Add files using upload-large-folder tool

config.json

@@ -0,0 +1,85 @@
+{
+  "activation_type": "silu",
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "architectures": [
+    "LlavaLladaForMaskedDiffusion"
+  ],
+  "attention_dropout": 0.0,
+  "attention_layer_norm": false,
+  "attention_layer_norm_with_affine": true,
+  "auto_map": {
+    "AutoConfig": "configuration_llada.LLaDAConfig",
+    "AutoModel": "modeling_llada.LLaDAModelLM",
+    "AutoModelForCausalLM": "modeling_llada.LLaDAModelLM"
+  },
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "llama",
+  "d_model": 4096,
+  "embedding_dropout": 0.0,
+  "embedding_size": 126464,
+  "eos_token_id": 126081,
+  "faster_token_stride": 10,
+  "flash_attention": false,
+  "force_sample": false,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "include_bias": false,
+  "include_qkv_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "meta",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "input_emb_norm": false,
+  "layer_norm_type": "rms",
+  "layer_norm_with_affine": true,
+  "mask_token_id": 126336,
+  "max_sequence_length": 4096,
+  "mlp_hidden_size": 12288,
+  "mlp_ratio": 4,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_pooler_ratio": 2,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
+  "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": "/data/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llada",
+  "multi_query_attention": null,
+  "n_heads": 32,
+  "n_kv_heads": 32,
+  "n_layers": 32,
+  "pad_token_id": 126081,
+  "pos_skipping_range": 4096,
+  "precision": "amp_bf16",
+  "resampler_type": null,
+  "residual_dropout": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope": true,
+  "rope_full_precision": true,
+  "rope_theta": 500000.0,
+  "scale_logits": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 126464,
+  "weight_tying": false
+}

configuration_llada.py

@@ -0,0 +1,463 @@
+"""
+LLaDA configuration
+"""
+from transformers import AutoConfig, PretrainedConfig
+
+from enum import Enum
+from os import PathLike
+from typing import Union
+from dataclasses import asdict, dataclass, field
+from glob import glob
+from pathlib import Path
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    List,
+    Optional,
+    Tuple,
+    Type,
+    TypeVar,
+    Union,
+    cast,
+)
+
+
+__all__ = [
+    "ActivationType",
+    "ActivationCheckpointingStrategy",
+    "BlockType",
+    "LayerNormType",
+    "InitFnType",
+    "ModelConfig",
+]
+
+PathOrStr = Union[str, PathLike]
+
+
+class StrEnum(str, Enum):
+    """
+    This is equivalent to Python's :class:`enum.StrEnum` since version 3.11.
+    We include this here for compatibility with older version of Python.
+    """
+
+    def __str__(self) -> str:
+        return self.value
+
+    def __repr__(self) -> str:
+        return f"'{str(self)}'"
+
+
+class LayerNormType(StrEnum):
+    default = "default"
+    """
+    The default LayerNorm implementation, equivalent to PyTorch's built-in version.
+    """
+
+    low_precision = "low_precision"
+    """
+    A low-precision version of the default LayerNorm.
+    """
+
+    rms = "rms"
+    """
+    An RMSNorm implementation. When using ``torch.compile`` this is
+    probably the fastest implementation.
+    """
+
+    gemma_rms = "gemma_rms"
+    """
+    An RMSNorm implementation by gemmma. When using ``torch.compile`` this is
+    probably the fastest implementation.
+    """
+
+    amd_compatible = "amd_compatible"
+    """
+    LayerNorm implemented manually to work around an issue with ROCm.
+    """
+
+
+class ActivationType(StrEnum):
+    gelu = "gelu"
+    relu = "relu"
+    silu = "silu"
+    swiglu = "swiglu"
+
+
+class BlockType(StrEnum):
+    sequential = "sequential"
+    parallel = "parallel"
+
+    llama = "llama"
+    """
+    A block similar to the sequential block with slightly different
+    implementations of operations like attention to imitate the behavior of Llama.
+    """
+
+
+class InitFnType(StrEnum):
+    mitchell = "mitchell"
+    """
+    The strategy suggested to us by Mitchell Wortsman from UW.
+    This uses a truncated normal distribution with an adaptive standard deviation that depends
+    on the size of the weights as well as the depth of the layer.
+    """
+
+    normal = "normal"
+    """
+    All weights are initialized from the same normal distribution.
+    """
+
+    kaiming_normal = "kaiming_normal"
+    """
+    All weights are initialized with the Kaiming method from a normal distribution.
+    Note this currently won't work with FSDP.
+    """
+
+    fan_in = "fan_in"
+    """
+    "Fan-in variance scaling", i.e. normal with a standard deviation of ``1/sqrt(d_in)`` where ``d_in``
+    is the input dimensionality of the kernel.
+    """
+
+    full_megatron = "full_megatron"
+    """
+    This is what metaseq calls "full megatron init". It is the init used for Llama 2.
+    """
+
+
+@dataclass
+class ModelConfig():
+    """
+    LLaDA (model) configuration.
+    """
+
+    # Note that the defaults for these attributes are equivalent to the base GPT2 model.
+
+    d_model: int = 768
+    """
+    The hidden size of the model.
+    """
+
+    n_heads: int = 12
+    """
+    The number of self-attention heads.
+    """
+
+    n_kv_heads: Optional[int] = None
+    """
+    The number of heads to use for keys and values. Defaults to `n_heads`.
+    Set this to ``None`` or ``n_heads`` for normal multi-head attention.
+    Set this to 1 for multi-query attention.
+    Set it to some in-between value for Llama2-style grouped query attention.
+    """
+
+    n_layers: int = 12
+    """
+    The number of layers/blocks.
+    """
+
+    mlp_ratio: int = 4
+    """
+    The ratio of the inner MLP dimensionality to ``d_model``.
+    This is only used when ``mlp_hidden_size`` is not set.
+    """
+
+    mlp_hidden_size: Optional[int] = None
+    """
+    Set the exact hidden size for the MLP. Otherwise the inner MLP hidden size will be set to `mlp_ratio * d_model`.
+    """
+
+    activation_type: ActivationType = ActivationType.swiglu
+    """
+    The activation function to use within the MLP layers.
+    """
+
+    block_type: BlockType = BlockType.sequential
+    """
+    The transformer block implementation.
+    """
+
+    block_group_size: int = 1
+    """
+    The number of blocks to group together into a single parent block.
+    This has no affect on the number of parameters in the model and is only used to wrap groups
+    of blocks together with a single FSDP wrapper during training.
+    """
+
+    alibi: bool = False
+    """
+    If ``True``, use ALiBi embeddings. Mutually exclusive with ``rope``.
+    """
+
+    alibi_bias_max: float = 8.0
+    """
+    Maximum absolute value of ALiBi bias.
+    """
+
+    rope: bool = False
+    """
+    Use rotary positional embeddings (RoPE). Mutually exclusive with ``alibi``.
+    """
+
+    rope_full_precision: bool = True
+    """
+    If ``True``, apply RoPE embeddings at full precision regardless of the input type. Otherwise,
+    apply RoPE at the precision of the input.
+    """
+
+    flash_attention: bool = False
+    """
+    If ``True``, use ``FlashAttention``.
+    """
+
+    attention_dropout: float = 0.1
+    """
+    The dropout probability within the attention modules.
+    """
+
+    multi_query_attention: Optional[bool] = None
+    """
+    Use the Multi-Query formulation of attention used in PaLM. This reduces the number of parameters
+    and is more efficient during inference.
+    """
+
+    attention_layer_norm: bool = False
+    """
+    Apply layer norm to the keys and queries within the attention mechanism.
+    This can help stabilize training.
+    """
+
+    residual_dropout: float = 0.1
+    """
+    The dropout probability for the MLP and attention output within each block.
+    """
+
+    embedding_dropout: float = 0.1
+    """
+    The dropout probability for embeddings.
+    """
+
+    input_emb_norm: bool = False
+    """
+    An input hidden_states norm implementation by gemmma.
+    """
+
+    layer_norm_type: LayerNormType = LayerNormType.default
+    """
+    The layernorm implementation to use.
+    """
+
+    layer_norm_with_affine: bool = True
+    """
+    Whether to include bias and weight parameters for the layer norms.
+    This only affects layer norms that are immediately followed by a linear layer in the forward pass,
+    so everything except QK-norms. To turn off affines for QK norms as well, set :attr:`attention_layer_norm_with_affine`
+    to ``False``.
+    """
+
+    rms_norm_eps: float = 1e-05
+    """
+    The rms layernorm eps param.
+    """
+
+    attention_layer_norm_with_affine: bool = True
+    """
+    Toggle affine transform for the QK norms.
+    """
+
+    max_sequence_length: int = 1024
+    """
+    The maximum input sequence length supported by the model.
+    """
+
+    rope_theta: float = 10000.0
+    """
+    The rope base param.
+    """
+
+    include_qkv_bias: Optional[bool] = False
+    """
+    Whether or not to include bias parameters in qkv linear layers.
+    """
+
+    include_bias: bool = False
+    """
+    Whether or not to include bias parameters in linear layers.
+    In PaLM, they got rid of all bias terms because they found that large
+    models tend to have near 0 bias terms anyway.
+    """
+
+    bias_for_layer_norm: Optional[bool] = None
+    """
+    Whether or not to include bias parameters in layer norm.
+    This is separate from the include_bias parameter, because of a ROCm crash when biases are disabled in
+    layer norm.
+    When this is None (the default), it inherits the setting from include_bias.
+    """
+
+    scale_logits: bool = False
+    """
+    If ``True``, scale the output logits by ``1 / sqrt(d_model)``.
+    """
+
+    vocab_size: int = 50257
+    """
+    Vocabulary size of the model.
+    """
+
+    embedding_size: Optional[int] = 50304
+    """
+    The number of embeddings, i.e. the number of tokens. If set to ``None`` it will default
+    to ``vocab_size``. If ``vocab_size`` is not a multiple of 128, setting this to the
+    next multiple of 128 that's greater than ``vocab_size`` can improve throughput
+    substantially.
+    """
+
+    weight_tying: bool = True
+    """
+    Whether to tie output linear weights to the input embedding.
+    """
+
+    eos_token_id: int = 50256
+    """
+    The ID of the end-of-sentence special token.
+    """
+
+    pad_token_id: int = 50256
+    """
+    The ID of the token to use for padding. Defaults to the ID of the EOS token.
+    """
+
+    mask_token_id: Optional[int] = 50256
+    """
+    The ID of the token to use for mask token. Defaults to the ID of the EOS token.
+    """
+
+    init_device: Optional[str] = None
+    """
+    The torch device to use when initializing the model parameters, e.g. "cpu", "cuda:0", "meta".
+    """
+
+    init_fn: InitFnType = InitFnType.normal
+    """
+    The weight initialization strategy.
+    """
+
+    init_std: float = 0.02
+    """
+    The standard deviation to use when initializing weights with a "fixed distribution" ``init_fn``, such
+    as "normal".
+    """
+
+    init_cutoff_factor: Optional[float] = None
+    """
+    A positive factor used to scale the cutoff values when initializing weights with a "fixed distribution" ``init_fn``, such
+    as "normal". Setting this to None means values are not cutoff.
+    """
+
+    precision: Optional[str] = None
+    """
+    Precision used to train/evaluate with. You shouldn't set this directly.
+    See :data:`TrainConfig.precision` instead.
+    """
+
+    @property
+    def effective_n_kv_heads(self) -> int:
+        if self.n_kv_heads is None:
+            if self.multi_query_attention is True:
+                return 1
+            else:
+                return self.n_heads
+        else:
+            if self.multi_query_attention is None:
+                return self.n_kv_heads
+            if self.multi_query_attention:
+                n_kv_heads_should_be = 1
+            else:
+                n_kv_heads_should_be = self.n_heads
+            if self.n_kv_heads == n_kv_heads_should_be:
+                return n_kv_heads_should_be
+            else:
+                raise Exception(
+                    "You can't set `multi_query_attention` and `n_kv_heads` at the same time."
+                )
+
+class ActivationCheckpointingStrategy(StrEnum):
+    whole_layer = "whole_layer"
+    """
+    Checkpoint every transformer layer.
+    """
+
+    one_in_two = "one_in_two"
+    """
+    Checkpoint one in two transformer layers.
+    """
+
+    one_in_three = "one_in_three"
+    """
+    Checkpoint one in three transformer layers.
+    """
+
+    one_in_four = "one_in_four"
+    """
+    Checkpoint one in four transformer layers.
+    """
+    
+    two_in_three = "two_in_three"
+    """
+    Checkpoint two out of every three transformer layers.
+    """
+
+    three_in_four = "three_in_four"
+    """
+    Checkpoint three out of four of every transformer layers.
+    """
+
+    four_in_five = "four_in_five"
+    """
+    Checkpoint four out of five of every transformer layers.
+    """
+
+    nine_in_ten = "nine_in_ten"
+    """
+    Checkpoint nine out of ten of every transformer layers.
+    """
+
+    fine_grained = "fine_grained"
+    """
+    Focus checkpointing on where it is cheap to recompute and saves most memory.
+    """
+
+
+class LLaDAConfig(PretrainedConfig):
+    model_type = "llada"
+    keys_to_ignore_at_inference = ["past_key_values"]  # TODO: confirm
+
+    def __init__(self, use_cache: bool = False, **kwargs):
+        model_config = ModelConfig()
+        all_kwargs = model_config.__dict__
+        all_kwargs.update(kwargs)
+        all_kwargs.update({"use_cache": use_cache})
+        all_kwargs.update(
+            {
+                "architectures": all_kwargs.get("architectures", ["LLaDAModelLM"])
+            }
+        )
+        super().__init__(**all_kwargs)
+
+    @property
+    def num_attention_heads(self):
+        return self.n_heads
+
+    @property
+    def num_hidden_layers(self):
+        return self.n_layers
+
+    @property
+    def hidden_size(self):
+        return self.d_model
+
+
+# Register the config class so that it is available for transformer pipelines, auto-loading etc.
