Upload 13 files

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "/cfs/cfs-lugcocyb/yongxinguo/videollama2_vllava/sft_v3_128_v4_sep_final_v5",
+  "architectures": [
+    "Videollama2MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "downsample_num": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "mm_hidden_size": 1024,
+  "mm_projector_lr": null,
+  "mm_projector_type": "spatial_slot",
+  "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": "model/clip-vit-large-patch14-336",
+  "model_type": "videollama2_mistral",
+  "num_attention_heads": 32,
+  "num_frames": 128,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "score_vocab_size": 13,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "time_vocab_size": 13,
+  "tokenizer_model_max_length": 4096,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "tune_lm_embed_head": true,
+  "tune_mm_embed_head": true,
+  "tune_mm_mlp_adapter": true,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50230d0c82382f215982841ffaa67c98dfcfdca7d373dc452a8dadc5a7d124d2
+size 4943162336

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f69cf96f6a1d4de9d049aff562d8eb720e3c2b72cf9dba9cad1424182120efd
+size 4999819336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e0429f1f5ba6798c6cab3ca27a515c2bccecdcebdd817541df8782208fc411
+size 4894079568

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d021f5bb946b9f72115a31aa168703ea2b2cdb5d6fba657842ecd080bf7e32a
+size 262365584

model.safetensors.index.json

@@ -0,0 +1,699 @@
+{
+  "metadata": {
+    "total_size": 15099330560
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-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.ln_vision.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.ln_vision.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.readout.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.slots": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.score_tower.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "model.sync_tower.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "model.time_tower.embed_tokens.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",
+    "score_head.weight": "model-00004-of-00004.safetensors",
+    "sync_head.weight": "model-00004-of-00004.safetensors",
+    "time_head.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.model

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

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": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2070 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 291,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010309278350515464,
+      "grad_norm": 56.530502862669195,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.0062,
+      "step": 1
+    },
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 56.85347935908914,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.0254,
+      "step": 2
+    },
+    {
+      "epoch": 0.030927835051546393,
+      "grad_norm": 52.80642762797087,
+      "learning_rate": 2.5e-06,
+      "loss": 0.9343,
+      "step": 3
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 14.460626748248101,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.7756,
+      "step": 4
+    },
+    {
+      "epoch": 0.05154639175257732,
+      "grad_norm": 33.77862103842921,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.7197,
+      "step": 5
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 19.887408911246457,
+      "learning_rate": 5e-06,
+      "loss": 0.6989,
+      "step": 6
+    },
+    {
+      "epoch": 0.07216494845360824,
+      "grad_norm": 18.88102575457493,
+      "learning_rate": 4.999650952964643e-06,
+      "loss": 0.7176,
+      "step": 7
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 14.291434565106155,
+      "learning_rate": 4.998603909325636e-06,
+      "loss": 0.7018,
+      "step": 8
+    },
+    {
+      "epoch": 0.09278350515463918,
+      "grad_norm": 17.830491359442135,
+      "learning_rate": 4.996859161456965e-06,
+      "loss": 0.6979,
+      "step": 9
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 22.258090145030344,
+      "learning_rate": 4.994417196557884e-06,
+      "loss": 0.6798,
+      "step": 10
+    },
+    {
+      "epoch": 0.1134020618556701,
+      "grad_norm": 22.704164044100065,
+      "learning_rate": 4.991278696516879e-06,
+      "loss": 0.6649,
+      "step": 11
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 18.16341564708439,
+      "learning_rate": 4.98744453772126e-06,
+      "loss": 0.6478,
+      "step": 12
+    },
+    {
+      "epoch": 0.13402061855670103,
+      "grad_norm": 14.932166260573126,
+      "learning_rate": 4.982915790812436e-06,
+      "loss": 0.6316,
+      "step": 13
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 12.635262425742601,
+      "learning_rate": 4.977693720386951e-06,
+      "loss": 0.6594,
+      "step": 14
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 11.94842253292838,
+      "learning_rate": 4.9717797846433655e-06,
+      "loss": 0.6488,
+      "step": 15
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 12.427372014843383,
+      "learning_rate": 4.965175634975072e-06,
+      "loss": 0.6507,
+      "step": 16
+    },
+    {
+      "epoch": 0.17525773195876287,
+      "grad_norm": 15.721796366237712,
+      "learning_rate": 4.9578831155091585e-06,
+      "loss": 0.6349,
+      "step": 17
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "grad_norm": 11.441586957645997,
+      "learning_rate": 4.949904262591467e-06,
+      "loss": 0.62,
+      "step": 18
+    },
+    {
+      "epoch": 0.1958762886597938,
+      "grad_norm": 17.146139866007378,
+      "learning_rate": 4.941241304217962e-06,
+      "loss": 0.6201,
+      "step": 19
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 13.569191402668975,
+      "learning_rate": 4.931896659412593e-06,
+      "loss": 0.6181,
+      "step": 20
+    },
+    {
+      "epoch": 0.21649484536082475,
+      "grad_norm": 13.738152410897145,
+      "learning_rate": 4.921872937551814e-06,
+      "loss": 0.6449,
+      "step": 21
+    },
+    {
+      "epoch": 0.2268041237113402,
+      "grad_norm": 11.330378951412754,
+      "learning_rate": 4.911172937635942e-06,
+      "loss": 0.5972,
+      "step": 22
+    },
+    {
+      "epoch": 0.23711340206185566,
+      "grad_norm": 17.60859685226136,
+      "learning_rate": 4.899799647507577e-06,
+      "loss": 0.6069,
+      "step": 23
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 24.313662307531697,
+      "learning_rate": 4.887756243017282e-06,
+      "loss": 0.6588,
+      "step": 24
+    },
+    {
+      "epoch": 0.25773195876288657,
+      "grad_norm": 20.364424318699296,
+      "learning_rate": 4.87504608713676e-06,
