Add files using upload-large-folder tool

llava-v1.6-13b-unk-vqa-v1.1/checkpoint-100/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da135efccfbe169c67add697ec23f2a800e37d8ffbf30cc6091fda9b51eb8529
+size 4933722216

llava-v1.6-13b-unk-vqa-v1.1/checkpoint-1000/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e6c108eb2709c5d2e6fea123e5d40624aadca4847f898b06d7a10fce2e4a85
+size 4978276128

llava-v1.6-13b-unk-vqa-v1.1/checkpoint-1000/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92a2cc3877cd2692fc9d91822412dff4c67e71f781fff153900d3e3500af761
+size 4970422232

llava-v1.6-13b-unk-vqa-v1.1/checkpoint-1000/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fc66e0aaeb848019c80e7d019b6c309a95fcda7e88ee535b457fc4b41ba94a
+size 4970422256

llava-v1.6-13b-unk-vqa-v1.1/checkpoint-1000/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e960d7d5f3cf8cfacf6c9e9671cc1a0d542755fc4b12f1ab764abf28bcb802ed
+size 4933701504

llava-v1.6-13b-unk-vqa-v1.1/checkpoint-200/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a852576a11d9705adf6a49d7c348e51d4522b7fdbdc4a99e4b9eefe0230d1e3
+size 1915248664

llava-v1.6-13b-unk-vqa-v1.1/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435c3ba6d58291a44089ae54647c918c8f305a5637656340c49e15fea5e66484
+size 4970422232

llava-v1.6-13b-unk-vqa-v1.1/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2faa848a5e62f541965430d0dbd462cc9fd0b5d42a2967adededc1957bbab87
+size 4933701504

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "../pretrained-models/llava-v1.6-mistral-7b",
+  "architectures": [
+    "LlavaMistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_crop_resolution": 224,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_split_resolution": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llava_mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/latest

@@ -0,0 +1 @@
+global_step500

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15132446720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.image_newline": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00003-of-00004.safetensors"
+  }
+}

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575119a228f98110923ffa2dedcb50e3317251b26054355d015e0b2240d566f2
+size 15984

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728b56dab7abb5ef8a0d4bae3519c5767c97467bdd886d26bf19cc8599d0312
+size 15984

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e481d4ef1546694da7337f6bb6c658b866dcb79b85deeb477da0d27ebe851e
+size 15984

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353c60be37ea56fc992fca446598ceca5d1fd002aa3bd6dbb9ad740e6f47ebb3
+size 15984

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9107fe964ba7205e354084b85210e5a5ea1c98cfd4d38adb9cd3926945dcae4
+size 15984

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d1bb1abee38b92e53f3f23549b642ce0f1edcdccf7b6129847ac61636e96d5
+size 15984

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd5516048e20f36959601574e29e40106085a7d3cdc7bf425ce5e84633490e6
+size 15984

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2c46927fc06939b4c976a01e4b95dec1f8b98ceaea86d31a5d756fc30ff006
+size 15984

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba951e21f6d1a10d2b40709b73d4b5bc264e27d179299a2b00f4a408ac2386be
+size 1064

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/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
+  }
+}