+AutoConfig.register("llada", LLaDAConfig)

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 126080,
+  "eos_token_id": 126081,
+  "transformers_version": "4.50.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff076387fed310be2055905e7c3141f4218bfaf3b4c5c2da1594b539fa7a6d8
+size 4995589944

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b3979a8abbdc8bce258ea67cf9d97cee2e21e07a00790b3bc2008a178c09d9
+size 4999819552

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb706f8125d1c0a6871f49fca65651001f5214928810768e7580fb4bae13c561
+size 4999802728

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b1306483e24248a2ebb355f7a5647987505d937b3784786c3a935e4ea91243
+size 1874563264

model.safetensors.index.json

@@ -0,0 +1,724 @@
+{
+  "metadata": {
+    "total_size": 16869674048
+  },
+  "weight_map": {
+    "model.image_newline": "model-00001-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
+    "model.transformer.blocks.0.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.10.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.2.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.20.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.21.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.3.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.30.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.4.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.9.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.ff_out.weight": "model-00004-of-00004.safetensors",
+    "model.transformer.ln_f.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.wte.weight": "model-00001-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<role>",
+    "</role>",
+    "<|arithmetic_start|>",
+    "<|arithmetic_end|>",
+    "<|number_start|>",
+    "<|number_end|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2184 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "126080": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126081": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126082": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126083": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126084": {
+      "content": "<|reserved_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126085": {
+      "content": "<|reserved_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126086": {
+      "content": "<|reserved_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126087": {
+      "content": "<|reserved_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126088": {
+      "content": "<|reserved_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126089": {
+      "content": "<|reserved_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126090": {
+      "content": "<|reserved_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126091": {
+      "content": "<|reserved_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126092": {
+      "content": "<|reserved_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126093": {
+      "content": "<|reserved_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126094": {
+      "content": "<|reserved_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126095": {
+      "content": "<|reserved_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126096": {
+      "content": "<|reserved_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126097": {
+      "content": "<|reserved_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126098": {
+      "content": "<|reserved_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126099": {
+      "content": "<|reserved_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126100": {
+      "content": "<|reserved_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126101": {
+      "content": "<|reserved_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126102": {
+      "content": "<|reserved_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126103": {
+      "content": "<|reserved_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126104": {
+      "content": "<|reserved_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126105": {
+      "content": "<|reserved_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126106": {
+      "content": "<|reserved_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126107": {
+      "content": "<|reserved_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126108": {
+      "content": "<|reserved_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126109": {
+      "content": "<|reserved_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126110": {
+      "content": "<|reserved_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126111": {
+      "content": "<|reserved_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126112": {
+      "content": "<|reserved_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126113": {
+      "content": "<|reserved_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126114": {
+      "content": "<|reserved_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126115": {
+      "content": "<|reserved_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126116": {
+      "content": "<|reserved_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126117": {
+      "content": "<|reserved_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126118": {
+      "content": "<|reserved_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126119": {
+      "content": "<|reserved_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126120": {
+      "content": "<|reserved_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126121": {
+      "content": "<|reserved_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126122": {
+      "content": "<|reserved_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126123": {
+      "content": "<|reserved_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126124": {
+      "content": "<|reserved_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126125": {
+      "content": "<|reserved_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126126": {
+      "content": "<|reserved_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126127": {
+      "content": "<|reserved_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126128": {
+      "content": "<|reserved_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126129": {
+      "content": "<|reserved_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126130": {
+      "content": "<|reserved_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126131": {
+      "content": "<|reserved_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126132": {
+      "content": "<|reserved_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126133": {
+      "content": "<|reserved_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126134": {
+      "content": "<|reserved_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126135": {
+      "content": "<|reserved_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126136": {
+      "content": "<|reserved_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126137": {
+      "content": "<|reserved_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126138": {
+      "content": "<|reserved_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126139": {
+      "content": "<|reserved_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126140": {
+      "content": "<|reserved_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126141": {
+      "content": "<|reserved_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126142": {
+      "content": "<|reserved_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126143": {
+      "content": "<|reserved_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126144": {
+      "content": "<|reserved_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126145": {
+      "content": "<|reserved_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126146": {
+      "content": "<|reserved_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126147": {
+      "content": "<|reserved_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126148": {
+      "content": "<|reserved_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126149": {
+      "content": "<|reserved_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126150": {
+      "content": "<|reserved_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126151": {
+      "content": "<|reserved_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126152": {
+      "content": "<|reserved_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126153": {
+      "content": "<|reserved_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126154": {
+      "content": "<|reserved_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126155": {
+      "content": "<|reserved_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126156": {
+      "content": "<|reserved_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126157": {
+      "content": "<|reserved_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126158": {
+      "content": "<|reserved_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126159": {
+      "content": "<|reserved_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126160": {
+      "content": "<|reserved_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126161": {
+      "content": "<|reserved_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126162": {
+      "content": "<|reserved_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126163": {
+      "content": "<|reserved_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126164": {
+      "content": "<|reserved_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126165": {
+      "content": "<|reserved_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126166": {
+      "content": "<|reserved_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126167": {
+      "content": "<|reserved_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126168": {
+      "content": "<|reserved_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126169": {
+      "content": "<|reserved_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126170": {
+      "content": "<|reserved_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126171": {
+      "content": "<|reserved_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126172": {
+      "content": "<|reserved_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126173": {
+      "content": "<|reserved_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126174": {
+      "content": "<|reserved_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126175": {
+      "content": "<|reserved_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126176": {
+      "content": "<|reserved_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126177": {
+      "content": "<|reserved_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126178": {
+      "content": "<|reserved_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126179": {
+      "content": "<|reserved_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126180": {
+      "content": "<|reserved_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126181": {
+      "content": "<|reserved_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126182": {
+      "content": "<|reserved_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126183": {
+      "content": "<|reserved_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126184": {
+      "content": "<|reserved_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126185": {
+      "content": "<|reserved_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126186": {
+      "content": "<|reserved_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126187": {
+      "content": "<|reserved_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126188": {
+      "content": "<|reserved_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126189": {
+      "content": "<|reserved_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126190": {
+      "content": "<|reserved_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126191": {
+      "content": "<|reserved_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126192": {
+      "content": "<|reserved_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126193": {
+      "content": "<|reserved_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126194": {
+      "content": "<|reserved_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126195": {
+      "content": "<|reserved_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126196": {
+      "content": "<|reserved_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126197": {
+      "content": "<|reserved_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126198": {
+      "content": "<|reserved_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126199": {
+      "content": "<|reserved_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126200": {
+      "content": "<|reserved_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126201": {
+      "content": "<|reserved_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126202": {
+      "content": "<|reserved_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126203": {
+      "content": "<|reserved_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126204": {
+      "content": "<|reserved_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126205": {
+      "content": "<|reserved_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126206": {
+      "content": "<|reserved_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126207": {
+      "content": "<|reserved_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126208": {
+      "content": "<|reserved_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126209": {
+      "content": "<|reserved_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126210": {
+      "content": "<|reserved_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126211": {
+      "content": "<|reserved_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126212": {
+      "content": "<|reserved_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126213": {
+      "content": "<|reserved_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126214": {
+      "content": "<|reserved_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126215": {
+      "content": "<|reserved_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126216": {
+      "content": "<|reserved_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126217": {
+      "content": "<|reserved_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126218": {
+      "content": "<|reserved_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126219": {
+      "content": "<|reserved_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126220": {
+      "content": "<|reserved_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126221": {
+      "content": "<|reserved_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126222": {
+      "content": "<|reserved_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126223": {
+      "content": "<|reserved_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126224": {
+      "content": "<|reserved_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126225": {
+      "content": "<|reserved_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126226": {
+      "content": "<|reserved_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126227": {
+      "content": "<|reserved_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126228": {
+      "content": "<|reserved_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126229": {
+      "content": "<|reserved_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126230": {
+      "content": "<|reserved_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126231": {
+      "content": "<|reserved_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126232": {
+      "content": "<|reserved_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126233": {
+      "content": "<|reserved_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126234": {
+      "content": "<|reserved_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126235": {
+      "content": "<|reserved_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126236": {
+      "content": "<|reserved_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126237": {
+      "content": "<|reserved_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126238": {
+      "content": "<|reserved_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126239": {
+      "content": "<|reserved_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126240": {
+      "content": "<|reserved_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126241": {
+      "content": "<|reserved_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126242": {
+      "content": "<|reserved_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126243": {
+      "content": "<|reserved_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126244": {
+      "content": "<|reserved_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126245": {
+      "content": "<|reserved_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126246": {
+      "content": "<|reserved_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126247": {
+      "content": "<|reserved_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126248": {
