[Major] Add OSS 13B weights

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "./checkpoints/llama-2-13b-mmc4-coyo-paper_reproduce",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 4096,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c39706afa558b02716192f67c8cb1b6c4dd7120746d3079cd9284e746ba894
+size 4978265800

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7e5c84d83d5fcab2f7cf90f56628918a58aa7ab4a8650db88554cc63910a9b
+size 4970422232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9225e367da8020968b294dfb1f7877adf5932edceda750331db465d9f951ad63
+size 4970422256

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f5772ff5396c4d57c174e35f51ba7a07577534e016f0e8fa3242f049b7e720
+size 4933701504

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504797954690d8763df1502b08af5c3b2068fa1d529c77218977e2b26d40d22f
+size 4933722216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e3d9c4e4a16a76d4c9e9408badd0d342db5e737654f4ac2e018355e264450a
+size 1915248664

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,3150 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.25e-06,
+      "loss": 2.1094,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.25e-05,
+      "loss": 2.1719,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.8203,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5e-05,
+      "loss": 1.1953,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.125e-05,
+      "loss": 1.0938,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.125,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.375e-05,
+      "loss": 1.0625,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-05,
+      "loss": 1.0859,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.6250000000000005e-05,
+      "loss": 1.0156,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.25e-05,
+      "loss": 1.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.875e-05,
+      "loss": 0.9844,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.9805,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 0.9727,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.75e-05,
+      "loss": 0.9648,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.375e-05,
+      "loss": 0.9258,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001,
+      "loss": 0.9531,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.999902864657691e-05,
+      "loss": 0.9453,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.999611462404875e-05,
+      "loss": 0.957,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.999125804563732e-05,
+      "loss": 0.9375,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.998445910004082e-05,
+      "loss": 0.9102,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.997571805142639e-05,
+      "loss": 0.9375,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.996503523941994e-05,
+      "loss": 0.918,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.99524110790929e-05,
+      "loss": 0.8906,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.993784606094612e-05,
+      "loss": 0.9102,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.992134075089084e-05,
+      "loss": 0.8984,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.99028957902266e-05,
+      "loss": 0.8945,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.988251189561645e-05,
+      "loss": 0.9219,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.986018985905901e-05,
+      "loss": 0.8789,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.983593054785776e-05,
+      "loss": 0.8984,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.980973490458728e-05,
+      "loss": 0.8945,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.978160394705668e-05,
+      "loss": 0.8789,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.975153876827008e-05,
+      "loss": 0.9062,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.971954053638399e-05,
+      "loss": 0.875,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.968561049466214e-05,
+      "loss": 0.8594,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.964974996142698e-05,
+      "loss": 0.8672,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.961196033000861e-05,
+      "loss": 0.8711,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.957224306869053e-05,
+      "loss": 0.8828,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.953059972065265e-05,
+      "loss": 0.8594,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.948703190391131e-05,
+      "loss": 0.8672,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.944154131125642e-05,
+      "loss": 0.8789,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.939412971018574e-05,
+      "loss": 0.875,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.934479894283606e-05,
+      "loss": 0.8672,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.92935509259118e-05,
+      "loss": 0.8594,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.8711,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.918531118254507e-05,
+      "loss": 0.8672,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.912832366166442e-05,
+      "loss": 0.8516,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.906942730216939e-05,
+      "loss": 0.8477,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.900862439242719e-05,
+      "loss": 0.8555,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.894591729488242e-05,
+      "loss": 0.875,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.888130844596524e-05,
+      "loss": 0.8438,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.881480035599667e-05,
+      "loss": 0.8516,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.874639560909117e-05,
+      "loss": 0.8789,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.867609686305617e-05,
+      "loss": 0.8711,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.860390684928873e-05,
+      "loss": 0.8594,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.852982837266955e-05,
+      "loss": 0.8555,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.84538643114539e-05,
+      "loss": 0.8633,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.837601761715983e-05,
+      "loss": 0.8438,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.829629131445342e-05,
+      "loss": 0.8438,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.82146885010314e-05,
+      "loss": 0.8555,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.81312123475006e-05,
+      "loss": 0.8477,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.804586609725499e-05,
+      "loss": 0.875,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.79586530663494e-05,
+      "loss": 0.8555,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.78695766433709e-05,
+      "loss": 0.8438,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.777864028930705e-05,
+      "loss": 0.8594,
+      "step": 64
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.768584753741134e-05,
+      "loss": 0.8203,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.759120199306613e-05,
