Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2-VL-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2_vl_ir65536_ds_embodied_o1_ct16384_lr1d0e-5_pbs1_g8_e1d0
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2_vl_ir65536_ds_embodied_o1_ct16384_lr1d0e-5_pbs1_g8_e1d0
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) on the embodied_o1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9987217724755006,
+    "total_flos": 6.719053758464e+16,
+    "train_loss": 0.8281301904863871,
+    "train_runtime": 9052.2037,
+    "train_samples_per_second": 1.037,
+    "train_steps_per_second": 0.065
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14,
+    "torch_dtype": "float32"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18561ea342fec1b5886b332ac35ad269929e594389e90ac7dd229ec31eeaded5
+size 4966659944

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2d9d3548780048f5c399036ae33b6d7bd41ad2790ac22369481a4c27d96d34
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e19c5bd7d93f9c26593caf5c8d5e6a6608e482b2f3368fd16f1a91603505387
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8791447f79409dc4c2a038095d39f66984b611664e3bdeab4b47525c69b1503a
+size 1691924384

model.safetensors.index.json

@@ -0,0 +1,737 @@
+{
+  "metadata": {
+    "total_size": 16582751232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9987217724755006,
+    "total_flos": 6.719053758464e+16,
+    "train_loss": 0.8281301904863871,
+    "train_runtime": 9052.2037,
+    "train_samples_per_second": 1.037,
+    "train_steps_per_second": 0.065
+}

trainer_log.jsonl

@@ -0,0 +1,294 @@
+{"current_steps": 2, "total_steps": 586, "loss": 1.5934, "lr": 3.3898305084745766e-07, "epoch": 0.0034086067319982955, "percentage": 0.34, "elapsed_time": "0:00:35", "remaining_time": "2:51:01"}
+{"current_steps": 4, "total_steps": 586, "loss": 1.6231, "lr": 6.779661016949153e-07, "epoch": 0.006817213463996591, "percentage": 0.68, "elapsed_time": "0:01:07", "remaining_time": "2:43:42"}
+{"current_steps": 6, "total_steps": 586, "loss": 1.5692, "lr": 1.016949152542373e-06, "epoch": 0.010225820195994887, "percentage": 1.02, "elapsed_time": "0:01:41", "remaining_time": "2:42:59"}
+{"current_steps": 8, "total_steps": 586, "loss": 1.5249, "lr": 1.3559322033898307e-06, "epoch": 0.013634426927993182, "percentage": 1.37, "elapsed_time": "0:02:12", "remaining_time": "2:39:30"}
+{"current_steps": 10, "total_steps": 586, "loss": 1.5132, "lr": 1.6949152542372882e-06, "epoch": 0.017043033659991477, "percentage": 1.71, "elapsed_time": "0:02:40", "remaining_time": "2:33:58"}
+{"current_steps": 12, "total_steps": 586, "loss": 1.4339, "lr": 2.033898305084746e-06, "epoch": 0.020451640391989774, "percentage": 2.05, "elapsed_time": "0:03:15", "remaining_time": "2:35:50"}
+{"current_steps": 14, "total_steps": 586, "loss": 1.3733, "lr": 2.372881355932204e-06, "epoch": 0.02386024712398807, "percentage": 2.39, "elapsed_time": "0:03:49", "remaining_time": "2:36:03"}
