loss": 0.4185,
+      "step": 328
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5261371521817247e-06,
+      "loss": 0.4273,
+      "step": 329
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.4712627213945084e-06,
+      "loss": 0.4138,
+      "step": 330
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.416728815242557e-06,
+      "loss": 0.4294,
+      "step": 331
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3625382780949576e-06,
+      "loss": 0.4274,
+      "step": 332
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.4183,
+      "step": 333
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.255198598594862e-06,
+      "loss": 0.4171,
+      "step": 334
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2020550548449213e-06,
+      "loss": 0.4285,
+      "step": 335
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1492660770124337e-06,
+      "loss": 0.4254,
+      "step": 336
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.096834418454844e-06,
+      "loss": 0.415,
+      "step": 337
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0447628138926153e-06,
+      "loss": 0.4124,
+      "step": 338
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.9930539792665767e-06,
+      "loss": 0.4059,
+      "step": 339
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.941710611596271e-06,
+      "loss": 0.4286,
+      "step": 340
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8907353888392955e-06,
+      "loss": 0.4267,
+      "step": 341
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8401309697515987e-06,
+      "loss": 0.4126,
+      "step": 342
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7898999937488415e-06,
+      "loss": 0.4362,
+      "step": 343
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.740045080768694e-06,
+      "loss": 0.4229,
+      "step": 344
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6905688311342113e-06,
+      "loss": 0.4161,
+      "step": 345
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.641473825418197e-06,
+      "loss": 0.4187,
+      "step": 346
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.59276262430861e-06,
+      "loss": 0.4317,
+      "step": 347
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.544437768474993e-06,
+      "loss": 0.4084,
+      "step": 348
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.496501778435977e-06,
+      "loss": 0.4214,
+      "step": 349
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4489571544277944e-06,
+      "loss": 0.4069,
+      "step": 350
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4018063762738863e-06,
+      "loss": 0.4208,
+      "step": 351
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.355051903255562e-06,
+      "loss": 0.4088,
+      "step": 352
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.308696173983711e-06,
+      "loss": 0.4261,
+      "step": 353
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2627416062716366e-06,
+      "loss": 0.4288,
+      "step": 354
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.217190597008927e-06,
+      "loss": 0.4002,
+      "step": 355
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1720455220364443e-06,
+      "loss": 0.4077,
+      "step": 356
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1273087360224086e-06,
+      "loss": 0.4103,
+      "step": 357
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0829825723395803e-06,
+      "loss": 0.4211,
+      "step": 358
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0390693429435626e-06,
+      "loss": 0.4245,
+      "step": 359
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9955713382522113e-06,
+      "loss": 0.4058,
+      "step": 360
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9524908270261655e-06,
+      "loss": 0.4089,
+      "step": 361
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.407,
+      "step": 362
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8675912510176476e-06,
+      "loss": 0.4289,
+      "step": 363
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8257766144110823e-06,
+      "loss": 0.4162,
+      "step": 364
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.784388327390687e-06,
+      "loss": 0.4221,
+      "step": 365
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.743428548678847e-06,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7028994146478983e-06,
+      "loss": 0.4192,
+      "step": 367
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6628030392087001e-06,
+      "loss": 0.4234,
+      "step": 368
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6231415137003536e-06,
+      "loss": 0.4095,
+      "step": 369
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5839169067811555e-06,
+      "loss": 0.4109,
+      "step": 370
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5451312643206828e-06,
+      "loss": 0.4117,
+      "step": 371
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.506786609293084e-06,
+      "loss": 0.4039,
+      "step": 372
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4688849416715734e-06,
+      "loss": 0.4206,
+      "step": 373
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4314282383241097e-06,
+      "loss": 0.4147,
+      "step": 374
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3944184529102878e-06,
+      "loss": 0.42,
+      "step": 375
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3578575157794504e-06,
+      "loss": 0.4269,
+      "step": 376
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.321747333869986e-06,
+      "loss": 0.4064,
+      "step": 377
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2860897906098869e-06,
+      "loss": 0.4084,
+      "step": 378
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2508867458185037e-06,
+      "loss": 0.4075,
+      "step": 379
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2161400356095376e-06,
+      "loss": 0.4285,
+      "step": 380
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1818514722952812e-06,
+      "loss": 0.4316,
+      "step": 381
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1480228442920848e-06,
+      "loss": 0.4089,
+      "step": 382
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1146559160270875e-06,
+      "loss": 0.4182,
+      "step": 383
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0817524278461777e-06,
+      "loss": 0.4172,
+      "step": 384
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0493140959232206e-06,
+      "loss": 0.4061,
+      "step": 385
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0173426121705577e-06,
+      "loss": 0.4179,
+      "step": 386
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.858396441507445e-07,
+      "loss": 0.4204,
+      "step": 387
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.548068349895845e-07,
+      "loss": 0.4166,
+      "step": 388
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.242458032904311e-07,
+      "loss": 0.4083,
+      "step": 389
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.941581430497481e-07,
+      "loss": 0.4125,
+      "step": 390
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.423,