+      "loss": 0.6561,
+      "step": 25
+    },
+    {
+      "epoch": 0.26804123711340205,
+      "grad_norm": 16.583878449086104,
+      "learning_rate": 4.861672729019798e-06,
+      "loss": 0.6385,
+      "step": 26
+    },
+    {
+      "epoch": 0.27835051546391754,
+      "grad_norm": 13.788499236016973,
+      "learning_rate": 4.847639903011196e-06,
+      "loss": 0.6265,
+      "step": 27
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 12.707772131029879,
+      "learning_rate": 4.832951527604007e-06,
+      "loss": 0.6332,
+      "step": 28
+    },
+    {
+      "epoch": 0.29896907216494845,
+      "grad_norm": 7.810381548716006,
+      "learning_rate": 4.817611704345344e-06,
+      "loss": 0.6151,
+      "step": 29
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 9.728230357128046,
+      "learning_rate": 4.801624716691072e-06,
+      "loss": 0.6125,
+      "step": 30
+    },
+    {
+      "epoch": 0.31958762886597936,
+      "grad_norm": 10.944377720387918,
+      "learning_rate": 4.784995028809707e-06,
+      "loss": 0.58,
+      "step": 31
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 12.674255975258161,
+      "learning_rate": 4.767727284335852e-06,
+      "loss": 0.6082,
+      "step": 32
+    },
+    {
+      "epoch": 0.3402061855670103,
+      "grad_norm": 9.393558697710056,
+      "learning_rate": 4.74982630507352e-06,
+      "loss": 0.5954,
+      "step": 33
+    },
+    {
+      "epoch": 0.35051546391752575,
+      "grad_norm": 8.86444796956786,
+      "learning_rate": 4.731297089649704e-06,
+      "loss": 0.6217,
+      "step": 34
+    },
+    {
+      "epoch": 0.36082474226804123,
+      "grad_norm": 12.651955410449714,
+      "learning_rate": 4.7121448121185716e-06,
+      "loss": 0.6329,
+      "step": 35
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 8.240685956235492,
+      "learning_rate": 4.692374820516679e-06,
+      "loss": 0.5939,
+      "step": 36
+    },
+    {
+      "epoch": 0.38144329896907214,
+      "grad_norm": 13.17155584670435,
+      "learning_rate": 4.671992635369592e-06,
+      "loss": 0.6052,
+      "step": 37
+    },
+    {
+      "epoch": 0.3917525773195876,
+      "grad_norm": 11.537115822592154,
+      "learning_rate": 4.651003948150349e-06,
+      "loss": 0.6137,
+      "step": 38
+    },
+    {
+      "epoch": 0.4020618556701031,
+      "grad_norm": 8.541467382075664,
+      "learning_rate": 4.62941461969019e-06,
+      "loss": 0.5953,
+      "step": 39
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 10.448612350979204,
+      "learning_rate": 4.607230678541993e-06,
+      "loss": 0.6003,
+      "step": 40
+    },
+    {
+      "epoch": 0.422680412371134,
+      "grad_norm": 10.535341277458436,
+      "learning_rate": 4.584458319296868e-06,
+      "loss": 0.6091,
+      "step": 41
+    },
+    {
+      "epoch": 0.4329896907216495,
+      "grad_norm": 9.278483893756524,
+      "learning_rate": 4.561103900854401e-06,
+      "loss": 0.6025,
+      "step": 42
+    },
+    {
+      "epoch": 0.44329896907216493,
+      "grad_norm": 9.020197774744622,
+      "learning_rate": 4.5371739446470085e-06,
+      "loss": 0.6007,
+      "step": 43
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 8.745226620703487,
+      "learning_rate": 4.512675132818908e-06,
+      "loss": 0.6172,
+      "step": 44
+    },
+    {
+      "epoch": 0.4639175257731959,
+      "grad_norm": 8.731588120354488,
+      "learning_rate": 4.487614306360208e-06,
+      "loss": 0.5845,
+      "step": 45
+    },
+    {
+      "epoch": 0.4742268041237113,
+      "grad_norm": 11.556358562184432,
+      "learning_rate": 4.461998463196653e-06,
+      "loss": 0.6059,
+      "step": 46
+    },
+    {
+      "epoch": 0.4845360824742268,
+      "grad_norm": 5.371593726729439,
+      "learning_rate": 4.435834756235534e-06,
+      "loss": 0.584,
+      "step": 47
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 8.615012315419184,
+      "learning_rate": 4.409130491368331e-06,
+      "loss": 0.6078,
+      "step": 48
+    },
+    {
+      "epoch": 0.5051546391752577,
+      "grad_norm": 9.933496976524289,
+      "learning_rate": 4.381893125430629e-06,
+      "loss": 0.6279,
+      "step": 49
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 9.416756778612212,
+      "learning_rate": 4.354130264119894e-06,
+      "loss": 0.6115,
+      "step": 50
+    },
+    {
+      "epoch": 0.5257731958762887,
+      "grad_norm": 10.168866112438264,
+      "learning_rate": 4.325849659871674e-06,
+      "loss": 0.6157,
+      "step": 51
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 7.283913317646919,
+      "learning_rate": 4.297059209694824e-06,
+      "loss": 0.5992,
+      "step": 52
+    },
+    {
+      "epoch": 0.5463917525773195,
+      "grad_norm": 10.672694251588519,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.6183,
+      "step": 53
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 9.525243048182714,
+      "learning_rate": 4.237981069186606e-06,
+      "loss": 0.6132,
+      "step": 54
+    },
+    {
+      "epoch": 0.5670103092783505,
+      "grad_norm": 8.914430094168027,
+      "learning_rate": 4.207709875695078e-06,
+      "loss": 0.6117,
+      "step": 55
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 9.559556695084922,
+      "learning_rate": 4.176961825348059e-06,
+      "loss": 0.5758,
+      "step": 56
+    },
+    {
+      "epoch": 0.5876288659793815,
+      "grad_norm": 8.900834428053642,
+      "learning_rate": 4.1457455041582044e-06,
+      "loss": 0.6044,
+      "step": 57
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 8.490217076773844,
+      "learning_rate": 4.114069628897006e-06,
+      "loss": 0.5871,
+      "step": 58
+    },
+    {
+      "epoch": 0.6082474226804123,
+      "grad_norm": 10.200895711427977,
+      "learning_rate": 4.081943044660746e-06,
+      "loss": 0.6148,
+      "step": 59
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 6.428485373269192,
+      "learning_rate": 4.049374722400613e-06,
+      "loss": 0.5836,
+      "step": 60
+    },
+    {
+      "epoch": 0.6288659793814433,
+      "grad_norm": 7.53120416017883,
+      "learning_rate": 4.016373756417669e-06,
+      "loss": 0.5851,
+      "step": 61
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 7.011364295097242,
+      "learning_rate": 3.982949361823388e-06,
+      "loss": 0.5867,
+      "step": 62
+    },
+    {
+      "epoch": 0.6494845360824743,
+      "grad_norm": 6.839016326755402,
+      "learning_rate": 3.949110871966444e-06,
+      "loss": 0.6056,
+      "step": 63
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 6.692603329875056,
+      "learning_rate": 3.914867735826489e-06,
+      "loss": 0.5795,
+      "step": 64