+{"current_steps": 16, "total_steps": 586, "loss": 1.2981, "lr": 2.7118644067796613e-06, "epoch": 0.027268853855986364, "percentage": 2.73, "elapsed_time": "0:04:22", "remaining_time": "2:35:40"}
+{"current_steps": 18, "total_steps": 586, "loss": 1.2152, "lr": 3.0508474576271192e-06, "epoch": 0.03067746058798466, "percentage": 3.07, "elapsed_time": "0:04:53", "remaining_time": "2:34:06"}
+{"current_steps": 20, "total_steps": 586, "loss": 1.1972, "lr": 3.3898305084745763e-06, "epoch": 0.034086067319982954, "percentage": 3.41, "elapsed_time": "0:05:24", "remaining_time": "2:32:52"}
+{"current_steps": 22, "total_steps": 586, "loss": 1.1098, "lr": 3.7288135593220342e-06, "epoch": 0.03749467405198125, "percentage": 3.75, "elapsed_time": "0:05:58", "remaining_time": "2:32:59"}
+{"current_steps": 24, "total_steps": 586, "loss": 1.1101, "lr": 4.067796610169492e-06, "epoch": 0.04090328078397955, "percentage": 4.1, "elapsed_time": "0:06:30", "remaining_time": "2:32:29"}
+{"current_steps": 26, "total_steps": 586, "loss": 1.0707, "lr": 4.40677966101695e-06, "epoch": 0.044311887515977845, "percentage": 4.44, "elapsed_time": "0:07:03", "remaining_time": "2:31:54"}
+{"current_steps": 28, "total_steps": 586, "loss": 1.0054, "lr": 4.745762711864408e-06, "epoch": 0.04772049424797614, "percentage": 4.78, "elapsed_time": "0:07:40", "remaining_time": "2:32:59"}
+{"current_steps": 30, "total_steps": 586, "loss": 0.9751, "lr": 5.084745762711865e-06, "epoch": 0.05112910097997444, "percentage": 5.12, "elapsed_time": "0:08:13", "remaining_time": "2:32:28"}
+{"current_steps": 32, "total_steps": 586, "loss": 1.0073, "lr": 5.423728813559323e-06, "epoch": 0.05453770771197273, "percentage": 5.46, "elapsed_time": "0:08:42", "remaining_time": "2:30:42"}
+{"current_steps": 34, "total_steps": 586, "loss": 0.9816, "lr": 5.7627118644067805e-06, "epoch": 0.057946314443971025, "percentage": 5.8, "elapsed_time": "0:09:13", "remaining_time": "2:29:49"}
+{"current_steps": 36, "total_steps": 586, "loss": 0.9969, "lr": 6.1016949152542385e-06, "epoch": 0.06135492117596932, "percentage": 6.14, "elapsed_time": "0:09:44", "remaining_time": "2:28:51"}
+{"current_steps": 38, "total_steps": 586, "loss": 0.9751, "lr": 6.440677966101695e-06, "epoch": 0.06476352790796762, "percentage": 6.48, "elapsed_time": "0:10:14", "remaining_time": "2:27:38"}
+{"current_steps": 40, "total_steps": 586, "loss": 0.9063, "lr": 6.779661016949153e-06, "epoch": 0.06817213463996591, "percentage": 6.83, "elapsed_time": "0:10:51", "remaining_time": "2:28:19"}
+{"current_steps": 42, "total_steps": 586, "loss": 0.9076, "lr": 7.1186440677966106e-06, "epoch": 0.07158074137196421, "percentage": 7.17, "elapsed_time": "0:11:25", "remaining_time": "2:28:05"}
+{"current_steps": 44, "total_steps": 586, "loss": 0.9544, "lr": 7.4576271186440685e-06, "epoch": 0.0749893481039625, "percentage": 7.51, "elapsed_time": "0:11:56", "remaining_time": "2:27:03"}
+{"current_steps": 46, "total_steps": 586, "loss": 0.9056, "lr": 7.796610169491526e-06, "epoch": 0.0783979548359608, "percentage": 7.85, "elapsed_time": "0:12:26", "remaining_time": "2:26:07"}