+      "content": "<|reserved_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126249": {
+      "content": "<|reserved_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126250": {
+      "content": "<|reserved_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126251": {
+      "content": "<|reserved_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126252": {
+      "content": "<|reserved_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126253": {
+      "content": "<|reserved_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126254": {
+      "content": "<|reserved_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126255": {
+      "content": "<|reserved_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126256": {
+      "content": "<|reserved_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126257": {
+      "content": "<|reserved_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126258": {
+      "content": "<|reserved_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126259": {
+      "content": "<|reserved_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126260": {
+      "content": "<|reserved_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126261": {
+      "content": "<|reserved_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126262": {
+      "content": "<|reserved_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126263": {
+      "content": "<|reserved_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126264": {
+      "content": "<|reserved_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126265": {
+      "content": "<|reserved_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126266": {
+      "content": "<|reserved_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126267": {
+      "content": "<|reserved_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126268": {
+      "content": "<|reserved_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126269": {
+      "content": "<|reserved_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126270": {
+      "content": "<|reserved_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126271": {
+      "content": "<|reserved_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126272": {
+      "content": "<|reserved_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126273": {
+      "content": "<|reserved_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126274": {
+      "content": "<|reserved_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126275": {
+      "content": "<|reserved_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126276": {
+      "content": "<|reserved_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126277": {
+      "content": "<|reserved_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126278": {
+      "content": "<|reserved_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126279": {
+      "content": "<|reserved_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126280": {
+      "content": "<|reserved_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126281": {
+      "content": "<|reserved_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126282": {
+      "content": "<|reserved_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126283": {
+      "content": "<|reserved_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126284": {
+      "content": "<|reserved_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126285": {
+      "content": "<|reserved_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126286": {
+      "content": "<|reserved_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126287": {
+      "content": "<|reserved_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126288": {
+      "content": "<|reserved_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126289": {
+      "content": "<|reserved_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126290": {
+      "content": "<|reserved_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126291": {
+      "content": "<|reserved_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126292": {
+      "content": "<|reserved_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126293": {
+      "content": "<|reserved_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126294": {
+      "content": "<|reserved_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126295": {
+      "content": "<|reserved_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126296": {
+      "content": "<|reserved_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126297": {
+      "content": "<|reserved_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126298": {
+      "content": "<|reserved_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126299": {
+      "content": "<|reserved_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126300": {
+      "content": "<|reserved_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126301": {
+      "content": "<|reserved_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126302": {
+      "content": "<|reserved_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126303": {
+      "content": "<|reserved_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126304": {
+      "content": "<|reserved_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126305": {
+      "content": "<|reserved_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126306": {
+      "content": "<|reserved_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126307": {
+      "content": "<|reserved_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126308": {
+      "content": "<|reserved_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126309": {
+      "content": "<|reserved_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126310": {
+      "content": "<|reserved_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126311": {
+      "content": "<|reserved_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126312": {
+      "content": "<|reserved_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126313": {
+      "content": "<|reserved_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126314": {
+      "content": "<|reserved_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126315": {
+      "content": "<|reserved_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126316": {
+      "content": "<|reserved_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126317": {
+      "content": "<|reserved_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126318": {
+      "content": "<|reserved_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126319": {
+      "content": "<|reserved_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126320": {
+      "content": "<|reserved_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126321": {
+      "content": "<|reserved_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126322": {
+      "content": "<|reserved_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126323": {
+      "content": "<|reserved_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126324": {
+      "content": "<|reserved_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126325": {
+      "content": "<|reserved_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126326": {
+      "content": "<|reserved_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126327": {
+      "content": "<|reserved_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126328": {
+      "content": "<|reserved_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126329": {
+      "content": "<|reserved_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126330": {
+      "content": "<|reserved_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126331": {
+      "content": "<|reserved_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126332": {
+      "content": "<|reserved_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126333": {
+      "content": "<|reserved_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126334": {
+      "content": "<|reserved_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126335": {
+      "content": "<|reserved_token_251|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126336": {
+      "content": "<|mdm_mask|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126337": {
+      "content": "<|reserved_token_253|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126338": {
+      "content": "<|reserved_token_254|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126339": {
+      "content": "<|reserved_token_255|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126340": {
+      "content": "<role>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126341": {
+      "content": "</role>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126342": {
+      "content": "<|arithmetic_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126343": {
+      "content": "<|arithmetic_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126344": {
+      "content": "<|number_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126345": {
+      "content": "<|number_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126346": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126347": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126348": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<role>",
+    "</role>",
+    "<|arithmetic_start|>",
+    "<|arithmetic_end|>",
+    "<|number_start|>",
+    "<|number_end|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "fast_tokenizer": true,
+  "gmask_token": "[gMASK]",
+  "merges_file": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "trust_remote_code": true
+}

trainer_state.json

@@ -0,0 +1,3781 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9873772791023843,
+  "eval_steps": 500,
+  "global_step": 534,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005610098176718092,
+      "grad_norm": 14.482704425563409,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 2.4829,
+      "step": 1
+    },
+    {
+      "epoch": 0.011220196353436185,
+      "grad_norm": 14.997611711402312,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 2.4709,
+      "step": 2
+    },
+    {
+      "epoch": 0.016830294530154277,
+      "grad_norm": 22.92634314434291,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 2.5972,
+      "step": 3
+    },
+    {
+      "epoch": 0.02244039270687237,
+      "grad_norm": 26.08298552783473,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 2.9709,
+      "step": 4
+    },
+    {
+      "epoch": 0.028050490883590462,
+      "grad_norm": 10.439925915517989,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.9377,
+      "step": 5
+    },
+    {
+      "epoch": 0.033660589060308554,
+      "grad_norm": 10.400122544958307,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 2.022,
+      "step": 6
+    },
+    {
+      "epoch": 0.03927068723702665,
+      "grad_norm": 14.00552108501915,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 2.2036,
+      "step": 7
+    },
+    {
+      "epoch": 0.04488078541374474,
+      "grad_norm": 7.983448917228911,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 1.7996,
+      "step": 8
+    },
+    {
+      "epoch": 0.05049088359046283,
+      "grad_norm": 14.607698611118,
+      "learning_rate": 1.0588235294117648e-05,
+      "loss": 1.7783,
+      "step": 9
+    },
+    {
+      "epoch": 0.056100981767180924,
+      "grad_norm": 18.30713741135737,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 2.3484,
+      "step": 10
+    },
+    {
+      "epoch": 0.061711079943899017,
+      "grad_norm": 13.136001683680378,
+      "learning_rate": 1.2941176470588238e-05,
+      "loss": 2.1121,
+      "step": 11
+    },
+    {
+      "epoch": 0.06732117812061711,
+      "grad_norm": 10.26556944471482,
+      "learning_rate": 1.4117647058823532e-05,
+      "loss": 1.6633,
+      "step": 12
+    },
+    {
+      "epoch": 0.0729312762973352,
+      "grad_norm": 20.81334203768653,
+      "learning_rate": 1.5294117647058822e-05,
+      "loss": 1.8455,
+      "step": 13
+    },
+    {
+      "epoch": 0.0785413744740533,
+      "grad_norm": 25.844425401837857,
+      "learning_rate": 1.647058823529412e-05,
+      "loss": 1.9926,
+      "step": 14
+    },
+    {
+      "epoch": 0.08415147265077139,
+      "grad_norm": 11.674830089702823,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 2.0823,
+      "step": 15
+    },
+    {
+      "epoch": 0.08976157082748948,
+      "grad_norm": 10.106380196868269,
+      "learning_rate": 1.8823529411764708e-05,
+      "loss": 1.6956,
+      "step": 16
+    },
+    {
+      "epoch": 0.09537166900420757,
+      "grad_norm": 13.239082572950917,
+      "learning_rate": 2e-05,
+      "loss": 1.6792,
+      "step": 17
+    },
+    {
+      "epoch": 0.10098176718092566,
+      "grad_norm": 14.095678950101247,
+      "learning_rate": 1.9999833838717115e-05,
+      "loss": 1.762,
+      "step": 18
+    },
+    {
+      "epoch": 0.10659186535764376,
+      "grad_norm": 10.75361523047076,
+      "learning_rate": 1.9999335361003903e-05,
+      "loss": 1.7206,
+      "step": 19
+    },
+    {
+      "epoch": 0.11220196353436185,
+      "grad_norm": 20.72078305937572,
+      "learning_rate": 1.9998504585266525e-05,
+      "loss": 1.7202,
+      "step": 20
+    },
+    {
+      "epoch": 0.11781206171107994,
+      "grad_norm": 8.174316973115733,
+      "learning_rate": 1.9997341542181152e-05,
+      "loss": 1.5443,
+      "step": 21
+    },
+    {
+      "epoch": 0.12342215988779803,
+      "grad_norm": 11.02373772633163,
+      "learning_rate": 1.9995846274692837e-05,
+      "loss": 1.7834,
+      "step": 22
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 12.907132265179525,
+      "learning_rate": 1.999401883801392e-05,
+      "loss": 1.6106,
+      "step": 23
+    },
+    {
+      "epoch": 0.13464235624123422,
+      "grad_norm": 11.666249990206644,
+      "learning_rate": 1.9991859299622017e-05,
+      "loss": 1.8916,
+      "step": 24
+    },
+    {
+      "epoch": 0.1402524544179523,
+      "grad_norm": 11.755169146289523,
+      "learning_rate": 1.9989367739257487e-05,
+      "loss": 1.4958,
+      "step": 25
+    },
+    {
+      "epoch": 0.1458625525946704,
+      "grad_norm": 14.21252914739186,
+      "learning_rate": 1.9986544248920533e-05,
+      "loss": 1.5,
+      "step": 26
+    },
+    {
+      "epoch": 0.1514726507713885,
+      "grad_norm": 9.52592172144483,
+      "learning_rate": 1.9983388932867766e-05,
+      "loss": 1.5516,
+      "step": 27
+    },
+    {
+      "epoch": 0.1570827489481066,
+      "grad_norm": 9.2197257965334,
+      "learning_rate": 1.997990190760838e-05,
+      "loss": 1.671,
+      "step": 28
+    },
+    {
+      "epoch": 0.16269284712482468,
+      "grad_norm": 9.623981436749904,
+      "learning_rate": 1.997608330189984e-05,
+      "loss": 1.7939,
+      "step": 29
+    },
+    {
+      "epoch": 0.16830294530154277,
+      "grad_norm": 9.961693725270193,
+      "learning_rate": 1.9971933256743125e-05,
+      "loss": 1.6443,
+      "step": 30
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 10.206809416567838,
+      "learning_rate": 1.9967451925377536e-05,
+      "loss": 1.6938,
+      "step": 31
+    },
+    {
+      "epoch": 0.17952314165497896,
+      "grad_norm": 17.28004161872836,
+      "learning_rate": 1.9962639473275015e-05,
+      "loss": 1.3949,
+      "step": 32
+    },
+    {
+      "epoch": 0.18513323983169705,
+      "grad_norm": 10.213936219479217,
+      "learning_rate": 1.995749607813406e-05,
+      "loss": 1.651,
+      "step": 33
+    },
+    {
+      "epoch": 0.19074333800841514,
+      "grad_norm": 10.931208369493481,
+      "learning_rate": 1.9952021929873144e-05,
+      "loss": 1.7842,
+      "step": 34
+    },
+    {
+      "epoch": 0.19635343618513323,
+      "grad_norm": 14.257442478586555,
+      "learning_rate": 1.994621723062371e-05,
+      "loss": 1.874,
+      "step": 35
+    },
+    {
+      "epoch": 0.20196353436185133,
+      "grad_norm": 11.657566039275686,
+      "learning_rate": 1.9940082194722707e-05,
+      "loss": 1.7837,
+      "step": 36
+    },
+    {
+      "epoch": 0.20757363253856942,
+      "grad_norm": 14.960516245890997,
+      "learning_rate": 1.9933617048704677e-05,
+      "loss": 1.8665,
+      "step": 37
+    },
+    {
+      "epoch": 0.2131837307152875,
+      "grad_norm": 10.898489261648411,
+      "learning_rate": 1.992682203129339e-05,
+      "loss": 1.6721,
+      "step": 38
+    },
+    {
+      "epoch": 0.2187938288920056,
+      "grad_norm": 11.367240208375325,
+      "learning_rate": 1.991969739339302e-05,
+      "loss": 1.5697,
+      "step": 39
+    },
+    {
+      "epoch": 0.2244039270687237,
+      "grad_norm": 33.69171915018733,
+      "learning_rate": 1.9912243398078905e-05,
+      "loss": 1.7683,
+      "step": 40
+    },
+    {
+      "epoch": 0.2300140252454418,
+      "grad_norm": 16.319511202580383,
+      "learning_rate": 1.9904460320587797e-05,
+      "loss": 1.6084,
+      "step": 41
+    },
+    {
+      "epoch": 0.23562412342215988,
+      "grad_norm": 169.4523919717209,
+      "learning_rate": 1.989634844830773e-05,
+      "loss": 1.3691,
+      "step": 42
+    },
+    {
+      "epoch": 0.24123422159887797,
+      "grad_norm": 10.82766829997138,
+      "learning_rate": 1.9887908080767395e-05,
+      "loss": 1.4698,
+      "step": 43
+    },
+    {
+      "epoch": 0.24684431977559607,
+      "grad_norm": 13.183269542497765,
+      "learning_rate": 1.9879139529625078e-05,
