Upload folder using huggingface_hub

PathVQA/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "/data5/yunfei/LLaVA/checkpoints/llava-llama-med-8b-stage2-finetune-ds-no-rag-100k",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "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": 8192,
+  "mm_hidden_size": 3072,
+  "mm_patch_merge_type": "flat",
+  "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_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128256,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "s2": true,
+  "s2_scales": "336,672,1008",
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 4096,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 128257
+}

PathVQA/generation_config.json

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

PathVQA/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f449b336daeacd5f39c88a2c633e41830fae290fbffd4858dac01194cd2140a5
+size 4976706864

PathVQA/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d532408b3745c75d3101ed406ae1fd52dca7e9aa36de0a176b8cefe3834d3db4
+size 4999802720

PathVQA/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc165ce3841c5e3ff1c293ff6493e8aec26021a1929a67bd782b292566ed551
+size 4915916176

PathVQA/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225efbd3230a099af5cc3be5c5d9bc19add8836b1b3666808cf295f02a3e2bc4
+size 1833960344

PathVQA/model.safetensors.index.json

@@ -0,0 +1,693 @@
+{
+  "metadata": {
+    "total_size": 16726290432
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00004-of-00004.safetensors"
+  }
+}

PathVQA/special_tokens_map.json

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

PathVQA/tokenizer_config.json

@@ -0,0 +1,2072 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

PathVQA/trainer_state.json

@@ -0,0 +1,4218 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998209489704566,
+  "eval_steps": 500,
+  "global_step": 698,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 5.8567,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 6.0371,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 6.0126,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 5.7297,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 4.5319,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 3.2653,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.8089,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 2.5048,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 2.3898,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 2.1694,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0476190476190477e-05,
+      "loss": 1.816,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.8469,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.2380952380952383e-05,
+      "loss": 1.7793,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.576,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 1.5517,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.523809523809524e-05,
+      "loss": 1.614,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 1.3789,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 1.401,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8095238095238097e-05,
+      "loss": 1.2179,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 1.309,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 1.248,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.99998923307636e-05,
+      "loss": 1.3434,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999569325372924e-05,
+      "loss": 1.2565,
+      "step": 23
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999903099078353e-05,
+      "loss": 1.4607,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9998277338587826e-05,
+      "loss": 1.2576,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9997308385014843e-05,
+      "loss": 1.2126,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9996124150929886e-05,
+      "loss": 1.1541,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9994724661834065e-05,
+      "loss": 1.0114,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9993109947863768e-05,
+      "loss": 1.1159,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9991280043789992e-05,
+      "loss": 0.9749,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9989234989017622e-05,
+      "loss": 1.0364,
+      "step": 31
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998697482758455e-05,
+      "loss": 1.0704,
+      "step": 32
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9984499608160744e-05,
+      "loss": 0.9538,
+      "step": 33
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998180938404721e-05,
+      "loss": 1.1589,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9978904213174812e-05,
+      "loss": 1.1763,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9975784158103062e-05,
+      "loss": 1.1016,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.997244928601875e-05,
+      "loss": 1.0959,
+      "step": 37
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9968899668734503e-05,
+      "loss": 1.058,
+      "step": 38
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9965135382687235e-05,
+      "loss": 0.9515,
+      "step": 39
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9961156508936505e-05,
+      "loss": 1.1494,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9956963133162776e-05,
+      "loss": 1.1608,
+      "step": 41
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9952555345665563e-05,
+      "loss": 1.0207,
+      "step": 42
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9947933241361482e-05,
+      "loss": 0.8301,
+      "step": 43
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9943096919782227e-05,
+      "loss": 1.0359,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.993804648507241e-05,
+      "loss": 0.9566,
+      "step": 45
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9932782045987317e-05,
+      "loss": 1.0352,
+      "step": 46
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9927303715890573e-05,
+      "loss": 1.0771,
+      "step": 47
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9921611612751707e-05,
+      "loss": 1.0692,
+      "step": 48
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9915705859143597e-05,
+      "loss": 1.0156,
+      "step": 49
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9909586582239835e-05,
+      "loss": 0.8363,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9903253913812003e-05,
+      "loss": 0.9625,
+      "step": 51
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.989670799022681e-05,
+      "loss": 0.9653,
+      "step": 52
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9889948952443174e-05,
+      "loss": 1.0257,
+      "step": 53
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9882976946009188e-05,
+      "loss": 0.9201,
+      "step": 54
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.987579212105897e-05,
+      "loss": 1.0039,
+      "step": 55
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9868394632309443e-05,
+      "loss": 0.9089,
+      "step": 56
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9860784639057e-05,
+      "loss": 0.9722,
+      "step": 57
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.985296230517408e-05,
+      "loss": 0.8276,
+      "step": 58
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9844927799105615e-05,
+      "loss": 0.9444,
+      "step": 59
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9836681293865437e-05,
+      "loss": 0.9135,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9828222967032533e-05,
+      "loss": 0.8918,
+      "step": 61
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.981955300074722e-05,
+      "loss": 0.9801,
+      "step": 62
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9810671581707223e-05,
+      "loss": 0.9516,
+      "step": 63
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9801578901163672e-05,
+      "loss": 1.041,
+      "step": 64
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.979227515491695e-05,
+      "loss": 0.8907,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9782760543312516e-05,
+      "loss": 0.8245,
+      "step": 66
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9773035271236566e-05,
+      "loss": 1.0137,
+      "step": 67
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9763099548111616e-05,
+      "loss": 0.9072,
+      "step": 68
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9752953587892013e-05,
+      "loss": 0.8409,
+      "step": 69
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9742597609059317e-05,
+      "loss": 0.9885,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.973203183461759e-05,
+      "loss": 0.8947,
+      "step": 71
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9721256492088612e-05,
+      "loss": 0.8884,
+      "step": 72
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9710271813506954e-05,
+      "loss": 0.9261,
+      "step": 73
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9699078035415016e-05,
+      "loss": 0.9486,
+      "step": 74
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.96876753988579e-05,
+      "loss": 0.9148,
+      "step": 75
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9676064149378246e-05,
+      "loss": 1.0073,
+      "step": 76
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9664244537010924e-05,
+      "loss": 0.9977,
+      "step": 77
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9652216816277657e-05,
+      "loss": 0.8075,
+      "step": 78
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9639981246181557e-05,
+      "loss": 0.8004,
+      "step": 79
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.962753809020151e-05,
+      "loss": 0.9598,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9614887616286544e-05,
+      "loss": 0.8931,
+      "step": 81
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.960203009685003e-05,
+      "loss": 0.781,
+      "step": 82
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.958896580876383e-05,
+      "loss": 0.8981,
+      "step": 83
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9575695033352325e-05,
+      "loss": 0.8702,
+      "step": 84
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9562218056386366e-05,