+    },
+    {
+      "epoch": 0.6701030927835051,
+      "grad_norm": 8.96125889994131,
+      "learning_rate": 3.880229515375642e-06,
+      "loss": 0.601,
+      "step": 65
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 6.438652453919476,
+      "learning_rate": 3.845205882908432e-06,
+      "loss": 0.5852,
+      "step": 66
+    },
+    {
+      "epoch": 0.6907216494845361,
+      "grad_norm": 5.959909972976633,
+      "learning_rate": 3.8098066183409223e-06,
+      "loss": 0.5908,
+      "step": 67
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 11.353215075638747,
+      "learning_rate": 3.774041606479794e-06,
+      "loss": 0.5967,
+      "step": 68
+    },
+    {
+      "epoch": 0.711340206185567,
+      "grad_norm": 8.149197273273636,
+      "learning_rate": 3.737920834262134e-06,
+      "loss": 0.5736,
+      "step": 69
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 11.946806310904744,
+      "learning_rate": 3.7014543879667097e-06,
+      "loss": 0.5635,
+      "step": 70
+    },
+    {
+      "epoch": 0.7319587628865979,
+      "grad_norm": 7.235189107810607,
+      "learning_rate": 3.6646524503974955e-06,
+      "loss": 0.5988,
+      "step": 71
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 9.00748429109896,
+      "learning_rate": 3.627525298040255e-06,
+      "loss": 0.6066,
+      "step": 72
+    },
+    {
+      "epoch": 0.7525773195876289,
+      "grad_norm": 5.543402990170008,
+      "learning_rate": 3.5900832981929574e-06,
+      "loss": 0.5766,
+      "step": 73
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 10.622044769393877,
+      "learning_rate": 3.552336906070838e-06,
+      "loss": 0.5984,
+      "step": 74
+    },
+    {
+      "epoch": 0.7731958762886598,
+      "grad_norm": 6.322017029596627,
+      "learning_rate": 3.5142966618869096e-06,
+      "loss": 0.6064,
+      "step": 75
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 8.698612269075731,
+      "learning_rate": 3.4759731879087373e-06,
+      "loss": 0.5691,
+      "step": 76
+    },
+    {
+      "epoch": 0.7938144329896907,
+      "grad_norm": 7.1078847811435235,
+      "learning_rate": 3.4373771854923032e-06,
+      "loss": 0.5993,
+      "step": 77
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 7.990782195608653,
+      "learning_rate": 3.398519432093782e-06,
+      "loss": 0.5884,
+      "step": 78
+    },
+    {
+      "epoch": 0.8144329896907216,
+      "grad_norm": 9.607410558859467,
+      "learning_rate": 3.3594107782600754e-06,
+      "loss": 0.5982,
+      "step": 79
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 14.083966363226939,
+      "learning_rate": 3.3200621445989227e-06,
+      "loss": 0.5839,
+      "step": 80
+    },
+    {
+      "epoch": 0.8350515463917526,
+      "grad_norm": 5.701568641983366,
+      "learning_rate": 3.2804845187294666e-06,
+      "loss": 0.6011,
+      "step": 81
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 6.773029741907651,
+      "learning_rate": 3.2406889522140854e-06,
+      "loss": 0.5522,
+      "step": 82
+    },
+    {
+      "epoch": 0.8556701030927835,
+      "grad_norm": 10.147092476062955,
+      "learning_rate": 3.2006865574723907e-06,
+      "loss": 0.5822,
+      "step": 83
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 8.873878085722918,
+      "learning_rate": 3.1604885046782158e-06,
+      "loss": 0.5997,
+      "step": 84
+    },
+    {
+      "epoch": 0.8762886597938144,
+      "grad_norm": 9.962104711025551,
+      "learning_rate": 3.1201060186404836e-06,
+      "loss": 0.5698,
+      "step": 85
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 11.526239728138046,
+      "learning_rate": 3.0795503756688212e-06,
+      "loss": 0.5893,
+      "step": 86
+    },
+    {
+      "epoch": 0.8969072164948454,
+      "grad_norm": 13.53827694453593,
+      "learning_rate": 3.038832900424784e-06,
+      "loss": 0.565,
+      "step": 87
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 7.373403085352247,
+      "learning_rate": 2.9979649627595904e-06,
+      "loss": 0.5865,
+      "step": 88
+    },
+    {
+      "epoch": 0.9175257731958762,
+      "grad_norm": 8.327398959176447,
+      "learning_rate": 2.9569579745392263e-06,
+      "loss": 0.5704,
+      "step": 89
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 7.734529867452049,
+      "learning_rate": 2.9158233864578256e-06,
+      "loss": 0.5702,
+      "step": 90
+    },
+    {
+      "epoch": 0.9381443298969072,
+      "grad_norm": 11.545112692182581,
+      "learning_rate": 2.8745726848402037e-06,
+      "loss": 0.5901,
+      "step": 91
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 8.481813159931104,
+      "learning_rate": 2.8332173884344477e-06,
+      "loss": 0.5799,
+      "step": 92
+    },
+    {
+      "epoch": 0.9587628865979382,
+      "grad_norm": 5.62478688154214,
+      "learning_rate": 2.791769045195441e-06,
+      "loss": 0.5757,
+      "step": 93
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 12.580963383160984,
+      "learning_rate": 2.7502392290602463e-06,
+      "loss": 0.6143,
+      "step": 94
+    },
+    {
+      "epoch": 0.979381443298969,
+      "grad_norm": 8.615561365578158,
+      "learning_rate": 2.708639536716225e-06,
+      "loss": 0.5856,
+      "step": 95
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 8.26963135051012,
+      "learning_rate": 2.6669815843628043e-06,
+      "loss": 0.584,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.96198935018297,
+      "learning_rate": 2.625277004467798e-06,
+      "loss": 0.5692,
+      "step": 97
+    },
+    {
+      "epoch": 1.0103092783505154,
+      "grad_norm": 9.223202215415496,
+      "learning_rate": 2.5835374425191867e-06,
+      "loss": 0.5844,
+      "step": 98
+    },
+    {
+      "epoch": 1.0206185567010309,
+      "grad_norm": 9.335854961716732,
+      "learning_rate": 2.5417745537732524e-06,
+      "loss": 0.5834,
+      "step": 99
+    },
+    {
+      "epoch": 1.0309278350515463,
+      "grad_norm": 8.859234628793157,
+      "learning_rate": 2.5e-06,
+      "loss": 0.5766,
+      "step": 100
+    },
+    {
+      "epoch": 1.041237113402062,
+      "grad_norm": 11.10978876086468,
+      "learning_rate": 2.4582254462267476e-06,
+      "loss": 0.5481,
+      "step": 101
+    },
+    {
+      "epoch": 1.0515463917525774,
+      "grad_norm": 14.13721579241571,
+      "learning_rate": 2.4164625574808145e-06,
+      "loss": 0.5391,
+      "step": 102
+    },
+    {
+      "epoch": 1.0618556701030928,
+      "grad_norm": 10.171726864440725,
+      "learning_rate": 2.3747229955322022e-06,
+      "loss": 0.5645,
+      "step": 103
+    },
+    {
+      "epoch": 1.0721649484536082,
+      "grad_norm": 8.353171526332968,