+      "loss": 1.6484,
+      "step": 44
+    },
+    {
+      "epoch": 0.25245441795231416,
+      "grad_norm": 13.74453433039017,
+      "learning_rate": 1.987004311865716e-05,
+      "loss": 1.682,
+      "step": 45
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 25.284432212762642,
+      "learning_rate": 1.986061918374616e-05,
+      "loss": 1.7417,
+      "step": 46
+    },
+    {
+      "epoch": 0.26367461430575034,
+      "grad_norm": 10.320026390736263,
+      "learning_rate": 1.9850868072868316e-05,
+      "loss": 1.6057,
+      "step": 47
+    },
+    {
+      "epoch": 0.26928471248246844,
+      "grad_norm": 11.710218180919735,
+      "learning_rate": 1.984079014608077e-05,
+      "loss": 1.6101,
+      "step": 48
+    },
+    {
+      "epoch": 0.27489481065918653,
+      "grad_norm": 19.568770924414054,
+      "learning_rate": 1.9830385775508233e-05,
+      "loss": 1.6445,
+      "step": 49
+    },
+    {
+      "epoch": 0.2805049088359046,
+      "grad_norm": 22.598203806640846,
+      "learning_rate": 1.9819655345329284e-05,
+      "loss": 1.4283,
+      "step": 50
+    },
+    {
+      "epoch": 0.2861150070126227,
+      "grad_norm": 15.19582950857613,
+      "learning_rate": 1.9808599251762145e-05,
+      "loss": 1.3715,
+      "step": 51
+    },
+    {
+      "epoch": 0.2917251051893408,
+      "grad_norm": 12.621837235302998,
+      "learning_rate": 1.979721790305009e-05,
+      "loss": 1.5691,
+      "step": 52
+    },
+    {
+      "epoch": 0.2973352033660589,
+      "grad_norm": 9.153518106932475,
+      "learning_rate": 1.978551171944634e-05,
+      "loss": 1.4436,
+      "step": 53
+    },
+    {
+      "epoch": 0.302945301542777,
+      "grad_norm": 9.895264955740506,
+      "learning_rate": 1.977348113319855e-05,
+      "loss": 1.6643,
+      "step": 54
+    },
+    {
+      "epoch": 0.3085553997194951,
+      "grad_norm": 23.27095547139845,
+      "learning_rate": 1.9761126588532875e-05,
+      "loss": 1.7594,
+      "step": 55
+    },
+    {
+      "epoch": 0.3141654978962132,
+      "grad_norm": 16.900190113880402,
+      "learning_rate": 1.974844854163753e-05,
+      "loss": 1.4728,
+      "step": 56
+    },
+    {
+      "epoch": 0.31977559607293127,
+      "grad_norm": 12.905411605150357,
+      "learning_rate": 1.9735447460645966e-05,
+      "loss": 1.4458,
+      "step": 57
+    },
+    {
+      "epoch": 0.32538569424964936,
+      "grad_norm": 31.337793336880274,
+      "learning_rate": 1.972212382561958e-05,
+      "loss": 1.5244,
+      "step": 58
+    },
+    {
+      "epoch": 0.33099579242636745,
+      "grad_norm": 16.41143055596397,
+      "learning_rate": 1.9708478128530002e-05,
+      "loss": 1.5635,
+      "step": 59
+    },
+    {
+      "epoch": 0.33660589060308554,
+      "grad_norm": 13.430850712385256,
+      "learning_rate": 1.9694510873240895e-05,
+      "loss": 1.575,
+      "step": 60
+    },
+    {
+      "epoch": 0.34221598877980364,
+      "grad_norm": 12.426823261781168,
+      "learning_rate": 1.9680222575489392e-05,
+      "loss": 1.5527,
+      "step": 61
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 11.631979677867267,
+      "learning_rate": 1.9665613762867016e-05,
+      "loss": 1.6676,
+      "step": 62
+    },
+    {
+      "epoch": 0.3534361851332398,
+      "grad_norm": 12.593635334214698,
+      "learning_rate": 1.965068497480022e-05,
+      "loss": 1.521,
+      "step": 63
+    },
+    {
+      "epoch": 0.3590462833099579,
+      "grad_norm": 29.46666265441875,
+      "learning_rate": 1.963543676253048e-05,
+      "loss": 1.1823,
+      "step": 64
+    },
+    {
+      "epoch": 0.364656381486676,
+      "grad_norm": 17.08155790602239,
+      "learning_rate": 1.9619869689093893e-05,
+      "loss": 1.4791,
+      "step": 65
+    },
+    {
+      "epoch": 0.3702664796633941,
+      "grad_norm": 17.295026461260033,
+      "learning_rate": 1.9603984329300443e-05,
+      "loss": 1.835,
+      "step": 66
+    },
+    {
+      "epoch": 0.3758765778401122,
+      "grad_norm": 28.11302094956105,
+      "learning_rate": 1.9587781269712743e-05,
+      "loss": 1.7666,
+      "step": 67
+    },
+    {
+      "epoch": 0.3814866760168303,
+      "grad_norm": 15.648509062666934,
+      "learning_rate": 1.9571261108624386e-05,
+      "loss": 1.5831,
+      "step": 68
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 11.295454125938116,
+      "learning_rate": 1.9554424456037856e-05,
+      "loss": 1.5546,
+      "step": 69
+    },
+    {
+      "epoch": 0.39270687237026647,
+      "grad_norm": 20.86600149222171,
+      "learning_rate": 1.9537271933641986e-05,
+      "loss": 1.5649,
+      "step": 70
+    },
+    {
+      "epoch": 0.39831697054698456,
+      "grad_norm": 12.413407895378603,
+      "learning_rate": 1.9519804174789037e-05,
+      "loss": 1.4971,
+      "step": 71
+    },
+    {
+      "epoch": 0.40392706872370265,
+      "grad_norm": 39.57009669926718,
+      "learning_rate": 1.950202182447127e-05,
+      "loss": 1.6082,
+      "step": 72
+    },
+    {
+      "epoch": 0.40953716690042075,
+      "grad_norm": 31.34749362616257,
+      "learning_rate": 1.948392553929717e-05,
+      "loss": 1.5098,
+      "step": 73
+    },
+    {
+      "epoch": 0.41514726507713884,
+      "grad_norm": 14.945037268714179,
+      "learning_rate": 1.9465515987467167e-05,
+      "loss": 1.7393,
+      "step": 74
+    },
+    {
+      "epoch": 0.42075736325385693,
+      "grad_norm": 47.715394673395544,
+      "learning_rate": 1.9446793848748988e-05,
+      "loss": 1.5907,
+      "step": 75
+    },
+    {
+      "epoch": 0.426367461430575,
+      "grad_norm": 22.307210800183924,
+      "learning_rate": 1.9427759814452535e-05,
+      "loss": 1.8286,
+      "step": 76
+    },
+    {
+      "epoch": 0.4319775596072931,
+      "grad_norm": 10.619179031781488,
+      "learning_rate": 1.940841458740438e-05,
+      "loss": 1.5184,
+      "step": 77
+    },
+    {
+      "epoch": 0.4375876577840112,
+      "grad_norm": 14.094325579812917,
+      "learning_rate": 1.9388758881921802e-05,
+      "loss": 1.4232,
+      "step": 78
+    },
+    {
+      "epoch": 0.4431977559607293,
+      "grad_norm": 19.72560091354988,
+      "learning_rate": 1.93687934237864e-05,
+      "loss": 1.6243,
+      "step": 79
+    },
+    {
+      "epoch": 0.4488078541374474,
+      "grad_norm": 19.753840295719044,
+      "learning_rate": 1.9348518950217327e-05,
+      "loss": 1.5801,
+      "step": 80
+    },
+    {
+      "epoch": 0.4544179523141655,
+      "grad_norm": 20.345860072141033,
+      "learning_rate": 1.932793620984403e-05,
+      "loss": 1.604,
+      "step": 81
+    },
+    {
+      "epoch": 0.4600280504908836,
+      "grad_norm": 16.101034336903197,
+      "learning_rate": 1.9307045962678633e-05,
+      "loss": 1.8381,
+      "step": 82
+    },
+    {
+      "epoch": 0.46563814866760167,
+      "grad_norm": 23.043596084469865,
+      "learning_rate": 1.928584898008786e-05,
+      "loss": 1.3656,
+      "step": 83
+    },
+    {
+      "epoch": 0.47124824684431976,
+      "grad_norm": 14.0013318273939,
+      "learning_rate": 1.9264346044764563e-05,
+      "loss": 1.6921,
+      "step": 84
+    },
+    {
+      "epoch": 0.47685834502103785,
+      "grad_norm": 10.088671867334291,
+      "learning_rate": 1.9242537950698808e-05,
+      "loss": 1.7664,
+      "step": 85
+    },
+    {
+      "epoch": 0.48246844319775595,
+      "grad_norm": 13.096601724817155,
+      "learning_rate": 1.9220425503148573e-05,
+      "loss": 1.6365,
+      "step": 86
+    },
+    {
+      "epoch": 0.48807854137447404,
+      "grad_norm": 10.293199079674654,
+      "learning_rate": 1.9198009518610006e-05,
+      "loss": 1.6372,
+      "step": 87
+    },
+    {
+      "epoch": 0.49368863955119213,
+      "grad_norm": 17.45696409243125,
+      "learning_rate": 1.917529082478727e-05,
+      "loss": 1.9688,
+      "step": 88
+    },
+    {
+      "epoch": 0.4992987377279102,
+      "grad_norm": 12.501332529093151,
+      "learning_rate": 1.9152270260561986e-05,
+      "loss": 1.7185,
+      "step": 89
+    },
+    {
+      "epoch": 0.5049088359046283,
+      "grad_norm": 9.567511469828927,
+      "learning_rate": 1.912894867596227e-05,
+      "loss": 1.5637,
+      "step": 90
+    },
+    {
+      "epoch": 0.5105189340813464,
+      "grad_norm": 10.588869643202907,
+      "learning_rate": 1.9105326932131318e-05,
+      "loss": 1.4875,
+      "step": 91
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 25.375515168691575,
+      "learning_rate": 1.9081405901295637e-05,
+      "loss": 1.5908,
+      "step": 92
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 34.618538302204044,
+      "learning_rate": 1.905718646673282e-05,
+      "loss": 1.73,
+      "step": 93
+    },
+    {
+      "epoch": 0.5273492286115007,
+      "grad_norm": 9.481578038519926,
+      "learning_rate": 1.9032669522738933e-05,
+      "loss": 1.4905,
+      "step": 94
+    },
+    {
+      "epoch": 0.5329593267882188,
+      "grad_norm": 15.199014159234617,
+      "learning_rate": 1.9007855974595508e-05,
+      "loss": 1.6711,
+      "step": 95
+    },
+    {
+      "epoch": 0.5385694249649369,
+      "grad_norm": 12.401899473450863,
+      "learning_rate": 1.8982746738536097e-05,
+      "loss": 1.4282,
+      "step": 96
+    },
+    {
+      "epoch": 0.544179523141655,
+      "grad_norm": 15.694607543801956,
+      "learning_rate": 1.8957342741712444e-05,
+      "loss": 1.6658,
+      "step": 97
+    },
+    {
+      "epoch": 0.5497896213183731,
+      "grad_norm": 10.78564261946902,
+      "learning_rate": 1.8931644922160274e-05,
+      "loss": 1.5895,
+      "step": 98
+    },
+    {
+      "epoch": 0.5553997194950911,
+      "grad_norm": 17.60784194989688,
+      "learning_rate": 1.8905654228764614e-05,
+      "loss": 1.4861,
+      "step": 99
+    },
+    {
+      "epoch": 0.5610098176718092,
+      "grad_norm": 14.053092600296077,
+      "learning_rate": 1.8879371621224787e-05,
+      "loss": 1.3578,
+      "step": 100
+    },
+    {
+      "epoch": 0.5666199158485273,
+      "grad_norm": 12.259536566697912,
+      "learning_rate": 1.8852798070018974e-05,
+      "loss": 1.4281,
+      "step": 101
+    },
+    {
+      "epoch": 0.5722300140252454,
+      "grad_norm": 13.137644468308233,
+      "learning_rate": 1.882593455636836e-05,
+      "loss": 1.3722,
+      "step": 102
+    },
+    {
+      "epoch": 0.5778401122019635,
+      "grad_norm": 9.494614193722693,
+      "learning_rate": 1.8798782072200924e-05,
+      "loss": 1.4653,
+      "step": 103
+    },
+    {
+      "epoch": 0.5834502103786816,
+      "grad_norm": 16.144017929658787,
+      "learning_rate": 1.8771341620114796e-05,
+      "loss": 1.5071,
+      "step": 104
+    },
+    {
+      "epoch": 0.5890603085553997,
+      "grad_norm": 14.436242746383904,
+      "learning_rate": 1.8743614213341256e-05,
+      "loss": 1.6482,
+      "step": 105
+    },
+    {
+      "epoch": 0.5946704067321178,
+      "grad_norm": 10.994748673603036,
+      "learning_rate": 1.8715600875707294e-05,
+      "loss": 1.4865,
+      "step": 106
+    },
+    {
+      "epoch": 0.6002805049088359,
+      "grad_norm": 12.3974862231508,
+      "learning_rate": 1.8687302641597824e-05,
+      "loss": 1.4387,
+      "step": 107
+    },
+    {
+      "epoch": 0.605890603085554,
+      "grad_norm": 15.733090579327103,
+      "learning_rate": 1.8658720555917487e-05,
+      "loss": 1.6455,
+      "step": 108
+    },
+    {
+      "epoch": 0.6115007012622721,
+      "grad_norm": 8.115989009375005,
+      "learning_rate": 1.862985567405207e-05,
+      "loss": 1.3164,
+      "step": 109
+    },
+    {
+      "epoch": 0.6171107994389902,
+      "grad_norm": 9.584544195435662,
+      "learning_rate": 1.860070906182953e-05,
+      "loss": 1.4764,
+      "step": 110
+    },
+    {
+      "epoch": 0.6227208976157083,
+      "grad_norm": 8.898340243711843,
+      "learning_rate": 1.8571281795480632e-05,
+      "loss": 1.5719,
+      "step": 111
+    },
+    {
+      "epoch": 0.6283309957924264,
+      "grad_norm": 22.902730670382045,
+      "learning_rate": 1.8541574961599233e-05,
+      "loss": 1.51,
+      "step": 112
+    },
+    {
+      "epoch": 0.6339410939691444,
+      "grad_norm": 12.53384464527916,
+      "learning_rate": 1.8511589657102137e-05,
+      "loss": 1.4294,
+      "step": 113
+    },
+    {
+      "epoch": 0.6395511921458625,
+      "grad_norm": 41.90777459667712,
+      "learning_rate": 1.8481326989188603e-05,
+      "loss": 1.4984,
+      "step": 114
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 12.684090261010915,
+      "learning_rate": 1.845078807529946e-05,
+      "loss": 1.3514,
+      "step": 115
+    },
+    {
+      "epoch": 0.6507713884992987,
+      "grad_norm": 9.037066734768192,
+      "learning_rate": 1.8419974043075842e-05,
+      "loss": 1.6403,
+      "step": 116
+    },
+    {
+      "epoch": 0.6563814866760168,
+      "grad_norm": 12.27393138414365,
+      "learning_rate": 1.838888603031756e-05,
+      "loss": 1.5217,
+      "step": 117
+    },
+    {
+      "epoch": 0.6619915848527349,
+      "grad_norm": 13.591447680784224,
+      "learning_rate": 1.8357525184941065e-05,
+      "loss": 1.6687,
+      "step": 118
+    },
+    {
+      "epoch": 0.667601683029453,
+      "grad_norm": 24.839843874937873,
+      "learning_rate": 1.8325892664937098e-05,
+      "loss": 1.6273,
+      "step": 119
+    },
+    {
+      "epoch": 0.6732117812061711,
+      "grad_norm": 40.24703694848467,
+      "learning_rate": 1.8293989638327906e-05,
+      "loss": 1.5715,
+      "step": 120
+    },
+    {
+      "epoch": 0.6788218793828892,
+      "grad_norm": 13.660745551221684,
+      "learning_rate": 1.8261817283124115e-05,
+      "loss": 1.4114,
+      "step": 121
+    },
+    {
+      "epoch": 0.6844319775596073,
+      "grad_norm": 35.89402465913394,
+      "learning_rate": 1.822937678728124e-05,
+      "loss": 1.3927,
+      "step": 122
+    },
+    {
+      "epoch": 0.6900420757363254,
+      "grad_norm": 11.308872740776515,
+      "learning_rate": 1.8196669348655817e-05,
+      "loss": 1.3174,
+      "step": 123
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 10.263689306849406,
+      "learning_rate": 1.8163696174961167e-05,
+      "loss": 1.5547,
+      "step": 124
+    },
+    {
+      "epoch": 0.7012622720897616,
+      "grad_norm": 13.801928996749705,
+      "learning_rate": 1.8130458483722814e-05,
+      "loss": 1.5886,
+      "step": 125
+    },
+    {
+      "epoch": 0.7068723702664796,
+      "grad_norm": 19.35669184267192,
+      "learning_rate": 1.809695750223351e-05,
+      "loss": 1.5143,
+      "step": 126
+    },
+    {
+      "epoch": 0.7124824684431977,
+      "grad_norm": 10.891218633996896,
+      "learning_rate": 1.806319446750795e-05,
+      "loss": 1.4685,
+      "step": 127
+    },
+    {
+      "epoch": 0.7180925666199158,
+      "grad_norm": 28.696150917144198,
+      "learning_rate": 1.802917062623705e-05,
+      "loss": 2.0259,
+      "step": 128
+    },
+    {
+      "epoch": 0.7237026647966339,
+      "grad_norm": 15.890258346122694,
+      "learning_rate": 1.7994887234741944e-05,
+      "loss": 1.4751,
+      "step": 129
+    },
+    {
+      "epoch": 0.729312762973352,
+      "grad_norm": 8.63985122916741,
+      "learning_rate": 1.7960345558927597e-05,
+      "loss": 1.2119,
+      "step": 130
+    },
+    {
+      "epoch": 0.7349228611500701,
+      "grad_norm": 18.584698267002675,
+      "learning_rate": 1.7925546874236043e-05,
+      "loss": 1.4341,
+      "step": 131
+    },
+    {
+      "epoch": 0.7405329593267882,
+      "grad_norm": 14.450827757949208,
+      "learning_rate": 1.7890492465599302e-05,
+      "loss": 1.608,
+      "step": 132
+    },
+    {
+      "epoch": 0.7461430575035063,
+      "grad_norm": 15.571705745790306,
+      "learning_rate": 1.785518362739193e-05,
+      "loss": 1.5671,
+      "step": 133
+    },
+    {
+      "epoch": 0.7517531556802244,
+      "grad_norm": 12.605049972249128,
+      "learning_rate": 1.7819621663383233e-05,
+      "loss": 1.4163,
+      "step": 134
+    },
+    {
+      "epoch": 0.7573632538569425,
+      "grad_norm": 11.318493509461359,
+      "learning_rate": 1.778380788668911e-05,
+      "loss": 1.5184,
+      "step": 135
+    },
+    {
+      "epoch": 0.7629733520336606,
+      "grad_norm": 10.337554569071575,
+      "learning_rate": 1.7747743619723576e-05,
+      "loss": 1.4598,
+      "step": 136
+    },
+    {
+      "epoch": 0.7685834502103787,
+      "grad_norm": 18.136003012039577,
+      "learning_rate": 1.771143019414994e-05,
+      "loss": 1.3933,
+      "step": 137
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 23.63615446575357,
+      "learning_rate": 1.7674868950831622e-05,
+      "loss": 1.476,
+      "step": 138
+    },
+    {
+      "epoch": 0.7798036465638148,
+      "grad_norm": 12.27648365093833,
+      "learning_rate": 1.763806123978263e-05,
+      "loss": 1.4272,
+      "step": 139
+    },
+    {
+      "epoch": 0.7854137447405329,
+      "grad_norm": 18.76442955908805,
+      "learning_rate": 1.7601008420117752e-05,
+      "loss": 1.5662,
+      "step": 140
+    },
+    {
+      "epoch": 0.791023842917251,
+      "grad_norm": 17.2691920820149,
+      "learning_rate": 1.756371186000233e-05,
+      "loss": 1.6274,
+      "step": 141
+    },
+    {
+      "epoch": 0.7966339410939691,
+      "grad_norm": 34.883527695882705,
+      "learning_rate": 1.7526172936601757e-05,
+      "loss": 1.4771,
+      "step": 142
+    },
+    {
+      "epoch": 0.8022440392706872,
+      "grad_norm": 23.56533760346909,