+      "loss": 0.8195,
+      "step": 85
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9548535168077124e-05,
+      "loss": 0.9101,
+      "step": 86
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9534646663069816e-05,
+      "loss": 0.9772,
+      "step": 87
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9520552840437396e-05,
+      "loss": 0.9102,
+      "step": 88
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9506254003674084e-05,
+      "loss": 0.8156,
+      "step": 89
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9491750460688845e-05,
+      "loss": 0.7806,
+      "step": 90
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9477042523798762e-05,
+      "loss": 0.8244,
+      "step": 91
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9462130509722307e-05,
+      "loss": 0.7807,
+      "step": 92
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9447014739572503e-05,
+      "loss": 0.8917,
+      "step": 93
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.943169553885004e-05,
+      "loss": 0.8531,
+      "step": 94
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9416173237436252e-05,
+      "loss": 0.9514,
+      "step": 95
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9400448169586004e-05,
+      "loss": 0.8841,
+      "step": 96
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9384520673920502e-05,
+      "loss": 0.8131,
+      "step": 97
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9368391093420004e-05,
+      "loss": 0.8181,
+      "step": 98
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9352059775416442e-05,
+      "loss": 0.8195,
+      "step": 99
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9335527071585918e-05,
+      "loss": 0.8074,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.931879333794115e-05,
+      "loss": 0.8649,
+      "step": 101
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.930185893482381e-05,
+      "loss": 0.8792,
+      "step": 102
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.928472422689674e-05,
+      "loss": 0.8648,
+      "step": 103
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9267389583136124e-05,
+      "loss": 0.8068,
+      "step": 104
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9249855376823542e-05,
+      "loss": 0.8233,
+      "step": 105
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9232121985537907e-05,
+      "loss": 0.8313,
+      "step": 106
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9214189791147363e-05,
+      "loss": 0.7466,
+      "step": 107
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9196059179801038e-05,
+      "loss": 0.8399,
+      "step": 108
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.917773054192076e-05,
+      "loss": 0.9008,
+      "step": 109
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.915920427219261e-05,
+      "loss": 0.7411,
+      "step": 110
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9140480769558448e-05,
+      "loss": 0.7961,
+      "step": 111
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.912156043720733e-05,
+      "loss": 0.8987,
+      "step": 112
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9102443682566792e-05,
+      "loss": 0.7881,
+      "step": 113
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.908313091729412e-05,
+      "loss": 0.8272,
+      "step": 114
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9063622557267443e-05,
+      "loss": 0.7862,
+      "step": 115
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9043919022576817e-05,
+      "loss": 0.8541,
+      "step": 116
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9024020737515135e-05,
+      "loss": 0.8827,
+      "step": 117
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.900392813056904e-05,
+      "loss": 0.8477,
+      "step": 118
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8983641634409657e-05,
+      "loss": 0.8459,
+      "step": 119
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8963161685883294e-05,
+      "loss": 0.8905,
+      "step": 120
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.894248872600204e-05,
+      "loss": 0.7484,
+      "step": 121
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8921623199934255e-05,
+      "loss": 0.8252,
+      "step": 122
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8900565556994986e-05,
+      "loss": 0.8301,
+      "step": 123
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8879316250636305e-05,
+      "loss": 0.8509,
+      "step": 124
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8857875738437526e-05,
+      "loss": 0.8303,
+      "step": 125
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8836244482095366e-05,
+      "loss": 0.869,
+      "step": 126
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8814422947414e-05,
+      "loss": 0.7672,
+      "step": 127
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8792411604295016e-05,
+      "loss": 0.8633,
+      "step": 128
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.877021092672732e-05,
+      "loss": 0.7947,
+      "step": 129
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.874782139277691e-05,
+      "loss": 0.8519,
+      "step": 130
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.872524348457659e-05,
+      "loss": 0.7401,
+      "step": 131
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.870247768831559e-05,
+      "loss": 0.8887,
+      "step": 132
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.867952449422909e-05,
+      "loss": 0.8262,
+      "step": 133
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8656384396587663e-05,
+      "loss": 0.7345,
+      "step": 134
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.863305789368664e-05,
+      "loss": 0.8879,
+      "step": 135
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.860954548783537e-05,
+      "loss": 0.7528,
+      "step": 136
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8585847685346415e-05,
+      "loss": 0.8162,
+      "step": 137
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8561964996524628e-05,
+      "loss": 0.8139,
+      "step": 138
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.853789793565618e-05,
+      "loss": 0.7945,
+      "step": 139
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.85136470209975e-05,
+      "loss": 0.8346,
+      "step": 140
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8489212774764064e-05,
+      "loss": 0.785,
+      "step": 141
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8464595723119206e-05,
+      "loss": 0.7792,
+      "step": 142
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8439796396162756e-05,
+      "loss": 0.7224,
+      "step": 143
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8414815327919633e-05,
+      "loss": 0.827,
+      "step": 144
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8389653056328344e-05,
+      "loss": 0.7432,
+      "step": 145
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8364310123229406e-05,
+      "loss": 0.8724,
+      "step": 146
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.833878707435367e-05,
+      "loss": 0.8208,
+      "step": 147
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8313084459310567e-05,
+      "loss": 0.8187,
+      "step": 148
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8287202831576292e-05,
+      "loss": 0.7933,
+      "step": 149
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.826114274848186e-05,
+      "loss": 0.8285,
+      "step": 150
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8234904771201115e-05,
+      "loss": 0.8506,
+      "step": 151
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8208489464738664e-05,
+      "loss": 0.8432,
+      "step": 152
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8181897397917672e-05,
+      "loss": 0.7251,
+      "step": 153
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8155129143367653e-05,
+      "loss": 0.7721,
+      "step": 154
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8128185277512106e-05,
+      "loss": 0.7181,
+      "step": 155
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8101066380556127e-05,
+      "loss": 0.7582,
+      "step": 156
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.80737730364739e-05,
+      "loss": 0.6928,
+      "step": 157
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8046305832996128e-05,
+      "loss": 0.6841,
+      "step": 158
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8018665361597378e-05,
+      "loss": 0.8184,
+      "step": 159
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.799085221748334e-05,
+      "loss": 0.6881,
+      "step": 160
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7962866999578005e-05,
+      "loss": 0.823,
+      "step": 161
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.793471031051079e-05,
+      "loss": 0.8332,
+      "step": 162
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7906382756603536e-05,
+      "loss": 0.7349,
+      "step": 163
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7877884947857457e-05,
+      "loss": 0.8319,
+      "step": 164
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.784921749794002e-05,
+      "loss": 0.734,
+      "step": 165
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7820381024171713e-05,
+      "loss": 0.8613,
+      "step": 166
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7791376147512754e-05,
+      "loss": 0.8122,
+      "step": 167
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.776220349254973e-05,
+      "loss": 0.7485,
+      "step": 168
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.773286368748214e-05,
+      "loss": 0.7714,
+      "step": 169
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7703357364108862e-05,
+      "loss": 0.8018,
+      "step": 170
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7673685157814556e-05,
+      "loss": 0.7894,
+      "step": 171
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.764384770755599e-05,
+      "loss": 0.7003,
+      "step": 172
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.761384565584825e-05,
+      "loss": 0.7932,