+      "loss": 0.8281,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.74947073336423e-05,
+      "loss": 0.8438,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.73963673083566e-05,
+      "loss": 0.8594,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.72961857381258e-05,
+      "loss": 0.8555,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.719416651541839e-05,
+      "loss": 0.8242,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.709031360410318e-05,
+      "loss": 0.8555,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 0.8359,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.687712292719997e-05,
+      "loss": 0.8438,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.67677934449517e-05,
+      "loss": 0.8594,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.665664684045333e-05,
+      "loss": 0.8516,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.654368743221022e-05,
+      "loss": 0.8242,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.642891960916268e-05,
+      "loss": 0.8281,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.631234783051544e-05,
+      "loss": 0.832,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.8398,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.607381059352038e-05,
+      "loss": 0.8359,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.595185440333103e-05,
+      "loss": 0.8086,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.582811279349882e-05,
+      "loss": 0.8281,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.570259057189717e-05,
+      "loss": 0.8125,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.557529261558367e-05,
+      "loss": 0.8359,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.544622387061055e-05,
+      "loss": 0.8398,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.8516,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.518279414271183e-05,
+      "loss": 0.8555,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.504844339512095e-05,
+      "loss": 0.8438,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.491234232914221e-05,
+      "loss": 0.8203,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.477449623286505e-05,
+      "loss": 0.8242,
+      "step": 90
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.463491046218058e-05,
+      "loss": 0.8164,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.449359044057345e-05,
+      "loss": 0.8164,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.435054165891109e-05,
+      "loss": 0.8164,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.420576967523049e-05,
+      "loss": 0.8359,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.405928011452211e-05,
+      "loss": 0.8398,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.391107866851143e-05,
+      "loss": 0.8164,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.376117109543769e-05,
+      "loss": 0.8516,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.360956321983028e-05,
+      "loss": 0.8281,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.345626093228233e-05,
+      "loss": 0.8164,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.8555,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.314459701268065e-05,
+      "loss": 0.8125,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.298624749005951e-05,
+      "loss": 0.8242,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.282622777389258e-05,
+      "loss": 0.8281,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.266454408160779e-05,
+      "loss": 0.832,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.250120269528546e-05,
+      "loss": 0.8242,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.233620996141421e-05,
+      "loss": 0.8438,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.21695722906443e-05,
+      "loss": 0.8281,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.200129615753859e-05,
+      "loss": 0.8203,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.183138810032099e-05,
+      "loss": 0.8398,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.165985472062246e-05,
+      "loss": 0.8359,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.148670268322438e-05,
+      "loss": 0.8281,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.131193871579975e-05,
+      "loss": 0.8125,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.113556960865167e-05,
+      "loss": 0.8359,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.09576022144496e-05,
+      "loss": 0.8281,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.077804344796302e-05,
+      "loss": 0.8047,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.059690028579284e-05,
+      "loss": 0.8125,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.041417976610027e-05,
+      "loss": 0.8203,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.022988898833342e-05,
+      "loss": 0.832,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.004403511295141e-05,
+      "loss": 0.8242,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.985662536114613e-05,
+      "loss": 0.8203,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.966766701456177e-05,
+      "loss": 0.8164,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.947716741501177e-05,
+      "loss": 0.8242,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.928513396419368e-05,
+      "loss": 0.8008,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.90915741234015e-05,
+      "loss": 0.8125,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.889649541323574e-05,
+      "loss": 0.832,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.869990541331138e-05,
+      "loss": 0.8047,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.850181176196315e-05,
+      "loss": 0.8086,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.8164,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.810114435015054e-05,
+      "loss": 0.8047,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.789858615727265e-05,
+      "loss": 0.8047,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.7694555447539e-05,
+      "loss": 0.8359,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.748906014838672e-05,
+      "loss": 0.832,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.728210824415827e-05,
+      "loss": 0.8086,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.707370777579133e-05,
+      "loss": 0.8008,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.68638668405062e-05,
+      "loss": 0.8164,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.665259359149132e-05,
+      "loss": 0.8125,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.643989623758643e-05,
+      "loss": 0.8281,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.622578304296364e-05,
+      "loss": 0.8125,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.601026232680634e-05,
+      "loss": 0.8047,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.579334246298593e-05,
+      "loss": 0.8008,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.557503187973651e-05,
+      "loss": 0.8164,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8164,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.513427253773346e-05,