+      "learning_rate": 2.333018415637196e-06,
+      "loss": 0.554,
+      "step": 104
+    },
+    {
+      "epoch": 1.0824742268041236,
+      "grad_norm": 5.776771584137868,
+      "learning_rate": 2.291360463283776e-06,
+      "loss": 0.5149,
+      "step": 105
+    },
+    {
+      "epoch": 1.0927835051546393,
+      "grad_norm": 5.645891177548563,
+      "learning_rate": 2.249760770939754e-06,
+      "loss": 0.5341,
+      "step": 106
+    },
+    {
+      "epoch": 1.1030927835051547,
+      "grad_norm": 17.194939796051738,
+      "learning_rate": 2.2082309548045595e-06,
+      "loss": 0.5509,
+      "step": 107
+    },
+    {
+      "epoch": 1.1134020618556701,
+      "grad_norm": 11.494112580944973,
+      "learning_rate": 2.1667826115655536e-06,
+      "loss": 0.5619,
+      "step": 108
+    },
+    {
+      "epoch": 1.1237113402061856,
+      "grad_norm": 12.344445935682346,
+      "learning_rate": 2.1254273151597967e-06,
+      "loss": 0.5609,
+      "step": 109
+    },
+    {
+      "epoch": 1.134020618556701,
+      "grad_norm": 8.048599443563438,
+      "learning_rate": 2.0841766135421753e-06,
+      "loss": 0.5341,
+      "step": 110
+    },
+    {
+      "epoch": 1.1443298969072164,
+      "grad_norm": 7.901613828746177,
+      "learning_rate": 2.043042025460775e-06,
+      "loss": 0.5673,
+      "step": 111
+    },
+    {
+      "epoch": 1.1546391752577319,
+      "grad_norm": 15.559956905825056,
+      "learning_rate": 2.0020350372404104e-06,
+      "loss": 0.5358,
+      "step": 112
+    },
+    {
+      "epoch": 1.1649484536082475,
+      "grad_norm": 8.318249542521562,
+      "learning_rate": 1.9611670995752164e-06,
+      "loss": 0.548,
+      "step": 113
+    },
+    {
+      "epoch": 1.175257731958763,
+      "grad_norm": 7.70563136678249,
+      "learning_rate": 1.920449624331179e-06,
+      "loss": 0.5217,
+      "step": 114
+    },
+    {
+      "epoch": 1.1855670103092784,
+      "grad_norm": 10.581055723999143,
+      "learning_rate": 1.8798939813595169e-06,
+      "loss": 0.536,
+      "step": 115
+    },
+    {
+      "epoch": 1.1958762886597938,
+      "grad_norm": 8.42303175758336,
+      "learning_rate": 1.8395114953217853e-06,
+      "loss": 0.5326,
+      "step": 116
+    },
+    {
+      "epoch": 1.2061855670103092,
+      "grad_norm": 8.916178847424373,
+      "learning_rate": 1.7993134425276095e-06,
+      "loss": 0.5423,
+      "step": 117
+    },
+    {
+      "epoch": 1.2164948453608249,
+      "grad_norm": 7.749722137392225,
+      "learning_rate": 1.7593110477859155e-06,
+      "loss": 0.5524,
+      "step": 118
+    },
+    {
+      "epoch": 1.2268041237113403,
+      "grad_norm": 6.204568152143213,
+      "learning_rate": 1.7195154812705344e-06,
+      "loss": 0.5162,
+      "step": 119
+    },
+    {
+      "epoch": 1.2371134020618557,
+      "grad_norm": 6.79722773195719,
+      "learning_rate": 1.6799378554010773e-06,
+      "loss": 0.5556,
+      "step": 120
+    },
+    {
+      "epoch": 1.2474226804123711,
+      "grad_norm": 7.992796754408021,
+      "learning_rate": 1.640589221739926e-06,
+      "loss": 0.5373,
+      "step": 121
+    },
+    {
+      "epoch": 1.2577319587628866,
+      "grad_norm": 8.603985381968347,
+      "learning_rate": 1.6014805679062185e-06,
+      "loss": 0.514,
+      "step": 122
+    },
+    {
+      "epoch": 1.268041237113402,
+      "grad_norm": 9.407620250978518,
+      "learning_rate": 1.5626228145076976e-06,
+      "loss": 0.5259,
+      "step": 123
+    },
+    {
+      "epoch": 1.2783505154639174,
+      "grad_norm": 7.062284213120056,
+      "learning_rate": 1.5240268120912631e-06,
+      "loss": 0.5356,
+      "step": 124
+    },
+    {
+      "epoch": 1.2886597938144329,
+      "grad_norm": 7.5572557157103475,
+      "learning_rate": 1.4857033381130912e-06,
+      "loss": 0.5116,
+      "step": 125
+    },
+    {
+      "epoch": 1.2989690721649485,
+      "grad_norm": 7.805829671961577,
+      "learning_rate": 1.4476630939291631e-06,
+      "loss": 0.5565,
+      "step": 126
+    },
+    {
+      "epoch": 1.309278350515464,
+      "grad_norm": 10.378458572627729,
+      "learning_rate": 1.4099167018070436e-06,
+      "loss": 0.5427,
+      "step": 127
+    },
+    {
+      "epoch": 1.3195876288659794,
+      "grad_norm": 7.5706417929381935,
+      "learning_rate": 1.372474701959745e-06,
+      "loss": 0.5143,
+      "step": 128
+    },
+    {
+      "epoch": 1.3298969072164948,
+      "grad_norm": 7.007827469587551,
+      "learning_rate": 1.3353475496025049e-06,
+      "loss": 0.559,
+      "step": 129
+    },
+    {
+      "epoch": 1.3402061855670104,
+      "grad_norm": 6.710862466838978,
+      "learning_rate": 1.2985456120332907e-06,
+      "loss": 0.5696,
+      "step": 130
+    },
+    {
+      "epoch": 1.3505154639175259,
+      "grad_norm": 9.333878728281068,
+      "learning_rate": 1.2620791657378664e-06,
+      "loss": 0.5554,
+      "step": 131
+    },
+    {
+      "epoch": 1.3608247422680413,
+      "grad_norm": 12.936977504923266,
+      "learning_rate": 1.2259583935202063e-06,
+      "loss": 0.553,
+      "step": 132
+    },
+    {
+      "epoch": 1.3711340206185567,
+      "grad_norm": 7.957065527893153,
+      "learning_rate": 1.1901933816590787e-06,
+      "loss": 0.5388,
+      "step": 133
+    },
+    {
+      "epoch": 1.3814432989690721,
+      "grad_norm": 6.7484097903496,
+      "learning_rate": 1.1547941170915686e-06,
+      "loss": 0.5363,
+      "step": 134
+    },
+    {
+      "epoch": 1.3917525773195876,
+      "grad_norm": 6.361664231123078,
+      "learning_rate": 1.1197704846243587e-06,
+      "loss": 0.5446,
+      "step": 135
+    },
+    {
+      "epoch": 1.402061855670103,
+      "grad_norm": 8.087687103135398,
+      "learning_rate": 1.0851322641735119e-06,
+      "loss": 0.5431,
+      "step": 136
+    },
+    {
+      "epoch": 1.4123711340206184,
+      "grad_norm": 5.308480571020336,
+      "learning_rate": 1.0508891280335562e-06,
+      "loss": 0.5482,
+      "step": 137
+    },
+    {
+      "epoch": 1.422680412371134,
+      "grad_norm": 7.8000899969924475,
+      "learning_rate": 1.0170506381766121e-06,
+      "loss": 0.5712,
+      "step": 138
+    },
+    {
+      "epoch": 1.4329896907216495,
+      "grad_norm": 8.473337430115116,
+      "learning_rate": 9.836262435823316e-07,
+      "loss": 0.5389,
+      "step": 139
+    },
+    {
+      "epoch": 1.443298969072165,
+      "grad_norm": 5.576258584866546,
+      "learning_rate": 9.506252775993882e-07,
+      "loss": 0.5234,
+      "step": 140
+    },
+    {
+      "epoch": 1.4536082474226804,
+      "grad_norm": 7.140077933091837,
+      "learning_rate": 9.180569553392535e-07,
+      "loss": 0.5593,
+      "step": 141
+    },
+    {