+      "step": 173
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7583679648750945e-05,
+      "loss": 0.7752,
+      "step": 174
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7553350335854253e-05,
+      "loss": 0.7647,
+      "step": 175
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7522858370264976e-05,
+      "loss": 0.8296,
+      "step": 176
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7492204408592447e-05,
+      "loss": 0.7772,
+      "step": 177
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7461389110934382e-05,
+      "loss": 0.7059,
+      "step": 178
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7430413140862705e-05,
+      "loss": 0.7803,
+      "step": 179
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7399277165409222e-05,
+      "loss": 0.743,
+      "step": 180
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7367981855051275e-05,
+      "loss": 0.7164,
+      "step": 181
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7336527883697293e-05,
+      "loss": 0.7179,
+      "step": 182
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.73049159286723e-05,
+      "loss": 0.8069,
+      "step": 183
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7273146670703298e-05,
+      "loss": 0.749,
+      "step": 184
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7241220793904644e-05,
+      "loss": 0.7535,
+      "step": 185
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7209138985763288e-05,
+      "loss": 0.6617,
+      "step": 186
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.717690193712399e-05,
+      "loss": 0.8043,
+      "step": 187
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.714451034217443e-05,
+      "loss": 0.7241,
+      "step": 188
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.711196489843027e-05,
+      "loss": 0.7573,
+      "step": 189
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7079266306720125e-05,
+      "loss": 0.8234,
+      "step": 190
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.704641527117047e-05,
+      "loss": 0.7087,
+      "step": 191
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7013412499190494e-05,
+      "loss": 0.6466,
+      "step": 192
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6980258701456843e-05,
+      "loss": 0.6502,
+      "step": 193
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.694695459189834e-05,
+      "loss": 0.6613,
+      "step": 194
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6913500887680588e-05,
+      "loss": 0.7887,
+      "step": 195
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.687989830919055e-05,
+      "loss": 0.7655,
+      "step": 196
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6846147580021016e-05,
+      "loss": 0.7749,
+      "step": 197
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6812249426955033e-05,
+      "loss": 0.6766,
+      "step": 198
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6778204579950258e-05,
+      "loss": 0.6377,
+      "step": 199
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.674401377212322e-05,
+      "loss": 0.7007,
+      "step": 200
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6709677739733555e-05,
+      "loss": 0.7397,
+      "step": 201
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6675197222168144e-05,
+      "loss": 0.7753,
+      "step": 202
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6640572961925182e-05,
+      "loss": 0.8122,
+      "step": 203
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6605805704598208e-05,
+      "loss": 0.6951,
+      "step": 204
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.657089619886002e-05,
+      "loss": 0.7008,
+      "step": 205
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6535845196446593e-05,
+      "loss": 0.7901,
+      "step": 206
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.650065345214086e-05,
+      "loss": 0.7753,
+      "step": 207
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6465321723756464e-05,
+      "loss": 0.8366,
+      "step": 208
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6429850772121448e-05,
+      "loss": 0.6737,
+      "step": 209
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6394241361061873e-05,
+      "loss": 0.6977,
+      "step": 210
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.635849425738535e-05,
+      "loss": 0.8065,
+      "step": 211
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.632261023086456e-05,
+      "loss": 0.7527,
+      "step": 212
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6286590054220643e-05,
+      "loss": 0.6199,
+      "step": 213
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.625043450310658e-05,
+      "loss": 0.6572,
+      "step": 214
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6214144356090494e-05,
+      "loss": 0.679,
+      "step": 215
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6177720394638865e-05,
+      "loss": 0.7324,
+      "step": 216
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6141163403099716e-05,
+      "loss": 0.7634,
+      "step": 217
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6104474168685724e-05,
+      "loss": 0.7243,
+      "step": 218
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6067653481457254e-05,
+      "loss": 0.7528,
+      "step": 219
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.603070213430536e-05,
+      "loss": 0.7936,
+      "step": 220
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5993620922934716e-05,
+      "loss": 0.782,
+      "step": 221
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.595641064584646e-05,
+      "loss": 0.6669,
+      "step": 222
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.591907210432102e-05,
+      "loss": 0.7199,
+      "step": 223
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.588160610240084e-05,
+      "loss": 0.7384,
+      "step": 224
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5844013446873087e-05,
+      "loss": 0.6975,
+      "step": 225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5806294947252264e-05,
+      "loss": 0.7367,
+      "step": 226
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5768451415762784e-05,
+      "loss": 0.6712,
+      "step": 227
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.573048366732147e-05,
+      "loss": 0.7853,
+      "step": 228
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5692392519520022e-05,
+      "loss": 0.702,
+      "step": 229
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.56541787926074e-05,
+      "loss": 0.7576,
+      "step": 230
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5615843309472162e-05,
+      "loss": 0.6459,
+      "step": 231
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5577386895624743e-05,
+      "loss": 0.6806,
+      "step": 232
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5538810379179694e-05,
+      "loss": 0.7799,
+      "step": 233
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5500114590837823e-05,
+      "loss": 0.6903,
+      "step": 234
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5461300363868326e-05,
+      "loss": 0.6198,
+      "step": 235
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5422368534090844e-05,
+      "loss": 0.6099,
+      "step": 236
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.538331993985745e-05,
+      "loss": 0.7392,
+      "step": 237
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5344155422034608e-05,
+      "loss": 0.6374,
+      "step": 238
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5304875823985067e-05,
+      "loss": 0.7201,
+      "step": 239
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.526548199154969e-05,
+      "loss": 0.651,
+      "step": 240
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5225974773029246e-05,
+      "loss": 0.7595,
+      "step": 241
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5186355019166153e-05,
+      "loss": 0.6956,
+      "step": 242
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5146623583126134e-05,
+      "loss": 0.6793,
+      "step": 243
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5106781320479864e-05,
+      "loss": 0.7099,
+      "step": 244
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5066829089184545e-05,
+      "loss": 0.7128,
+      "step": 245
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5026767749565423e-05,
+      "loss": 0.6939,
+      "step": 246
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.498659816429727e-05,
+      "loss": 0.7006,
+      "step": 247
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4946321198385796e-05,
+      "loss": 0.639,
+      "step": 248
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4905937719149038e-05,
+      "loss": 0.6143,
+      "step": 249
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4865448596198666e-05,
+      "loss": 0.7363,
+      "step": 250
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4824854701421277e-05,
+      "loss": 0.6142,
+      "step": 251
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4784156908959593e-05,
+      "loss": 0.7525,
+      "step": 252
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4743356095193665e-05,
+      "loss": 0.5949,
+      "step": 253
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4702453138721993e-05,
+      "loss": 0.5521,
+      "step": 254
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4661448920342585e-05,
+      "loss": 0.6692,
+      "step": 255
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4620344323034016e-05,
+      "loss": 0.6782,
+      "step": 256
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4579140231936415e-05,
+      "loss": 0.723,
+      "step": 257
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4537837534332386e-05,
+      "loss": 0.6467,
+      "step": 258
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4496437119627907e-05,
+      "loss": 0.6532,
+      "step": 259
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.445493987933319e-05,
+      "loss": 0.8364,
+      "step": 260
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4413346707043467e-05,
+      "loss": 0.6203,
+      "step": 261