+      "loss": 0.8047,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.491184090430364e-05,
+      "loss": 0.8008,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.468805280142709e-05,
+      "loss": 0.7969,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.446291692419736e-05,
+      "loss": 0.8086,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.423644202007467e-05,
+      "loss": 0.7969,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.400863688854597e-05,
+      "loss": 0.8281,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.377951038078302e-05,
+      "loss": 0.8203,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.354907139929851e-05,
+      "loss": 0.8164,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.33173288976002e-05,
+      "loss": 0.8203,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.308429187984297e-05,
+      "loss": 0.8125,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.284996940047903e-05,
+      "loss": 0.8242,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.261437056390606e-05,
+      "loss": 0.8125,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.237750452411353e-05,
+      "loss": 0.8164,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.8164,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.190000769665044e-05,
+      "loss": 0.8203,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.1659395461707e-05,
+      "loss": 0.7969,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.141755312827736e-05,
+      "loss": 0.8125,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 0.8086,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.093021579968941e-05,
+      "loss": 0.8047,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.068473973960238e-05,
+      "loss": 0.8047,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.793,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.019022051627388e-05,
+      "loss": 0.8359,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.994119656715002e-05,
+      "loss": 0.7891,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.969100927867507e-05,
+      "loss": 0.8047,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.943966837166023e-05,
+      "loss": 0.8008,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.91871836117395e-05,
+      "loss": 0.8125,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.89335648089903e-05,
+      "loss": 0.793,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.86788218175523e-05,
+      "loss": 0.8125,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.842296453524463e-05,
+      "loss": 0.8047,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.81660029031811e-05,
+      "loss": 0.7969,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.79079469053842e-05,
+      "loss": 0.7969,
+      "step": 173
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.764880656839696e-05,
+      "loss": 0.8203,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.738859196089358e-05,
+      "loss": 0.8008,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.712731319328798e-05,
+      "loss": 0.8203,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.7891,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.660160382576683e-05,
+      "loss": 0.8008,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.633719365183504e-05,
+      "loss": 0.8125,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.60717601689749e-05,
+      "loss": 0.793,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.580531369037533e-05,
+      "loss": 0.7969,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.553786456858429e-05,
+      "loss": 0.7969,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.526942319510655e-05,
+      "loss": 0.8008,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.8008,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.472960545147038e-05,
+      "loss": 0.8008,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.445825005546448e-05,
+      "loss": 0.8125,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.4185944355262e-05,
+      "loss": 0.8203,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.391269893106592e-05,
+      "loss": 0.8164,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.363852439959135e-05,
+      "loss": 0.8203,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.33634314136531e-05,
+      "loss": 0.8164,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.7969,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.281053286765815e-05,
+      "loss": 0.7852,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.253274878999727e-05,
+      "loss": 0.8164,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.225408922182961e-05,
+      "loss": 0.8203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.197456499023225e-05,
+      "loss": 0.7891,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.169418695587791e-05,
+      "loss": 0.8125,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.141296601261314e-05,
+      "loss": 0.8008,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.7891,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.084803913806641e-05,
+      "loss": 0.8086,
+      "step": 199
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.056435515653059e-05,
+      "loss": 0.8125,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.027987216472377e-05,
+      "loss": 0.8125,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.999460121598704e-05,
+      "loss": 0.7852,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.970855339427698e-05,
+      "loss": 0.7891,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.942173981373474e-05,
+      "loss": 0.8125,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.8125,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.884585998105026e-05,
+      "loss": 0.8047,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.855681610422189e-05,
+      "loss": 0.8008,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.826705121831976e-05,
+      "loss": 0.8047,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.797657658190839e-05,
+      "loss": 0.8164,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.768540348112907e-05,
+      "loss": 0.8047,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.739354322926136e-05,
+      "loss": 0.8164,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.7969,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.680780665843155e-05,
+      "loss": 0.7969,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.651395309775837e-05,
+      "loss": 0.793,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.621945790169036e-05,
+      "loss": 0.8047,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.592433251258423e-05,
+      "loss": 0.7969,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.562858839728223e-05,
+      "loss": 0.7969,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.533223704666672e-05,
+      "loss": 0.7773,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.8086,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.473775872054521e-05,