+      "epoch": 1.463917525773196,
+      "grad_norm": 7.173765643870978,
+      "learning_rate": 8.85930371102994e-07,
+      "loss": 0.5084,
+      "step": 142
+    },
+    {
+      "epoch": 1.4742268041237114,
+      "grad_norm": 7.911307786551771,
+      "learning_rate": 8.542544958417962e-07,
+      "loss": 0.534,
+      "step": 143
+    },
+    {
+      "epoch": 1.4845360824742269,
+      "grad_norm": 6.200762166583492,
+      "learning_rate": 8.23038174651942e-07,
+      "loss": 0.5332,
+      "step": 144
+    },
+    {
+      "epoch": 1.4948453608247423,
+      "grad_norm": 6.031208888096604,
+      "learning_rate": 7.922901243049231e-07,
+      "loss": 0.5348,
+      "step": 145
+    },
+    {
+      "epoch": 1.5051546391752577,
+      "grad_norm": 5.448085084528034,
+      "learning_rate": 7.620189308133943e-07,
+      "loss": 0.5244,
+      "step": 146
+    },
+    {
+      "epoch": 1.5154639175257731,
+      "grad_norm": 8.397115629983924,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.526,
+      "step": 147
+    },
+    {
+      "epoch": 1.5257731958762886,
+      "grad_norm": 7.963177815905807,
+      "learning_rate": 7.029407903051771e-07,
+      "loss": 0.5409,
+      "step": 148
+    },
+    {
+      "epoch": 1.536082474226804,
+      "grad_norm": 5.610457547002628,
+      "learning_rate": 6.741503401283273e-07,
+      "loss": 0.525,
+      "step": 149
+    },
+    {
+      "epoch": 1.5463917525773194,
+      "grad_norm": 6.0265411811750225,
+      "learning_rate": 6.458697358801061e-07,
+      "loss": 0.5224,
+      "step": 150
+    },
+    {
+      "epoch": 1.556701030927835,
+      "grad_norm": 8.139901449370793,
+      "learning_rate": 6.181068745693716e-07,
+      "loss": 0.5153,
+      "step": 151
+    },
+    {
+      "epoch": 1.5670103092783505,
+      "grad_norm": 8.698508772807294,
+      "learning_rate": 5.908695086316701e-07,
+      "loss": 0.5391,
+      "step": 152
+    },
+    {
+      "epoch": 1.577319587628866,
+      "grad_norm": 7.077929091952878,
+      "learning_rate": 5.641652437644668e-07,
+      "loss": 0.5123,
+      "step": 153
+    },
+    {
+      "epoch": 1.5876288659793816,
+      "grad_norm": 6.897372101956063,
+      "learning_rate": 5.380015368033476e-07,
+      "loss": 0.5383,
+      "step": 154
+    },
+    {
+      "epoch": 1.597938144329897,
+      "grad_norm": 7.544723172377018,
+      "learning_rate": 5.123856936397925e-07,
+      "loss": 0.5008,
+      "step": 155
+    },
+    {
+      "epoch": 1.6082474226804124,
+      "grad_norm": 8.15135168556466,
+      "learning_rate": 4.873248671810929e-07,
+      "loss": 0.4988,
+      "step": 156
+    },
+    {
+      "epoch": 1.6185567010309279,
+      "grad_norm": 9.054018879676315,
+      "learning_rate": 4.628260553529917e-07,
+      "loss": 0.5297,
+      "step": 157
+    },
+    {
+      "epoch": 1.6288659793814433,
+      "grad_norm": 5.634019698515158,
+      "learning_rate": 4.388960991455998e-07,
+      "loss": 0.5355,
+      "step": 158
+    },
+    {
+      "epoch": 1.6391752577319587,
+      "grad_norm": 7.717492869935791,
+      "learning_rate": 4.155416807031326e-07,
+      "loss": 0.4994,
+      "step": 159
+    },
+    {
+      "epoch": 1.6494845360824741,
+      "grad_norm": 5.70781191187035,
+      "learning_rate": 3.927693214580075e-07,
+      "loss": 0.5264,
+      "step": 160
+    },
+    {
+      "epoch": 1.6597938144329896,
+      "grad_norm": 6.247396918854984,
+      "learning_rate": 3.7058538030980946e-07,
+      "loss": 0.5238,
+      "step": 161
+    },
+    {
+      "epoch": 1.670103092783505,
+      "grad_norm": 8.970736081000318,
+      "learning_rate": 3.489960518496521e-07,
+      "loss": 0.5176,
+      "step": 162
+    },
+    {
+      "epoch": 1.6804123711340206,
+      "grad_norm": 6.52050803188651,
+      "learning_rate": 3.2800736463040883e-07,
+      "loss": 0.5333,
+      "step": 163
+    },
+    {
+      "epoch": 1.690721649484536,
+      "grad_norm": 8.678189564713009,
+      "learning_rate": 3.076251794833213e-07,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 1.7010309278350515,
+      "grad_norm": 7.63188885788194,
+      "learning_rate": 2.878551878814287e-07,
+      "loss": 0.5382,
+      "step": 165
+    },
+    {
+      "epoch": 1.7113402061855671,
+      "grad_norm": 6.734689090068864,
+      "learning_rate": 2.6870291035029724e-07,
+      "loss": 0.546,
+      "step": 166
+    },
+    {
+      "epoch": 1.7216494845360826,
+      "grad_norm": 6.992143309043317,
+      "learning_rate": 2.501736949264805e-07,
+      "loss": 0.5486,
+      "step": 167
+    },
+    {
+      "epoch": 1.731958762886598,
+      "grad_norm": 9.076794104921877,
+      "learning_rate": 2.3227271566414827e-07,
+      "loss": 0.5289,
+      "step": 168
+    },
+    {
+      "epoch": 1.7422680412371134,
+      "grad_norm": 7.405248131571063,
+      "learning_rate": 2.1500497119029324e-07,
+      "loss": 0.5419,
+      "step": 169
+    },
+    {
+      "epoch": 1.7525773195876289,
+      "grad_norm": 7.261676461936444,
+      "learning_rate": 1.9837528330892781e-07,
+      "loss": 0.5412,
+      "step": 170
+    },
+    {
+      "epoch": 1.7628865979381443,
+      "grad_norm": 6.772741086153254,
+      "learning_rate": 1.823882956546566e-07,
+      "loss": 0.5324,
+      "step": 171
+    },
+    {
+      "epoch": 1.7731958762886597,
+      "grad_norm": 7.0347083508864285,
+      "learning_rate": 1.6704847239599364e-07,
+      "loss": 0.5336,
+      "step": 172
+    },
+    {
+      "epoch": 1.7835051546391751,
+      "grad_norm": 7.381399190947017,
+      "learning_rate": 1.5236009698880532e-07,
+      "loss": 0.5235,
+      "step": 173
+    },
+    {
+      "epoch": 1.7938144329896906,
+      "grad_norm": 5.087687623409436,
+      "learning_rate": 1.3832727098020333e-07,
+      "loss": 0.5317,
+      "step": 174
+    },
+    {
+      "epoch": 1.8041237113402062,
+      "grad_norm": 6.551357146160097,
+      "learning_rate": 1.2495391286323988e-07,
+      "loss": 0.5555,
+      "step": 175
+    },
+    {
+      "epoch": 1.8144329896907216,
+      "grad_norm": 5.892841923681646,
+      "learning_rate": 1.1224375698271894e-07,
+      "loss": 0.536,
+      "step": 176
+    },
+    {
+      "epoch": 1.824742268041237,
+      "grad_norm": 6.6646217388808555,
+      "learning_rate": 1.0020035249242304e-07,
+      "loss": 0.5387,
+      "step": 177
+    },
+    {
+      "epoch": 1.8350515463917527,
+      "grad_norm": 6.8242492151044365,
+      "learning_rate": 8.882706236405886e-08,
+      "loss": 0.4794,
+      "step": 178
+    },
+    {
+      "epoch": 1.8453608247422681,
+      "grad_norm": 7.100289040713055,
+      "learning_rate": 7.812706244818669e-08,
+      "loss": 0.4986,
+      "step": 179