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/trainer_state.json

@@ -0,0 +1,3021 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9615384615384616,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.25e-06,
+      "loss": 3.7473,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.5e-06,
+      "loss": 3.7223,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 2.4038,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 1.1629,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.25e-06,
+      "loss": 0.5964,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.4181,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.4785,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 0.3043,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.125e-05,
+      "loss": 0.3688,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.25e-05,
+      "loss": 0.3231,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.375e-05,
+      "loss": 2.1367,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.2016,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 0.4149,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.0182,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.6984,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.5766,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999805729315383e-05,
+      "loss": 0.3989,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999922292480975e-05,
+      "loss": 0.367,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9998251609127465e-05,
+      "loss": 0.44,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9996891820008165e-05,
+      "loss": 0.3184,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9995143610285275e-05,
+      "loss": 0.3657,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9993007047883988e-05,
+      "loss": 0.3184,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999048221581858e-05,
+      "loss": 0.2976,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9987569212189224e-05,
+      "loss": 0.3187,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998426815017817e-05,
+      "loss": 0.3374,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9980579158045322e-05,
+      "loss": 0.3043,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.997650237912329e-05,
+      "loss": 0.3127,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9972037971811802e-05,
+      "loss": 0.3154,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996718610957155e-05,
+      "loss": 0.296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 0.4204,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9956320789411338e-05,
+      "loss": 0.365,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9950307753654016e-05,
+      "loss": 0.3546,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.99439081072768e-05,
+      "loss": 0.3308,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9937122098932428e-05,
+      "loss": 0.3251,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9929949992285397e-05,
+      "loss": 0.3876,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9922392066001724e-05,
+      "loss": 0.305,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9914448613738107e-05,
+      "loss": 0.2708,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9906119944130527e-05,
+      "loss": 0.3192,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9897406380782262e-05,
+      "loss": 0.3663,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.4343,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9878825942037147e-05,
+      "loss": 0.3598,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9868959788567213e-05,
+      "loss": 0.3101,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.985871018518236e-05,
+      "loss": 0.3289,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.2666,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9837062236509013e-05,
+      "loss": 0.3743,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9825664732332886e-05,
+      "loss": 0.319,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.981388546043388e-05,
+      "loss": 0.3083,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9801724878485438e-05,
+      "loss": 0.2742,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9789183458976485e-05,
+      "loss": 0.2902,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.977626168919305e-05,
+      "loss": 0.3808,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9762960071199334e-05,
+      "loss": 0.3679,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.2926,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9735219372611232e-05,
+      "loss": 0.341,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9720781369857747e-05,
+      "loss": 0.277,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.970596567453391e-05,
+      "loss": 0.3394,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.969077286229078e-05,
+      "loss": 0.3706,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9675203523431964e-05,
+      "loss": 0.3312,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.3441,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.964293770020628e-05,
+      "loss": 0.2805,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.962624246950012e-05,
+      "loss": 0.4209,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9609173219450998e-05,
+      "loss": 0.2951,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9591730613269878e-05,
+      "loss": 0.3099,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.957391532867418e-05,
+      "loss": 0.3366,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 0.3389,
+      "step": 64
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.953716950748227e-05,
+      "loss": 0.3793,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9518240398613226e-05,
+      "loss": 0.309,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9498941466728462e-05,
+      "loss": 0.377,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.947927346167132e-05,
+      "loss": 0.325,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.945923714762516e-05,
+      "loss": 0.3787,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9438833303083677e-05,
+      "loss": 0.2878,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9418062720820636e-05,
+      "loss": 0.3333,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2919,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9375424585439994e-05,
+      "loss": 0.3297,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.935355868899034e-05,
+      "loss": 0.3355,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9331329368090664e-05,
+      "loss": 0.3286,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9308737486442045e-05,
+      "loss": 0.3542,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9285783921832537e-05,
+      "loss": 0.3415,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.926246956610309e-05,
+      "loss": 0.2879,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.3777,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9190370880666206e-05,
+      "loss": 0.3088,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9165622558699763e-05,
+      "loss": 0.3047,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9140518114379433e-05,
+      "loss": 0.3617,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9115058523116734e-05,
+      "loss": 0.3315,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.908924477412211e-05,
+      "loss": 0.3732,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 0.352,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.903655882854237e-05,
+      "loss": 0.3583,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.3372,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.898246846582844e-05,
+      "loss": 0.2925,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.895489924657301e-05,
+      "loss": 0.2697,
+      "step": 90
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8926982092436117e-05,
+      "loss": 0.3653,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8898718088114688e-05,
+      "loss": 0.2705,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.887010833178222e-05,
+      "loss": 0.2846,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8841153935046098e-05,
+      "loss": 0.329,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8811856022904423e-05,
+      "loss": 0.3468,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8782215733702286e-05,
+      "loss": 0.3879,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8752234219087538e-05,
+      "loss": 0.2718,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8721912643966055e-05,
+      "loss": 0.269,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8691252186456465e-05,
+      "loss": 0.3551,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.3023,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.862891940253613e-05,
+      "loss": 0.3975,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8597249498011906e-05,
+      "loss": 0.3149,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8565245554778516e-05,
+      "loss": 0.2837,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8532908816321557e-05,
+      "loss": 0.3284,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8500240539057093e-05,
+      "loss": 0.2755,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 0.3491,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.843391445812886e-05,
+      "loss": 0.3455,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8400259231507716e-05,
+      "loss": 0.3834,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.83662776200642e-05,
+      "loss": 0.317,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.833197094412449e-05,
+      "loss": 0.3171,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8297340536644877e-05,
+      "loss": 0.3372,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 0.307,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8227113921730336e-05,
+      "loss": 0.3899,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 0.3514,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8155608689592604e-05,
+      "loss": 0.2991,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.811938005715857e-05,
+      "loss": 0.2913,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8082835953220055e-05,
+      "loss": 0.2639,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8045977797666685e-05,
+      "loss": 0.3344,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8008807022590283e-05,
+      "loss": 0.3501,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.3369,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7933533402912354e-05,
+      "loss": 0.3157,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7895433483002356e-05,
+      "loss": 0.2841,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.785702679283874e-05,
+      "loss": 0.347,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.3704,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.777929908264715e-05,
+      "loss": 0.356,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7739981082662275e-05,
+      "loss": 0.3221,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7700362352392632e-05,
+      "loss": 0.3251,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.2718,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.762022887003011e-05,
+      "loss": 0.4306,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.757971723145453e-05,
+      "loss": 0.3108,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.75389110895078e-05,
+      "loss": 0.3185,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7497812029677344e-05,
+      "loss": 0.328,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7456421648831658e-05,
+      "loss": 0.3537,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.741474155515827e-05,
+      "loss": 0.3029,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.737277336810124e-05,
+      "loss": 0.398,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.3295,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7287979247517285e-05,
+      "loss": 0.2651,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7245156608592727e-05,
+      "loss": 0.3531,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7202052465361268e-05,
+      "loss": 0.2723,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7158668492597186e-05,
+      "loss": 0.3286,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7115006375947304e-05,
+      "loss": 0.3359,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.2959,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7026854507546694e-05,
+      "loss": 0.3241,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.698236818086073e-05,
+      "loss": 0.3472,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.693761056028542e-05,
+      "loss": 0.3085,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.689258338483947e-05,
+      "loss": 0.2469,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6847288404014937e-05,
+      "loss": 0.3253,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6801727377709195e-05,
+      "loss": 0.4326,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6755902076156606e-05,
+      "loss": 0.2812,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.67098142798597e-05,
+      "loss": 0.2828,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6663465779520042e-05,
+      "loss": 0.3705,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6616858375968596e-05,
+      "loss": 0.3308,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6569993880095807e-05,
+      "loss": 0.3065,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6522874112781213e-05,
+      "loss": 0.2854,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6475500904822707e-05,
+      "loss": 0.3087,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.396,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6380001539330088e-05,
+      "loss": 0.3022,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6331879092341402e-05,
+      "loss": 0.3622,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6283510625655474e-05,
+      "loss": 0.3552,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.3417,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6186043159937884e-05,
+      "loss": 0.3246,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6136947947920477e-05,
+      "loss": 0.3281,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.608761429008721e-05,
+      "loss": 0.3224,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6038044103254775e-05,
+      "loss": 0.2562,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5988239313430004e-05,
+      "loss": 0.2622,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5938201855735017e-05,
+      "loss": 0.3247,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5887933674332048e-05,
+      "loss": 0.3902,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5837436722347902e-05,
+      "loss": 0.3079,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.578671296179806e-05,
+      "loss": 0.2822,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 0.3139,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5684592907048925e-05,
+      "loss": 0.2522,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.563320058063622e-05,
+      "loss": 0.2726,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5581589381076843e-05,