+{"current_steps": 48, "total_steps": 586, "loss": 0.853, "lr": 8.135593220338983e-06, "epoch": 0.0818065615679591, "percentage": 8.19, "elapsed_time": "0:12:54", "remaining_time": "2:24:42"}
+{"current_steps": 50, "total_steps": 586, "loss": 0.8894, "lr": 8.47457627118644e-06, "epoch": 0.08521516829995739, "percentage": 8.53, "elapsed_time": "0:13:22", "remaining_time": "2:23:20"}
+{"current_steps": 52, "total_steps": 586, "loss": 0.9133, "lr": 8.8135593220339e-06, "epoch": 0.08862377503195569, "percentage": 8.87, "elapsed_time": "0:13:49", "remaining_time": "2:21:56"}
+{"current_steps": 54, "total_steps": 586, "loss": 0.8895, "lr": 9.152542372881356e-06, "epoch": 0.09203238176395398, "percentage": 9.22, "elapsed_time": "0:14:23", "remaining_time": "2:21:44"}
+{"current_steps": 56, "total_steps": 586, "loss": 0.8563, "lr": 9.491525423728815e-06, "epoch": 0.09544098849595228, "percentage": 9.56, "elapsed_time": "0:14:51", "remaining_time": "2:20:34"}
+{"current_steps": 58, "total_steps": 586, "loss": 0.8813, "lr": 9.830508474576272e-06, "epoch": 0.09884959522795057, "percentage": 9.9, "elapsed_time": "0:15:23", "remaining_time": "2:20:04"}
+{"current_steps": 60, "total_steps": 586, "loss": 0.9337, "lr": 9.999911158222826e-06, "epoch": 0.10225820195994888, "percentage": 10.24, "elapsed_time": "0:15:56", "remaining_time": "2:19:47"}
+{"current_steps": 62, "total_steps": 586, "loss": 0.924, "lr": 9.999200442948178e-06, "epoch": 0.10566680869194717, "percentage": 10.58, "elapsed_time": "0:16:28", "remaining_time": "2:19:11"}
+{"current_steps": 64, "total_steps": 586, "loss": 0.9312, "lr": 9.997779113423916e-06, "epoch": 0.10907541542394546, "percentage": 10.92, "elapsed_time": "0:16:55", "remaining_time": "2:18:00"}
+{"current_steps": 66, "total_steps": 586, "loss": 0.9062, "lr": 9.99564737168575e-06, "epoch": 0.11248402215594376, "percentage": 11.26, "elapsed_time": "0:17:21", "remaining_time": "2:16:47"}
+{"current_steps": 68, "total_steps": 586, "loss": 0.9032, "lr": 9.992805520751352e-06, "epoch": 0.11589262888794205, "percentage": 11.6, "elapsed_time": "0:17:47", "remaining_time": "2:15:32"}
+{"current_steps": 70, "total_steps": 586, "loss": 0.8851, "lr": 9.989253964577267e-06, "epoch": 0.11930123561994035, "percentage": 11.95, "elapsed_time": "0:18:17", "remaining_time": "2:14:46"}
+{"current_steps": 72, "total_steps": 586, "loss": 0.8663, "lr": 9.984993208001513e-06, "epoch": 0.12270984235193864, "percentage": 12.29, "elapsed_time": "0:18:46", "remaining_time": "2:14:02"}
+{"current_steps": 74, "total_steps": 586, "loss": 0.889, "lr": 9.980023856671805e-06, "epoch": 0.12611844908393693, "percentage": 12.63, "elapsed_time": "0:19:17", "remaining_time": "2:13:26"}
+{"current_steps": 76, "total_steps": 586, "loss": 0.8293, "lr": 9.974346616959476e-06, "epoch": 0.12952705581593524, "percentage": 12.97, "elapsed_time": "0:19:44", "remaining_time": "2:12:28"}
+{"current_steps": 78, "total_steps": 586, "loss": 0.8746, "lr": 9.96796229585906e-06, "epoch": 0.13293566254793354, "percentage": 13.31, "elapsed_time": "0:20:10", "remaining_time": "2:11:25"}