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4371658498419758e-05,
+      "loss": 0.6979,
+      "step": 262
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4329876151169581e-05,
+      "loss": 0.6578,
+      "step": 263
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4288000565027625e-05,
+      "loss": 0.6033,
+      "step": 264
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4246032641736362e-05,
+      "loss": 0.7435,
+      "step": 265
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4203973285026642e-05,
+      "loss": 0.6783,
+      "step": 266
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4161823400598234e-05,
+      "loss": 0.6228,
+      "step": 267
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4119583896100309e-05,
+      "loss": 0.6166,
+      "step": 268
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4077255681111905e-05,
+      "loss": 0.6846,
+      "step": 269
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.403483966712234e-05,
+      "loss": 0.7459,
+      "step": 270
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3992336767511585e-05,
+      "loss": 0.7032,
+      "step": 271
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3949747897530583e-05,
+      "loss": 0.6372,
+      "step": 272
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3907073974281562e-05,
+      "loss": 0.609,
+      "step": 273
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3864315916698266e-05,
+      "loss": 0.6418,
+      "step": 274
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3821474645526174e-05,
+      "loss": 0.657,
+      "step": 275
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3778551083302683e-05,
+      "loss": 0.527,
+      "step": 276
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3735546154337218e-05,
+      "loss": 0.6964,
+      "step": 277
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3692460784691357e-05,
+      "loss": 0.746,
+      "step": 278
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3649295902158874e-05,
+      "loss": 0.6308,
+      "step": 279
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.360605243624575e-05,
+      "loss": 0.699,
+      "step": 280
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3562731318150177e-05,
+      "loss": 0.596,
+      "step": 281
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3519333480742502e-05,
+      "loss": 0.7016,
+      "step": 282
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3475859858545121e-05,
+      "loss": 0.5943,
+      "step": 283
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3432311387712378e-05,
+      "loss": 0.6255,
+      "step": 284
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3388689006010394e-05,
+      "loss": 0.6161,
+      "step": 285
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3344993652796872e-05,
+      "loss": 0.659,
+      "step": 286
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.330122626900088e-05,
+      "loss": 0.7248,
+      "step": 287
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.325738779710257e-05,
+      "loss": 0.6769,
+      "step": 288
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3213479181112906e-05,
+      "loss": 0.656,
+      "step": 289
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3169501366553314e-05,
+      "loss": 0.7008,
+      "step": 290
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3125455300435343e-05,
+      "loss": 0.6463,
+      "step": 291
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3081341931240248e-05,
+      "loss": 0.5619,
+      "step": 292
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.303716220889859e-05,
+      "loss": 0.5967,
+      "step": 293
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2992917084769757e-05,
+      "loss": 0.6877,
+      "step": 294
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2948607511621498e-05,
+      "loss": 0.5901,
+      "step": 295
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2904234443609395e-05,
+      "loss": 0.7197,
+      "step": 296
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2859798836256316e-05,
+      "loss": 0.7116,
+      "step": 297
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2815301646431846e-05,
+      "loss": 0.668,
+      "step": 298
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.277074383233167e-05,
+      "loss": 0.7152,
+      "step": 299
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2726126353456955e-05,
+      "loss": 0.5837,
+      "step": 300
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2681450170593683e-05,
+      "loss": 0.6508,
+      "step": 301
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2636716245791945e-05,
+      "loss": 0.622,
+      "step": 302
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2591925542345244e-05,
+      "loss": 0.5665,
+      "step": 303
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2547079024769757e-05,
+      "loss": 0.6986,
+      "step": 304
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2502177658783538e-05,
+      "loss": 0.5567,
+      "step": 305
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2457222411285745e-05,
+      "loss": 0.637,
+      "step": 306
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2412214250335815e-05,
+      "loss": 0.601,
+      "step": 307
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2367154145132609e-05,
+      "loss": 0.7463,
+      "step": 308
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2322043065993556e-05,
+      "loss": 0.6863,
+      "step": 309
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2276881984333738e-05,
+      "loss": 0.6335,
+      "step": 310
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2231671872644995e-05,
+      "loss": 0.6756,
+      "step": 311
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2186413704474964e-05,
+      "loss": 0.6561,
+      "step": 312
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.214110845440613e-05,
+      "loss": 0.5206,
+      "step": 313
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.209575709803483e-05,
+      "loss": 0.5541,
+      "step": 314
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2050360611950245e-05,
+      "loss": 0.7716,
+      "step": 315
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.200491997371337e-05,
+      "loss": 0.565,
+      "step": 316
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1959436161835971e-05,
+      "loss": 0.6736,
+      "step": 317
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.191391015575951e-05,
+      "loss": 0.5984,
+      "step": 318
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1868342935834043e-05,
+      "loss": 0.5351,
+      "step": 319
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.182273548329713e-05,
+      "loss": 0.5762,
+      "step": 320
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1777088780252688e-05,
+      "loss": 0.5658,
+      "step": 321
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1731403809649847e-05,
+      "loss": 0.668,
+      "step": 322
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1685681555261788e-05,
+      "loss": 0.6045,
+      "step": 323
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1639923001664557e-05,
+      "loss": 0.6554,
+      "step": 324
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1594129134215852e-05,
+      "loss": 0.5964,
+      "step": 325
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.154830093903383e-05,
+      "loss": 0.6268,
+      "step": 326
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1502439402975842e-05,
+      "loss": 0.643,
+      "step": 327
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1456545513617199e-05,
+      "loss": 0.674,
+      "step": 328
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.141062025922991e-05,
+      "loss": 0.6062,
+      "step": 329
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1364664628761391e-05,
+      "loss": 0.716,
+      "step": 330
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1318679611813166e-05,
+      "loss": 0.6475,
+      "step": 331
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1272666198619567e-05,
+      "loss": 0.669,
+      "step": 332
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1226625380026407e-05,
+      "loss": 0.586,
+      "step": 333
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1180558147469645e-05,
+      "loss": 0.5703,
+      "step": 334
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1134465492954028e-05,
+      "loss": 0.6057,
+      "step": 335
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1088348409031744e-05,
+      "loss": 0.6938,
+      "step": 336
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1042207888781031e-05,
+      "loss": 0.6842,
+      "step": 337
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0996044925784805e-05,
+      "loss": 0.5665,
+      "step": 338
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0949860514109265e-05,
+      "loss": 0.5285,
+      "step": 339
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0903655648282476e-05,
+      "loss": 0.5631,
+      "step": 340
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.085743132327296e-05,
+      "loss": 0.6012,
+      "step": 341
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0811188534468275e-05,
+      "loss": 0.5105,
+      "step": 342
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0764928277653577e-05,
+      "loss": 0.6936,
+      "step": 343
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0718651548990165e-05,
+      "loss": 0.5982,
+      "step": 344
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.067235934499405e-05,
+      "loss": 0.5279,
+      "step": 345
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0626052662514484e-05,
+      "loss": 0.6138,
+      "step": 346
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.057973249871249e-05,
+      "loss": 0.7268,
+      "step": 347
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.053339985103941e-05,
+      "loss": 0.6102,
+      "step": 348
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0487055717215394e-05,
+      "loss": 0.5865,
+      "step": 349
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0440701095207948e-05,