+      "loss": 0.3524,
+      "step": 173
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5529761313679396e-05,
+      "loss": 0.2888,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5477718392178716e-05,
+      "loss": 0.3418,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5425462638657597e-05,
+      "loss": 0.322,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5372996083468242e-05,
+      "loss": 0.279,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5320320765153367e-05,
+      "loss": 0.3396,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.526743873036701e-05,
+      "loss": 0.4238,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5214352033794981e-05,
+      "loss": 0.3893,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5161062738075068e-05,
+      "loss": 0.3877,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5107572913716859e-05,
+      "loss": 0.3096,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.505388463902131e-05,
+      "loss": 0.2542,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.3074,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4945921090294076e-05,
+      "loss": 0.318,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4891650011092896e-05,
+      "loss": 0.3095,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4837188871052399e-05,
+      "loss": 0.347,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4782539786213184e-05,
+      "loss": 0.3056,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4727704879918272e-05,
+      "loss": 0.3651,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4672686282730622e-05,
+      "loss": 0.361,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4617486132350343e-05,
+      "loss": 0.3252,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4562106573531632e-05,
+      "loss": 0.3671,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4506549757999456e-05,
+      "loss": 0.2934,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4450817844365924e-05,
+      "loss": 0.3612,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4394912998046451e-05,
+      "loss": 0.3131,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.3875,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4282593202522627e-05,
+      "loss": 0.2545,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 0.2573,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4169607827613284e-05,
+      "loss": 0.3089,
+      "step": 199
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.3096,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4055974432944753e-05,
+      "loss": 0.3481,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3998920243197408e-05,
+      "loss": 0.3076,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3941710678855396e-05,
+      "loss": 0.3079,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3884347962746949e-05,
+      "loss": 0.3306,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.3745,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3769171996210053e-05,
+      "loss": 0.2773,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.371136322084438e-05,
+      "loss": 0.2897,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3653410243663953e-05,
+      "loss": 0.3391,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3595315316381676e-05,
+      "loss": 0.2885,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3537080696225815e-05,
+      "loss": 0.3336,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3478708645852272e-05,
+      "loss": 0.2904,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.2822,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.336156133168631e-05,
+      "loss": 0.369,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3302790619551673e-05,
+      "loss": 0.3387,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3243891580338074e-05,
+      "loss": 0.3428,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3184866502516846e-05,
+      "loss": 0.3211,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3125717679456447e-05,
+      "loss": 0.2601,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3066447409333345e-05,
+      "loss": 0.3782,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.300705799504273e-05,
+      "loss": 0.2641,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2947551744109044e-05,
+      "loss": 0.3129,
+      "step": 220
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.28879309685963e-05,
+      "loss": 0.3096,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2828197985018276e-05,
+      "loss": 0.3007,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2768355114248493e-05,
+      "loss": 0.3149,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2708404681430054e-05,
+      "loss": 0.3493,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2648349015885272e-05,
+      "loss": 0.3406,
+      "step": 225
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.301,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2527931324258975e-05,
+      "loss": 0.3252,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2467573976902936e-05,
+      "loss": 0.374,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2407120754089733e-05,
+      "loss": 0.2819,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2346574004677154e-05,
+      "loss": 0.2936,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2285936081156897e-05,
+      "loss": 0.3504,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.2735,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2164396139381029e-05,
+      "loss": 0.2653,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.210349884345496e-05,
+      "loss": 0.2795,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2042519817896805e-05,
+      "loss": 0.2784,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1981461431993978e-05,
+      "loss": 0.2865,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1920326058117364e-05,
+      "loss": 0.3273,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1859116071629148e-05,
+      "loss": 0.3055,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1797833850790527e-05,
+      "loss": 0.2781,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.2747,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1675062233047365e-05,
+      "loss": 0.2615,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1613577606328068e-05,
+      "loss": 0.2741,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1552030285443516e-05,
+      "loss": 0.4037,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1490422661761744e-05,
+      "loss": 0.3396,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1428757128993801e-05,
+      "loss": 0.3196,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1367036083100735e-05,
+      "loss": 0.3166,
+      "step": 246
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.130526192220052e-05,
+      "loss": 0.3005,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1243437046474854e-05,
+      "loss": 0.34,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.118156385807593e-05,
+      "loss": 0.2704,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1119644761033079e-05,
+      "loss": 0.3103,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.105768216115938e-05,
+      "loss": 0.2643,
+      "step": 251
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0995678465958168e-05,
+      "loss": 0.2804,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0933636084529507e-05,
+      "loss": 0.3296,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0871557427476585e-05,
+      "loss": 0.2671,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0809444906812034e-05,
+      "loss": 0.3268,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 0.3031,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0685127929183567e-05,
+      "loss": 0.3609,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0622928302448523e-05,
+      "loss": 0.3359,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0560704472371919e-05,
+      "loss": 0.2838,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0498458856606972e-05,
+      "loss": 0.3347,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0436193873653362e-05,
+      "loss": 0.3121,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.037391194276326e-05,
+      "loss": 0.2965,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0311615483847333e-05,
+      "loss": 0.3587,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0249306917380731e-05,
+      "loss": 0.3694,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0186988664309023e-05,
+      "loss": 0.3086,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0124663145954152e-05,
+      "loss": 0.2684,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0062332783920337e-05,
+      "loss": 0.3054,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.3558,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.937667216079665e-06,
+      "loss": 0.3235,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.87533685404585e-06,
+      "loss": 0.3369,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.81301133569098e-06,
+      "loss": 0.3373,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.750693082619274e-06,
+      "loss": 0.2917,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.68838451615267e-06,
+      "loss": 0.2838,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.626088057236745e-06,
+      "loss": 0.3127,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.563806126346643e-06,
+      "loss": 0.3115,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.501541143393028e-06,
+      "loss": 0.3445,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.439295527628083e-06,
+      "loss": 0.3708,
+      "step": 277
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.377071697551479e-06,
+      "loss": 0.2742,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.314872070816435e-06,
+      "loss": 0.3338,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.252,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.190555093187968e-06,
+      "loss": 0.2629,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 0.3567,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.066363915470494e-06,
+      "loss": 0.3941,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.004321534041836e-06,
+      "loss": 0.34,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.942317838840625e-06,
+      "loss": 0.3793,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 0.3451,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.818436141924072e-06,
+      "loss": 0.2892,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.756562953525151e-06,
+      "loss": 0.3142,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.694738077799487e-06,
+      "loss": 0.2782,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.632963916899268e-06,
+      "loss": 0.2284,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.571242871006202e-06,
+      "loss": 0.3189,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.509577338238255e-06,
+      "loss": 0.2888,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.447969714556484e-06,
+      "loss": 0.3124,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.386422393671934e-06,
+      "loss": 0.3607,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.324937766952638e-06,
+      "loss": 0.3074,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.3403,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.202166149209475e-06,
+      "loss": 0.3296,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.140883928370855e-06,
+      "loss": 0.2788,
+      "step": 298
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.079673941882639e-06,
+      "loss": 0.3306,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.018538568006027e-06,
+      "loss": 0.3092,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.957480182103198e-06,
+      "loss": 0.3324,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.896501156545044e-06,
+      "loss": 0.293,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.835603860618973e-06,
+      "loss": 0.408,
+      "step": 303
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.3254,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.714063918843106e-06,
+      "loss": 0.2916,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.653425995322852e-06,
+      "loss": 0.3205,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.592879245910273e-06,
+      "loss": 0.274,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.532426023097063e-06,
+      "loss": 0.2606,
+      "step": 308
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.472068675741024e-06,
+      "loss": 0.3173,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.2818,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.3516509841147276e-06,
+      "loss": 0.3386,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.291595318569951e-06,
+      "loss": 0.3264,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.2316448857515076e-06,
+      "loss": 0.233,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.171802014981726e-06,
+      "loss": 0.2876,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.112069031403704e-06,
+      "loss": 0.2514,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.052448255890958e-06,
+      "loss": 0.3363,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.992942004957271e-06,
+      "loss": 0.3113,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.933552590666659e-06,
+      "loss": 0.2884,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.874282320543557e-06,
+      "loss": 0.3039,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.2625,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.7561084196619306e-06,
+      "loss": 0.3116,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.697209380448333e-06,
+      "loss": 0.3497,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.638438668313695e-06,
+      "loss": 0.319,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.3007,
+      "step": 324
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.521291354147727e-06,
+      "loss": 0.2998,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.462919303774186e-06,
+      "loss": 0.2918,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.404684683618325e-06,
+      "loss": 0.2604,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.34658975633605e-06,
+      "loss": 0.3346,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.288636779155621e-06,
+      "loss": 0.3309,
+      "step": 329
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.230828003789949e-06,
+      "loss": 0.4091,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.301,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.115652037253054e-06,
+      "loss": 0.3056,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.058289321144608e-06,
+      "loss": 0.2798,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.001079756802592e-06,
+      "loss": 0.2976,
+      "step": 334
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.944025567055251e-06,
+      "loss": 0.3189,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.887128968693887e-06,
+      "loss": 0.3335,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.830392172386723e-06,
+      "loss": 0.3092,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.773817382593008e-06,
+      "loss": 0.3579,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.717406797477371e-06,