+{"current_steps": 80, "total_steps": 586, "loss": 0.9004, "lr": 9.960871800873586e-06, "epoch": 0.13634426927993182, "percentage": 13.65, "elapsed_time": "0:20:42", "remaining_time": "2:10:59"}
+{"current_steps": 82, "total_steps": 586, "loss": 0.9384, "lr": 9.953076139885581e-06, "epoch": 0.13975287601193012, "percentage": 13.99, "elapsed_time": "0:21:12", "remaining_time": "2:10:18"}
+{"current_steps": 84, "total_steps": 586, "loss": 0.8679, "lr": 9.944576421013804e-06, "epoch": 0.14316148274392843, "percentage": 14.33, "elapsed_time": "0:21:41", "remaining_time": "2:09:38"}
+{"current_steps": 86, "total_steps": 586, "loss": 0.855, "lr": 9.935373852455724e-06, "epoch": 0.1465700894759267, "percentage": 14.68, "elapsed_time": "0:22:12", "remaining_time": "2:09:05"}
+{"current_steps": 88, "total_steps": 586, "loss": 0.8509, "lr": 9.925469742315799e-06, "epoch": 0.149978696207925, "percentage": 15.02, "elapsed_time": "0:22:42", "remaining_time": "2:08:28"}
+{"current_steps": 90, "total_steps": 586, "loss": 0.8774, "lr": 9.91486549841951e-06, "epoch": 0.1533873029399233, "percentage": 15.36, "elapsed_time": "0:23:14", "remaining_time": "2:08:06"}
+{"current_steps": 92, "total_steps": 586, "loss": 0.9293, "lr": 9.903562628113266e-06, "epoch": 0.1567959096719216, "percentage": 15.7, "elapsed_time": "0:23:40", "remaining_time": "2:07:08"}
+{"current_steps": 94, "total_steps": 586, "loss": 0.835, "lr": 9.891562738050127e-06, "epoch": 0.1602045164039199, "percentage": 16.04, "elapsed_time": "0:24:14", "remaining_time": "2:06:55"}
+{"current_steps": 96, "total_steps": 586, "loss": 0.8594, "lr": 9.878867533961434e-06, "epoch": 0.1636131231359182, "percentage": 16.38, "elapsed_time": "0:24:47", "remaining_time": "2:06:30"}
+{"current_steps": 98, "total_steps": 586, "loss": 0.85, "lr": 9.865478820414344e-06, "epoch": 0.1670217298679165, "percentage": 16.72, "elapsed_time": "0:25:21", "remaining_time": "2:06:14"}
+{"current_steps": 100, "total_steps": 586, "loss": 0.8647, "lr": 9.851398500555321e-06, "epoch": 0.17043033659991477, "percentage": 17.06, "elapsed_time": "0:25:51", "remaining_time": "2:05:39"}
+{"current_steps": 102, "total_steps": 586, "loss": 0.8374, "lr": 9.8366285758396e-06, "epoch": 0.17383894333191308, "percentage": 17.41, "elapsed_time": "0:26:23", "remaining_time": "2:05:16"}
+{"current_steps": 104, "total_steps": 586, "loss": 0.8625, "lr": 9.82117114574671e-06, "epoch": 0.17724755006391138, "percentage": 17.75, "elapsed_time": "0:26:54", "remaining_time": "2:04:40"}
+{"current_steps": 106, "total_steps": 586, "loss": 0.8418, "lr": 9.805028407482027e-06, "epoch": 0.18065615679590968, "percentage": 18.09, "elapsed_time": "0:27:28", "remaining_time": "2:04:24"}
+{"current_steps": 108, "total_steps": 586, "loss": 0.8378, "lr": 9.78820265566445e-06, "epoch": 0.18406476352790796, "percentage": 18.43, "elapsed_time": "0:27:58", "remaining_time": "2:03:48"}
+{"current_steps": 110, "total_steps": 586, "loss": 0.8717, "lr": 9.770696282000245e-06, "epoch": 0.18747337025990626, "percentage": 18.77, "elapsed_time": "0:28:29", "remaining_time": "2:03:16"}