+      "loss": 0.5869,
+      "step": 350
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.039433698321042e-05,
+      "loss": 0.6136,
+      "step": 351
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.034796437962052e-05,
+      "loss": 0.6175,
+      "step": 352
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0301584283018813e-05,
+      "loss": 0.5578,
+      "step": 353
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.025519769214721e-05,
+      "loss": 0.7355,
+      "step": 354
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.020880560588748e-05,
+      "loss": 0.6317,
+      "step": 355
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0162409023239718e-05,
+      "loss": 0.6411,
+      "step": 356
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0116008943300852e-05,
+      "loss": 0.6395,
+      "step": 357
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0069606365243123e-05,
+      "loss": 0.6126,
+      "step": 358
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0023202288292552e-05,
+      "loss": 0.5297,
+      "step": 359
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.97679771170745e-06,
+      "loss": 0.5626,
+      "step": 360
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.930393634756877e-06,
+      "loss": 0.5696,
+      "step": 361
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.883991056699146e-06,
+      "loss": 0.6071,
+      "step": 362
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.837590976760283e-06,
+      "loss": 0.6008,
+      "step": 363
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.791194394112525e-06,
+      "loss": 0.525,
+      "step": 364
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.744802307852794e-06,
+      "loss": 0.4788,
+      "step": 365
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.69841571698119e-06,
+      "loss": 0.62,
+      "step": 366
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.652035620379481e-06,
+      "loss": 0.5697,
+      "step": 367
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.605663016789583e-06,
+      "loss": 0.6032,
+      "step": 368
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.559298904792054e-06,
+      "loss": 0.4847,
+      "step": 369
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.51294428278461e-06,
+      "loss": 0.6121,
+      "step": 370
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.466600148960597e-06,
+      "loss": 0.5883,
+      "step": 371
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.420267501287512e-06,
+      "loss": 0.5999,
+      "step": 372
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.373947337485521e-06,
+      "loss": 0.6836,
+      "step": 373
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.327640655005951e-06,
+      "loss": 0.5001,
+      "step": 374
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.281348451009837e-06,
+      "loss": 0.5704,
+      "step": 375
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.235071722346424e-06,
+      "loss": 0.5429,
+      "step": 376
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.188811465531725e-06,
+      "loss": 0.5853,
+      "step": 377
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.142568676727043e-06,
+      "loss": 0.4976,
+      "step": 378
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.096344351717528e-06,
+      "loss": 0.5841,
+      "step": 379
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.050139485890738e-06,
+      "loss": 0.5662,
+      "step": 380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.003955074215198e-06,
+      "loss": 0.5292,
+      "step": 381
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.95779211121897e-06,
+      "loss": 0.5485,
+      "step": 382
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.911651590968259e-06,
+      "loss": 0.6976,
+      "step": 383
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.865534507045974e-06,
+      "loss": 0.6143,
+      "step": 384
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.819441852530358e-06,
+      "loss": 0.6539,
+      "step": 385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.773374619973598e-06,
+      "loss": 0.5753,
+      "step": 386
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.72733380138044e-06,
+      "loss": 0.5288,
+      "step": 387
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.68132038818684e-06,
+      "loss": 0.5158,
+      "step": 388
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.63533537123861e-06,
+      "loss": 0.4977,
+      "step": 389
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.589379740770091e-06,
+      "loss": 0.6709,
+      "step": 390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.543454486382803e-06,
+      "loss": 0.5111,
+      "step": 391
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.497560597024161e-06,
+      "loss": 0.6411,
+      "step": 392
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.451699060966174e-06,
+      "loss": 0.651,
+      "step": 393
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.405870865784151e-06,
+      "loss": 0.6071,
+      "step": 394
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.360076998335447e-06,
+      "loss": 0.593,
+      "step": 395
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.314318444738215e-06,
+      "loss": 0.5674,
+      "step": 396
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.268596190350158e-06,
+      "loss": 0.5944,
+      "step": 397
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.222911219747317e-06,
+      "loss": 0.6004,
+      "step": 398
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.177264516702875e-06,
+      "loss": 0.5214,
+      "step": 399
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.131657064165962e-06,
+      "loss": 0.613,
+      "step": 400
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.086089844240495e-06,
+      "loss": 0.6016,
+      "step": 401
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.040563838164034e-06,
+      "loss": 0.4822,
+      "step": 402
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.995080026286632e-06,
+      "loss": 0.5671,
+      "step": 403
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.949639388049758e-06,
+      "loss": 0.6044,
+      "step": 404
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.904242901965171e-06,
+      "loss": 0.6211,
+      "step": 405
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.858891545593871e-06,
+      "loss": 0.5418,
+      "step": 406
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.81358629552504e-06,
+      "loss": 0.576,
+      "step": 407
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.768328127355008e-06,
+      "loss": 0.5502,
+      "step": 408
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.723118015666266e-06,
+      "loss": 0.5358,
+      "step": 409
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.677956934006447e-06,
+      "loss": 0.6183,
+      "step": 410
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.632845854867393e-06,
+      "loss": 0.591,
+      "step": 411
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.5877857496641885e-06,
+      "loss": 0.5402,
+      "step": 412
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.542777588714256e-06,
+      "loss": 0.5547,
+      "step": 413
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.497822341216465e-06,
+      "loss": 0.508,
+      "step": 414
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.452920975230247e-06,
+      "loss": 0.599,
+      "step": 415
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.408074457654757e-06,
+      "loss": 0.47,
+      "step": 416
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.363283754208061e-06,
+      "loss": 0.566,
+      "step": 417
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.318549829406318e-06,
+      "loss": 0.6632,
+      "step": 418
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.273873646543044e-06,
+      "loss": 0.5991,
+      "step": 419
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.2292561676683305e-06,
+      "loss": 0.5955,
+      "step": 420
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.184698353568157e-06,
+      "loss": 0.5297,
+      "step": 421
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.140201163743686e-06,
+      "loss": 0.5336,
+      "step": 422
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.095765556390606e-06,
+      "loss": 0.531,
+      "step": 423
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.051392488378503e-06,
+      "loss": 0.5654,
+      "step": 424
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.007082915230247e-06,
+      "loss": 0.485,
+      "step": 425
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.962837791101414e-06,
+      "loss": 0.5386,
+      "step": 426
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.918658068759754e-06,
+      "loss": 0.5497,
+      "step": 427
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.874544699564662e-06,
+      "loss": 0.5798,
+      "step": 428
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.8304986334466884e-06,
+      "loss": 0.5768,
+      "step": 429
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.786520818887099e-06,
+      "loss": 0.5271,
+      "step": 430
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.742612202897436e-06,
+      "loss": 0.5497,
+      "step": 431
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.698773730999124e-06,
+      "loss": 0.5568,
+      "step": 432
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.655006347203128e-06,
+      "loss": 0.5791,
+      "step": 433
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.611310993989608e-06,
+      "loss": 0.5516,
+      "step": 434
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.567688612287625e-06,
+      "loss": 0.4615,
+      "step": 435
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.524140141454881e-06,
+      "loss": 0.644,
+      "step": 436
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.480666519257501e-06,
+      "loss": 0.5063,
+      "step": 437
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.437268681849824e-06,
+      "loss": 0.6262,