+      "learning_rate": 1.748839303603062e-05,
+      "loss": 1.6044,
+      "step": 143
+    },
+    {
+      "epoch": 0.8078541374474053,
+      "grad_norm": 57.11894729578249,
+      "learning_rate": 1.7450373553301543e-05,
+      "loss": 1.3727,
+      "step": 144
+    },
+    {
+      "epoch": 0.8134642356241234,
+      "grad_norm": 8.265029503541601,
+      "learning_rate": 1.741211589227363e-05,
+      "loss": 1.3591,
+      "step": 145
+    },
+    {
+      "epoch": 0.8190743338008415,
+      "grad_norm": 138.3935650140209,
+      "learning_rate": 1.7373621465600675e-05,
+      "loss": 1.425,
+      "step": 146
+    },
+    {
+      "epoch": 0.8246844319775596,
+      "grad_norm": 24.359106304785023,
+      "learning_rate": 1.733489169467897e-05,
+      "loss": 1.5576,
+      "step": 147
+    },
+    {
+      "epoch": 0.8302945301542777,
+      "grad_norm": 9.862752909579248,
+      "learning_rate": 1.7295928009594828e-05,
+      "loss": 1.4147,
+      "step": 148
+    },
+    {
+      "epoch": 0.8359046283309958,
+      "grad_norm": 23.537743248039938,
+      "learning_rate": 1.7256731849071784e-05,
+      "loss": 1.6989,
+      "step": 149
+    },
+    {
+      "epoch": 0.8415147265077139,
+      "grad_norm": 14.04775976293614,
+      "learning_rate": 1.721730466041746e-05,
+      "loss": 1.4941,
+      "step": 150
+    },
+    {
+      "epoch": 0.847124824684432,
+      "grad_norm": 12.168431113203132,
+      "learning_rate": 1.717764789947014e-05,
+      "loss": 1.3478,
+      "step": 151
+    },
+    {
+      "epoch": 0.85273492286115,
+      "grad_norm": 14.932661016457688,
+      "learning_rate": 1.7137763030544993e-05,
+      "loss": 1.468,
+      "step": 152
+    },
+    {
+      "epoch": 0.8583450210378681,
+      "grad_norm": 16.571205525117712,
+      "learning_rate": 1.709765152638002e-05,
+      "loss": 1.7317,
+      "step": 153
+    },
+    {
+      "epoch": 0.8639551192145862,
+      "grad_norm": 14.117927089933083,
+      "learning_rate": 1.7057314868081657e-05,
+      "loss": 1.4775,
+      "step": 154
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 13.662454658161607,
+      "learning_rate": 1.7016754545070106e-05,
+      "loss": 1.7002,
+      "step": 155
+    },
+    {
+      "epoch": 0.8751753155680224,
+      "grad_norm": 16.492645273733498,
+      "learning_rate": 1.6975972055024322e-05,
+      "loss": 1.5245,
+      "step": 156
+    },
+    {
+      "epoch": 0.8807854137447405,
+      "grad_norm": 16.82235019269752,
+      "learning_rate": 1.693496890382672e-05,
+      "loss": 1.7002,
+      "step": 157
+    },
+    {
+      "epoch": 0.8863955119214586,
+      "grad_norm": 9.585860481675596,
+      "learning_rate": 1.6893746605507567e-05,
+      "loss": 1.4924,
+      "step": 158
+    },
+    {
+      "epoch": 0.8920056100981767,
+      "grad_norm": 14.39753403643121,
+      "learning_rate": 1.685230668218908e-05,
+      "loss": 1.2832,
+      "step": 159
+    },
+    {
+      "epoch": 0.8976157082748948,
+      "grad_norm": 17.068205819906623,
+      "learning_rate": 1.681065066402922e-05,
+      "loss": 1.3861,
+      "step": 160
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 15.23446199758208,
+      "learning_rate": 1.6768780089165196e-05,
+      "loss": 1.3945,
+      "step": 161
+    },
+    {
+      "epoch": 0.908835904628331,
+      "grad_norm": 13.204881161532553,
+      "learning_rate": 1.672669650365665e-05,
+      "loss": 1.5229,
+      "step": 162
+    },
+    {
+      "epoch": 0.9144460028050491,
+      "grad_norm": 10.822302558242614,
+      "learning_rate": 1.66844014614286e-05,
+      "loss": 1.4491,
+      "step": 163
+    },
+    {
+      "epoch": 0.9200561009817672,
+      "grad_norm": 13.40338254856901,
+      "learning_rate": 1.6641896524214037e-05,
+      "loss": 1.5619,
+      "step": 164
+    },
+    {
+      "epoch": 0.9256661991584852,
+      "grad_norm": 17.69450894792508,
+      "learning_rate": 1.6599183261496278e-05,
+      "loss": 1.4905,
+      "step": 165
+    },
+    {
+      "epoch": 0.9312762973352033,
+      "grad_norm": 13.944664173351105,
+      "learning_rate": 1.6556263250450995e-05,
+      "loss": 1.3102,
+      "step": 166
+    },
+    {
+      "epoch": 0.9368863955119214,
+      "grad_norm": 22.354089172464942,
+      "learning_rate": 1.6513138075887982e-05,
+      "loss": 1.4281,
+      "step": 167
+    },
+    {
+      "epoch": 0.9424964936886395,
+      "grad_norm": 12.888048658450844,
+      "learning_rate": 1.6469809330192644e-05,
+      "loss": 1.2822,
+      "step": 168
+    },
+    {
+      "epoch": 0.9481065918653576,
+      "grad_norm": 14.132338918324168,
+      "learning_rate": 1.642627861326721e-05,
+      "loss": 1.6548,
+      "step": 169
+    },
+    {
+      "epoch": 0.9537166900420757,
+      "grad_norm": 17.359600887821536,
+      "learning_rate": 1.638254753247162e-05,
+      "loss": 1.5647,
+      "step": 170
+    },
+    {
+      "epoch": 0.9593267882187938,
+      "grad_norm": 13.222024309183224,
+      "learning_rate": 1.63386177025642e-05,
+      "loss": 1.634,
+      "step": 171
+    },
+    {
+      "epoch": 0.9649368863955119,
+      "grad_norm": 17.14309674478443,
+      "learning_rate": 1.6294490745642044e-05,
+      "loss": 1.4728,
+      "step": 172
+    },
+    {
+      "epoch": 0.97054698457223,
+      "grad_norm": 15.152308719340205,
+      "learning_rate": 1.6250168291081095e-05,
+      "loss": 1.1627,
+      "step": 173
+    },
+    {
+      "epoch": 0.9761570827489481,
+      "grad_norm": 15.348018396503871,
+      "learning_rate": 1.6205651975476013e-05,
+      "loss": 1.3184,
+      "step": 174
+    },
+    {
+      "epoch": 0.9817671809256662,
+      "grad_norm": 14.030740196357252,
+      "learning_rate": 1.61609434425797e-05,
+      "loss": 1.5187,
+      "step": 175
+    },
+    {
+      "epoch": 0.9873772791023843,
+      "grad_norm": 12.340831899480172,
+      "learning_rate": 1.6116044343242643e-05,
+      "loss": 1.4763,
+      "step": 176
+    },
+    {
+      "epoch": 0.9929873772791024,
+      "grad_norm": 12.874192526939726,
+      "learning_rate": 1.607095633535194e-05,
+      "loss": 1.2938,
+      "step": 177
+    },
+    {
+      "epoch": 0.9985974754558204,
+      "grad_norm": 14.359777239220444,
+      "learning_rate": 1.6025681083770094e-05,
+      "loss": 1.4761,
+      "step": 178
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 14.359777239220444,
+      "learning_rate": 1.5980220260273517e-05,
+      "loss": 0.4634,
+      "step": 179
+    },
+    {
+      "epoch": 1.0056100981767182,
+      "grad_norm": 14.690822186999577,
+      "learning_rate": 1.5934575543490827e-05,
+      "loss": 1.7605,
+      "step": 180
+    },
+    {
+      "epoch": 1.0112201963534362,
+      "grad_norm": 19.381128219060844,
+      "learning_rate": 1.588874861884084e-05,
+      "loss": 1.3774,
+      "step": 181
+    },
+    {
+      "epoch": 1.0168302945301542,
+      "grad_norm": 13.764508415825427,
+      "learning_rate": 1.5842741178470356e-05,
+      "loss": 1.3739,
+      "step": 182
+    },
+    {
+      "epoch": 1.0224403927068724,
+      "grad_norm": 16.824436408164395,
+      "learning_rate": 1.5796554921191666e-05,
+      "loss": 1.4756,
+      "step": 183
+    },
+    {
+      "epoch": 1.0280504908835906,
+      "grad_norm": 10.377967714732288,
+      "learning_rate": 1.5750191552419834e-05,
+      "loss": 1.2113,
+      "step": 184
+    },
+    {
+      "epoch": 1.0336605890603086,
+      "grad_norm": 7.564193930068618,
+      "learning_rate": 1.5703652784109704e-05,
+      "loss": 1.1498,
+      "step": 185
+    },
+    {
+      "epoch": 1.0392706872370265,
+      "grad_norm": 11.965238823644222,
+      "learning_rate": 1.565694033469271e-05,
+      "loss": 1.5756,
+      "step": 186
+    },
+    {
+      "epoch": 1.0448807854137447,
+      "grad_norm": 14.689919910120953,
+      "learning_rate": 1.5610055929013422e-05,
+      "loss": 1.4575,
+      "step": 187
+    },
+    {
+      "epoch": 1.050490883590463,
+      "grad_norm": 22.539021928944944,
+      "learning_rate": 1.5563001298265826e-05,
+      "loss": 1.4551,
+      "step": 188
+    },
+    {
+      "epoch": 1.056100981767181,
+      "grad_norm": 19.696373241342833,
+      "learning_rate": 1.5515778179929444e-05,
+      "loss": 1.6987,
+      "step": 189
+    },
+    {
+      "epoch": 1.061711079943899,
+      "grad_norm": 12.848174310076084,
+      "learning_rate": 1.5468388317705145e-05,
+      "loss": 1.4525,
+      "step": 190
+    },
+    {
+      "epoch": 1.067321178120617,
+      "grad_norm": 15.431121772973855,
+      "learning_rate": 1.5420833461450773e-05,
+      "loss": 1.5082,
+      "step": 191
+    },
+    {
+      "epoch": 1.0729312762973353,
+      "grad_norm": 16.165697573890178,
+      "learning_rate": 1.5373115367116532e-05,
+      "loss": 1.5569,
+      "step": 192
+    },
+    {
+      "epoch": 1.0785413744740533,
+      "grad_norm": 11.167625826904903,
+      "learning_rate": 1.5325235796680155e-05,
+      "loss": 1.4128,
+      "step": 193
+    },
+    {
+      "epoch": 1.0841514726507713,
+      "grad_norm": 14.862256623967552,
+      "learning_rate": 1.5277196518081826e-05,
+      "loss": 1.4904,
+      "step": 194
+    },
+    {
+      "epoch": 1.0897615708274895,
+      "grad_norm": 14.141157026149255,
+      "learning_rate": 1.5228999305158915e-05,
+      "loss": 1.42,
+      "step": 195
+    },
+    {
+      "epoch": 1.0953716690042077,
+      "grad_norm": 25.352183474376506,
+      "learning_rate": 1.5180645937580474e-05,
+      "loss": 1.4163,
+      "step": 196
+    },
+    {
+      "epoch": 1.1009817671809257,
+      "grad_norm": 10.055312720961254,
+      "learning_rate": 1.5132138200781523e-05,
+      "loss": 1.0222,
+      "step": 197
+    },
+    {
+      "epoch": 1.1065918653576436,
+      "grad_norm": 13.796900933925889,
+      "learning_rate": 1.5083477885897122e-05,
+      "loss": 1.759,
+      "step": 198
+    },
+    {
+      "epoch": 1.1122019635343618,
+      "grad_norm": 12.433488935186917,
+      "learning_rate": 1.5034666789696239e-05,
+      "loss": 1.3977,
+      "step": 199
+    },
+    {
+      "epoch": 1.11781206171108,
+      "grad_norm": 18.535695256124203,
+      "learning_rate": 1.4985706714515394e-05,
+      "loss": 1.6248,
+      "step": 200
+    },
+    {
+      "epoch": 1.123422159887798,
+      "grad_norm": 12.996630182675128,
+      "learning_rate": 1.4936599468192128e-05,
+      "loss": 1.5048,
+      "step": 201
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 10.587914458016622,
+      "learning_rate": 1.4887346863998226e-05,
+      "loss": 1.3652,
+      "step": 202
+    },
+    {
+      "epoch": 1.1346423562412342,
+      "grad_norm": 10.705843179552653,
+      "learning_rate": 1.4837950720572777e-05,
+      "loss": 1.3677,
+      "step": 203
+    },
+    {
+      "epoch": 1.1402524544179524,
+      "grad_norm": 9.860740526338978,
+      "learning_rate": 1.4788412861855018e-05,
+      "loss": 1.4839,
+      "step": 204
+    },
+    {
+      "epoch": 1.1458625525946704,
+      "grad_norm": 46.04382771539066,
+      "learning_rate": 1.473873511701698e-05,
+      "loss": 1.6699,
+      "step": 205
+    },
+    {
+      "epoch": 1.1514726507713884,
+      "grad_norm": 21.90608450068067,
+      "learning_rate": 1.4688919320395958e-05,
+      "loss": 1.5415,
+      "step": 206
+    },
+    {
+      "epoch": 1.1570827489481066,
+      "grad_norm": 11.517380135013592,
+      "learning_rate": 1.4638967311426769e-05,
+      "loss": 1.4757,
+      "step": 207
+    },
+    {
+      "epoch": 1.1626928471248248,
+      "grad_norm": 22.45752042141559,
+      "learning_rate": 1.4588880934573832e-05,
+      "loss": 1.1128,
+      "step": 208
+    },
+    {
+      "epoch": 1.1683029453015428,
+      "grad_norm": 15.859260925124287,
+      "learning_rate": 1.4538662039263067e-05,
+      "loss": 1.3533,
+      "step": 209
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 11.911198424099664,
+      "learning_rate": 1.4488312479813598e-05,
+      "loss": 1.5547,
+      "step": 210
+    },
+    {
+      "epoch": 1.179523141654979,
+      "grad_norm": 15.032622370869328,
+      "learning_rate": 1.4437834115369293e-05,
+      "loss": 1.5527,
+      "step": 211
+    },
+    {
+      "epoch": 1.1851332398316972,
+      "grad_norm": 13.163219102851839,
+      "learning_rate": 1.4387228809830107e-05,
+      "loss": 1.4507,
+      "step": 212
+    },
+    {
+      "epoch": 1.1907433380084151,
+      "grad_norm": 11.55782752088526,
+      "learning_rate": 1.4336498431783255e-05,
+      "loss": 1.5752,
+      "step": 213
+    },
+    {
+      "epoch": 1.1963534361851331,
+      "grad_norm": 8.939604195134024,
+      "learning_rate": 1.428564485443423e-05,
+      "loss": 1.2458,
+      "step": 214
+    },
+    {
+      "epoch": 1.2019635343618513,
+      "grad_norm": 13.076558990973293,
+      "learning_rate": 1.4234669955537615e-05,
+      "loss": 1.5947,
+      "step": 215
+    },
+    {
+      "epoch": 1.2075736325385695,
+      "grad_norm": 29.61425820551926,
+      "learning_rate": 1.4183575617327774e-05,
+      "loss": 1.4435,
+      "step": 216
+    },
+    {
+      "epoch": 1.2131837307152875,
+      "grad_norm": 17.139513231632446,
+      "learning_rate": 1.413236372644932e-05,
+      "loss": 1.5416,
+      "step": 217
+    },
+    {
+      "epoch": 1.2187938288920055,
+      "grad_norm": 11.538723658632415,
+      "learning_rate": 1.4081036173887473e-05,
+      "loss": 1.2324,
+      "step": 218
+    },
+    {
+      "epoch": 1.2244039270687237,
+      "grad_norm": 11.952863288381689,
+      "learning_rate": 1.402959485489823e-05,
+      "loss": 1.509,
+      "step": 219
+    },
+    {
+      "epoch": 1.230014025245442,
+      "grad_norm": 19.47240211007032,
+      "learning_rate": 1.3978041668938383e-05,
+      "loss": 1.6639,
+      "step": 220
+    },
+    {
+      "epoch": 1.2356241234221599,
+      "grad_norm": 15.07334914756095,
+      "learning_rate": 1.3926378519595374e-05,
+      "loss": 1.7645,
+      "step": 221
+    },
+    {
+      "epoch": 1.2412342215988779,
+      "grad_norm": 22.910378041692734,
+      "learning_rate": 1.3874607314517021e-05,
+      "loss": 1.5825,
+      "step": 222
+    },
+    {
+      "epoch": 1.246844319775596,
+      "grad_norm": 15.057996546883961,
+      "learning_rate": 1.3822729965341078e-05,
+      "loss": 1.2952,
+      "step": 223
+    },
+    {
+      "epoch": 1.2524544179523143,
+      "grad_norm": 10.933853220414331,
+      "learning_rate": 1.3770748387624621e-05,
+      "loss": 1.292,
+      "step": 224
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 12.1607776522528,
+      "learning_rate": 1.3718664500773354e-05,
+      "loss": 1.3202,
+      "step": 225
+    },
+    {
+      "epoch": 1.2636746143057502,
+      "grad_norm": 11.360620610919614,
+      "learning_rate": 1.3666480227970709e-05,
+      "loss": 1.5078,
+      "step": 226
+    },
+    {
+      "epoch": 1.2692847124824684,
+      "grad_norm": 9.312895139596053,
+      "learning_rate": 1.3614197496106844e-05,
+      "loss": 1.2955,
+      "step": 227
+    },
+    {
+      "epoch": 1.2748948106591866,
+      "grad_norm": 22.942061123573257,
+      "learning_rate": 1.3561818235707496e-05,
+      "loss": 1.278,
+      "step": 228
+    },
+    {
+      "epoch": 1.2805049088359046,
+      "grad_norm": 18.018595754740154,
+      "learning_rate": 1.3509344380862686e-05,
+      "loss": 1.5696,
+      "step": 229
+    },
+    {
+      "epoch": 1.2861150070126226,
+      "grad_norm": 11.395912452185224,
+      "learning_rate": 1.3456777869155313e-05,
+      "loss": 1.532,
+      "step": 230
+    },
+    {
+      "epoch": 1.2917251051893408,
+      "grad_norm": 11.638674568201234,
+      "learning_rate": 1.3404120641589603e-05,
+      "loss": 1.811,
+      "step": 231
+    },
+    {
+      "epoch": 1.297335203366059,
+      "grad_norm": 15.157516555268536,
+      "learning_rate": 1.3351374642519442e-05,
+      "loss": 1.5383,
+      "step": 232
+    },
+    {
+      "epoch": 1.302945301542777,
+      "grad_norm": 15.58095439499807,
+      "learning_rate": 1.3298541819576576e-05,
+      "loss": 1.37,
+      "step": 233
+    },
+    {
+      "epoch": 1.308555399719495,
+      "grad_norm": 35.4984649494009,
+      "learning_rate": 1.324562412359871e-05,
+      "loss": 1.4839,
+      "step": 234
+    },
+    {
+      "epoch": 1.3141654978962132,
+      "grad_norm": 10.350141828953962,
+      "learning_rate": 1.3192623508557451e-05,
+      "loss": 1.2646,
+      "step": 235
+    },
+    {
+      "epoch": 1.3197755960729314,
+      "grad_norm": 12.999057294234326,
+      "learning_rate": 1.3139541931486173e-05,
+      "loss": 1.5151,
+      "step": 236
+    },
+    {
+      "epoch": 1.3253856942496494,
+      "grad_norm": 17.4509215245749,
+      "learning_rate": 1.3086381352407755e-05,
+      "loss": 1.3827,
+      "step": 237
+    },
+    {
+      "epoch": 1.3309957924263673,
+      "grad_norm": 11.463089763795967,
+      "learning_rate": 1.3033143734262204e-05,
+      "loss": 1.1956,
+      "step": 238
+    },
+    {
+      "epoch": 1.3366058906030855,
+      "grad_norm": 168.91450904514727,
+      "learning_rate": 1.2979831042834164e-05,
+      "loss": 1.4713,
+      "step": 239
+    },
+    {
+      "epoch": 1.3422159887798037,
+      "grad_norm": 11.567925095640721,
+      "learning_rate": 1.2926445246680348e-05,
+      "loss": 1.2264,
+      "step": 240
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 10.54147800166849,
+      "learning_rate": 1.2872988317056845e-05,
+      "loss": 1.5958,
+      "step": 241