+      "loss": 0.2755,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.2702,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.6050870019535496e-06,
+      "loss": 0.3047,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.549182155634076e-06,
+      "loss": 0.3235,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.493450242000546e-06,
+      "loss": 0.271,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.43789342646837e-06,
+      "loss": 0.2651,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.382513867649663e-06,
+      "loss": 0.2757,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.32731371726938e-06,
+      "loss": 0.282,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.2722951200817315e-06,
+      "loss": 0.3017,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.217460213786822e-06,
+      "loss": 0.248,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.1628111289476025e-06,
+      "loss": 0.3195,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.108349988907111e-06,
+      "loss": 0.3289,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.054078909705926e-06,
+      "loss": 0.3232,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3053,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.946115360978696e-06,
+      "loss": 0.2811,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.892427086283147e-06,
+      "loss": 0.2756,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.838937261924933e-06,
+      "loss": 0.3213,
+      "step": 355
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.78564796620502e-06,
+      "loss": 0.3865,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.732561269632992e-06,
+      "loss": 0.2899,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.679679234846636e-06,
+      "loss": 0.3323,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.627003916531761e-06,
+      "loss": 0.2954,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.2722,
+      "step": 360
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.522281607821288e-06,
+      "loss": 0.2635,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.470238686320606e-06,
+      "loss": 0.3068,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.418410618923163e-06,
+      "loss": 0.3263,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.3667994193637794e-06,
+      "loss": 0.2904,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.315407092951078e-06,
+      "loss": 0.3106,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.264235636489542e-06,
+      "loss": 0.3729,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.213287038201943e-06,
+      "loss": 0.2611,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.162563277652104e-06,
+      "loss": 0.3506,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.112066325667954e-06,
+      "loss": 0.263,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.061798144264986e-06,
+      "loss": 0.2519,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.0117606865699975e-06,
+      "loss": 0.319,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.961955896745224e-06,
+      "loss": 0.3457,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.912385709912794e-06,
+      "loss": 0.2825,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8630520520795275e-06,
+      "loss": 0.2782,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8139568400621184e-06,
+      "loss": 0.2852,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.2699,
+      "step": 376
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7164893743445274e-06,
+      "loss": 0.2634,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6681209076586035e-06,
+      "loss": 0.2939,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.619998460669916e-06,
+      "loss": 0.3233,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.2729,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5244990951772972e-06,
+      "loss": 0.3827,
+      "step": 381
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.4771258872187917e-06,
+      "loss": 0.3219,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4300061199041967e-06,
+      "loss": 0.2812,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3831416240314085e-06,
+      "loss": 0.2616,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3365342204799613e-06,
+      "loss": 0.3082,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.290185720140301e-06,
+      "loss": 0.2526,
+      "step": 386
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2440979238433977e-06,
+      "loss": 0.3027,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1982726222908046e-06,
+      "loss": 0.2902,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.152711595985065e-06,
+      "loss": 0.283,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.10741661516053e-06,
+      "loss": 0.238,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0623894397145837e-06,
+      "loss": 0.2777,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.017631819139273e-06,
+      "loss": 0.2997,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9731454924533086e-06,
+      "loss": 0.317,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.2685,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.884993624052701e-06,
+      "loss": 0.2233,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8413315074028157e-06,
+      "loss": 0.2934,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7979475346387363e-06,
+      "loss": 0.2844,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7548433914072736e-06,
+      "loss": 0.3373,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.712020752482717e-06,
+      "loss": 0.3245,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.3674,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6272266318987606e-06,
+      "loss": 0.3053,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5852584448417327e-06,
+      "loss": 0.3318,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.5435783511683444e-06,
+      "loss": 0.2434,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.502187970322657e-06,
+      "loss": 0.2829,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.461088910492202e-06,
+      "loss": 0.2951,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.420282768545469e-06,
+      "loss": 0.2691,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3797711299698924e-06,
+      "loss": 0.238,
+      "step": 407
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.437,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2996376476073724e-06,
+      "loss": 0.3255,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2600189173377263e-06,
+      "loss": 0.3383,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2207009173528528e-06,
+      "loss": 0.2849,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.3324,
+      "step": 412
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1429732071612653e-06,
+      "loss": 0.298,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.104566516997647e-06,
+      "loss": 0.2391,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0664665970876496e-06,
+      "loss": 0.2806,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0286749277707783e-06,
+      "loss": 0.3077,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9911929774097216e-06,
+      "loss": 0.3469,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9540222023333165e-06,
+      "loss": 0.3025,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9171640467799478e-06,
+      "loss": 0.3226,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.880619942841435e-06,
+      "loss": 0.2776,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8443913104073984e-06,
+      "loss": 0.2289,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.808479557110081e-06,
+      "loss": 0.2402,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7728860782696666e-06,
+      "loss": 0.3265,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7376122568400533e-06,
+      "loss": 0.2353,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7026594633551252e-06,
+      "loss": 0.2629,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6680290558755119e-06,
+      "loss": 0.3611,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6337223799358025e-06,
+      "loss": 0.3559,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.599740768492286e-06,
+      "loss": 0.3488,
+      "step": 428
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.566085541871145e-06,
+      "loss": 0.3067,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5327580077171589e-06,
+      "loss": 0.3063,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.499759460942909e-06,
+      "loss": 0.2918,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.467091183678444e-06,
+      "loss": 0.2416,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4347544452214869e-06,
+      "loss": 0.2829,
+      "step": 433
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4027505019880972e-06,
+      "loss": 0.278,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3710805974638697e-06,
+      "loss": 0.3117,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.2856,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3087478135435361e-06,
+      "loss": 0.2803,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.278087356033947e-06,
+      "loss": 0.2639,
+      "step": 438
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2477657809124632e-06,
+      "loss": 0.3482,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.308,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.188143977095576e-06,
+      "loss": 0.2487,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1588460649539036e-06,
+      "loss": 0.2937,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.129891668217783e-06,
+      "loss": 0.2821,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1012819118853147e-06,
+      "loss": 0.2694,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.073017907563887e-06,
+      "loss": 0.317,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0451007534269908e-06,
+      "loss": 0.3102,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0175315341715598e-06,
+      "loss": 0.3156,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.2957,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.634411714576353e-07,
+      "loss": 0.2966,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.369221296335007e-07,
+      "loss": 0.3048,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.107552258778907e-07,
+      "loss": 0.3222,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.849414768832687e-07,
+      "loss": 0.2689,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.5948188562057e-07,
+      "loss": 0.2808,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.343774413002382e-07,
+      "loss": 0.2847,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.096291193337935e-07,
+      "loss": 0.3227,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.852378812959227e-07,
+      "loss": 0.3605,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.2973,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.375304338969135e-07,
+      "loss": 0.3464,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.142160781674645e-07,
+      "loss": 0.2984,
+      "step": 459
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.912625135579587e-07,
+      "loss": 0.2863,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.68670631909335e-07,
+      "loss": 0.2629,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.464413110096601e-07,
+      "loss": 0.322,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.245754145600091e-07,
+      "loss": 0.2915,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.3556,
+      "step": 464
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.819372791793654e-07,
+      "loss": 0.2811,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.611666969163243e-07,
+      "loss": 0.3172,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.407628523748398e-07,
+      "loss": 0.2509,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.207265383286831e-07,
+      "loss": 0.3164,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.010585332715401e-07,
+      "loss": 0.3269,
+      "step": 469
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.817596013867765e-07,
+      "loss": 0.2737,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.628304925177318e-07,
+      "loss": 0.2989,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4427194213859216e-07,
+      "loss": 0.2985,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.2608467132581934e-07,
+      "loss": 0.2354,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.082693867301224e-07,
+      "loss": 0.2953,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.908267805490051e-07,
+      "loss": 0.3005,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.7375753049987974e-07,
+      "loss": 0.3116,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.570622997937234e-07,
+      "loss": 0.3119,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.3156,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.247964765680389e-07,
+      "loss": 0.297,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.2563,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.940343254660905e-07,
+      "loss": 0.2928,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7921863014225504e-07,
+      "loss": 0.282,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6478062738876654e-07,
+      "loss": 0.2774,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.3289,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.370399288006664e-07,
+      "loss": 0.2862,
+      "step": 485
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.2373831080695463e-07,
+      "loss": 0.2452,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1081654102351634e-07,
+      "loss": 0.2631,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9827512151456175e-07,
+      "loss": 0.2316,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8611453956612346e-07,
+      "loss": 0.302,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7433526766711727e-07,
+      "loss": 0.2666,
+      "step": 490
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.629377634909868e-07,
+      "loss": 0.2707,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.3028,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4128981481764115e-07,
+      "loss": 0.2957,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3104021143278911e-07,
+      "loss": 0.2482,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2117405796285286e-07,
+      "loss": 0.2428,
+      "step": 495
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1169173774871478e-07,
+      "loss": 0.2928,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0259361921774014e-07,
+      "loss": 0.3246,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.388005586947191e-08,
+      "loss": 0.3169,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.555138626189619e-08,
+      "loss": 0.2443,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.760793399827937e-08,
+      "loss": 0.2289,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 520,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.4945008316094874e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42912442e5d8f9e398ee97dcde794c208655796c7c92721476a3581f306c2c4e
+size 6264