+{"current_steps": 112, "total_steps": 586, "loss": 0.8626, "lr": 9.75251177494306e-06, "epoch": 0.19088197699190457, "percentage": 19.11, "elapsed_time": "0:28:57", "remaining_time": "2:02:34"}
+{"current_steps": 114, "total_steps": 586, "loss": 0.8714, "lr": 9.733651719340207e-06, "epoch": 0.19429058372390284, "percentage": 19.45, "elapsed_time": "0:29:24", "remaining_time": "2:01:43"}
+{"current_steps": 116, "total_steps": 586, "loss": 0.8529, "lr": 9.714118796065243e-06, "epoch": 0.19769919045590115, "percentage": 19.8, "elapsed_time": "0:29:54", "remaining_time": "2:01:11"}
+{"current_steps": 118, "total_steps": 586, "loss": 0.8508, "lr": 9.693915781636887e-06, "epoch": 0.20110779718789945, "percentage": 20.14, "elapsed_time": "0:30:24", "remaining_time": "2:00:34"}
+{"current_steps": 120, "total_steps": 586, "loss": 0.8699, "lr": 9.673045547824356e-06, "epoch": 0.20451640391989775, "percentage": 20.48, "elapsed_time": "0:30:50", "remaining_time": "1:59:47"}
+{"current_steps": 122, "total_steps": 586, "loss": 0.8746, "lr": 9.651511061239151e-06, "epoch": 0.20792501065189603, "percentage": 20.82, "elapsed_time": "0:31:19", "remaining_time": "1:59:07"}
+{"current_steps": 124, "total_steps": 586, "loss": 0.8643, "lr": 9.62931538291337e-06, "epoch": 0.21133361738389433, "percentage": 21.16, "elapsed_time": "0:31:46", "remaining_time": "1:58:21"}
+{"current_steps": 126, "total_steps": 586, "loss": 0.8518, "lr": 9.606461667864603e-06, "epoch": 0.21474222411589264, "percentage": 21.5, "elapsed_time": "0:32:13", "remaining_time": "1:57:37"}
+{"current_steps": 128, "total_steps": 586, "loss": 0.8036, "lr": 9.582953164647438e-06, "epoch": 0.21815083084789091, "percentage": 21.84, "elapsed_time": "0:32:40", "remaining_time": "1:56:54"}
+{"current_steps": 130, "total_steps": 586, "loss": 0.8749, "lr": 9.558793214891716e-06, "epoch": 0.22155943757988922, "percentage": 22.18, "elapsed_time": "0:33:07", "remaining_time": "1:56:11"}
+{"current_steps": 132, "total_steps": 586, "loss": 0.8442, "lr": 9.533985252827525e-06, "epoch": 0.22496804431188752, "percentage": 22.53, "elapsed_time": "0:33:35", "remaining_time": "1:55:32"}
+{"current_steps": 134, "total_steps": 586, "loss": 0.8331, "lr": 9.508532804797035e-06, "epoch": 0.22837665104388583, "percentage": 22.87, "elapsed_time": "0:34:02", "remaining_time": "1:54:51"}
+{"current_steps": 136, "total_steps": 586, "loss": 0.8404, "lr": 9.482439488753248e-06, "epoch": 0.2317852577758841, "percentage": 23.21, "elapsed_time": "0:34:34", "remaining_time": "1:54:24"}
+{"current_steps": 138, "total_steps": 586, "loss": 0.8518, "lr": 9.455709013745726e-06, "epoch": 0.2351938645078824, "percentage": 23.55, "elapsed_time": "0:35:01", "remaining_time": "1:53:41"}
+{"current_steps": 140, "total_steps": 586, "loss": 0.8224, "lr": 9.42834517939336e-06, "epoch": 0.2386024712398807, "percentage": 23.89, "elapsed_time": "0:35:30", "remaining_time": "1:53:05"}