+      "loss": 0.8086,
+      "step": 220
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.44396548429815e-05,
+      "loss": 0.793,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.414098992509138e-05,
+      "loss": 0.7852,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.384177557124247e-05,
+      "loss": 0.7969,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.354202340715026e-05,
+      "loss": 0.8164,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.324174507942637e-05,
+      "loss": 0.7695,
+      "step": 225
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.7852,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.263965662129487e-05,
+      "loss": 0.7891,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.233786988451468e-05,
+      "loss": 0.8008,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.203560377044866e-05,
+      "loss": 0.793,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.173287002338577e-05,
+      "loss": 0.793,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.142968040578449e-05,
+      "loss": 0.7969,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.112604669781572e-05,
+      "loss": 0.8047,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.7812,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.0517494217274794e-05,
+      "loss": 0.8047,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.021259908948402e-05,
+      "loss": 0.7734,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 5.9907307159969884e-05,
+      "loss": 0.7734,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.960163029058682e-05,
+      "loss": 0.793,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.9295580358145744e-05,
+      "loss": 0.7812,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.898916925395264e-05,
+      "loss": 0.7969,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.7891,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.837531116523682e-05,
+      "loss": 0.7695,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.806788803164034e-05,
+      "loss": 0.7812,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.7760151427217576e-05,
+      "loss": 0.8008,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.745211330880872e-05,
+      "loss": 0.7969,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.714378564496901e-05,
+      "loss": 0.7773,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.683518041550368e-05,
+      "loss": 0.7812,
+      "step": 246
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.7773,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.621718523237427e-05,
+      "loss": 0.7969,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.590781929037965e-05,
+      "loss": 0.7852,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.559822380516539e-05,
+      "loss": 0.8008,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.5288410805796895e-05,
+      "loss": 0.7852,
+      "step": 251
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.497839232979084e-05,
+      "loss": 0.8008,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.466818042264753e-05,
+      "loss": 0.7969,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.793,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.404722453406017e-05,
+      "loss": 0.7812,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.373650467932122e-05,
+      "loss": 0.7773,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.3425639645917834e-05,
+      "loss": 0.793,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.311464151224261e-05,
+      "loss": 0.7734,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.2803522361859594e-05,
+      "loss": 0.7773,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.249229428303486e-05,
+      "loss": 0.7773,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.7812,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.18695597138163e-05,
+      "loss": 0.8047,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.155807741923666e-05,
+      "loss": 0.7852,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.124653458690365e-05,
+      "loss": 0.7617,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.0934943321545115e-05,
+      "loss": 0.7852,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.062331572977076e-05,
+      "loss": 0.7852,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.031166391960168e-05,
+      "loss": 0.7812,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5e-05,
+      "loss": 0.8008,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.968833608039832e-05,
+      "loss": 0.7852,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.9376684270229254e-05,
+      "loss": 0.7773,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.9065056678454904e-05,
+      "loss": 0.7812,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.875346541309637e-05,
+      "loss": 0.793,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.844192258076336e-05,
+      "loss": 0.7812,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.813044028618373e-05,
+      "loss": 0.8008,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.793,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.750770571696514e-05,
+      "loss": 0.7852,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.7196477638140404e-05,
+      "loss": 0.7617,
+      "step": 277
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.68853584877574e-05,
+      "loss": 0.7734,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.657436035408217e-05,
+      "loss": 0.7734,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.626349532067879e-05,
+      "loss": 0.7773,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.595277546593984e-05,
+      "loss": 0.7695,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.7891,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.5331819577352474e-05,
+      "loss": 0.7734,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.502160767020918e-05,
+      "loss": 0.7734,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.471158919420312e-05,
+      "loss": 0.793,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.4401776194834613e-05,
+      "loss": 0.7812,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.409218070962036e-05,
+      "loss": 0.7891,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.378281476762576e-05,
+      "loss": 0.7773,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7734,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.316481958449634e-05,
+      "loss": 0.7812,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.285621435503101e-05,
+      "loss": 0.7734,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.254788669119127e-05,
+      "loss": 0.7812,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.223984857278242e-05,
+      "loss": 0.7812,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.1932111968359664e-05,
+      "loss": 0.7773,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.162468883476319e-05,
+      "loss": 0.7891,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.7773,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.101083074604737e-05,