llava-v1.6-mistral-7b-unk-vqa-v1.1/checkpoint-500/zero_to_fp32.py

@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)

llava-v1.6-mistral-7b-unk-vqa-v1.1/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

llava-v1.6-mistral-7b-unk-vqa-v1.1/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3fecd6689807ffc0ab1ce28cf9ca5512f68eae63cfd417ed82ec11dc4527bf4
+size 262144128

llava-v1.6-mistral-7b-unk-vqa-v1.1/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": 1.25e-06,
+      "loss": 3.7473,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.5e-06,
+      "loss": 3.7223,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 2.4038,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 1.1629,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.25e-06,
+      "loss": 0.5964,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.4181,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.4785,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 0.3043,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.125e-05,
+      "loss": 0.3688,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.25e-05,
+      "loss": 0.3231,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.375e-05,
+      "loss": 2.1367,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.2016,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 0.4149,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.0182,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.6984,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.5766,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999805729315383e-05,
+      "loss": 0.3989,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999922292480975e-05,
+      "loss": 0.367,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9998251609127465e-05,
+      "loss": 0.44,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9996891820008165e-05,
+      "loss": 0.3184,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9995143610285275e-05,
+      "loss": 0.3657,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9993007047883988e-05,
+      "loss": 0.3184,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999048221581858e-05,
+      "loss": 0.2976,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9987569212189224e-05,
+      "loss": 0.3187,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998426815017817e-05,
+      "loss": 0.3374,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9980579158045322e-05,
+      "loss": 0.3043,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.997650237912329e-05,
+      "loss": 0.3127,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9972037971811802e-05,
+      "loss": 0.3154,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996718610957155e-05,
+      "loss": 0.296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 0.4204,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9956320789411338e-05,
+      "loss": 0.365,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9950307753654016e-05,
+      "loss": 0.3546,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.99439081072768e-05,
+      "loss": 0.3308,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9937122098932428e-05,
+      "loss": 0.3251,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9929949992285397e-05,
+      "loss": 0.3876,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9922392066001724e-05,
+      "loss": 0.305,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9914448613738107e-05,
+      "loss": 0.2708,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9906119944130527e-05,
+      "loss": 0.3192,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9897406380782262e-05,
+      "loss": 0.3663,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.4343,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9878825942037147e-05,
+      "loss": 0.3598,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9868959788567213e-05,
+      "loss": 0.3101,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.985871018518236e-05,
+      "loss": 0.3289,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.2666,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9837062236509013e-05,
+      "loss": 0.3743,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9825664732332886e-05,
+      "loss": 0.319,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.981388546043388e-05,
+      "loss": 0.3083,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9801724878485438e-05,
+      "loss": 0.2742,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9789183458976485e-05,
+      "loss": 0.2902,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.977626168919305e-05,
+      "loss": 0.3808,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9762960071199334e-05,
+      "loss": 0.3679,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.2926,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9735219372611232e-05,
+      "loss": 0.341,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9720781369857747e-05,
+      "loss": 0.277,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.970596567453391e-05,
+      "loss": 0.3394,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.969077286229078e-05,
+      "loss": 0.3706,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9675203523431964e-05,
+      "loss": 0.3312,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.3441,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.964293770020628e-05,
+      "loss": 0.2805,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.962624246950012e-05,
+      "loss": 0.4209,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9609173219450998e-05,
+      "loss": 0.2951,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9591730613269878e-05,
+      "loss": 0.3099,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.957391532867418e-05,
+      "loss": 0.3366,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 0.3389,
+      "step": 64
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.953716950748227e-05,
+      "loss": 0.3793,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9518240398613226e-05,
+      "loss": 0.309,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9498941466728462e-05,
+      "loss": 0.377,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.947927346167132e-05,
+      "loss": 0.325,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.945923714762516e-05,
+      "loss": 0.3787,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9438833303083677e-05,
+      "loss": 0.2878,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9418062720820636e-05,
+      "loss": 0.3333,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2919,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9375424585439994e-05,
+      "loss": 0.3297,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.935355868899034e-05,
+      "loss": 0.3355,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9331329368090664e-05,
+      "loss": 0.3286,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9308737486442045e-05,
+      "loss": 0.3542,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9285783921832537e-05,
+      "loss": 0.3415,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.926246956610309e-05,
+      "loss": 0.2879,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.3777,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9190370880666206e-05,
+      "loss": 0.3088,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9165622558699763e-05,
+      "loss": 0.3047,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9140518114379433e-05,
+      "loss": 0.3617,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9115058523116734e-05,
+      "loss": 0.3315,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.908924477412211e-05,
+      "loss": 0.3732,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 0.352,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.903655882854237e-05,
+      "loss": 0.3583,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.3372,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.898246846582844e-05,
+      "loss": 0.2925,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.895489924657301e-05,
+      "loss": 0.2697,
+      "step": 90
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8926982092436117e-05,
+      "loss": 0.3653,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8898718088114688e-05,
+      "loss": 0.2705,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.887010833178222e-05,
+      "loss": 0.2846,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8841153935046098e-05,
+      "loss": 0.329,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8811856022904423e-05,
+      "loss": 0.3468,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8782215733702286e-05,
+      "loss": 0.3879,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8752234219087538e-05,
+      "loss": 0.2718,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8721912643966055e-05,
+      "loss": 0.269,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8691252186456465e-05,
+      "loss": 0.3551,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.3023,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.862891940253613e-05,
+      "loss": 0.3975,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8597249498011906e-05,
+      "loss": 0.3149,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8565245554778516e-05,
+      "loss": 0.2837,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8532908816321557e-05,
+      "loss": 0.3284,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8500240539057093e-05,
+      "loss": 0.2755,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 0.3491,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.843391445812886e-05,
+      "loss": 0.3455,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8400259231507716e-05,
+      "loss": 0.3834,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.83662776200642e-05,
+      "loss": 0.317,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.833197094412449e-05,
+      "loss": 0.3171,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8297340536644877e-05,
+      "loss": 0.3372,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 0.307,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8227113921730336e-05,
+      "loss": 0.3899,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 0.3514,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8155608689592604e-05,
+      "loss": 0.2991,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.811938005715857e-05,
+      "loss": 0.2913,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8082835953220055e-05,
+      "loss": 0.2639,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8045977797666685e-05,
+      "loss": 0.3344,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8008807022590283e-05,
+      "loss": 0.3501,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.3369,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7933533402912354e-05,
+      "loss": 0.3157,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7895433483002356e-05,
+      "loss": 0.2841,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.785702679283874e-05,
+      "loss": 0.347,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.3704,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.777929908264715e-05,
+      "loss": 0.356,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7739981082662275e-05,
+      "loss": 0.3221,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7700362352392632e-05,
+      "loss": 0.3251,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.2718,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.762022887003011e-05,
+      "loss": 0.4306,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.757971723145453e-05,
+      "loss": 0.3108,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.75389110895078e-05,
+      "loss": 0.3185,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7497812029677344e-05,
+      "loss": 0.328,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7456421648831658e-05,
+      "loss": 0.3537,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.741474155515827e-05,