+      "step": 438
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.393947563754253e-06,
+      "loss": 0.6606,
+      "step": 439
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.350704097841129e-06,
+      "loss": 0.5263,
+      "step": 440
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.307539215308644e-06,
+      "loss": 0.5027,
+      "step": 441
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.264453845662785e-06,
+      "loss": 0.5184,
+      "step": 442
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.2214489166973235e-06,
+      "loss": 0.6031,
+      "step": 443
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.17852535447383e-06,
+      "loss": 0.4828,
+      "step": 444
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.135684083301738e-06,
+      "loss": 0.5925,
+      "step": 445
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.092926025718438e-06,
+      "loss": 0.5344,
+      "step": 446
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.050252102469417e-06,
+      "loss": 0.6122,
+      "step": 447
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.007663232488418e-06,
+      "loss": 0.5284,
+      "step": 448
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.9651603328776606e-06,
+      "loss": 0.5838,
+      "step": 449
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.922744318888098e-06,
+      "loss": 0.6277,
+      "step": 450
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.880416103899696e-06,
+      "loss": 0.5112,
+      "step": 451
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.838176599401768e-06,
+      "loss": 0.6094,
+      "step": 452
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.796026714973359e-06,
+      "loss": 0.5793,
+      "step": 453
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.753967358263643e-06,
+      "loss": 0.5859,
+      "step": 454
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.711999434972378e-06,
+      "loss": 0.5951,
+      "step": 455
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.670123848830419e-06,
+      "loss": 0.4739,
+      "step": 456
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.628341501580246e-06,
+      "loss": 0.5585,
+      "step": 457
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.586653292956536e-06,
+      "loss": 0.6364,
+      "step": 458
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.545060120666812e-06,
+      "loss": 0.4729,
+      "step": 459
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5035628803720975e-06,
+      "loss": 0.5906,
+      "step": 460
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.462162465667614e-06,
+      "loss": 0.5259,
+      "step": 461
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.4208597680635866e-06,
+      "loss": 0.5606,
+      "step": 462
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.379655676965984e-06,
+      "loss": 0.5555,
+      "step": 463
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.338551079657419e-06,
+      "loss": 0.4976,
+      "step": 464
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.297546861278013e-06,
+      "loss": 0.5368,
+      "step": 465
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.256643904806335e-06,
+      "loss": 0.5036,
+      "step": 466
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.215843091040409e-06,
+      "loss": 0.5338,
+      "step": 467
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.17514529857873e-06,
+      "loss": 0.4907,
+      "step": 468
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.134551403801336e-06,
+      "loss": 0.5693,
+      "step": 469
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.0940622808509645e-06,
+      "loss": 0.6064,
+      "step": 470
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.053678801614205e-06,
+      "loss": 0.5129,
+      "step": 471
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.013401835702733e-06,
+      "loss": 0.6519,
+      "step": 472
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.973232250434579e-06,
+      "loss": 0.5084,
+      "step": 473
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.933170910815457e-06,
+      "loss": 0.5823,
+      "step": 474
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.893218679520137e-06,
+      "loss": 0.4856,
+      "step": 475
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.853376416873867e-06,
+      "loss": 0.5387,
+      "step": 476
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.813644980833851e-06,
+      "loss": 0.5285,
+      "step": 477
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.774025226970754e-06,
+      "loss": 0.538,
+      "step": 478
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.734518008450312e-06,
+      "loss": 0.5506,
+      "step": 479
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.695124176014938e-06,
+      "loss": 0.4618,
+      "step": 480
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.6558445779653946e-06,
+      "loss": 0.5938,
+      "step": 481
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.616680060142552e-06,
+      "loss": 0.5627,
+      "step": 482
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.57763146590916e-06,
+      "loss": 0.4912,
+      "step": 483
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.538699636131676e-06,
+      "loss": 0.5197,
+      "step": 484
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.49988540916218e-06,
+      "loss": 0.4991,
+      "step": 485
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.461189620820312e-06,
+      "loss": 0.5795,
+      "step": 486
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.422613104375259e-06,
+      "loss": 0.4703,
+      "step": 487
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.384156690527842e-06,
+      "loss": 0.5486,
+      "step": 488
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.345821207392605e-06,
+      "loss": 0.499,
+      "step": 489
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.307607480479977e-06,
+      "loss": 0.5496,
+      "step": 490
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.269516332678529e-06,
+      "loss": 0.5846,
+      "step": 491
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.231548584237219e-06,
+      "loss": 0.5554,
+      "step": 492
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.193705052747737e-06,
+      "loss": 0.5126,
+      "step": 493
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.155986553126914e-06,
+      "loss": 0.523,
+      "step": 494
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.1183938975991644e-06,
+      "loss": 0.4926,
+      "step": 495
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.080927895678984e-06,
+      "loss": 0.4799,
+      "step": 496
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.043589354153541e-06,
+      "loss": 0.502,
+      "step": 497
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.006379077065288e-06,
+      "loss": 0.5447,
+      "step": 498
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.969297865694641e-06,
+      "loss": 0.4702,
+      "step": 499
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.93234651854275e-06,
+      "loss": 0.5145,
+      "step": 500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.895525831314282e-06,
+      "loss": 0.4896,
+      "step": 501
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.858836596900286e-06,
+      "loss": 0.5074,
+      "step": 502
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.822279605361138e-06,
+      "loss": 0.5589,
+      "step": 503
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7858556439095073e-06,
+      "loss": 0.5544,
+      "step": 504
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.74956549689342e-06,
+      "loss": 0.483,
+      "step": 505
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7134099457793625e-06,
+      "loss": 0.5127,
+      "step": 506
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.677389769135444e-06,
+      "loss": 0.6738,
+      "step": 507
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6415057426146504e-06,
+      "loss": 0.506,
+      "step": 508
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6057586389381326e-06,
+      "loss": 0.5462,
+      "step": 509
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5701492278785543e-06,
+      "loss": 0.5466,
+      "step": 510
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5346782762435383e-06,
+      "loss": 0.6327,
+      "step": 511
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.4993465478591447e-06,
+      "loss": 0.4681,
+      "step": 512
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.464154803553408e-06,
+      "loss": 0.5137,
+      "step": 513
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.429103801139981e-06,
+      "loss": 0.5108,
+      "step": 514
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.394194295401796e-06,
+      "loss": 0.5533,
+      "step": 515
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3594270380748205e-06,
+      "loss": 0.4782,
+      "step": 516
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3248027778318593e-06,
+      "loss": 0.5367,
+      "step": 517
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2903222602664464e-06,
+      "loss": 0.53,
+      "step": 518
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.255986227876782e-06,
+      "loss": 0.5079,
+      "step": 519
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.221795420049744e-06,
+      "loss": 0.4688,
+      "step": 520
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1877505730449677e-06,
+      "loss": 0.5587,
+      "step": 521
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1538524199789853e-06,
+      "loss": 0.5302,
+      "step": 522
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1201016908094518e-06,
+      "loss": 0.4613,
+      "step": 523
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.086499112319414e-06,
+      "loss": 0.6063,
+      "step": 524
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0530454081016637e-06,
+      "loss": 0.5349,
+      "step": 525
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0197412985431584e-06,
+      "loss": 0.4467,
+      "step": 526