+      "step": 391
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.354091893977401e-07,
+      "loss": 0.4085,
+      "step": 392
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.067509602031465e-07,
+      "loss": 0.4135,
+      "step": 393
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.785722307406685e-07,
+      "loss": 0.4206,
+      "step": 394
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.508744707511118e-07,
+      "loss": 0.4137,
+      "step": 395
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.236591248889624e-07,
+      "loss": 0.4133,
+      "step": 396
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.969276126470493e-07,
+      "loss": 0.4289,
+      "step": 397
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.70681328282492e-07,
+      "loss": 0.4245,
+      "step": 398
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.449216407439906e-07,
+      "loss": 0.4254,
+      "step": 399
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.196498936004236e-07,
+      "loss": 0.4163,
+      "step": 400
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.948674049707604e-07,
+      "loss": 0.4277,
+      "step": 401
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.705754674553243e-07,
+      "loss": 0.4084,
+      "step": 402
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.467753480683658e-07,
+      "loss": 0.4086,
+      "step": 403
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.234682881719766e-07,
+      "loss": 0.4164,
+      "step": 404
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.006555034113459e-07,
+      "loss": 0.4242,
+      "step": 405
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.783381836513557e-07,
+      "loss": 0.4207,
+      "step": 406
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.5651749291451884e-07,
+      "loss": 0.4053,
+      "step": 407
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.351945693202686e-07,
+      "loss": 0.4011,
+      "step": 408
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1437052502558693e-07,
+      "loss": 0.406,
+      "step": 409
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.940464461670135e-07,
+      "loss": 0.4055,
+      "step": 410
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.742233928039796e-07,
+      "loss": 0.4123,
+      "step": 411
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.5490239886352584e-07,
+      "loss": 0.421,
+      "step": 412
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.360844720863765e-07,
+      "loss": 0.4208,
+      "step": 413
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1777059397436693e-07,
+      "loss": 0.4021,
+      "step": 414
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.9996171973926567e-07,
+      "loss": 0.4165,
+      "step": 415
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.826587782529444e-07,
+      "loss": 0.4181,
+      "step": 416
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.658626719989266e-07,
+      "loss": 0.4139,
+      "step": 417
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.4957427702532177e-07,
+      "loss": 0.4287,
+      "step": 418
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.3379444289913344e-07,
+      "loss": 0.4059,
+      "step": 419
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.4077,
+      "step": 420
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.037637227869871e-07,
+      "loss": 0.422,
+      "step": 421
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8951440313760838e-07,
+      "loss": 0.4134,
+      "step": 422
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7577677692710682e-07,
+      "loss": 0.4232,
+      "step": 423
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6255156067997325e-07,
+      "loss": 0.3997,
+      "step": 424
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.4983944419451613e-07,
+      "loss": 0.4099,
+      "step": 425
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.37641090506887e-07,
+      "loss": 0.4217,
+      "step": 426
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2595713585649482e-07,
+      "loss": 0.4144,
+      "step": 427
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1478818965281912e-07,
+      "loss": 0.4142,
+      "step": 428
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.041348344436277e-07,
+      "loss": 0.416,
+      "step": 429
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.399762588459205e-08,
+      "loss": 0.4084,
+      "step": 430
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.437709271030603e-08,
+      "loss": 0.4072,
+      "step": 431
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.52737367067069e-08,
+      "loss": 0.4159,
+      "step": 432
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.668803268490066e-08,
+      "loss": 0.4043,
+      "step": 433
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.862042845640403e-08,
+      "loss": 0.4046,
+      "step": 434
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.1071344809781045e-08,
+      "loss": 0.4229,
+      "step": 435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.404117548869824e-08,
+      "loss": 0.4237,
+      "step": 436
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.753028717138785e-08,
+      "loss": 0.4022,
+      "step": 437
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.1539019451521935e-08,
+      "loss": 0.4169,
+      "step": 438
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.606768482050215e-08,
+      "loss": 0.4075,
+      "step": 439
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.1116568651156076e-08,
+      "loss": 0.4125,
+      "step": 440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.6685929182860274e-08,
+      "loss": 0.4117,
+      "step": 441
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2775997508061023e-08,
+      "loss": 0.4217,
+      "step": 442
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.38697756023288e-09,
+      "loss": 0.4083,
+      "step": 443
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.5190461032305085e-09,
+      "loss": 0.4089,
+      "step": 444
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.172352722077167e-09,
+      "loss": 0.4124,
+      "step": 445
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.347019815158724e-09,
+      "loss": 0.4066,
+      "step": 446
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0431425878421053e-09,
+      "loss": 0.4044,
+      "step": 447
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.607890475070374e-10,
+      "loss": 0.4174,
+      "step": 448
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.4229,
+      "step": 449
+    },
+    {
+      "epoch": 1.0,
+      "step": 449,
+      "total_flos": 9646744103026688.0,
+      "train_loss": 0.4881489513844318,
+      "train_runtime": 23304.0276,
+      "train_samples_per_second": 9.879,
+      "train_steps_per_second": 0.019
+    }
+  ],
+  "max_steps": 449,
+  "num_train_epochs": 1,
+  "total_flos": 9646744103026688.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dcd52aa07b03e2db1b0b39cafb9d6c3bb9f389fc0dd06dd8702eb4055c89e99
+size 5947