+      "loss": 0.3029,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.737277336810124e-05,
+      "loss": 0.398,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.3295,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7287979247517285e-05,
+      "loss": 0.2651,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7245156608592727e-05,
+      "loss": 0.3531,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7202052465361268e-05,
+      "loss": 0.2723,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7158668492597186e-05,
+      "loss": 0.3286,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7115006375947304e-05,
+      "loss": 0.3359,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.2959,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7026854507546694e-05,
+      "loss": 0.3241,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.698236818086073e-05,
+      "loss": 0.3472,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.693761056028542e-05,
+      "loss": 0.3085,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.689258338483947e-05,
+      "loss": 0.2469,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6847288404014937e-05,
+      "loss": 0.3253,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6801727377709195e-05,
+      "loss": 0.4326,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6755902076156606e-05,
+      "loss": 0.2812,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.67098142798597e-05,
+      "loss": 0.2828,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6663465779520042e-05,
+      "loss": 0.3705,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6616858375968596e-05,
+      "loss": 0.3308,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6569993880095807e-05,
+      "loss": 0.3065,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6522874112781213e-05,
+      "loss": 0.2854,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6475500904822707e-05,
+      "loss": 0.3087,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.396,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6380001539330088e-05,
+      "loss": 0.3022,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6331879092341402e-05,
+      "loss": 0.3622,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6283510625655474e-05,
+      "loss": 0.3552,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.3417,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6186043159937884e-05,
+      "loss": 0.3246,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6136947947920477e-05,
+      "loss": 0.3281,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.608761429008721e-05,
+      "loss": 0.3224,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6038044103254775e-05,
+      "loss": 0.2562,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5988239313430004e-05,
+      "loss": 0.2622,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5938201855735017e-05,
+      "loss": 0.3247,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5887933674332048e-05,
+      "loss": 0.3902,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5837436722347902e-05,
+      "loss": 0.3079,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.578671296179806e-05,
+      "loss": 0.2822,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 0.3139,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5684592907048925e-05,
+      "loss": 0.2522,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.563320058063622e-05,
+      "loss": 0.2726,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5581589381076843e-05,
+      "loss": 0.3524,
+      "step": 173
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5529761313679396e-05,
+      "loss": 0.2888,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5477718392178716e-05,
+      "loss": 0.3418,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5425462638657597e-05,
+      "loss": 0.322,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5372996083468242e-05,
+      "loss": 0.279,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5320320765153367e-05,
+      "loss": 0.3396,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.526743873036701e-05,
+      "loss": 0.4238,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5214352033794981e-05,
+      "loss": 0.3893,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5161062738075068e-05,
+      "loss": 0.3877,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5107572913716859e-05,
+      "loss": 0.3096,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.505388463902131e-05,
+      "loss": 0.2542,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.3074,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4945921090294076e-05,
+      "loss": 0.318,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4891650011092896e-05,
+      "loss": 0.3095,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4837188871052399e-05,
+      "loss": 0.347,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4782539786213184e-05,
+      "loss": 0.3056,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4727704879918272e-05,
+      "loss": 0.3651,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4672686282730622e-05,
+      "loss": 0.361,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4617486132350343e-05,
+      "loss": 0.3252,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4562106573531632e-05,
+      "loss": 0.3671,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4506549757999456e-05,
+      "loss": 0.2934,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4450817844365924e-05,
+      "loss": 0.3612,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4394912998046451e-05,
+      "loss": 0.3131,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.3875,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4282593202522627e-05,
+      "loss": 0.2545,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 0.2573,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4169607827613284e-05,
+      "loss": 0.3089,
+      "step": 199
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.3096,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4055974432944753e-05,
+      "loss": 0.3481,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3998920243197408e-05,
+      "loss": 0.3076,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3941710678855396e-05,
+      "loss": 0.3079,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3884347962746949e-05,
+      "loss": 0.3306,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.3745,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3769171996210053e-05,
+      "loss": 0.2773,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.371136322084438e-05,
+      "loss": 0.2897,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3653410243663953e-05,
+      "loss": 0.3391,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3595315316381676e-05,
+      "loss": 0.2885,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3537080696225815e-05,
+      "loss": 0.3336,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3478708645852272e-05,
+      "loss": 0.2904,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.2822,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.336156133168631e-05,
+      "loss": 0.369,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3302790619551673e-05,
+      "loss": 0.3387,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3243891580338074e-05,
+      "loss": 0.3428,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3184866502516846e-05,
+      "loss": 0.3211,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3125717679456447e-05,
+      "loss": 0.2601,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3066447409333345e-05,
+      "loss": 0.3782,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.300705799504273e-05,
+      "loss": 0.2641,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2947551744109044e-05,
+      "loss": 0.3129,
+      "step": 220
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.28879309685963e-05,
+      "loss": 0.3096,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2828197985018276e-05,
+      "loss": 0.3007,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2768355114248493e-05,
+      "loss": 0.3149,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2708404681430054e-05,
+      "loss": 0.3493,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2648349015885272e-05,
+      "loss": 0.3406,
+      "step": 225
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.301,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2527931324258975e-05,
+      "loss": 0.3252,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2467573976902936e-05,
+      "loss": 0.374,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2407120754089733e-05,
+      "loss": 0.2819,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2346574004677154e-05,
+      "loss": 0.2936,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2285936081156897e-05,
+      "loss": 0.3504,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.2735,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2164396139381029e-05,
+      "loss": 0.2653,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.210349884345496e-05,
+      "loss": 0.2795,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2042519817896805e-05,
+      "loss": 0.2784,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1981461431993978e-05,
+      "loss": 0.2865,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1920326058117364e-05,
+      "loss": 0.3273,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1859116071629148e-05,
+      "loss": 0.3055,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1797833850790527e-05,
+      "loss": 0.2781,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.2747,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1675062233047365e-05,
+      "loss": 0.2615,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1613577606328068e-05,
+      "loss": 0.2741,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1552030285443516e-05,
+      "loss": 0.4037,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1490422661761744e-05,
+      "loss": 0.3396,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1428757128993801e-05,
+      "loss": 0.3196,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1367036083100735e-05,
+      "loss": 0.3166,
+      "step": 246
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.130526192220052e-05,
+      "loss": 0.3005,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1243437046474854e-05,
+      "loss": 0.34,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.118156385807593e-05,
+      "loss": 0.2704,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1119644761033079e-05,
+      "loss": 0.3103,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.105768216115938e-05,
+      "loss": 0.2643,
+      "step": 251
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0995678465958168e-05,
+      "loss": 0.2804,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0933636084529507e-05,
+      "loss": 0.3296,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0871557427476585e-05,
+      "loss": 0.2671,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0809444906812034e-05,
+      "loss": 0.3268,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 0.3031,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0685127929183567e-05,
+      "loss": 0.3609,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0622928302448523e-05,
+      "loss": 0.3359,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0560704472371919e-05,
+      "loss": 0.2838,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0498458856606972e-05,
+      "loss": 0.3347,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0436193873653362e-05,
+      "loss": 0.3121,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.037391194276326e-05,
+      "loss": 0.2965,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0311615483847333e-05,
+      "loss": 0.3587,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0249306917380731e-05,
+      "loss": 0.3694,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0186988664309023e-05,
+      "loss": 0.3086,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0124663145954152e-05,