+{"current_steps": 142, "total_steps": 586, "loss": 0.8368, "lr": 9.400351875344268e-06, "epoch": 0.24201107797187899, "percentage": 24.23, "elapsed_time": "0:35:57", "remaining_time": "1:52:25"}
+{"current_steps": 144, "total_steps": 586, "loss": 0.8753, "lr": 9.371733080722911e-06, "epoch": 0.2454196847038773, "percentage": 24.57, "elapsed_time": "0:36:23", "remaining_time": "1:51:41"}
+{"current_steps": 146, "total_steps": 586, "loss": 0.8382, "lr": 9.342492863564468e-06, "epoch": 0.2488282914358756, "percentage": 24.91, "elapsed_time": "0:36:54", "remaining_time": "1:51:13"}
+{"current_steps": 148, "total_steps": 586, "loss": 0.8311, "lr": 9.312635380236582e-06, "epoch": 0.25223689816787387, "percentage": 25.26, "elapsed_time": "0:37:21", "remaining_time": "1:50:33"}
+{"current_steps": 150, "total_steps": 586, "loss": 0.8731, "lr": 9.282164874848554e-06, "epoch": 0.2556455048998722, "percentage": 25.6, "elapsed_time": "0:37:48", "remaining_time": "1:49:54"}
+{"current_steps": 152, "total_steps": 586, "loss": 0.832, "lr": 9.251085678648072e-06, "epoch": 0.2590541116318705, "percentage": 25.94, "elapsed_time": "0:38:18", "remaining_time": "1:49:23"}
+{"current_steps": 154, "total_steps": 586, "loss": 0.8715, "lr": 9.219402209405519e-06, "epoch": 0.26246271836386875, "percentage": 26.28, "elapsed_time": "0:38:46", "remaining_time": "1:48:46"}
+{"current_steps": 156, "total_steps": 586, "loss": 0.8809, "lr": 9.18711897078603e-06, "epoch": 0.2658713250958671, "percentage": 26.62, "elapsed_time": "0:39:16", "remaining_time": "1:48:15"}
+{"current_steps": 158, "total_steps": 586, "loss": 0.8159, "lr": 9.154240551709298e-06, "epoch": 0.26927993182786536, "percentage": 26.96, "elapsed_time": "0:39:46", "remaining_time": "1:47:45"}
+{"current_steps": 160, "total_steps": 586, "loss": 0.8443, "lr": 9.1207716256973e-06, "epoch": 0.27268853855986364, "percentage": 27.3, "elapsed_time": "0:40:17", "remaining_time": "1:47:16"}
+{"current_steps": 162, "total_steps": 586, "loss": 0.8718, "lr": 9.08671695020995e-06, "epoch": 0.27609714529186197, "percentage": 27.65, "elapsed_time": "0:40:50", "remaining_time": "1:46:52"}
+{"current_steps": 164, "total_steps": 586, "loss": 0.827, "lr": 9.052081365968873e-06, "epoch": 0.27950575202386024, "percentage": 27.99, "elapsed_time": "0:41:17", "remaining_time": "1:46:14"}
+{"current_steps": 166, "total_steps": 586, "loss": 0.8478, "lr": 9.016869796269299e-06, "epoch": 0.2829143587558585, "percentage": 28.33, "elapsed_time": "0:41:46", "remaining_time": "1:45:42"}
+{"current_steps": 168, "total_steps": 586, "loss": 0.8063, "lr": 8.981087246280246e-06, "epoch": 0.28632296548785685, "percentage": 28.67, "elapsed_time": "0:42:16", "remaining_time": "1:45:10"}
+{"current_steps": 170, "total_steps": 586, "loss": 0.8345, "lr": 8.944738802333062e-06, "epoch": 0.2897315722198551, "percentage": 29.01, "elapsed_time": "0:42:42", "remaining_time": "1:44:31"}
+{"current_steps": 172, "total_steps": 586, "loss": 0.7921, "lr": 8.907829631198412e-06, "epoch": 0.2931401789518534, "percentage": 29.35, "elapsed_time": "0:43:16", "remaining_time": "1:44:10"}