+      "loss": 0.7773,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.0704419641854274e-05,
+      "loss": 0.8008,
+      "step": 298
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.03983697094132e-05,
+      "loss": 0.7656,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.0092692840030134e-05,
+      "loss": 0.7773,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.978740091051599e-05,
+      "loss": 0.7695,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.9482505782725224e-05,
+      "loss": 0.7578,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.7812,
+      "step": 303
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.887395330218429e-05,
+      "loss": 0.7773,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.857031959421553e-05,
+      "loss": 0.7773,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.8267129976614254e-05,
+      "loss": 0.7734,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.7964396229551364e-05,
+      "loss": 0.7617,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.7662130115485314e-05,
+      "loss": 0.7656,
+      "step": 308
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.7360343378705124e-05,
+      "loss": 0.7852,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7812,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.675825492057364e-05,
+      "loss": 0.7773,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.6457976592849754e-05,
+      "loss": 0.7695,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.6158224428757535e-05,
+      "loss": 0.7578,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.585901007490863e-05,
+      "loss": 0.793,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.556034515701852e-05,
+      "loss": 0.7656,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.5262241279454785e-05,
+      "loss": 0.7617,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.7812,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.4667762953333295e-05,
+      "loss": 0.7539,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.4371411602717784e-05,
+      "loss": 0.7812,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.4075667487415785e-05,
+      "loss": 0.7656,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.3780542098309654e-05,
+      "loss": 0.7578,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.3486046902241664e-05,
+      "loss": 0.7539,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.319219334156847e-05,
+      "loss": 0.7656,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.7695,
+      "step": 324
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.2606456770738636e-05,
+      "loss": 0.7773,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.231459651887093e-05,
+      "loss": 0.793,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.2023423418091626e-05,
+      "loss": 0.7656,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.173294878168025e-05,
+      "loss": 0.7617,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.1443183895778105e-05,
+      "loss": 0.7773,
+      "step": 329
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.115414001894974e-05,
+      "loss": 0.7578,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7656,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.0578260186265265e-05,
+      "loss": 0.7539,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.029144660572304e-05,
+      "loss": 0.7656,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.000539878401296e-05,
+      "loss": 0.7734,
+      "step": 334
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.9720127835276256e-05,
+      "loss": 0.7617,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.9435644843469436e-05,
+      "loss": 0.7734,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.9151960861933614e-05,
+      "loss": 0.7539,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.7852,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.858703398738686e-05,
+      "loss": 0.7852,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.8305813044122097e-05,
+      "loss": 0.7656,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.8025435009767747e-05,
+      "loss": 0.7656,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.774591077817038e-05,
+      "loss": 0.7656,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.746725121000273e-05,
+      "loss": 0.7656,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.718946713234185e-05,
+      "loss": 0.7617,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.7656,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.66365685863469e-05,
+      "loss": 0.7578,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.636147560040866e-05,
+      "loss": 0.7695,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.6087301068934106e-05,
+      "loss": 0.7617,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.581405564473801e-05,
+      "loss": 0.7695,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.5541749944535554e-05,
+      "loss": 0.7617,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.527039454852963e-05,
+      "loss": 0.7812,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7578,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.473057680489348e-05,
+      "loss": 0.7617,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.4462135431415733e-05,
+      "loss": 0.7656,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.4194686309624663e-05,
+      "loss": 0.75,
+      "step": 355
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.39282398310251e-05,
+      "loss": 0.7617,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.366280634816496e-05,
+      "loss": 0.7656,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.3398396174233178e-05,
+      "loss": 0.7695,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.7422,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.2872686806712035e-05,
+      "loss": 0.7695,
+      "step": 360
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.261140803910644e-05,
+      "loss": 0.7695,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.235119343160303e-05,
+      "loss": 0.7539,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.2092053094615813e-05,
+      "loss": 0.7695,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.1833997096818898e-05,
+      "loss": 0.7773,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.157703546475539e-05,
+      "loss": 0.7461,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.75,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.1066435191009715e-05,
+      "loss": 0.7422,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.0812816388260518e-05,
+      "loss": 0.7617,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.056033162833977e-05,
+      "loss": 0.7695,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.0308990721324927e-05,
+      "loss": 0.7617,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.0058803432849987e-05,
+      "loss": 0.7656,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.980977948372612e-05,