+      "loss": 0.2684,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0062332783920337e-05,
+      "loss": 0.3054,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.3558,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.937667216079665e-06,
+      "loss": 0.3235,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.87533685404585e-06,
+      "loss": 0.3369,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.81301133569098e-06,
+      "loss": 0.3373,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.750693082619274e-06,
+      "loss": 0.2917,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.68838451615267e-06,
+      "loss": 0.2838,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.626088057236745e-06,
+      "loss": 0.3127,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.563806126346643e-06,
+      "loss": 0.3115,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.501541143393028e-06,
+      "loss": 0.3445,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.439295527628083e-06,
+      "loss": 0.3708,
+      "step": 277
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.377071697551479e-06,
+      "loss": 0.2742,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.314872070816435e-06,
+      "loss": 0.3338,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.252,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.190555093187968e-06,
+      "loss": 0.2629,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 0.3567,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.066363915470494e-06,
+      "loss": 0.3941,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.004321534041836e-06,
+      "loss": 0.34,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.942317838840625e-06,
+      "loss": 0.3793,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 0.3451,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.818436141924072e-06,
+      "loss": 0.2892,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.756562953525151e-06,
+      "loss": 0.3142,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.694738077799487e-06,
+      "loss": 0.2782,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.632963916899268e-06,
+      "loss": 0.2284,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.571242871006202e-06,
+      "loss": 0.3189,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.509577338238255e-06,
+      "loss": 0.2888,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.447969714556484e-06,
+      "loss": 0.3124,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.386422393671934e-06,
+      "loss": 0.3607,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.324937766952638e-06,
+      "loss": 0.3074,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.3403,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.202166149209475e-06,
+      "loss": 0.3296,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.140883928370855e-06,
+      "loss": 0.2788,
+      "step": 298
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.079673941882639e-06,
+      "loss": 0.3306,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.018538568006027e-06,
+      "loss": 0.3092,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.957480182103198e-06,
+      "loss": 0.3324,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.896501156545044e-06,
+      "loss": 0.293,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.835603860618973e-06,
+      "loss": 0.408,
+      "step": 303
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.3254,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.714063918843106e-06,
+      "loss": 0.2916,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.653425995322852e-06,
+      "loss": 0.3205,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.592879245910273e-06,
+      "loss": 0.274,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.532426023097063e-06,
+      "loss": 0.2606,
+      "step": 308
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.472068675741024e-06,
+      "loss": 0.3173,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.2818,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.3516509841147276e-06,
+      "loss": 0.3386,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.291595318569951e-06,
+      "loss": 0.3264,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.2316448857515076e-06,
+      "loss": 0.233,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.171802014981726e-06,
+      "loss": 0.2876,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.112069031403704e-06,
+      "loss": 0.2514,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.052448255890958e-06,
+      "loss": 0.3363,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.992942004957271e-06,
+      "loss": 0.3113,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.933552590666659e-06,
+      "loss": 0.2884,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.874282320543557e-06,
+      "loss": 0.3039,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.2625,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.7561084196619306e-06,
+      "loss": 0.3116,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.697209380448333e-06,
+      "loss": 0.3497,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.638438668313695e-06,
+      "loss": 0.319,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.3007,
+      "step": 324
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.521291354147727e-06,
+      "loss": 0.2998,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.462919303774186e-06,
+      "loss": 0.2918,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.404684683618325e-06,
+      "loss": 0.2604,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.34658975633605e-06,
+      "loss": 0.3346,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.288636779155621e-06,
+      "loss": 0.3309,
+      "step": 329
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.230828003789949e-06,
+      "loss": 0.4091,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.301,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.115652037253054e-06,
+      "loss": 0.3056,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.058289321144608e-06,
+      "loss": 0.2798,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.001079756802592e-06,
+      "loss": 0.2976,
+      "step": 334
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.944025567055251e-06,
+      "loss": 0.3189,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.887128968693887e-06,
+      "loss": 0.3335,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.830392172386723e-06,
+      "loss": 0.3092,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.773817382593008e-06,
+      "loss": 0.3579,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.717406797477371e-06,
+      "loss": 0.2755,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.2702,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.6050870019535496e-06,
+      "loss": 0.3047,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.549182155634076e-06,
+      "loss": 0.3235,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.493450242000546e-06,
+      "loss": 0.271,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.43789342646837e-06,
+      "loss": 0.2651,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.382513867649663e-06,
+      "loss": 0.2757,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.32731371726938e-06,
+      "loss": 0.282,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.2722951200817315e-06,
+      "loss": 0.3017,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.217460213786822e-06,
+      "loss": 0.248,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.1628111289476025e-06,
+      "loss": 0.3195,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.108349988907111e-06,
+      "loss": 0.3289,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.054078909705926e-06,
+      "loss": 0.3232,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3053,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.946115360978696e-06,
+      "loss": 0.2811,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.892427086283147e-06,
+      "loss": 0.2756,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.838937261924933e-06,
+      "loss": 0.3213,
+      "step": 355
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.78564796620502e-06,
+      "loss": 0.3865,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.732561269632992e-06,
+      "loss": 0.2899,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.679679234846636e-06,
+      "loss": 0.3323,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.627003916531761e-06,
+      "loss": 0.2954,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.2722,
+      "step": 360
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.522281607821288e-06,
+      "loss": 0.2635,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.470238686320606e-06,
+      "loss": 0.3068,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.418410618923163e-06,
+      "loss": 0.3263,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.3667994193637794e-06,
+      "loss": 0.2904,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.315407092951078e-06,
+      "loss": 0.3106,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.264235636489542e-06,
+      "loss": 0.3729,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.213287038201943e-06,
+      "loss": 0.2611,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.162563277652104e-06,
+      "loss": 0.3506,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.112066325667954e-06,
+      "loss": 0.263,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.061798144264986e-06,
+      "loss": 0.2519,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.0117606865699975e-06,
+      "loss": 0.319,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.961955896745224e-06,
+      "loss": 0.3457,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.912385709912794e-06,
+      "loss": 0.2825,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8630520520795275e-06,
+      "loss": 0.2782,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8139568400621184e-06,
+      "loss": 0.2852,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.2699,
+      "step": 376
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7164893743445274e-06,
+      "loss": 0.2634,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6681209076586035e-06,
+      "loss": 0.2939,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.619998460669916e-06,
+      "loss": 0.3233,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.2729,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5244990951772972e-06,
+      "loss": 0.3827,
+      "step": 381
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.4771258872187917e-06,
+      "loss": 0.3219,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4300061199041967e-06,
+      "loss": 0.2812,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3831416240314085e-06,
+      "loss": 0.2616,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3365342204799613e-06,
+      "loss": 0.3082,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.290185720140301e-06,
+      "loss": 0.2526,
+      "step": 386
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2440979238433977e-06,
+      "loss": 0.3027,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1982726222908046e-06,
+      "loss": 0.2902,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.152711595985065e-06,
+      "loss": 0.283,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.10741661516053e-06,
+      "loss": 0.238,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0623894397145837e-06,
+      "loss": 0.2777,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.017631819139273e-06,
+      "loss": 0.2997,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9731454924533086e-06,
+      "loss": 0.317,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.2685,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.884993624052701e-06,
+      "loss": 0.2233,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8413315074028157e-06,