+{"current_steps": 174, "total_steps": 586, "loss": 0.8122, "lr": 8.870364979351862e-06, "epoch": 0.29654878568385173, "percentage": 29.69, "elapsed_time": "0:43:48", "remaining_time": "1:43:44"}
+{"current_steps": 176, "total_steps": 586, "loss": 0.82, "lr": 8.832350172228099e-06, "epoch": 0.29995739241585, "percentage": 30.03, "elapsed_time": "0:44:18", "remaining_time": "1:43:13"}
+{"current_steps": 178, "total_steps": 586, "loss": 0.8362, "lr": 8.793790613463956e-06, "epoch": 0.30336599914784834, "percentage": 30.38, "elapsed_time": "0:44:51", "remaining_time": "1:42:48"}
+{"current_steps": 180, "total_steps": 586, "loss": 0.8283, "lr": 8.754691784130298e-06, "epoch": 0.3067746058798466, "percentage": 30.72, "elapsed_time": "0:45:23", "remaining_time": "1:42:23"}
+{"current_steps": 182, "total_steps": 586, "loss": 0.8055, "lr": 8.715059241952925e-06, "epoch": 0.3101832126118449, "percentage": 31.06, "elapsed_time": "0:45:51", "remaining_time": "1:41:47"}
+{"current_steps": 184, "total_steps": 586, "loss": 0.8238, "lr": 8.674898620522558e-06, "epoch": 0.3135918193438432, "percentage": 31.4, "elapsed_time": "0:46:20", "remaining_time": "1:41:15"}
+{"current_steps": 186, "total_steps": 586, "loss": 0.7946, "lr": 8.634215628494044e-06, "epoch": 0.3170004260758415, "percentage": 31.74, "elapsed_time": "0:46:50", "remaining_time": "1:40:43"}
+{"current_steps": 188, "total_steps": 586, "loss": 0.8269, "lr": 8.593016048774911e-06, "epoch": 0.3204090328078398, "percentage": 32.08, "elapsed_time": "0:47:20", "remaining_time": "1:40:13"}
+{"current_steps": 190, "total_steps": 586, "loss": 0.8205, "lr": 8.551305737703338e-06, "epoch": 0.3238176395398381, "percentage": 32.42, "elapsed_time": "0:47:46", "remaining_time": "1:39:34"}
+{"current_steps": 192, "total_steps": 586, "loss": 0.7965, "lr": 8.509090624215708e-06, "epoch": 0.3272262462718364, "percentage": 32.76, "elapsed_time": "0:48:15", "remaining_time": "1:39:02"}
+{"current_steps": 194, "total_steps": 586, "loss": 0.8444, "lr": 8.466376709003841e-06, "epoch": 0.33063485300383466, "percentage": 33.11, "elapsed_time": "0:48:41", "remaining_time": "1:38:23"}
+{"current_steps": 196, "total_steps": 586, "loss": 0.8301, "lr": 8.423170063662014e-06, "epoch": 0.334043459735833, "percentage": 33.45, "elapsed_time": "0:49:09", "remaining_time": "1:37:48"}
+{"current_steps": 198, "total_steps": 586, "loss": 0.8194, "lr": 8.379476829823919e-06, "epoch": 0.33745206646783127, "percentage": 33.79, "elapsed_time": "0:49:36", "remaining_time": "1:37:13"}
+{"current_steps": 200, "total_steps": 586, "loss": 0.8223, "lr": 8.335303218289645e-06, "epoch": 0.34086067319982954, "percentage": 34.13, "elapsed_time": "0:50:05", "remaining_time": "1:36:40"}
+{"current_steps": 202, "total_steps": 586, "loss": 0.8066, "lr": 8.290655508142855e-06, "epoch": 0.3442692799318279, "percentage": 34.47, "elapsed_time": "0:50:33", "remaining_time": "1:36:06"}