+      "loss": 0.7461,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7461,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.931526026039764e-05,
+      "loss": 0.7461,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.906978420031059e-05,
+      "loss": 0.7422,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 0.75,
+      "step": 376
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8582446871722636e-05,
+      "loss": 0.7344,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.8340604538293015e-05,
+      "loss": 0.7461,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.8099992303349577e-05,
+      "loss": 0.7422,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.7617,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7622495475886487e-05,
+      "loss": 0.7539,
+      "step": 381
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.738562943609396e-05,
+      "loss": 0.7539,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7150030599520984e-05,
+      "loss": 0.7617,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.691570812015704e-05,
+      "loss": 0.7422,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6682671102399805e-05,
+      "loss": 0.75,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6450928600701504e-05,
+      "loss": 0.75,
+      "step": 386
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.7617,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.599136311145402e-05,
+      "loss": 0.7695,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.5763557979925324e-05,
+      "loss": 0.7461,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.553708307580265e-05,
+      "loss": 0.7617,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.531194719857292e-05,
+      "loss": 0.793,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.5088159095696363e-05,
+      "loss": 0.7539,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4865727462266543e-05,
+      "loss": 0.7734,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7734,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4424968120263504e-05,
+      "loss": 0.7461,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4206657537014079e-05,
+      "loss": 0.7578,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.398973767319368e-05,
+      "loss": 0.7578,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3774216957036367e-05,
+      "loss": 0.7539,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3560103762413584e-05,
+      "loss": 0.7539,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3347406408508695e-05,
+      "loss": 0.7539,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.7617,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.2926292224208664e-05,
+      "loss": 0.7422,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2717891755841722e-05,
+      "loss": 0.7734,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2510939851613285e-05,
+      "loss": 0.7734,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.230544455246101e-05,
+      "loss": 0.75,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2101413842727345e-05,
+      "loss": 0.7461,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.1898855649849461e-05,
+      "loss": 0.7539,
+      "step": 407
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7305,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.1498188238036861e-05,
+      "loss": 0.7422,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.130009458668863e-05,
+      "loss": 0.75,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.1103504586764263e-05,
+      "loss": 0.7539,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.090842587659851e-05,
+      "loss": 0.7617,
+      "step": 412
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.0714866035806326e-05,
+      "loss": 0.7422,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.0522832584988234e-05,
+      "loss": 0.7617,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7656,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.0143374638853891e-05,
+      "loss": 0.7656,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.955964887048607e-06,
+      "loss": 0.7656,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.770111011666583e-06,
+      "loss": 0.7617,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.58582023389974e-06,
+      "loss": 0.7461,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.403099714207175e-06,
+      "loss": 0.7539,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.221956552036992e-06,
+      "loss": 0.7422,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.7461,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.864430391348332e-06,
+      "loss": 0.7578,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.688061284200266e-06,
+      "loss": 0.7383,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.513297316775625e-06,
+      "loss": 0.7539,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.34014527937756e-06,
+      "loss": 0.75,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.168611899679013e-06,
+      "loss": 0.7383,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 7.998703842461431e-06,
+      "loss": 0.7695,
+      "step": 428
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.7383,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 7.663790038585793e-06,
+      "loss": 0.7578,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 7.498797304714544e-06,
+      "loss": 0.7539,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 7.33545591839222e-06,
+      "loss": 0.7227,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 7.173772226107434e-06,
+      "loss": 0.75,
+      "step": 433
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 7.013752509940485e-06,
+      "loss": 0.7617,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.855402987319348e-06,
+      "loss": 0.7344,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7539,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.54373906771768e-06,
+      "loss": 0.7656,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.390436780169734e-06,
+      "loss": 0.7344,
+      "step": 438
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.238828904562316e-06,
+      "loss": 0.7305,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.088921331488568e-06,
+      "loss": 0.7617,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.94071988547788e-06,
+      "loss": 0.7422,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.794230324769517e-06,
+      "loss": 0.7383,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.7617,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.506409559426573e-06,
+      "loss": 0.7461,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.365089537819434e-06,
+      "loss": 0.75,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.2255037671349535e-06,
+      "loss": 0.7266,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.087657670857798e-06,
+      "loss": 0.7578,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 0.75,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.8172058572881765e-06,