+    },
+    {
+      "epoch": 1.3534361851332397,
+      "grad_norm": 21.074707300205976,
+      "learning_rate": 1.2819462227846317e-05,
+      "loss": 1.2939,
+      "step": 242
+    },
+    {
+      "epoch": 1.359046283309958,
+      "grad_norm": 13.48881127446839,
+      "learning_rate": 1.2765868955485137e-05,
+      "loss": 1.5187,
+      "step": 243
+    },
+    {
+      "epoch": 1.3646563814866761,
+      "grad_norm": 10.154890818774664,
+      "learning_rate": 1.2712210478890383e-05,
+      "loss": 1.5038,
+      "step": 244
+    },
+    {
+      "epoch": 1.370266479663394,
+      "grad_norm": 18.469132063362895,
+      "learning_rate": 1.26584887793868e-05,
+      "loss": 1.6212,
+      "step": 245
+    },
+    {
+      "epoch": 1.375876577840112,
+      "grad_norm": 12.225168956623056,
+      "learning_rate": 1.2604705840633607e-05,
+      "loss": 1.3629,
+      "step": 246
+    },
+    {
+      "epoch": 1.3814866760168303,
+      "grad_norm": 17.894894417221984,
+      "learning_rate": 1.255086364855127e-05,
+      "loss": 1.3347,
+      "step": 247
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 14.962485611796625,
+      "learning_rate": 1.2496964191248173e-05,
+      "loss": 1.5094,
+      "step": 248
+    },
+    {
+      "epoch": 1.3927068723702665,
+      "grad_norm": 18.88682118132516,
+      "learning_rate": 1.244300945894719e-05,
+      "loss": 1.3175,
+      "step": 249
+    },
+    {
+      "epoch": 1.3983169705469845,
+      "grad_norm": 18.655608529046333,
+      "learning_rate": 1.2389001443912231e-05,
+      "loss": 1.5244,
+      "step": 250
+    },
+    {
+      "epoch": 1.4039270687237027,
+      "grad_norm": 10.075456800604965,
+      "learning_rate": 1.2334942140374634e-05,
+      "loss": 1.3944,
+      "step": 251
+    },
+    {
+      "epoch": 1.4095371669004209,
+      "grad_norm": 15.028865589899354,
+      "learning_rate": 1.228083354445957e-05,
+      "loss": 1.3883,
+      "step": 252
+    },
+    {
+      "epoch": 1.4151472650771388,
+      "grad_norm": 42.583340154253584,
+      "learning_rate": 1.2226677654112296e-05,
+      "loss": 1.5854,
+      "step": 253
+    },
+    {
+      "epoch": 1.4207573632538568,
+      "grad_norm": 10.056718092820645,
+      "learning_rate": 1.2172476469024422e-05,
+      "loss": 1.6826,
+      "step": 254
+    },
+    {
+      "epoch": 1.426367461430575,
+      "grad_norm": 46.13023482300682,
+      "learning_rate": 1.211823199056005e-05,
+      "loss": 1.3374,
+      "step": 255
+    },
+    {
+      "epoch": 1.4319775596072932,
+      "grad_norm": 10.072978707803287,
+      "learning_rate": 1.2063946221681872e-05,
+      "loss": 1.428,
+      "step": 256
+    },
+    {
+      "epoch": 1.4375876577840112,
+      "grad_norm": 11.02574282037852,
+      "learning_rate": 1.2009621166877224e-05,
+      "loss": 1.3809,
+      "step": 257
+    },
+    {
+      "epoch": 1.4431977559607292,
+      "grad_norm": 9.564143846905477,
+      "learning_rate": 1.1955258832084058e-05,
+      "loss": 1.4093,
+      "step": 258
+    },
+    {
+      "epoch": 1.4488078541374474,
+      "grad_norm": 8.930878694659077,
+      "learning_rate": 1.1900861224616888e-05,
+      "loss": 1.5132,
+      "step": 259
+    },
+    {
+      "epoch": 1.4544179523141656,
+      "grad_norm": 67.29834215473018,
+      "learning_rate": 1.1846430353092653e-05,
+      "loss": 1.5392,
+      "step": 260
+    },
+    {
+      "epoch": 1.4600280504908836,
+      "grad_norm": 11.575055969929595,
+      "learning_rate": 1.1791968227356563e-05,
+      "loss": 1.1486,
+      "step": 261
+    },
+    {
+      "epoch": 1.4656381486676016,
+      "grad_norm": 19.633803271594928,
+      "learning_rate": 1.173747685840788e-05,
+      "loss": 1.7273,
+      "step": 262
+    },
+    {
+      "epoch": 1.4712482468443198,
+      "grad_norm": 15.14394386124325,
+      "learning_rate": 1.168295825832566e-05,
+      "loss": 1.5624,
+      "step": 263
+    },
+    {
+      "epoch": 1.476858345021038,
+      "grad_norm": 10.448296386160346,
+      "learning_rate": 1.1628414440194475e-05,
+      "loss": 1.6643,
+      "step": 264
+    },
+    {
+      "epoch": 1.482468443197756,
+      "grad_norm": 10.794099359683328,
+      "learning_rate": 1.1573847418030053e-05,
+      "loss": 1.5638,
+      "step": 265
+    },
+    {
+      "epoch": 1.488078541374474,
+      "grad_norm": 14.889289307369161,
+      "learning_rate": 1.151925920670493e-05,
+      "loss": 1.4022,
+      "step": 266
+    },
+    {
+      "epoch": 1.4936886395511921,
+      "grad_norm": 13.098686565529942,
+      "learning_rate": 1.1464651821874037e-05,
+      "loss": 1.5339,
+      "step": 267
+    },
+    {
+      "epoch": 1.4992987377279103,
+      "grad_norm": 22.334352986107007,
+      "learning_rate": 1.1410027279900297e-05,
+      "loss": 1.4507,
+      "step": 268
+    },
+    {
+      "epoch": 1.5049088359046283,
+      "grad_norm": 25.84919623189595,
+      "learning_rate": 1.1355387597780147e-05,
+      "loss": 1.7249,
+      "step": 269
+    },
+    {
+      "epoch": 1.5105189340813463,
+      "grad_norm": 15.08636605686211,
+      "learning_rate": 1.1300734793069073e-05,
+      "loss": 1.6036,
+      "step": 270
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 9.556192428160092,
+      "learning_rate": 1.1246070883807103e-05,
+      "loss": 1.6183,
+      "step": 271
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 9.945367086120191,
+      "learning_rate": 1.1191397888444303e-05,
+      "loss": 1.4395,
+      "step": 272
+    },
+    {
+      "epoch": 1.5273492286115007,
+      "grad_norm": 11.691573124439154,
+      "learning_rate": 1.1136717825766236e-05,
+      "loss": 1.3199,
+      "step": 273
+    },
+    {
+      "epoch": 1.5329593267882187,
+      "grad_norm": 15.728068778759177,
+      "learning_rate": 1.1082032714819435e-05,
+      "loss": 1.4037,
+      "step": 274
+    },
+    {
+      "epoch": 1.5385694249649369,
+      "grad_norm": 35.24549151590082,
+      "learning_rate": 1.1027344574836825e-05,
+      "loss": 1.5653,
+      "step": 275
+    },
+    {
+      "epoch": 1.544179523141655,
+      "grad_norm": 16.731762943741455,
+      "learning_rate": 1.0972655425163183e-05,
+      "loss": 1.5923,
+      "step": 276
+    },
+    {
+      "epoch": 1.549789621318373,
+      "grad_norm": 12.833069361335747,
+      "learning_rate": 1.0917967285180571e-05,
+      "loss": 1.5142,
+      "step": 277
+    },
+    {
+      "epoch": 1.555399719495091,
+      "grad_norm": 19.33521264857588,
+      "learning_rate": 1.0863282174233766e-05,
+      "loss": 1.3127,
+      "step": 278
+    },
+    {
+      "epoch": 1.5610098176718092,
+      "grad_norm": 10.886910197548698,
+      "learning_rate": 1.0808602111555702e-05,
+      "loss": 1.6208,
+      "step": 279
+    },
+    {
+      "epoch": 1.5666199158485274,
+      "grad_norm": 12.801692217446645,
+      "learning_rate": 1.07539291161929e-05,
+      "loss": 1.3401,
+      "step": 280
+    },
+    {
+      "epoch": 1.5722300140252454,
+      "grad_norm": 17.836580126577534,
+      "learning_rate": 1.0699265206930934e-05,
+      "loss": 1.5505,
+      "step": 281
+    },
+    {
+      "epoch": 1.5778401122019634,
+      "grad_norm": 17.357322700028668,
+      "learning_rate": 1.0644612402219854e-05,
+      "loss": 1.698,
+      "step": 282
+    },
+    {
+      "epoch": 1.5834502103786816,
+      "grad_norm": 15.409331750453493,
+      "learning_rate": 1.0589972720099704e-05,
+      "loss": 1.5117,
+      "step": 283
+    },
+    {
+      "epoch": 1.5890603085553998,
+      "grad_norm": 11.164793017120967,
+      "learning_rate": 1.0535348178125965e-05,
+      "loss": 1.5952,
+      "step": 284
+    },
+    {
+      "epoch": 1.5946704067321178,
+      "grad_norm": 19.906733367495576,
+      "learning_rate": 1.0480740793295074e-05,
+      "loss": 1.3231,
+      "step": 285
+    },
+    {
+      "epoch": 1.6002805049088358,
+      "grad_norm": 9.391700103965178,
+      "learning_rate": 1.042615258196995e-05,
+      "loss": 1.5088,
+      "step": 286
+    },
+    {
+      "epoch": 1.605890603085554,
+      "grad_norm": 11.364457340008288,
+      "learning_rate": 1.0371585559805528e-05,
+      "loss": 1.2463,
+      "step": 287
+    },
+    {
+      "epoch": 1.6115007012622722,
+      "grad_norm": 14.723407501563633,
+      "learning_rate": 1.0317041741674341e-05,
+      "loss": 1.4825,
+      "step": 288
+    },
+    {
+      "epoch": 1.6171107994389902,
+      "grad_norm": 12.584544998433199,
+      "learning_rate": 1.0262523141592126e-05,
+      "loss": 1.8245,
+      "step": 289
+    },
+    {
+      "epoch": 1.6227208976157081,
+      "grad_norm": 13.733073782677504,
+      "learning_rate": 1.0208031772643443e-05,
+      "loss": 1.4269,
+      "step": 290
+    },
+    {
+      "epoch": 1.6283309957924264,
+      "grad_norm": 14.624299291370347,
+      "learning_rate": 1.0153569646907355e-05,
+      "loss": 1.3492,
+      "step": 291
+    },
+    {
+      "epoch": 1.6339410939691446,
+      "grad_norm": 12.581946392558763,
+      "learning_rate": 1.0099138775383115e-05,
+      "loss": 1.4458,
+      "step": 292
+    },
+    {
+      "epoch": 1.6395511921458625,
+      "grad_norm": 14.444232112139593,
+      "learning_rate": 1.0044741167915946e-05,
+      "loss": 1.3966,
+      "step": 293
+    },
+    {
+      "epoch": 1.6451612903225805,
+      "grad_norm": 19.357239455692902,
+      "learning_rate": 9.990378833122782e-06,
+      "loss": 1.3954,
+      "step": 294
+    },
+    {
+      "epoch": 1.6507713884992987,
+      "grad_norm": 16.39319341444051,
+      "learning_rate": 9.93605377831813e-06,
+      "loss": 1.4255,
+      "step": 295
+    },
+    {
+      "epoch": 1.656381486676017,
+      "grad_norm": 30.389343705342387,
+      "learning_rate": 9.881768009439952e-06,
+      "loss": 1.3105,
+      "step": 296
+    },
+    {
+      "epoch": 1.661991584852735,
+      "grad_norm": 10.78767731128213,
+      "learning_rate": 9.82752353097558e-06,
+      "loss": 1.5082,
+      "step": 297
+    },
+    {
+      "epoch": 1.6676016830294529,
+      "grad_norm": 10.851960829756253,
+      "learning_rate": 9.773322345887705e-06,
+      "loss": 1.3302,
+      "step": 298
+    },
+    {
+      "epoch": 1.673211781206171,
+      "grad_norm": 9.059627340481349,
+      "learning_rate": 9.719166455540437e-06,
+      "loss": 1.428,
+      "step": 299
+    },
+    {
+      "epoch": 1.6788218793828893,
+      "grad_norm": 11.056590609678853,
+      "learning_rate": 9.665057859625367e-06,
+      "loss": 1.4933,
+      "step": 300
+    },
+    {
+      "epoch": 1.6844319775596073,
+      "grad_norm": 18.000797951799324,
+      "learning_rate": 9.61099855608777e-06,
+      "loss": 1.3368,
+      "step": 301
+    },
+    {
+      "epoch": 1.6900420757363253,
+      "grad_norm": 12.711029397236132,
+      "learning_rate": 9.556990541052811e-06,
+      "loss": 1.5315,
+      "step": 302
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 16.660350616242294,
+      "learning_rate": 9.50303580875183e-06,
+      "loss": 1.5576,
+      "step": 303
+    },
+    {
+      "epoch": 1.7012622720897617,
+      "grad_norm": 14.18477102640596,
+      "learning_rate": 9.449136351448733e-06,
+      "loss": 1.4395,
+      "step": 304
+    },
+    {
+      "epoch": 1.7068723702664796,
+      "grad_norm": 16.66543319989344,
+      "learning_rate": 9.395294159366398e-06,
+      "loss": 1.3333,
+      "step": 305
+    },
+    {
+      "epoch": 1.7124824684431976,
+      "grad_norm": 12.550767222637742,
+      "learning_rate": 9.341511220613203e-06,
+      "loss": 1.4948,
+      "step": 306
+    },
+    {
+      "epoch": 1.7180925666199158,
+      "grad_norm": 23.14843194571176,
+      "learning_rate": 9.287789521109619e-06,
+      "loss": 1.3759,
+      "step": 307
+    },
+    {
+      "epoch": 1.723702664796634,
+      "grad_norm": 10.179110221624262,
+      "learning_rate": 9.234131044514866e-06,
+      "loss": 1.4955,
+      "step": 308
+    },
+    {
+      "epoch": 1.729312762973352,
+      "grad_norm": 11.671550250237754,
+      "learning_rate": 9.180537772153689e-06,
+      "loss": 1.5044,
+      "step": 309
+    },
+    {
+      "epoch": 1.73492286115007,
+      "grad_norm": 18.158491953419958,
+      "learning_rate": 9.12701168294316e-06,
+      "loss": 1.5487,
+      "step": 310
+    },
+    {
+      "epoch": 1.7405329593267882,
+      "grad_norm": 16.378480991727116,
+      "learning_rate": 9.073554753319653e-06,
+      "loss": 1.6555,
+      "step": 311
+    },
+    {
+      "epoch": 1.7461430575035064,
+      "grad_norm": 14.612627221953167,
+      "learning_rate": 9.020168957165843e-06,
+      "loss": 1.3901,
+      "step": 312
+    },
+    {
+      "epoch": 1.7517531556802244,
+      "grad_norm": 22.199668296254806,
+      "learning_rate": 8.9668562657378e-06,
+      "loss": 1.2821,
+      "step": 313
+    },
+    {
+      "epoch": 1.7573632538569424,
+      "grad_norm": 48.85051417469821,
+      "learning_rate": 8.913618647592246e-06,
+      "loss": 1.4017,
+      "step": 314
+    },
+    {
+      "epoch": 1.7629733520336606,
+      "grad_norm": 11.525812973776294,
+      "learning_rate": 8.860458068513831e-06,
+      "loss": 1.405,
+      "step": 315
+    },
+    {
+      "epoch": 1.7685834502103788,
+      "grad_norm": 9.926236369384918,
+      "learning_rate": 8.807376491442552e-06,
+      "loss": 1.498,
+      "step": 316
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 12.644238947963776,
+      "learning_rate": 8.754375876401296e-06,
+      "loss": 1.5187,
+      "step": 317
+    },
+    {
+      "epoch": 1.7798036465638147,
+      "grad_norm": 17.063941988263224,
+      "learning_rate": 8.701458180423425e-06,
+      "loss": 1.4912,
+      "step": 318
+    },
+    {
+      "epoch": 1.785413744740533,
+      "grad_norm": 21.892751402938607,
+      "learning_rate": 8.648625357480563e-06,
+      "loss": 1.6582,
+      "step": 319
+    },
+    {
+      "epoch": 1.7910238429172511,
+      "grad_norm": 11.579396690290965,
+      "learning_rate": 8.595879358410402e-06,
+      "loss": 1.2974,
+      "step": 320
+    },
+    {
+      "epoch": 1.7966339410939691,
+      "grad_norm": 7.407872465259077,
+      "learning_rate": 8.543222130844693e-06,
+      "loss": 1.3936,
+      "step": 321
+    },
+    {
+      "epoch": 1.802244039270687,
+      "grad_norm": 13.541093138926195,
+      "learning_rate": 8.490655619137318e-06,
+      "loss": 1.4678,
+      "step": 322
+    },
+    {
+      "epoch": 1.8078541374474053,
+      "grad_norm": 13.169175604119717,
+      "learning_rate": 8.438181764292509e-06,
+      "loss": 1.4833,
+      "step": 323
+    },
+    {
+      "epoch": 1.8134642356241235,
+      "grad_norm": 9.29297616022089,
+      "learning_rate": 8.385802503893159e-06,
+      "loss": 1.3668,
+      "step": 324
+    },
+    {
+      "epoch": 1.8190743338008415,
+      "grad_norm": 21.69771394920528,
+      "learning_rate": 8.333519772029297e-06,
+      "loss": 1.5304,
+      "step": 325
+    },
+    {
+      "epoch": 1.8246844319775595,
+      "grad_norm": 8.695597330254802,
+      "learning_rate": 8.28133549922665e-06,
+      "loss": 1.183,
+      "step": 326
+    },
+    {
+      "epoch": 1.8302945301542777,
+      "grad_norm": 11.450047920423891,
+      "learning_rate": 8.229251612375383e-06,
+      "loss": 1.0692,
+      "step": 327
+    },
+    {
+      "epoch": 1.8359046283309959,
+      "grad_norm": 15.564245276964593,
+      "learning_rate": 8.177270034658926e-06,
+      "loss": 1.3317,
+      "step": 328
+    },
+    {
+      "epoch": 1.8415147265077139,
+      "grad_norm": 12.643991254106773,
+      "learning_rate": 8.12539268548298e-06,
+      "loss": 1.1766,
+      "step": 329
+    },
+    {
+      "epoch": 1.8471248246844318,
+      "grad_norm": 13.666387299973383,
+      "learning_rate": 8.073621480404632e-06,
+      "loss": 1.4672,
+      "step": 330
+    },
+    {
+      "epoch": 1.85273492286115,
+      "grad_norm": 15.118851784764775,
+      "learning_rate": 8.021958331061622e-06,
+      "loss": 1.5273,
+      "step": 331
+    },
+    {
+      "epoch": 1.8583450210378682,
+      "grad_norm": 14.20758535775456,
+      "learning_rate": 7.97040514510177e-06,
+      "loss": 1.4684,
+      "step": 332
+    },
+    {
+      "epoch": 1.8639551192145862,
+      "grad_norm": 10.973607901863156,
+      "learning_rate": 7.91896382611253e-06,
+      "loss": 1.4965,
+      "step": 333
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 14.247686399471148,
+      "learning_rate": 7.86763627355068e-06,
+      "loss": 1.2917,
+      "step": 334
+    },
+    {
+      "epoch": 1.8751753155680224,
+      "grad_norm": 21.50390844260042,
+      "learning_rate": 7.816424382672229e-06,
+      "loss": 1.562,
+      "step": 335
+    },
+    {
+      "epoch": 1.8807854137447406,
+      "grad_norm": 11.819217383633273,
+      "learning_rate": 7.765330044462386e-06,
+      "loss": 1.4822,
+      "step": 336
+    },
+    {
+      "epoch": 1.8863955119214586,
+      "grad_norm": 14.161357008398616,
+      "learning_rate": 7.714355145565774e-06,
+      "loss": 1.6368,
+      "step": 337
+    },
+    {
+      "epoch": 1.8920056100981766,
+      "grad_norm": 16.56545755056043,
+      "learning_rate": 7.663501568216748e-06,
+      "loss": 1.3914,
+      "step": 338
+    },
+    {
+      "epoch": 1.8976157082748948,
+      "grad_norm": 14.791392493152658,
+      "learning_rate": 7.612771190169896e-06,
+      "loss": 1.5294,
+      "step": 339
+    },
+    {
+      "epoch": 1.903225806451613,
+      "grad_norm": 16.282820183914083,