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.9865875008095114e-06,
+      "loss": 0.5005,
+      "step": 527
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.953584728829533e-06,
+      "loss": 0.4915,
+      "step": 528
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.920733693279879e-06,
+      "loss": 0.4643,
+      "step": 529
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8880351015697337e-06,
+      "loss": 0.573,
+      "step": 530
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.855489657825573e-06,
+      "loss": 0.462,
+      "step": 531
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.823098062876013e-06,
+      "loss": 0.5971,
+      "step": 532
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7908610142367144e-06,
+      "loss": 0.5416,
+      "step": 533
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.758779206095359e-06,
+      "loss": 0.4902,
+      "step": 534
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7268533292967026e-06,
+      "loss": 0.5425,
+      "step": 535
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6950840713277037e-06,
+      "loss": 0.5577,
+      "step": 536
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6634721163027076e-06,
+      "loss": 0.5675,
+      "step": 537
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.632018144948727e-06,
+      "loss": 0.5889,
+      "step": 538
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.600722834590781e-06,
+      "loss": 0.5252,
+      "step": 539
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5695868591372975e-06,
+      "loss": 0.5297,
+      "step": 540
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.538610889065619e-06,
+      "loss": 0.5192,
+      "step": 541
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.507795591407559e-06,
+      "loss": 0.499,
+      "step": 542
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.477141629735025e-06,
+      "loss": 0.4614,
+      "step": 543
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4466496641457483e-06,
+      "loss": 0.5016,
+      "step": 544
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.416320351249062e-06,
+      "loss": 0.4386,
+      "step": 545
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.386154344151752e-06,
+      "loss": 0.5361,
+      "step": 546
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3561522924440127e-06,
+      "loss": 0.5185,
+      "step": 547
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.326314842185443e-06,
+      "loss": 0.5295,
+      "step": 548
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2966426358911387e-06,
+      "loss": 0.5863,
+      "step": 549
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2671363125178635e-06,
+      "loss": 0.5446,
+      "step": 550
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.237796507450272e-06,
+      "loss": 0.5217,
+      "step": 551
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.208623852487248e-06,
+      "loss": 0.4801,
+      "step": 552
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1796189758282917e-06,
+      "loss": 0.5402,
+      "step": 553
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1507825020599827e-06,
+      "loss": 0.419,
+      "step": 554
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.122115052142545e-06,
+      "loss": 0.5494,
+      "step": 555
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0936172433964696e-06,
+      "loss": 0.4936,
+      "step": 556
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.065289689489213e-06,
+      "loss": 0.5906,
+      "step": 557
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.037133000421997e-06,
+      "loss": 0.4602,
+      "step": 558
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0091477825166637e-06,
+      "loss": 0.4716,
+      "step": 559
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9813346384026266e-06,
+      "loss": 0.5926,
+      "step": 560
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9536941670038745e-06,
+      "loss": 0.46,
+      "step": 561
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.926226963526103e-06,
+      "loss": 0.4761,
+      "step": 562
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8989336194438756e-06,
+      "loss": 0.4689,
+      "step": 563
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8718147224878957e-06,
+      "loss": 0.5164,
+      "step": 564
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8448708566323504e-06,
+      "loss": 0.5523,
+      "step": 565
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.818102602082329e-06,
+      "loss": 0.487,
+      "step": 566
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7915105352613382e-06,
+      "loss": 0.4778,
+      "step": 567
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7650952287988864e-06,
+      "loss": 0.5652,
+      "step": 568
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7388572515181445e-06,
+      "loss": 0.5723,
+      "step": 569
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7127971684237098e-06,
+      "loss": 0.4921,
+      "step": 570
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6869155406894344e-06,
+      "loss": 0.4978,
+      "step": 571
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6612129256463338e-06,
+      "loss": 0.532,
+      "step": 572
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6356898767705954e-06,
+      "loss": 0.4466,
+      "step": 573
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.610346943671659e-06,
+      "loss": 0.5068,
+      "step": 574
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.585184672080371e-06,
+      "loss": 0.5097,
+      "step": 575
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5602036038372448e-06,
+      "loss": 0.4844,
+      "step": 576
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5354042768807976e-06,
+      "loss": 0.5384,
+      "step": 577
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.510787225235939e-06,
+      "loss": 0.5508,
+      "step": 578
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4863529790025033e-06,
+      "loss": 0.5572,
+      "step": 579
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.46210206434382e-06,
+      "loss": 0.5417,
+      "step": 580
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4380350034753766e-06,
+      "loss": 0.5127,
+      "step": 581
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4141523146535886e-06,
+      "loss": 0.5064,
+      "step": 582
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3904545121646319e-06,
+      "loss": 0.5853,
+      "step": 583
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3669421063133626e-06,
+      "loss": 0.5566,
+      "step": 584
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3436156034123383e-06,
+      "loss": 0.5032,
+      "step": 585
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.320475505770913e-06,
+      "loss": 0.5101,
+      "step": 586
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2975223116844115e-06,
+      "loss": 0.556,
+      "step": 587
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.274756515423411e-06,
+      "loss": 0.5616,
+      "step": 588
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2521786072230935e-06,
+      "loss": 0.4534,
+      "step": 589
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2297890732726814e-06,
+      "loss": 0.5217,
+      "step": 590
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2075883957049862e-06,
+      "loss": 0.4903,
+      "step": 591
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1855770525860033e-06,
+      "loss": 0.5061,
+      "step": 592
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1637555179046344e-06,
+      "loss": 0.5087,
+      "step": 593
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1421242615624772e-06,
+      "loss": 0.5611,
+      "step": 594
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1206837493636992e-06,
+      "loss": 0.5706,
+      "step": 595
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0994344430050163e-06,
+      "loss": 0.4671,
+      "step": 596
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.078376800065749e-06,
+      "loss": 0.4745,
+      "step": 597
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.057511273997962e-06,
+      "loss": 0.5482,
+      "step": 598
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.036838314116706e-06,
+      "loss": 0.4953,
+      "step": 599
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0163583655903464e-06,
+      "loss": 0.4589,
+      "step": 600
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.960718694309623e-07,
+      "loss": 0.4736,
+      "step": 601
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.759792624848662e-07,
+      "loss": 0.53,
+      "step": 602
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.560809774231872e-07,
+      "loss": 0.5382,
+      "step": 603
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.363774427325578e-07,
+      "loss": 0.5388,
+      "step": 604
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.168690827058813e-07,
+      "loss": 0.4865,
+      "step": 605
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.975563174332091e-07,
+      "loss": 0.4705,
+      "step": 606
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.784395627926734e-07,
+      "loss": 0.5287,
+      "step": 607
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.595192304415534e-07,
+      "loss": 0.5257,
+      "step": 608
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.407957278073952e-07,
+      "loss": 0.5747,
+      "step": 609
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.222694580792434e-07,
+      "loss": 0.51,
+      "step": 610
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.039408201989618e-07,
+      "loss": 0.5299,
+      "step": 611
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.85810208852642e-07,
+      "loss": 0.5341,
+      "step": 612
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.678780144620956e-07,
+      "loss": 0.5411,
+      "step": 613
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.501446231764609e-07,
+      "loss": 0.4272,
+      "step": 614
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.32610416863877e-07,