+      "loss": 0.2934,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7979475346387363e-06,
+      "loss": 0.2844,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7548433914072736e-06,
+      "loss": 0.3373,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.712020752482717e-06,
+      "loss": 0.3245,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.3674,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6272266318987606e-06,
+      "loss": 0.3053,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5852584448417327e-06,
+      "loss": 0.3318,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.5435783511683444e-06,
+      "loss": 0.2434,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.502187970322657e-06,
+      "loss": 0.2829,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.461088910492202e-06,
+      "loss": 0.2951,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.420282768545469e-06,
+      "loss": 0.2691,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3797711299698924e-06,
+      "loss": 0.238,
+      "step": 407
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.437,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2996376476073724e-06,
+      "loss": 0.3255,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2600189173377263e-06,
+      "loss": 0.3383,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2207009173528528e-06,
+      "loss": 0.2849,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.3324,
+      "step": 412
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1429732071612653e-06,
+      "loss": 0.298,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.104566516997647e-06,
+      "loss": 0.2391,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0664665970876496e-06,
+      "loss": 0.2806,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0286749277707783e-06,
+      "loss": 0.3077,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9911929774097216e-06,
+      "loss": 0.3469,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9540222023333165e-06,
+      "loss": 0.3025,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9171640467799478e-06,
+      "loss": 0.3226,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.880619942841435e-06,
+      "loss": 0.2776,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8443913104073984e-06,
+      "loss": 0.2289,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.808479557110081e-06,
+      "loss": 0.2402,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7728860782696666e-06,
+      "loss": 0.3265,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7376122568400533e-06,
+      "loss": 0.2353,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7026594633551252e-06,
+      "loss": 0.2629,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6680290558755119e-06,
+      "loss": 0.3611,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6337223799358025e-06,
+      "loss": 0.3559,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.599740768492286e-06,
+      "loss": 0.3488,
+      "step": 428
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.566085541871145e-06,
+      "loss": 0.3067,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5327580077171589e-06,
+      "loss": 0.3063,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.499759460942909e-06,
+      "loss": 0.2918,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.467091183678444e-06,
+      "loss": 0.2416,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4347544452214869e-06,
+      "loss": 0.2829,
+      "step": 433
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4027505019880972e-06,
+      "loss": 0.278,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3710805974638697e-06,
+      "loss": 0.3117,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.2856,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3087478135435361e-06,
+      "loss": 0.2803,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.278087356033947e-06,
+      "loss": 0.2639,
+      "step": 438
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2477657809124632e-06,
+      "loss": 0.3482,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.308,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.188143977095576e-06,
+      "loss": 0.2487,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1588460649539036e-06,
+      "loss": 0.2937,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.129891668217783e-06,
+      "loss": 0.2821,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1012819118853147e-06,
+      "loss": 0.2694,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.073017907563887e-06,
+      "loss": 0.317,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0451007534269908e-06,
+      "loss": 0.3102,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0175315341715598e-06,
+      "loss": 0.3156,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.2957,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.634411714576353e-07,
+      "loss": 0.2966,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.369221296335007e-07,
+      "loss": 0.3048,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.107552258778907e-07,
+      "loss": 0.3222,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.849414768832687e-07,
+      "loss": 0.2689,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.5948188562057e-07,
+      "loss": 0.2808,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.343774413002382e-07,
+      "loss": 0.2847,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.096291193337935e-07,
+      "loss": 0.3227,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.852378812959227e-07,
+      "loss": 0.3605,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.2973,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.375304338969135e-07,
+      "loss": 0.3464,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.142160781674645e-07,
+      "loss": 0.2984,
+      "step": 459
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.912625135579587e-07,
+      "loss": 0.2863,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.68670631909335e-07,
+      "loss": 0.2629,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.464413110096601e-07,
+      "loss": 0.322,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.245754145600091e-07,
+      "loss": 0.2915,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.3556,
+      "step": 464
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.819372791793654e-07,
+      "loss": 0.2811,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.611666969163243e-07,
+      "loss": 0.3172,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.407628523748398e-07,
+      "loss": 0.2509,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.207265383286831e-07,
+      "loss": 0.3164,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.010585332715401e-07,
+      "loss": 0.3269,
+      "step": 469
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.817596013867765e-07,
+      "loss": 0.2737,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.628304925177318e-07,
+      "loss": 0.2989,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4427194213859216e-07,
+      "loss": 0.2985,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.2608467132581934e-07,
+      "loss": 0.2354,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.082693867301224e-07,
+      "loss": 0.2953,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.908267805490051e-07,
+      "loss": 0.3005,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.7375753049987974e-07,
+      "loss": 0.3116,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.570622997937234e-07,
+      "loss": 0.3119,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.3156,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.247964765680389e-07,
+      "loss": 0.297,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.2563,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.940343254660905e-07,
+      "loss": 0.2928,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7921863014225504e-07,
+      "loss": 0.282,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6478062738876654e-07,
+      "loss": 0.2774,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.3289,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.370399288006664e-07,
+      "loss": 0.2862,
+      "step": 485
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.2373831080695463e-07,
+      "loss": 0.2452,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1081654102351634e-07,
+      "loss": 0.2631,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9827512151456175e-07,
+      "loss": 0.2316,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8611453956612346e-07,
+      "loss": 0.302,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7433526766711727e-07,
+      "loss": 0.2666,
+      "step": 490
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.629377634909868e-07,
+      "loss": 0.2707,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.3028,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4128981481764115e-07,
+      "loss": 0.2957,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3104021143278911e-07,
+      "loss": 0.2482,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2117405796285286e-07,
+      "loss": 0.2428,
+      "step": 495
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1169173774871478e-07,
+      "loss": 0.2928,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0259361921774014e-07,
+      "loss": 0.3246,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.388005586947191e-08,
+      "loss": 0.3169,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.555138626189619e-08,
+      "loss": 0.2443,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.760793399827937e-08,
+      "loss": 0.2289,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.00500077146038e-08,
+      "loss": 0.3218,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.287790106757396e-08,
+      "loss": 0.2334,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.609189272320237e-08,
+      "loss": 0.2643,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.9692246345985905e-08,
+      "loss": 0.25,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.367921058866187e-08,
+      "loss": 0.279,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.805301908254455e-08,
+      "loss": 0.3023,
+      "step": 506
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.281389042844918e-08,
+      "loss": 0.2862,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.796202818819871e-08,
+      "loss": 0.2905,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.349762087671126e-08,
+      "loss": 0.2741,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.9420841954681525e-08,
+      "loss": 0.2657,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5731849821833955e-08,
+      "loss": 0.2763,
+      "step": 511
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2430787810776556e-08,
+      "loss": 0.3208,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.517784181422018e-09,
+      "loss": 0.246,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.992952116013918e-09,
+      "loss": 0.3307,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.856389714723575e-09,
+      "loss": 0.3072,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.1081799918375454e-09,
+      "loss": 0.311,
+      "step": 516
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.7483908725357546e-09,
+      "loss": 0.3303,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.770751902513862e-10,
+      "loss": 0.2496,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.9427068461808086e-10,
+      "loss": 0.2792,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.2959,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "step": 520,
+      "total_flos": 2.5944498742126182e+17,
+      "train_loss": 0.3417217805981636,
+      "train_runtime": 2008.3483,
+      "train_samples_per_second": 33.136,
+      "train_steps_per_second": 0.259
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 520,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.5944498742126182e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}