+    },
+    {
+      "epoch": 1.8556701030927836,
+      "grad_norm": 5.845790241687149,
+      "learning_rate": 6.810334058740736e-08,
+      "loss": 0.5535,
+      "step": 180
+    },
+    {
+      "epoch": 1.865979381443299,
+      "grad_norm": 5.68361589879705,
+      "learning_rate": 5.8758695782038245e-08,
+      "loss": 0.5437,
+      "step": 181
+    },
+    {
+      "epoch": 1.8762886597938144,
+      "grad_norm": 7.994426454699525,
+      "learning_rate": 5.009573740853313e-08,
+      "loss": 0.5086,
+      "step": 182
+    },
+    {
+      "epoch": 1.8865979381443299,
+      "grad_norm": 6.571363294762953,
+      "learning_rate": 4.211688449084123e-08,
+      "loss": 0.5167,
+      "step": 183
+    },
+    {
+      "epoch": 1.8969072164948453,
+      "grad_norm": 8.467171947790893,
+      "learning_rate": 3.4824365024928585e-08,
+      "loss": 0.5244,
+      "step": 184
+    },
+    {
+      "epoch": 1.9072164948453607,
+      "grad_norm": 9.804710065960087,
+      "learning_rate": 2.8220215356634662e-08,
+      "loss": 0.5255,
+      "step": 185
+    },
+    {
+      "epoch": 1.9175257731958761,
+      "grad_norm": 7.2557000739578825,
+      "learning_rate": 2.230627961304993e-08,
+      "loss": 0.4976,
+      "step": 186
+    },
+    {
+      "epoch": 1.9278350515463918,
+      "grad_norm": 7.499859617826814,
+      "learning_rate": 1.708420918756476e-08,
+      "loss": 0.515,
+      "step": 187
+    },
+    {
+      "epoch": 1.9381443298969072,
+      "grad_norm": 7.626640018381011,
+      "learning_rate": 1.255546227873966e-08,
+      "loss": 0.4789,
+      "step": 188
+    },
+    {
+      "epoch": 1.9484536082474226,
+      "grad_norm": 6.930888281586003,
+      "learning_rate": 8.721303483121002e-09,
+      "loss": 0.5328,
+      "step": 189
+    },
+    {
+      "epoch": 1.9587628865979383,
+      "grad_norm": 6.843490525992252,
+      "learning_rate": 5.582803442117091e-09,
+      "loss": 0.5124,
+      "step": 190
+    },
+    {
+      "epoch": 1.9690721649484537,
+      "grad_norm": 6.535875936350926,
+      "learning_rate": 3.1408385430356513e-09,
+      "loss": 0.5221,
+      "step": 191
+    },
+    {
+      "epoch": 1.9793814432989691,
+      "grad_norm": 6.59860470212397,
+      "learning_rate": 1.3960906743634706e-09,
+      "loss": 0.5168,
+      "step": 192
+    },
+    {
+      "epoch": 1.9896907216494846,
+      "grad_norm": 9.644943778515387,
+      "learning_rate": 3.490470353573194e-10,
+      "loss": 0.5166,
+      "step": 193
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.0885009068108324,
+      "learning_rate": 0.0,
+      "loss": 0.5012,
+      "step": 194
+    },
+    {
+      "epoch": 2.0103092783505154,
+      "grad_norm": 6.7429744751815,
+      "learning_rate": 1.2985456120332907e-06,
+      "loss": 0.5071,
+      "step": 195
+    },
+    {
+      "epoch": 2.020618556701031,
+      "grad_norm": 7.653675627458454,
+      "learning_rate": 1.27419674050107e-06,
+      "loss": 0.4717,
+      "step": 196
+    },
+    {
+      "epoch": 2.0309278350515463,
+      "grad_norm": 10.177207568583976,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.5465,
+      "step": 197
+    },
+    {
+      "epoch": 2.0412371134020617,
+      "grad_norm": 5.872999784168543,
+      "learning_rate": 1.2259583935202063e-06,
+      "loss": 0.4681,
+      "step": 198
+    },
+    {
+      "epoch": 2.051546391752577,
+      "grad_norm": 8.033564727531939,
+      "learning_rate": 1.2020749047985627e-06,
+      "loss": 0.4898,
+      "step": 199
+    },
+    {
+      "epoch": 2.0618556701030926,
+      "grad_norm": 10.111825165552998,
+      "learning_rate": 1.178352497948384e-06,
+      "loss": 0.4888,
+      "step": 200
+    },
+    {
+      "epoch": 2.0721649484536084,
+      "grad_norm": 9.056178341326012,
+      "learning_rate": 1.1547941170915686e-06,
+      "loss": 0.4933,
+      "step": 201
+    },
+    {
+      "epoch": 2.082474226804124,
+      "grad_norm": 8.801087260270211,
+      "learning_rate": 1.131402685993201e-06,
+      "loss": 0.5084,
+      "step": 202
+    },
+    {
+      "epoch": 2.0927835051546393,
+      "grad_norm": 8.35974781951926,
+      "learning_rate": 1.1081811076986965e-06,
+      "loss": 0.5066,
+      "step": 203
+    },
+    {
+      "epoch": 2.1030927835051547,
+      "grad_norm": 11.00021188705284,
+      "learning_rate": 1.0851322641735119e-06,
+      "loss": 0.5176,
+      "step": 204
+    },
+    {
+      "epoch": 2.11340206185567,
+      "grad_norm": 10.087911233945551,
+      "learning_rate": 1.0622590159454741e-06,
+      "loss": 0.4977,
+      "step": 205
+    },
+    {
+      "epoch": 2.1237113402061856,
+      "grad_norm": 7.390720229714829,
+      "learning_rate": 1.0395642017497648e-06,
+      "loss": 0.495,
+      "step": 206
+    },
+    {
+      "epoch": 2.134020618556701,
+      "grad_norm": 7.781154402180078,
+      "learning_rate": 1.0170506381766121e-06,
+      "loss": 0.4662,
+      "step": 207
+    },
+    {
+      "epoch": 2.1443298969072164,
+      "grad_norm": 8.64835633995342,
+      "learning_rate": 9.94721119321739e-07,
+      "loss": 0.4963,
+      "step": 208
+    },
+    {
+      "epoch": 2.154639175257732,
+      "grad_norm": 8.758238483451327,
+      "learning_rate": 9.72578416439587e-07,
+      "loss": 0.5021,
+      "step": 209
+    },
+    {
+      "epoch": 2.1649484536082473,
+      "grad_norm": 7.794658338144042,
+      "learning_rate": 9.506252775993882e-07,
+      "loss": 0.4839,
+      "step": 210
+    },
+    {
+      "epoch": 2.1752577319587627,
+      "grad_norm": 10.778506784155853,
+      "learning_rate": 9.288644273441083e-07,
+      "loss": 0.4862,
+      "step": 211
+    },
+    {
+      "epoch": 2.1855670103092786,
+      "grad_norm": 10.070848117786477,
+      "learning_rate": 9.072985663523137e-07,
+      "loss": 0.5122,
+      "step": 212
+    },
+    {
+      "epoch": 2.195876288659794,
+      "grad_norm": 7.398951801603466,
+      "learning_rate": 8.85930371102994e-07,
+      "loss": 0.4785,
+      "step": 213
+    },
+    {
+      "epoch": 2.2061855670103094,
+      "grad_norm": 9.910836394550703,
+      "learning_rate": 8.647624935433949e-07,
+      "loss": 0.5005,
+      "step": 214
+    },
+    {
+      "epoch": 2.216494845360825,
+      "grad_norm": 6.958374510622299,
+      "learning_rate": 8.437975607598889e-07,
+      "loss": 0.4773,
+      "step": 215
+    },
+    {
+      "epoch": 2.2268041237113403,
+      "grad_norm": 7.528132256313958,
+      "learning_rate": 8.23038174651942e-07,
+      "loss": 0.5051,
+      "step": 216
+    },
+    {
+      "epoch": 2.2371134020618557,
+      "grad_norm": 11.559406258405966,
+      "learning_rate": 8.02486911609188e-07,
+      "loss": 0.4966,