+      "loss": 0.5023,
+      "step": 615
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.152757731032645e-07,
+      "loss": 0.4607,
+      "step": 616
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.981410651761933e-07,
+      "loss": 0.5416,
+      "step": 617
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.81206662058852e-07,
+      "loss": 0.5301,
+      "step": 618
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.644729284140828e-07,
+      "loss": 0.4581,
+      "step": 619
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.479402245835587e-07,
+      "loss": 0.606,
+      "step": 620
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.316089065799958e-07,
+      "loss": 0.5818,
+      "step": 621
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.154793260795011e-07,
+      "loss": 0.6078,
+      "step": 622
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.995518304139991e-07,
+      "loss": 0.4643,
+      "step": 623
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.838267625637495e-07,
+      "loss": 0.3653,
+      "step": 624
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.6830446114996e-07,
+      "loss": 0.4498,
+      "step": 625
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.529852604274987e-07,
+      "loss": 0.5397,
+      "step": 626
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.37869490277697e-07,
+      "loss": 0.4457,
+      "step": 627
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.229574762012379e-07,
+      "loss": 0.5155,
+      "step": 628
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.082495393111564e-07,
+      "loss": 0.3884,
+      "step": 629
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.937459963259206e-07,
+      "loss": 0.5399,
+      "step": 630
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.794471595626071e-07,
+      "loss": 0.5594,
+      "step": 631
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.653533369301855e-07,
+      "loss": 0.5078,
+      "step": 632
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.514648319228798e-07,
+      "loss": 0.5837,
+      "step": 633
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.3778194361363323e-07,
+      "loss": 0.5007,
+      "step": 634
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.243049666476784e-07,
+      "loss": 0.4823,
+      "step": 635
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.110341912361726e-07,
+      "loss": 0.4576,
+      "step": 636
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.9796990314997176e-07,
+      "loss": 0.4334,
+      "step": 637
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.851123837134585e-07,
+      "loss": 0.5832,
+      "step": 638
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.7246190979849164e-07,
+      "loss": 0.4585,
+      "step": 639
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.600187538184463e-07,
+      "loss": 0.5534,
+      "step": 640
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.477831837223433e-07,
+      "loss": 0.5029,
+      "step": 641
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.3575546298907914e-07,
+      "loss": 0.5229,
+      "step": 642
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.239358506217549e-07,
+      "loss": 0.5767,
+      "step": 643
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1232460114209994e-07,
+      "loss": 0.3828,
+      "step": 644
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.009219645849859e-07,
+      "loss": 0.5912,
+      "step": 645
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.897281864930468e-07,
+      "loss": 0.4827,
+      "step": 646
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7874350791139203e-07,
+      "loss": 0.4718,
+      "step": 647
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6796816538241065e-07,
+      "loss": 0.5658,
+      "step": 648
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.574023909406853e-07,
+      "loss": 0.5658,
+      "step": 649
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.4704641210798853e-07,
+      "loss": 0.5866,
+      "step": 650
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.369004518883855e-07,
+      "loss": 0.472,
+      "step": 651
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.2696472876343467e-07,
+      "loss": 0.5015,
+      "step": 652
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1723945668748248e-07,
+      "loss": 0.4904,
+      "step": 653
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0772484508304937e-07,
+      "loss": 0.5254,
+      "step": 654
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.984210988363311e-07,
+      "loss": 0.3971,
+      "step": 655
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8932841829277794e-07,
+      "loss": 0.5335,
+      "step": 656
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8044699925278242e-07,
+      "loss": 0.4604,
+      "step": 657
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7177703296746838e-07,
+      "loss": 0.5667,
+      "step": 658
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6331870613456423e-07,
+      "loss": 0.4999,
+      "step": 659
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5507220089438724e-07,
+      "loss": 0.484,
+      "step": 660
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4703769482592335e-07,
+      "loss": 0.479,
+      "step": 661
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3921536094299914e-07,
+      "loss": 0.4738,
+      "step": 662
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3160536769055708e-07,
+      "loss": 0.5374,
+      "step": 663
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2420787894103058e-07,
+      "loss": 0.5197,
+      "step": 664
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1702305399081349e-07,
+      "loss": 0.5258,
+      "step": 665
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1005104755682617e-07,
+      "loss": 0.5347,
+      "step": 666
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0329200977319265e-07,
+      "loss": 0.4883,
+      "step": 667
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.674608618799986e-08,
+      "loss": 0.5169,
+      "step": 668
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.041341776016565e-08,
+      "loss": 0.5368,
+      "step": 669
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.429414085640574e-08,
+      "loss": 0.5595,
+      "step": 670
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.83883872482949e-08,
+      "loss": 0.4733,
+      "step": 671
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.269628410942808e-08,
+      "loss": 0.3585,
+      "step": 672
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.721795401268493e-08,
+      "loss": 0.3875,
+      "step": 673
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.195351492759183e-08,
+      "loss": 0.5666,
+      "step": 674
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.69030802177728e-08,
+      "loss": 0.5308,
+      "step": 675
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.206675863851818e-08,
+      "loss": 0.4619,
+      "step": 676
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.744465433443979e-08,
+      "loss": 0.5458,
+      "step": 677
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.303686683722497e-08,
+      "loss": 0.4714,
+      "step": 678
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.884349106349716e-08,
+      "loss": 0.4355,
+      "step": 679
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.486461731276869e-08,
+      "loss": 0.4941,
+      "step": 680
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.110033126549894e-08,
+      "loss": 0.5258,
+      "step": 681
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.755071398125031e-08,
+      "loss": 0.5551,
+      "step": 682
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.4215841896938486e-08,
+      "loss": 0.575,
+      "step": 683
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.1095786825190423e-08,
+      "loss": 0.489,
+      "step": 684
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.8190615952794477e-08,
+      "loss": 0.4864,
+      "step": 685
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5500391839256002e-08,
+      "loss": 0.5031,
+      "step": 686
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3025172415451758e-08,
+      "loss": 0.5158,
+      "step": 687
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0765010982378698e-08,
+      "loss": 0.5214,
+      "step": 688
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.719956210007096e-09,
+      "loss": 0.5405,
+      "step": 689
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.890052136234726e-09,
+      "loss": 0.4096,
+      "step": 690
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.275338165935395e-09,
+      "loss": 0.5636,
+      "step": 691
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.875849070115179e-09,
+      "loss": 0.5095,
+      "step": 692
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.6916149851563542e-09,
+      "loss": 0.4996,
+      "step": 693
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.7226614121756968e-09,
+      "loss": 0.5245,
+      "step": 694
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.690092164715835e-10,
+      "loss": 0.4947,
+      "step": 695
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.3067462707546693e-10,
+      "loss": 0.5609,
+      "step": 696
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0766923640215254e-10,
+      "loss": 0.5161,
+      "step": 697
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.5087,
+      "step": 698
+    },
+    {
+      "epoch": 1.0,
+      "step": 698,
+      "total_flos": 407653124669440.0,
+      "train_loss": 0.714859038890262,
+      "train_runtime": 15566.5988,
+      "train_samples_per_second": 1.435,
+      "train_steps_per_second": 0.045
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 698,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 407653124669440.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

PathVQA/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179e6fef0e44983eb3f99150aa3da2ae374a6eb61d8dad0de439ad4e071e2eb7
+size 6776