+      "learning_rate": 7.56216588463071e-06,
+      "loss": 1.4449,
+      "step": 340
+    },
+    {
+      "epoch": 1.908835904628331,
+      "grad_norm": 24.6122748043118,
+      "learning_rate": 7.511687520186404e-06,
+      "loss": 1.5496,
+      "step": 341
+    },
+    {
+      "epoch": 1.914446002805049,
+      "grad_norm": 9.878894269958142,
+      "learning_rate": 7.461337960736936e-06,
+      "loss": 1.3899,
+      "step": 342
+    },
+    {
+      "epoch": 1.9200561009817672,
+      "grad_norm": 17.380558867917127,
+      "learning_rate": 7.411119065426174e-06,
+      "loss": 1.2366,
+      "step": 343
+    },
+    {
+      "epoch": 1.9256661991584854,
+      "grad_norm": 11.312914459477994,
+      "learning_rate": 7.361032688573235e-06,
+      "loss": 1.4102,
+      "step": 344
+    },
+    {
+      "epoch": 1.9312762973352033,
+      "grad_norm": 103.5132378549981,
+      "learning_rate": 7.311080679604048e-06,
+      "loss": 1.5552,
+      "step": 345
+    },
+    {
+      "epoch": 1.9368863955119213,
+      "grad_norm": 11.141721273139423,
+      "learning_rate": 7.261264882983024e-06,
+      "loss": 1.2666,
+      "step": 346
+    },
+    {
+      "epoch": 1.9424964936886395,
+      "grad_norm": 13.191713261655808,
+      "learning_rate": 7.211587138144986e-06,
+      "loss": 1.3972,
+      "step": 347
+    },
+    {
+      "epoch": 1.9481065918653577,
+      "grad_norm": 10.217614055594426,
+      "learning_rate": 7.162049279427228e-06,
+      "loss": 1.4429,
+      "step": 348
+    },
+    {
+      "epoch": 1.9537166900420757,
+      "grad_norm": 29.313597844076863,
+      "learning_rate": 7.112653136001777e-06,
+      "loss": 1.3011,
+      "step": 349
+    },
+    {
+      "epoch": 1.9593267882187937,
+      "grad_norm": 13.292763277903367,
+      "learning_rate": 7.063400531807873e-06,
+      "loss": 1.5477,
+      "step": 350
+    },
+    {
+      "epoch": 1.964936886395512,
+      "grad_norm": 13.900844713934955,
+      "learning_rate": 7.0142932854846104e-06,
+      "loss": 1.5371,
+      "step": 351
+    },
+    {
+      "epoch": 1.97054698457223,
+      "grad_norm": 9.80007860324782,
+      "learning_rate": 6.965333210303764e-06,
+      "loss": 1.4814,
+      "step": 352
+    },
+    {
+      "epoch": 1.976157082748948,
+      "grad_norm": 31.719102324919326,
+      "learning_rate": 6.9165221141028825e-06,
+      "loss": 1.5109,
+      "step": 353
+    },
+    {
+      "epoch": 1.981767180925666,
+      "grad_norm": 41.16300740394282,
+      "learning_rate": 6.8678617992184785e-06,
+      "loss": 1.3093,
+      "step": 354
+    },
+    {
+      "epoch": 1.9873772791023843,
+      "grad_norm": 14.381052416660255,
+      "learning_rate": 6.819354062419525e-06,
+      "loss": 1.4739,
+      "step": 355
+    },
+    {
+      "epoch": 1.9929873772791025,
+      "grad_norm": 18.327960590810015,
+      "learning_rate": 6.771000694841085e-06,
+      "loss": 1.4016,
+      "step": 356
+    },
+    {
+      "epoch": 1.9985974754558204,
+      "grad_norm": 23.842506596521428,
+      "learning_rate": 6.722803481918174e-06,
+      "loss": 1.3469,
+      "step": 357
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 23.842506596521428,
+      "learning_rate": 6.674764203319847e-06,
+      "loss": 0.4292,
+      "step": 358
+    },
+    {
+      "epoch": 2.005610098176718,
+      "grad_norm": 62.91644908073718,
+      "learning_rate": 6.626884632883468e-06,
+      "loss": 1.3894,
+      "step": 359
+    },
+    {
+      "epoch": 2.0112201963534364,
+      "grad_norm": 17.385006546849574,
+      "learning_rate": 6.579166538549232e-06,
+      "loss": 1.396,
+      "step": 360
+    },
+    {
+      "epoch": 2.016830294530154,
+      "grad_norm": 11.14616894465407,
+      "learning_rate": 6.531611682294862e-06,
+      "loss": 1.3324,
+      "step": 361
+    },
+    {
+      "epoch": 2.0224403927068724,
+      "grad_norm": 13.234762237299156,
+      "learning_rate": 6.48422182007056e-06,
+      "loss": 1.5692,
+      "step": 362
+    },
+    {
+      "epoch": 2.0280504908835906,
+      "grad_norm": 16.139630982243954,
+      "learning_rate": 6.436998701734178e-06,
+      "loss": 1.5417,
+      "step": 363
+    },
+    {
+      "epoch": 2.0336605890603083,
+      "grad_norm": 10.479080049599737,
+      "learning_rate": 6.389944070986582e-06,
+      "loss": 1.5044,
+      "step": 364
+    },
+    {
+      "epoch": 2.0392706872370265,
+      "grad_norm": 9.271240066180434,
+      "learning_rate": 6.343059665307288e-06,
+      "loss": 1.3809,
+      "step": 365
+    },
+    {
+      "epoch": 2.0448807854137447,
+      "grad_norm": 12.665084229385839,
+      "learning_rate": 6.296347215890299e-06,
+      "loss": 1.7156,
+      "step": 366
+    },
+    {
+      "epoch": 2.050490883590463,
+      "grad_norm": 11.925013818106061,
+      "learning_rate": 6.24980844758017e-06,
+      "loss": 1.3325,
+      "step": 367
+    },
+    {
+      "epoch": 2.056100981767181,
+      "grad_norm": 28.984453902503265,
+      "learning_rate": 6.203445078808334e-06,
+      "loss": 1.5709,
+      "step": 368
+    },
+    {
+      "epoch": 2.061711079943899,
+      "grad_norm": 36.32322282586609,
+      "learning_rate": 6.157258821529648e-06,
+      "loss": 1.3057,
+      "step": 369
+    },
+    {
+      "epoch": 2.067321178120617,
+      "grad_norm": 18.435527641328143,
+      "learning_rate": 6.1112513811591625e-06,
+      "loss": 1.4139,
+      "step": 370
+    },
+    {
+      "epoch": 2.0729312762973353,
+      "grad_norm": 15.316146790050897,
+      "learning_rate": 6.065424456509177e-06,
+      "loss": 1.4445,
+      "step": 371
+    },
+    {
+      "epoch": 2.078541374474053,
+      "grad_norm": 9.049133203538355,
+      "learning_rate": 6.019779739726483e-06,
+      "loss": 1.3055,
+      "step": 372
+    },
+    {
+      "epoch": 2.0841514726507713,
+      "grad_norm": 24.250935935571302,
+      "learning_rate": 5.974318916229909e-06,
+      "loss": 1.2852,
+      "step": 373
+    },
+    {
+      "epoch": 2.0897615708274895,
+      "grad_norm": 11.121746868870078,
+      "learning_rate": 5.9290436646480635e-06,
+      "loss": 1.3112,
+      "step": 374
+    },
+    {
+      "epoch": 2.0953716690042077,
+      "grad_norm": 27.640809058263656,
+      "learning_rate": 5.883955656757361e-06,
+      "loss": 1.2175,
+      "step": 375
+    },
+    {
+      "epoch": 2.100981767180926,
+      "grad_norm": 7.733612352649396,
+      "learning_rate": 5.839056557420306e-06,
+      "loss": 1.5557,
+      "step": 376
+    },
+    {
+      "epoch": 2.1065918653576436,
+      "grad_norm": 18.803659684472592,
+      "learning_rate": 5.794348024523991e-06,
+      "loss": 1.3253,
+      "step": 377
+    },
+    {
+      "epoch": 2.112201963534362,
+      "grad_norm": 8.840256456646525,
+      "learning_rate": 5.749831708918905e-06,
+      "loss": 1.5209,
+      "step": 378
+    },
+    {
+      "epoch": 2.11781206171108,
+      "grad_norm": 9.645779423670444,
+      "learning_rate": 5.705509254357962e-06,
+      "loss": 1.4534,
+      "step": 379
+    },
+    {
+      "epoch": 2.123422159887798,
+      "grad_norm": 19.518741348844134,
+      "learning_rate": 5.6613822974358046e-06,
+      "loss": 1.3217,
+      "step": 380
+    },
+    {
+      "epoch": 2.129032258064516,
+      "grad_norm": 22.14350090057281,
+      "learning_rate": 5.617452467528387e-06,
+      "loss": 1.3701,
+      "step": 381
+    },
+    {
+      "epoch": 2.134642356241234,
+      "grad_norm": 12.240003119839916,
+      "learning_rate": 5.573721386732792e-06,
+      "loss": 1.2617,
+      "step": 382
+    },
+    {
+      "epoch": 2.1402524544179524,
+      "grad_norm": 9.94341073314739,
+      "learning_rate": 5.530190669807354e-06,
+      "loss": 1.433,
+      "step": 383
+    },
+    {
+      "epoch": 2.1458625525946706,
+      "grad_norm": 19.958625594652514,
+      "learning_rate": 5.486861924112021e-06,
+      "loss": 1.1168,
+      "step": 384
+    },
+    {
+      "epoch": 2.1514726507713884,
+      "grad_norm": 19.91297539332411,
+      "learning_rate": 5.443736749549008e-06,
+      "loss": 1.5081,
+      "step": 385
+    },
+    {
+      "epoch": 2.1570827489481066,
+      "grad_norm": 9.46122164871927,
+      "learning_rate": 5.400816738503725e-06,
+      "loss": 1.6113,
+      "step": 386
+    },
+    {
+      "epoch": 2.162692847124825,
+      "grad_norm": 15.132774640948087,
+      "learning_rate": 5.358103475785963e-06,
+      "loss": 1.7156,
+      "step": 387
+    },
+    {
+      "epoch": 2.1683029453015426,
+      "grad_norm": 27.73349930634087,
+      "learning_rate": 5.315598538571405e-06,
+      "loss": 1.4951,
+      "step": 388
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 21.02138889105744,
+      "learning_rate": 5.273303496343356e-06,
+      "loss": 1.4608,
+      "step": 389
+    },
+    {
+      "epoch": 2.179523141654979,
+      "grad_norm": 15.21722666958038,
+      "learning_rate": 5.231219910834808e-06,
+      "loss": 1.3213,
+      "step": 390
+    },
+    {
+      "epoch": 2.185133239831697,
+      "grad_norm": 17.053473708225102,
+      "learning_rate": 5.189349335970779e-06,
+      "loss": 1.6626,
+      "step": 391
+    },
+    {
+      "epoch": 2.1907433380084154,
+      "grad_norm": 30.125323797473353,
+      "learning_rate": 5.147693317810922e-06,
+      "loss": 1.4193,
+      "step": 392
+    },
+    {
+      "epoch": 2.196353436185133,
+      "grad_norm": 14.582213567512756,
+      "learning_rate": 5.106253394492435e-06,
+      "loss": 1.396,
+      "step": 393
+    },
+    {
+      "epoch": 2.2019635343618513,
+      "grad_norm": 18.58071509244748,
+      "learning_rate": 5.065031096173285e-06,
+      "loss": 1.3126,
+      "step": 394
+    },
+    {
+      "epoch": 2.2075736325385695,
+      "grad_norm": 18.323391904983588,
+      "learning_rate": 5.024027944975682e-06,
+      "loss": 1.5001,
+      "step": 395
+    },
+    {
+      "epoch": 2.2131837307152873,
+      "grad_norm": 9.131786473934786,
+      "learning_rate": 4.983245454929897e-06,
+      "loss": 1.1489,
+      "step": 396
+    },
+    {
+      "epoch": 2.2187938288920055,
+      "grad_norm": 19.531251954860753,
+      "learning_rate": 4.942685131918347e-06,
+      "loss": 1.7063,
+      "step": 397
+    },
+    {
+      "epoch": 2.2244039270687237,
+      "grad_norm": 11.650215958091437,
+      "learning_rate": 4.902348473619982e-06,
+      "loss": 1.3877,
+      "step": 398
+    },
+    {
+      "epoch": 2.230014025245442,
+      "grad_norm": 14.244474600713215,
+      "learning_rate": 4.862236969455008e-06,
+      "loss": 1.3306,
+      "step": 399
+    },
+    {
+      "epoch": 2.23562412342216,
+      "grad_norm": 27.134645926912214,
+      "learning_rate": 4.82235210052986e-06,
+      "loss": 1.5161,
+      "step": 400
+    },
+    {
+      "epoch": 2.241234221598878,
+      "grad_norm": 19.080120264645604,
+      "learning_rate": 4.782695339582542e-06,
+      "loss": 1.2893,
+      "step": 401
+    },
+    {
+      "epoch": 2.246844319775596,
+      "grad_norm": 11.03852579482729,
+      "learning_rate": 4.74326815092822e-06,
+      "loss": 1.3512,
+      "step": 402
+    },
+    {
+      "epoch": 2.2524544179523143,
+      "grad_norm": 8.02379081596676,
+      "learning_rate": 4.704071990405177e-06,
+      "loss": 1.2449,
+      "step": 403
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 9.947902369037147,
+      "learning_rate": 4.6651083053210335e-06,
+      "loss": 1.2081,
+      "step": 404
+    },
+    {
+      "epoch": 2.2636746143057502,
+      "grad_norm": 18.939217068942586,
+      "learning_rate": 4.6263785343993275e-06,
+      "loss": 1.5017,
+      "step": 405
+    },
+    {
+      "epoch": 2.2692847124824684,
+      "grad_norm": 49.48205350763517,
+      "learning_rate": 4.587884107726371e-06,
+      "loss": 1.5256,
+      "step": 406
+    },
+    {
+      "epoch": 2.2748948106591866,
+      "grad_norm": 62.34571721147613,
+      "learning_rate": 4.549626446698462e-06,
+      "loss": 1.2649,
+      "step": 407
+    },
+    {
+      "epoch": 2.280504908835905,
+      "grad_norm": 11.301553295405313,
+      "learning_rate": 4.51160696396938e-06,
+      "loss": 1.3876,
+      "step": 408
+    },
+    {
+      "epoch": 2.2861150070126226,
+      "grad_norm": 14.545319112891631,
+      "learning_rate": 4.473827063398246e-06,
+      "loss": 1.6277,
+      "step": 409
+    },
+    {
+      "epoch": 2.291725105189341,
+      "grad_norm": 12.111799331941523,
+      "learning_rate": 4.436288139997673e-06,
+      "loss": 1.4128,
+      "step": 410
+    },
+    {
+      "epoch": 2.297335203366059,
+      "grad_norm": 25.16319364869307,
+      "learning_rate": 4.398991579882247e-06,
+      "loss": 1.3649,
+      "step": 411
+    },
+    {
+      "epoch": 2.3029453015427768,
+      "grad_norm": 9.705872335231792,
+      "learning_rate": 4.361938760217371e-06,
+      "loss": 1.2412,
+      "step": 412
+    },
+    {
+      "epoch": 2.308555399719495,
+      "grad_norm": 15.004750384511468,
+      "learning_rate": 4.325131049168382e-06,
+      "loss": 1.6177,
+      "step": 413
+    },
+    {
+      "epoch": 2.314165497896213,
+      "grad_norm": 13.353110396095241,
+      "learning_rate": 4.288569805850059e-06,
+      "loss": 1.2242,
+      "step": 414
+    },
+    {
+      "epoch": 2.3197755960729314,
+      "grad_norm": 10.438909781171024,
+      "learning_rate": 4.2522563802764255e-06,
+      "loss": 1.1428,
+      "step": 415
+    },
+    {
+      "epoch": 2.3253856942496496,
+      "grad_norm": 12.320780473313446,
+      "learning_rate": 4.216192113310895e-06,
+      "loss": 1.2153,
+      "step": 416
+    },
+    {
+      "epoch": 2.3309957924263673,
+      "grad_norm": 18.27797507745344,
+      "learning_rate": 4.180378336616773e-06,
+      "loss": 1.2527,
+      "step": 417
+    },
+    {
+      "epoch": 2.3366058906030855,
+      "grad_norm": 12.936629262597277,
+      "learning_rate": 4.144816372608073e-06,
+      "loss": 1.3047,
+      "step": 418
+    },
+    {
+      "epoch": 2.3422159887798037,
+      "grad_norm": 15.908852685108856,
+      "learning_rate": 4.1095075344007014e-06,
+      "loss": 1.5486,
+      "step": 419
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 15.463005059149006,
+      "learning_rate": 4.074453125763961e-06,
+      "loss": 1.3726,
+      "step": 420
+    },
+    {
+      "epoch": 2.3534361851332397,
+      "grad_norm": 14.294215716320576,
+      "learning_rate": 4.039654441072405e-06,
+      "loss": 1.3427,
+      "step": 421
+    },
+    {
+      "epoch": 2.359046283309958,
+      "grad_norm": 15.768455718275225,
+      "learning_rate": 4.005112765258057e-06,
+      "loss": 1.3789,
+      "step": 422
+    },
+    {
+      "epoch": 2.364656381486676,
+      "grad_norm": 10.424506077881269,
+      "learning_rate": 3.970829373762954e-06,
+      "loss": 1.3088,
+      "step": 423
+    },
+    {
+      "epoch": 2.3702664796633943,
+      "grad_norm": 10.54267428276343,
+      "learning_rate": 3.936805532492052e-06,
+      "loss": 1.6141,
+      "step": 424
+    },
+    {
+      "epoch": 2.375876577840112,
+      "grad_norm": 16.449513998300606,
+      "learning_rate": 3.90304249776649e-06,
+      "loss": 1.3617,
+      "step": 425
+    },
+    {
+      "epoch": 2.3814866760168303,
+      "grad_norm": 13.957587681425652,
+      "learning_rate": 3.869541516277191e-06,
+      "loss": 1.4329,
+      "step": 426
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 9.769958163690362,
+      "learning_rate": 3.836303825038835e-06,
+      "loss": 1.5039,
+      "step": 427
+    },
+    {
+      "epoch": 2.3927068723702662,
+      "grad_norm": 16.573641265327524,
+      "learning_rate": 3.8033306513441876e-06,
+      "loss": 1.4685,
+      "step": 428
+    },
+    {
+      "epoch": 2.3983169705469845,
+      "grad_norm": 61.04935510961862,
+      "learning_rate": 3.770623212718765e-06,
+      "loss": 1.5065,
+      "step": 429
+    },
+    {
+      "epoch": 2.4039270687237027,
+      "grad_norm": 13.814139766936878,
+      "learning_rate": 3.7381827168758867e-06,
+      "loss": 1.708,
+      "step": 430
+    },
+    {
+      "epoch": 2.409537166900421,
+      "grad_norm": 12.20707134653504,
+      "learning_rate": 3.7060103616720973e-06,
+      "loss": 1.4541,
+      "step": 431
+    },
+    {
+      "epoch": 2.415147265077139,
+      "grad_norm": 10.831279423590178,
+      "learning_rate": 3.674107335062903e-06,
+      "loss": 1.3367,
+      "step": 432
+    },
+    {
+      "epoch": 2.420757363253857,
+      "grad_norm": 15.17957774472088,
+      "learning_rate": 3.6424748150589383e-06,
+      "loss": 1.4451,
+      "step": 433
+    },
+    {
+      "epoch": 2.426367461430575,
+      "grad_norm": 43.88550095171706,
+      "learning_rate": 3.6111139696824445e-06,
+      "loss": 1.4897,
+      "step": 434
+    },
+    {
+      "epoch": 2.4319775596072932,
+      "grad_norm": 17.022424144766777,
+      "learning_rate": 3.5800259569241597e-06,
+      "loss": 1.4451,
+      "step": 435
+    },
+    {
+      "epoch": 2.437587657784011,
+      "grad_norm": 13.121459950014572,
+      "learning_rate": 3.5492119247005406e-06,
+      "loss": 1.4099,
+      "step": 436
+    },
+    {
+      "epoch": 2.443197755960729,
+      "grad_norm": 20.854465875412313,
+      "learning_rate": 3.5186730108113966e-06,
+      "loss": 1.3777,
+      "step": 437
+    },
+    {
+      "epoch": 2.4488078541374474,
+      "grad_norm": 19.82240306986655,
+      "learning_rate": 3.4884103428978655e-06,
+      "loss": 1.3162,
+      "step": 438
+    },
+    {
+      "epoch": 2.4544179523141656,