+      "loss": 0.7461,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.7578,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.5537761293894535e-06,
+      "loss": 0.7578,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.424707384416344e-06,
+      "loss": 0.7383,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.29740942810285e-06,
+      "loss": 0.7383,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.1718872065011904e-06,
+      "loss": 0.7422,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.048145596668967e-06,
+      "loss": 0.7305,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.9261894064796135e-06,
+      "loss": 0.7617,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7695,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.687652169484568e-06,
+      "loss": 0.7383,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.5710803908373224e-06,
+      "loss": 0.75,
+      "step": 459
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.4563125677897932e-06,
+      "loss": 0.7578,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.343353159546675e-06,
+      "loss": 0.7383,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.2322065550483007e-06,
+      "loss": 0.7461,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.1228770728000455e-06,
+      "loss": 0.7461,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7539,
+      "step": 464
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.9096863958968268e-06,
+      "loss": 0.7422,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.8058334845816213e-06,
+      "loss": 0.7461,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.7038142618741992e-06,
+      "loss": 0.7617,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.603632691643415e-06,
+      "loss": 0.7422,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.5052926663577e-06,
+      "loss": 0.7656,
+      "step": 469
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.408798006933882e-06,
+      "loss": 0.7461,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.7422,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.221359710692961e-06,
+      "loss": 0.75,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.1304233566290964e-06,
+      "loss": 0.7578,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.041346933650612e-06,
+      "loss": 0.7539,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.9541339027450256e-06,
+      "loss": 0.75,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.8687876524993987e-06,
+      "loss": 0.7656,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.785311498968617e-06,
+      "loss": 0.7578,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7305,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6239823828401945e-06,
+      "loss": 0.7266,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5461356885461075e-06,
+      "loss": 0.7617,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.4701716273304521e-06,
+      "loss": 0.7383,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.3960931507112752e-06,
+      "loss": 0.7617,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.3239031369438326e-06,
+      "loss": 0.75,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 0.7539,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.7578,
+      "step": 485
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.118691554034773e-06,
+      "loss": 0.75,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0540827051175818e-06,
+      "loss": 0.75,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.913756075728087e-07,
+      "loss": 0.7695,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.305726978306173e-07,
+      "loss": 0.75,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.716763383355864e-07,
+      "loss": 0.7656,
+      "step": 490
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.146888174549339e-07,
+      "loss": 0.7773,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.7695,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.064490740882057e-07,
+      "loss": 0.7461,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 6.552010571639456e-07,
+      "loss": 0.7539,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 6.058702898142643e-07,
+      "loss": 0.7656,
+      "step": 495
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.584586887435739e-07,
+      "loss": 0.7539,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.129680960887007e-07,
+      "loss": 0.7461,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.6940027934735954e-07,
+      "loss": 0.7656,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7656,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.8803966999139684e-07,
+      "loss": 0.7734,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.50250038573019e-07,
+      "loss": 0.7461,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.143895053378698e-07,
+      "loss": 0.7539,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.8045946361601183e-07,
+      "loss": 0.7383,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.4846123172992954e-07,
+      "loss": 0.7422,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.1839605294330933e-07,
+      "loss": 0.7578,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.7422,
+      "step": 506
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.640694521422459e-07,
+      "loss": 0.7422,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3981014094099353e-07,
+      "loss": 0.7461,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1748810438355628e-07,
+      "loss": 0.75,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.710420977340762e-08,
+      "loss": 0.7461,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.865924910916977e-08,
+      "loss": 0.7539,
+      "step": 511
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.215393905388278e-08,
+      "loss": 0.7578,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.7422,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.496476058006959e-08,
+      "loss": 0.7422,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.4281948573617874e-08,
+      "loss": 0.7578,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5540899959187727e-08,
+      "loss": 0.7539,
+      "step": 516
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.741954362678772e-09,
+      "loss": 0.7656,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.885375951256931e-09,
+      "loss": 0.75,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.713534230904041e-10,
+      "loss": 0.75,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.7578,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "step": 520,
+      "total_flos": 2.976872756622131e+16,
+      "train_loss": 0.17339993990384617,
+      "train_runtime": 2924.9681,
+      "train_samples_per_second": 728.716,
+      "train_steps_per_second": 0.178
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 520,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "total_flos": 2.976872756622131e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b87ca0b3571ff01ae796139be5d9fe5f3592d4094c477db08bddf3bc2dd38c8
+size 6523