+      "step": 217
+    },
+    {
+      "epoch": 2.247422680412371,
+      "grad_norm": 8.045424247257529,
+      "learning_rate": 7.8214632219169e-07,
+      "loss": 0.4942,
+      "step": 218
+    },
+    {
+      "epoch": 2.2577319587628866,
+      "grad_norm": 9.024692147623375,
+      "learning_rate": 7.620189308133943e-07,
+      "loss": 0.4592,
+      "step": 219
+    },
+    {
+      "epoch": 2.268041237113402,
+      "grad_norm": 8.608428072215723,
+      "learning_rate": 7.421072354288303e-07,
+      "loss": 0.4692,
+      "step": 220
+    },
+    {
+      "epoch": 2.2783505154639174,
+      "grad_norm": 8.94979119936365,
+      "learning_rate": 7.224137072230982e-07,
+      "loss": 0.4988,
+      "step": 221
+    },
+    {
+      "epoch": 2.288659793814433,
+      "grad_norm": 8.663269061674175,
+      "learning_rate": 7.029407903051771e-07,
+      "loss": 0.5092,
+      "step": 222
+    },
+    {
+      "epoch": 2.2989690721649483,
+      "grad_norm": 10.165201133618265,
+      "learning_rate": 6.836909014045925e-07,
+      "loss": 0.5058,
+      "step": 223
+    },
+    {
+      "epoch": 2.3092783505154637,
+      "grad_norm": 9.604858329399347,
+      "learning_rate": 6.646664295714835e-07,
+      "loss": 0.4779,
+      "step": 224
+    },
+    {
+      "epoch": 2.319587628865979,
+      "grad_norm": 8.752834623859673,
+      "learning_rate": 6.458697358801061e-07,
+      "loss": 0.4756,
+      "step": 225
+    },
+    {
+      "epoch": 2.329896907216495,
+      "grad_norm": 9.898712660194837,
+      "learning_rate": 6.273031531358034e-07,
+      "loss": 0.4821,
+      "step": 226
+    },
+    {
+      "epoch": 2.3402061855670104,
+      "grad_norm": 10.040266601548774,
+      "learning_rate": 6.089689855854869e-07,
+      "loss": 0.4922,
+      "step": 227
+    },
+    {
+      "epoch": 2.350515463917526,
+      "grad_norm": 8.965499873865442,
+      "learning_rate": 5.908695086316701e-07,
+      "loss": 0.4953,
+      "step": 228
+    },
+    {
+      "epoch": 2.3608247422680413,
+      "grad_norm": 7.950737195653351,
+      "learning_rate": 5.730069685500669e-07,
+      "loss": 0.4983,
+      "step": 229
+    },
+    {
+      "epoch": 2.3711340206185567,
+      "grad_norm": 11.903188557153433,
+      "learning_rate": 5.553835822108152e-07,
+      "loss": 0.4854,
+      "step": 230
+    },
+    {
+      "epoch": 2.381443298969072,
+      "grad_norm": 8.455526352825133,
+      "learning_rate": 5.380015368033476e-07,
+      "loss": 0.49,
+      "step": 231
+    },
+    {
+      "epoch": 2.3917525773195876,
+      "grad_norm": 9.999344995027917,
+      "learning_rate": 5.20862989564947e-07,
+      "loss": 0.4923,
+      "step": 232
+    },
+    {
+      "epoch": 2.402061855670103,
+      "grad_norm": 9.5259722996865,
+      "learning_rate": 5.039700675130144e-07,
+      "loss": 0.4807,
+      "step": 233
+    },
+    {
+      "epoch": 2.4123711340206184,
+      "grad_norm": 7.4446205225882265,
+      "learning_rate": 4.873248671810929e-07,
+      "loss": 0.4855,
+      "step": 234
+    },
+    {
+      "epoch": 2.422680412371134,
+      "grad_norm": 8.216411301343888,
+      "learning_rate": 4.7092945435867205e-07,
+      "loss": 0.4598,
+      "step": 235
+    },
+    {
+      "epoch": 2.4329896907216497,
+      "grad_norm": 9.208869423659547,
+      "learning_rate": 4.547858638348107e-07,
+      "loss": 0.5051,
+      "step": 236
+    },
+    {
+      "epoch": 2.443298969072165,
+      "grad_norm": 9.70808242233489,
+      "learning_rate": 4.388960991455998e-07,
+      "loss": 0.4822,
+      "step": 237
+    },
+    {
+      "epoch": 2.4536082474226806,
+      "grad_norm": 9.645304874804616,
+      "learning_rate": 4.23262132325514e-07,
+      "loss": 0.461,
+      "step": 238
+    },
+    {
+      "epoch": 2.463917525773196,
+      "grad_norm": 9.228997796596868,
+      "learning_rate": 4.0788590366266754e-07,
+      "loss": 0.4737,
+      "step": 239
+    },
+    {
+      "epoch": 2.4742268041237114,
+      "grad_norm": 7.779464578125827,
+      "learning_rate": 3.927693214580075e-07,
+      "loss": 0.4784,
+      "step": 240
+    },
+    {
+      "epoch": 2.484536082474227,
+      "grad_norm": 7.548505713522384,
+      "learning_rate": 3.7791426178848235e-07,
+      "loss": 0.4996,
+      "step": 241
+    },
+    {
+      "epoch": 2.4948453608247423,
+      "grad_norm": 7.480983276201638,
+      "learning_rate": 3.633225682742053e-07,
+      "loss": 0.452,
+      "step": 242
+    },
+    {
+      "epoch": 2.5051546391752577,
+      "grad_norm": 9.60264825850974,
+      "learning_rate": 3.489960518496521e-07,
+      "loss": 0.4875,
+      "step": 243
+    },
+    {
+      "epoch": 2.515463917525773,
+      "grad_norm": 8.226938092387504,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 0.4689,
+      "step": 244
+    },
+    {
+      "epoch": 2.5257731958762886,
+      "grad_norm": 10.802468293312753,
+      "learning_rate": 3.2114562923498765e-07,
+      "loss": 0.4757,
+      "step": 245
+    },
+    {
+      "epoch": 2.536082474226804,
+      "grad_norm": 9.606058084808302,
+      "learning_rate": 3.076251794833213e-07,
+      "loss": 0.4963,
+      "step": 246
+    },
+    {
+      "epoch": 2.5463917525773194,
+      "grad_norm": 9.436856481578294,
+      "learning_rate": 2.9437681926929583e-07,
+      "loss": 0.4452,
+      "step": 247
+    },
+    {
+      "epoch": 2.556701030927835,
+      "grad_norm": 9.725834168890692,
+      "learning_rate": 2.8140219281002717e-07,
+      "loss": 0.4968,
+      "step": 248
+    },
+    {
+      "epoch": 2.5670103092783503,
+      "grad_norm": 9.488327886875917,
+      "learning_rate": 2.6870291035029724e-07,
+      "loss": 0.4682,
+      "step": 249
+    },
+    {
+      "epoch": 2.5773195876288657,
+      "grad_norm": 9.82180209155548,
+      "learning_rate": 2.5628054796271064e-07,
+      "loss": 0.4688,
+      "step": 250
+    },
+    {
+      "epoch": 2.5876288659793816,
+      "grad_norm": 9.093873747412966,
+      "learning_rate": 2.441366473520909e-07,
+      "loss": 0.4852,
+      "step": 251
+    },
+    {
+      "epoch": 2.597938144329897,
+      "grad_norm": 7.449464038797156,
+      "learning_rate": 2.3227271566414827e-07,
+      "loss": 0.4805,
+      "step": 252
+    },
+    {
+      "epoch": 2.6082474226804124,
+      "grad_norm": 10.772309684780893,
+      "learning_rate": 2.2069022529842664e-07,
+      "loss": 0.4902,
+      "step": 253
+    },
+    {
+      "epoch": 2.618556701030928,
+      "grad_norm": 10.691112242486527,
+      "learning_rate": 2.0939061372557136e-07,
+      "loss": 0.5194,
+      "step": 254
+    },
+    {
+      "epoch": 2.6288659793814433,
+      "grad_norm": 10.964675015957674,
+      "learning_rate": 1.9837528330892781e-07,