+      "grad_norm": 19.743675967797774,
+      "learning_rate": 3.4584250384007687e-06,
+      "loss": 1.3477,
+      "step": 439
+    },
+    {
+      "epoch": 2.460028050490884,
+      "grad_norm": 31.40435038497109,
+      "learning_rate": 3.428718204519369e-06,
+      "loss": 1.2245,
+      "step": 440
+    },
+    {
+      "epoch": 2.4656381486676016,
+      "grad_norm": 10.470367402241134,
+      "learning_rate": 3.399290938170473e-06,
+      "loss": 1.5034,
+      "step": 441
+    },
+    {
+      "epoch": 2.4712482468443198,
+      "grad_norm": 10.92687941414526,
+      "learning_rate": 3.3701443259479293e-06,
+      "loss": 1.4631,
+      "step": 442
+    },
+    {
+      "epoch": 2.476858345021038,
+      "grad_norm": 11.388896835005518,
+      "learning_rate": 3.3412794440825138e-06,
+      "loss": 1.4725,
+      "step": 443
+    },
+    {
+      "epoch": 2.4824684431977557,
+      "grad_norm": 9.600043291161747,
+      "learning_rate": 3.3126973584021793e-06,
+      "loss": 1.3522,
+      "step": 444
+    },
+    {
+      "epoch": 2.488078541374474,
+      "grad_norm": 14.275333506225046,
+      "learning_rate": 3.2843991242927097e-06,
+      "loss": 1.2974,
+      "step": 445
+    },
+    {
+      "epoch": 2.493688639551192,
+      "grad_norm": 12.809793948684316,
+      "learning_rate": 3.256385786658748e-06,
+      "loss": 1.3043,
+      "step": 446
+    },
+    {
+      "epoch": 2.4992987377279103,
+      "grad_norm": 13.618393566140282,
+      "learning_rate": 3.2286583798852045e-06,
+      "loss": 1.3538,
+      "step": 447
+    },
+    {
+      "epoch": 2.5049088359046285,
+      "grad_norm": 33.32529639238415,
+      "learning_rate": 3.2012179277990814e-06,
+      "loss": 1.4108,
+      "step": 448
+    },
+    {
+      "epoch": 2.5105189340813463,
+      "grad_norm": 14.302476484830468,
+      "learning_rate": 3.1740654436316443e-06,
+      "loss": 1.4814,
+      "step": 449
+    },
+    {
+      "epoch": 2.5161290322580645,
+      "grad_norm": 16.872183410879636,
+      "learning_rate": 3.1472019299810296e-06,
+      "loss": 1.4011,
+      "step": 450
+    },
+    {
+      "epoch": 2.5217391304347827,
+      "grad_norm": 8.486077404359225,
+      "learning_rate": 3.120628378775216e-06,
+      "loss": 1.4185,
+      "step": 451
+    },
+    {
+      "epoch": 2.5273492286115005,
+      "grad_norm": 11.71800465321583,
+      "learning_rate": 3.09434577123539e-06,
+      "loss": 1.2849,
+      "step": 452
+    },
+    {
+      "epoch": 2.5329593267882187,
+      "grad_norm": 14.853119779061982,
+      "learning_rate": 3.06835507783973e-06,
+      "loss": 1.5649,
+      "step": 453
+    },
+    {
+      "epoch": 2.538569424964937,
+      "grad_norm": 65.58056847644397,
+      "learning_rate": 3.0426572582875557e-06,
+      "loss": 1.6189,
+      "step": 454
+    },
+    {
+      "epoch": 2.544179523141655,
+      "grad_norm": 12.530368758694713,
+      "learning_rate": 3.017253261463906e-06,
+      "loss": 1.3411,
+      "step": 455
+    },
+    {
+      "epoch": 2.5497896213183733,
+      "grad_norm": 11.055810688338571,
+      "learning_rate": 2.992144025404495e-06,
+      "loss": 1.5449,
+      "step": 456
+    },
+    {
+      "epoch": 2.555399719495091,
+      "grad_norm": 27.908163066834966,
+      "learning_rate": 2.9673304772610702e-06,
+      "loss": 1.4863,
+      "step": 457
+    },
+    {
+      "epoch": 2.5610098176718092,
+      "grad_norm": 19.88479296802079,
+      "learning_rate": 2.942813533267185e-06,
+      "loss": 1.5879,
+      "step": 458
+    },
+    {
+      "epoch": 2.5666199158485274,
+      "grad_norm": 12.78986539705726,
+      "learning_rate": 2.918594098704367e-06,
+      "loss": 1.697,
+      "step": 459
+    },
+    {
+      "epoch": 2.572230014025245,
+      "grad_norm": 10.969686431630194,
+      "learning_rate": 2.894673067868685e-06,
+      "loss": 1.338,
+      "step": 460
+    },
+    {
+      "epoch": 2.5778401122019634,
+      "grad_norm": 24.827786234269603,
+      "learning_rate": 2.871051324037735e-06,
+      "loss": 1.5449,
+      "step": 461
+    },
+    {
+      "epoch": 2.5834502103786816,
+      "grad_norm": 9.469236231927587,
+      "learning_rate": 2.8477297394380167e-06,
+      "loss": 1.5096,
+      "step": 462
+    },
+    {
+      "epoch": 2.5890603085554,
+      "grad_norm": 17.452000273913672,
+      "learning_rate": 2.824709175212734e-06,
+      "loss": 1.5273,
+      "step": 463
+    },
+    {
+      "epoch": 2.594670406732118,
+      "grad_norm": 13.256452994228898,
+      "learning_rate": 2.8019904813899974e-06,
+      "loss": 1.5446,
+      "step": 464
+    },
+    {
+      "epoch": 2.6002805049088358,
+      "grad_norm": 23.868494536366445,
+      "learning_rate": 2.7795744968514276e-06,
+      "loss": 1.2896,
+      "step": 465
+    },
+    {
+      "epoch": 2.605890603085554,
+      "grad_norm": 21.606197493757485,
+      "learning_rate": 2.7574620493011945e-06,
+      "loss": 1.348,
+      "step": 466
+    },
+    {
+      "epoch": 2.611500701262272,
+      "grad_norm": 16.889481350139746,
+      "learning_rate": 2.735653955235441e-06,
+      "loss": 1.6912,
+      "step": 467
+    },
+    {
+      "epoch": 2.61711079943899,
+      "grad_norm": 10.061444950954213,
+      "learning_rate": 2.7141510199121402e-06,
+      "loss": 1.4507,
+      "step": 468
+    },
+    {
+      "epoch": 2.622720897615708,
+      "grad_norm": 22.843764698250858,
+      "learning_rate": 2.6929540373213693e-06,
+      "loss": 1.1088,
+      "step": 469
+    },
+    {
+      "epoch": 2.6283309957924264,
+      "grad_norm": 57.54763815772751,
+      "learning_rate": 2.672063790155971e-06,
+      "loss": 1.3167,
+      "step": 470
+    },
+    {
+      "epoch": 2.6339410939691446,
+      "grad_norm": 14.012079397996779,
+      "learning_rate": 2.6514810497826755e-06,
+      "loss": 1.4568,
+      "step": 471
+    },
+    {
+      "epoch": 2.6395511921458628,
+      "grad_norm": 11.72337445092119,
+      "learning_rate": 2.6312065762136023e-06,
+      "loss": 1.3044,
+      "step": 472
+    },
+    {
+      "epoch": 2.6451612903225805,
+      "grad_norm": 11.45913716212178,
+      "learning_rate": 2.611241118078204e-06,
+      "loss": 1.6543,
+      "step": 473
+    },
+    {
+      "epoch": 2.6507713884992987,
+      "grad_norm": 34.40436182190075,
+      "learning_rate": 2.5915854125956237e-06,
+      "loss": 1.1738,
+      "step": 474
+    },
+    {
+      "epoch": 2.656381486676017,
+      "grad_norm": 29.120537029967604,
+      "learning_rate": 2.572240185547469e-06,
+      "loss": 1.4869,
+      "step": 475
+    },
+    {
+      "epoch": 2.6619915848527347,
+      "grad_norm": 29.563771869983317,
+      "learning_rate": 2.553206151251016e-06,
+      "loss": 1.3673,
+      "step": 476
+    },
+    {
+      "epoch": 2.667601683029453,
+      "grad_norm": 11.031768588310115,
+      "learning_rate": 2.534484012532836e-06,
+      "loss": 1.4917,
+      "step": 477
+    },
+    {
+      "epoch": 2.673211781206171,
+      "grad_norm": 31.01674108223117,
+      "learning_rate": 2.516074460702832e-06,
+      "loss": 1.5571,
+      "step": 478
+    },
+    {
+      "epoch": 2.6788218793828893,
+      "grad_norm": 12.153681224765794,
+      "learning_rate": 2.497978175528732e-06,
+      "loss": 1.4064,
+      "step": 479
+    },
+    {
+      "epoch": 2.6844319775596075,
+      "grad_norm": 16.113536815274934,
+      "learning_rate": 2.480195825210967e-06,
+      "loss": 1.4236,
+      "step": 480
+    },
+    {
+      "epoch": 2.6900420757363253,
+      "grad_norm": 31.39801837106822,
+      "learning_rate": 2.4627280663580147e-06,
+      "loss": 1.46,
+      "step": 481
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 11.928549532005288,
+      "learning_rate": 2.445575543962148e-06,
+      "loss": 1.293,
+      "step": 482
+    },
+    {
+      "epoch": 2.7012622720897617,
+      "grad_norm": 12.85881510061664,
+      "learning_rate": 2.428738891375614e-06,
+      "loss": 1.2772,
+      "step": 483
+    },
+    {
+      "epoch": 2.7068723702664794,
+      "grad_norm": 8.372011225533786,
+      "learning_rate": 2.412218730287258e-06,
+      "loss": 1.3799,
+      "step": 484
+    },
+    {
+      "epoch": 2.7124824684431976,
+      "grad_norm": 11.043459774828861,
+      "learning_rate": 2.3960156706995585e-06,
+      "loss": 1.6409,
+      "step": 485
+    },
+    {
+      "epoch": 2.718092566619916,
+      "grad_norm": 15.24112173517461,
+      "learning_rate": 2.3801303109061096e-06,
+      "loss": 1.4136,
+      "step": 486
+    },
+    {
+      "epoch": 2.723702664796634,
+      "grad_norm": 16.22094507739665,
+      "learning_rate": 2.364563237469525e-06,
+      "loss": 1.3207,
+      "step": 487
+    },
+    {
+      "epoch": 2.7293127629733522,
+      "grad_norm": 30.720161936633414,
+      "learning_rate": 2.3493150251997785e-06,
+      "loss": 1.3901,
+      "step": 488
+    },
+    {
+      "epoch": 2.73492286115007,
+      "grad_norm": 11.60665902371763,
+      "learning_rate": 2.334386237132988e-06,
+      "loss": 1.4446,
+      "step": 489
+    },
+    {
+      "epoch": 2.740532959326788,
+      "grad_norm": 12.321559833371005,
+      "learning_rate": 2.3197774245106123e-06,
+      "loss": 1.5776,
+      "step": 490
+    },
+    {
+      "epoch": 2.7461430575035064,
+      "grad_norm": 18.09110828044268,
+      "learning_rate": 2.3054891267591058e-06,
+      "loss": 1.7661,
+      "step": 491
+    },
+    {
+      "epoch": 2.751753155680224,
+      "grad_norm": 23.7097652014346,
+      "learning_rate": 2.2915218714700015e-06,
+      "loss": 1.395,
+      "step": 492
+    },
+    {
+      "epoch": 2.7573632538569424,
+      "grad_norm": 19.104951625171648,
+      "learning_rate": 2.2778761743804203e-06,
+      "loss": 1.4431,
+      "step": 493
+    },
+    {
+      "epoch": 2.7629733520336606,
+      "grad_norm": 11.734034381021537,
+      "learning_rate": 2.2645525393540367e-06,
+      "loss": 1.3761,
+      "step": 494
+    },
+    {
+      "epoch": 2.7685834502103788,
+      "grad_norm": 16.148466253040784,
+      "learning_rate": 2.2515514583624734e-06,
+      "loss": 1.447,
+      "step": 495
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": 8.3147371004889,
+      "learning_rate": 2.238873411467126e-06,
+      "loss": 1.5092,
+      "step": 496
+    },
+    {
+      "epoch": 2.7798036465638147,
+      "grad_norm": 21.439520034906838,
+      "learning_rate": 2.2265188668014505e-06,
+      "loss": 1.6416,
+      "step": 497
+    },
+    {
+      "epoch": 2.785413744740533,
+      "grad_norm": 15.340300048538328,
+      "learning_rate": 2.214488280553663e-06,
+      "loss": 1.4431,
+      "step": 498
+    },
+    {
+      "epoch": 2.791023842917251,
+      "grad_norm": 23.64651049663467,
+      "learning_rate": 2.2027820969499108e-06,
+      "loss": 1.4033,
+      "step": 499
+    },
+    {
+      "epoch": 2.796633941093969,
+      "grad_norm": 17.537330409566238,
+      "learning_rate": 2.191400748237856e-06,
+      "loss": 1.4545,
+      "step": 500
+    },
+    {
+      "epoch": 2.802244039270687,
+      "grad_norm": 13.387827217231019,
+      "learning_rate": 2.1803446546707198e-06,
+      "loss": 1.4768,
+      "step": 501
+    },
+    {
+      "epoch": 2.8078541374474053,
+      "grad_norm": 12.31938827830441,
+      "learning_rate": 2.1696142244917686e-06,
+      "loss": 1.3513,
+      "step": 502
+    },
+    {
+      "epoch": 2.8134642356241235,
+      "grad_norm": 9.56317144380213,
+      "learning_rate": 2.1592098539192337e-06,
+      "loss": 1.4576,
+      "step": 503
+    },
+    {
+      "epoch": 2.8190743338008417,
+      "grad_norm": 15.664022628440854,
+      "learning_rate": 2.149131927131684e-06,
+      "loss": 1.2717,
+      "step": 504
+    },
+    {
+      "epoch": 2.8246844319775595,
+      "grad_norm": 10.973638788779944,
+      "learning_rate": 2.1393808162538427e-06,
+      "loss": 1.5818,
+      "step": 505
+    },
+    {
+      "epoch": 2.8302945301542777,
+      "grad_norm": 11.696358945441519,
+      "learning_rate": 2.129956881342839e-06,
+      "loss": 1.5115,
+      "step": 506
+    },
+    {
+      "epoch": 2.835904628330996,
+      "grad_norm": 35.59073283765529,
+      "learning_rate": 2.120860470374923e-06,
+      "loss": 1.4507,
+      "step": 507
+    },
+    {
+      "epoch": 2.8415147265077136,
+      "grad_norm": 8.511008157750572,
+      "learning_rate": 2.1120919192326068e-06,
+      "loss": 1.6359,
+      "step": 508
+    },
+    {
+      "epoch": 2.847124824684432,
+      "grad_norm": 14.507595686447782,
+      "learning_rate": 2.1036515516922707e-06,
+      "loss": 1.3308,
+      "step": 509
+    },
+    {
+      "epoch": 2.85273492286115,
+      "grad_norm": 10.038060403672617,
+      "learning_rate": 2.0955396794122045e-06,
+      "loss": 1.538,
+      "step": 510
+    },
+    {
+      "epoch": 2.8583450210378682,
+      "grad_norm": 38.19467872715205,
+      "learning_rate": 2.0877566019210964e-06,
+      "loss": 1.27,
+      "step": 511
+    },
+    {
+      "epoch": 2.8639551192145865,
+      "grad_norm": 11.1405731929677,
+      "learning_rate": 2.08030260660698e-06,
+      "loss": 1.5597,
+      "step": 512
+    },
+    {
+      "epoch": 2.869565217391304,
+      "grad_norm": 39.113003355372584,
+      "learning_rate": 2.0731779687066127e-06,
+      "loss": 1.4037,
+      "step": 513
+    },
+    {
+      "epoch": 2.8751753155680224,
+      "grad_norm": 16.446670937193733,
+      "learning_rate": 2.0663829512953256e-06,
+      "loss": 1.782,
+      "step": 514
+    },
+    {
+      "epoch": 2.8807854137447406,
+      "grad_norm": 13.566342003661653,
+      "learning_rate": 2.0599178052772954e-06,
+      "loss": 1.4863,
+      "step": 515
+    },
+    {
+      "epoch": 2.8863955119214584,
+      "grad_norm": 9.581024556505865,
+      "learning_rate": 2.0537827693762933e-06,
+      "loss": 1.4205,
+      "step": 516
+    },
+    {
+      "epoch": 2.8920056100981766,
+      "grad_norm": 12.300805161743316,
+      "learning_rate": 2.047978070126859e-06,
+      "loss": 1.1908,
+      "step": 517
+    },
+    {
+      "epoch": 2.897615708274895,
+      "grad_norm": 9.130444624343745,
+      "learning_rate": 2.042503921865942e-06,
+      "loss": 1.4871,
+      "step": 518
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 12.067399220622741,
+      "learning_rate": 2.0373605267249856e-06,
+      "loss": 1.3093,
+      "step": 519
+    },
+    {
+      "epoch": 2.908835904628331,
+      "grad_norm": 20.77624775965342,
+      "learning_rate": 2.0325480746224673e-06,
+      "loss": 1.4156,
+      "step": 520
+    },
+    {
+      "epoch": 2.914446002805049,
+      "grad_norm": 21.80730408847714,
+      "learning_rate": 2.028066743256877e-06,
+      "loss": 1.4802,
+      "step": 521
+    },
+    {
+      "epoch": 2.920056100981767,
+      "grad_norm": 14.511189470372491,
+      "learning_rate": 2.0239166981001634e-06,
+      "loss": 1.3718,
+      "step": 522
+    },
+    {
+      "epoch": 2.9256661991584854,
+      "grad_norm": 24.388657913241754,
+      "learning_rate": 2.020098092391622e-06,
+      "loss": 1.3668,
+      "step": 523
+    },
+    {
+      "epoch": 2.931276297335203,
+      "grad_norm": 17.0026639824568,
+      "learning_rate": 2.0166110671322357e-06,
+      "loss": 1.1583,
+      "step": 524
+    },
+    {
+      "epoch": 2.9368863955119213,
+      "grad_norm": 13.89007224984465,
+      "learning_rate": 2.013455751079469e-06,
+      "loss": 1.6348,
+      "step": 525
+    },
+    {
+      "epoch": 2.9424964936886395,
+      "grad_norm": 29.20020338138551,
+      "learning_rate": 2.0106322607425133e-06,
+      "loss": 1.4146,
+      "step": 526
+    },
+    {
+      "epoch": 2.9481065918653577,
+      "grad_norm": 13.501005733452327,
+      "learning_rate": 2.008140700377986e-06,
+      "loss": 1.3433,
+      "step": 527
+    },
+    {
+      "epoch": 2.953716690042076,
+      "grad_norm": 11.018447723777982,
+      "learning_rate": 2.00598116198608e-06,
+      "loss": 1.4188,
+      "step": 528
+    },
+    {
+      "epoch": 2.9593267882187937,
+      "grad_norm": 11.852148777496266,
+      "learning_rate": 2.0041537253071663e-06,
+      "loss": 1.1538,
+      "step": 529
+    },
+    {
+      "epoch": 2.964936886395512,
+      "grad_norm": 11.760188283123103,
+      "learning_rate": 2.002658457818849e-06,
+      "loss": 1.6892,
+      "step": 530
+    },
+    {
+      "epoch": 2.97054698457223,
+      "grad_norm": 11.470050929329823,
+      "learning_rate": 2.0014954147334775e-06,
+      "loss": 1.5842,
+      "step": 531
+    },
+    {
+      "epoch": 2.976157082748948,
+      "grad_norm": 29.651793877306915,
+      "learning_rate": 2.000664638996101e-06,
+      "loss": 1.2993,
+      "step": 532
+    },
+    {
+      "epoch": 2.981767180925666,
+      "grad_norm": 10.304539896385103,
+      "learning_rate": 2.0001661612828903e-06,
+      "loss": 1.3348,
+      "step": 533
+    },
+    {
+      "epoch": 2.9873772791023843,
+      "grad_norm": 12.263498025363374,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4921,
+      "step": 534
+    },
+    {
+      "epoch": 2.9873772791023843,
+      "step": 534,
+      "total_flos": 262773815541760.0,
+      "train_loss": 1.490938222363647,
+      "train_runtime": 43801.9866,
+      "train_samples_per_second": 1.563,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 534,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 262773815541760.0,
+  "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 sha256:42ccc01b6cc30f097b3d9e4434206dee3084f3d984c4357115a3f96767ec4a40
+size 8120