+      "loss": 0.4933,
+      "step": 255
+    },
+    {
+      "epoch": 2.6391752577319587,
+      "grad_norm": 7.146996257972618,
+      "learning_rate": 1.876456011305003e-07,
+      "loss": 0.4736,
+      "step": 256
+    },
+    {
+      "epoch": 2.649484536082474,
+      "grad_norm": 8.527751722375397,
+      "learning_rate": 1.7720289882128095e-07,
+      "loss": 0.4789,
+      "step": 257
+    },
+    {
+      "epoch": 2.6597938144329896,
+      "grad_norm": 9.492478053037697,
+      "learning_rate": 1.6704847239599364e-07,
+      "loss": 0.4701,
+      "step": 258
+    },
+    {
+      "epoch": 2.670103092783505,
+      "grad_norm": 10.196087733936238,
+      "learning_rate": 1.5718358209224155e-07,
+      "loss": 0.4562,
+      "step": 259
+    },
+    {
+      "epoch": 2.680412371134021,
+      "grad_norm": 10.20078352368436,
+      "learning_rate": 1.4760945221410638e-07,
+      "loss": 0.499,
+      "step": 260
+    },
+    {
+      "epoch": 2.6907216494845363,
+      "grad_norm": 9.305265548008038,
+      "learning_rate": 1.3832727098020333e-07,
+      "loss": 0.4913,
+      "step": 261
+    },
+    {
+      "epoch": 2.7010309278350517,
+      "grad_norm": 8.908621703126363,
+      "learning_rate": 1.2933819037621227e-07,
+      "loss": 0.4843,
+      "step": 262
+    },
+    {
+      "epoch": 2.711340206185567,
+      "grad_norm": 9.697082505509188,
+      "learning_rate": 1.2064332601191163e-07,
+      "loss": 0.4572,
+      "step": 263
+    },
+    {
+      "epoch": 2.7216494845360826,
+      "grad_norm": 7.970433913687569,
+      "learning_rate": 1.1224375698271894e-07,
+      "loss": 0.4756,
+      "step": 264
+    },
+    {
+      "epoch": 2.731958762886598,
+      "grad_norm": 8.87972810552369,
+      "learning_rate": 1.0414052573577137e-07,
+      "loss": 0.459,
+      "step": 265
+    },
+    {
+      "epoch": 2.7422680412371134,
+      "grad_norm": 8.46520426378118,
+      "learning_rate": 9.633463794054776e-08,
+      "loss": 0.4698,
+      "step": 266
+    },
+    {
+      "epoch": 2.752577319587629,
+      "grad_norm": 8.323482285728723,
+      "learning_rate": 8.882706236405886e-08,
+      "loss": 0.4617,
+      "step": 267
+    },
+    {
+      "epoch": 2.7628865979381443,
+      "grad_norm": 9.704235560062203,
+      "learning_rate": 8.1618730750615e-08,
+      "loss": 0.4627,
+      "step": 268
+    },
+    {
+      "epoch": 2.7731958762886597,
+      "grad_norm": 8.52883239697346,
+      "learning_rate": 7.471053770619352e-08,
+      "loss": 0.4473,
+      "step": 269
+    },
+    {
+      "epoch": 2.783505154639175,
+      "grad_norm": 9.049891046532084,
+      "learning_rate": 6.810334058740736e-08,
+      "loss": 0.512,
+      "step": 270
+    },
+    {
+      "epoch": 2.7938144329896906,
+      "grad_norm": 9.351205154513341,
+      "learning_rate": 6.179795939510264e-08,
+      "loss": 0.4642,
+      "step": 271
+    },
+    {
+      "epoch": 2.804123711340206,
+      "grad_norm": 9.158307466016296,
+      "learning_rate": 5.5795176672591714e-08,
+      "loss": 0.4471,
+      "step": 272
+    },
+    {
+      "epoch": 2.8144329896907214,
+      "grad_norm": 7.714445945044509,
+      "learning_rate": 5.009573740853313e-08,
+      "loss": 0.4613,
+      "step": 273
+    },
+    {
+      "epoch": 2.824742268041237,
+      "grad_norm": 10.072671050292586,
+      "learning_rate": 4.4700348944471946e-08,
+      "loss": 0.4608,
+      "step": 274
+    },
+    {
+      "epoch": 2.8350515463917527,
+      "grad_norm": 9.221620067665079,
+      "learning_rate": 3.9609680887055247e-08,
+      "loss": 0.4601,
+      "step": 275
+    },
+    {
+      "epoch": 2.845360824742268,
+      "grad_norm": 9.452260581603698,
+      "learning_rate": 3.4824365024928585e-08,
+      "loss": 0.467,
+      "step": 276
+    },
+    {
+      "epoch": 2.8556701030927836,
+      "grad_norm": 10.946772367065448,
+      "learning_rate": 3.034499525032625e-08,
+      "loss": 0.4567,
+      "step": 277
+    },
+    {
+      "epoch": 2.865979381443299,
+      "grad_norm": 8.94754765333994,
+      "learning_rate": 2.6172127485364905e-08,
+      "loss": 0.4738,
+      "step": 278
+    },
+    {
+      "epoch": 2.8762886597938144,
+      "grad_norm": 8.822797237760415,
+      "learning_rate": 2.230627961304993e-08,
+      "loss": 0.4521,
+      "step": 279
+    },
+    {
+      "epoch": 2.88659793814433,
+      "grad_norm": 8.953604746908766,
+      "learning_rate": 1.8747931413001795e-08,
+      "loss": 0.4849,
+      "step": 280
+    },
+    {
+      "epoch": 2.8969072164948453,
+      "grad_norm": 8.1573186298565,
+      "learning_rate": 1.5497524501913163e-08,
+      "loss": 0.4743,
+      "step": 281
+    },
+    {
+      "epoch": 2.9072164948453607,
+      "grad_norm": 7.678394662843834,
+      "learning_rate": 1.255546227873966e-08,
+      "loss": 0.4394,
+      "step": 282
+    },
+    {
+      "epoch": 2.917525773195876,
+      "grad_norm": 10.108055724388532,
+      "learning_rate": 9.922109874636875e-09,
+      "loss": 0.4715,
+      "step": 283
+    },
+    {
+      "epoch": 2.927835051546392,
+      "grad_norm": 8.599838042397586,
+      "learning_rate": 7.597794107641887e-09,
+      "loss": 0.4954,
+      "step": 284
+    },
+    {
+      "epoch": 2.9381443298969074,
+      "grad_norm": 9.481046139581798,
+      "learning_rate": 5.582803442117091e-09,
+      "loss": 0.4657,
+      "step": 285
+    },
+    {
+      "epoch": 2.948453608247423,
+      "grad_norm": 9.453713340420872,
+      "learning_rate": 3.877387952945788e-09,
+      "loss": 0.4788,
+      "step": 286
+    },
+    {
+      "epoch": 2.9587628865979383,
+      "grad_norm": 8.763446611978422,
+      "learning_rate": 2.4817592944983983e-09,
+      "loss": 0.4363,
+      "step": 287
+    },
+    {
+      "epoch": 2.9690721649484537,
+      "grad_norm": 9.418576702303165,
+      "learning_rate": 1.3960906743634706e-09,
+      "loss": 0.4728,
+      "step": 288
+    },
+    {
+      "epoch": 2.979381443298969,
+      "grad_norm": 7.824055175290262,
+      "learning_rate": 6.205168318523802e-10,
+      "loss": 0.4648,
+      "step": 289
+    },
+    {
+      "epoch": 2.9896907216494846,
+      "grad_norm": 10.036077270769853,
+      "learning_rate": 1.5513402127603772e-10,
+      "loss": 0.4502,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.520420413311138,
+      "learning_rate": 0.0,
+      "loss": 0.4383,
+      "step": 291
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 291,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 5000.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 15989412249600.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108575f53862cfd7098e267ef79a782f77a5af4433664ec43f161b1c316518cb
+size 7480