+{"current_steps": 204, "total_steps": 586, "loss": 0.8035, "lr": 8.245540045858229e-06, "epoch": 0.34767788666382615, "percentage": 34.81, "elapsed_time": "0:51:00", "remaining_time": "1:35:31"}
+{"current_steps": 206, "total_steps": 586, "loss": 0.8115, "lr": 8.199963244399351e-06, "epoch": 0.3510864933958245, "percentage": 35.15, "elapsed_time": "0:51:30", "remaining_time": "1:35:00"}
+{"current_steps": 208, "total_steps": 586, "loss": 0.8333, "lr": 8.153931582307124e-06, "epoch": 0.35449510012782276, "percentage": 35.49, "elapsed_time": "0:51:56", "remaining_time": "1:34:23"}
+{"current_steps": 210, "total_steps": 586, "loss": 0.8114, "lr": 8.107451602778887e-06, "epoch": 0.35790370685982104, "percentage": 35.84, "elapsed_time": "0:52:30", "remaining_time": "1:34:00"}
+{"current_steps": 212, "total_steps": 586, "loss": 0.8084, "lr": 8.060529912738316e-06, "epoch": 0.36131231359181937, "percentage": 36.18, "elapsed_time": "0:53:00", "remaining_time": "1:33:31"}
+{"current_steps": 214, "total_steps": 586, "loss": 0.8036, "lr": 8.013173181896283e-06, "epoch": 0.36472092032381764, "percentage": 36.52, "elapsed_time": "0:53:27", "remaining_time": "1:32:55"}
+{"current_steps": 216, "total_steps": 586, "loss": 0.8493, "lr": 7.965388141802792e-06, "epoch": 0.3681295270558159, "percentage": 36.86, "elapsed_time": "0:53:53", "remaining_time": "1:32:19"}
+{"current_steps": 218, "total_steps": 586, "loss": 0.8666, "lr": 7.917181584890113e-06, "epoch": 0.37153813378781425, "percentage": 37.2, "elapsed_time": "0:54:24", "remaining_time": "1:31:50"}
+{"current_steps": 220, "total_steps": 586, "loss": 0.8104, "lr": 7.868560363507268e-06, "epoch": 0.3749467405198125, "percentage": 37.54, "elapsed_time": "0:54:53", "remaining_time": "1:31:18"}
+{"current_steps": 222, "total_steps": 586, "loss": 0.7423, "lr": 7.819531388946e-06, "epoch": 0.3783553472518108, "percentage": 37.88, "elapsed_time": "0:55:21", "remaining_time": "1:30:45"}
+{"current_steps": 224, "total_steps": 586, "loss": 0.7817, "lr": 7.770101630458364e-06, "epoch": 0.38176395398380913, "percentage": 38.23, "elapsed_time": "0:55:51", "remaining_time": "1:30:16"}
+{"current_steps": 226, "total_steps": 586, "loss": 0.8055, "lr": 7.720278114266084e-06, "epoch": 0.3851725607158074, "percentage": 38.57, "elapsed_time": "0:56:32", "remaining_time": "1:30:04"}
+{"current_steps": 228, "total_steps": 586, "loss": 0.8181, "lr": 7.670067922561795e-06, "epoch": 0.3885811674478057, "percentage": 38.91, "elapsed_time": "0:57:03", "remaining_time": "1:29:35"}
+{"current_steps": 230, "total_steps": 586, "loss": 0.786, "lr": 7.619478192502352e-06, "epoch": 0.391989774179804, "percentage": 39.25, "elapsed_time": "0:57:33", "remaining_time": "1:29:05"}
+{"current_steps": 232, "total_steps": 586, "loss": 0.7861, "lr": 7.5685161151943066e-06, "epoch": 0.3953983809118023, "percentage": 39.59, "elapsed_time": "0:58:04", "remaining_time": "1:28:36"}
+{"current_steps": 234, "total_steps": 586, "loss": 0.8314, "lr": 7.5171889346717264e-06, "epoch": 0.39880698764380057, "percentage": 39.93, "elapsed_time": "0:58:34", "remaining_time": "1:28:06"}
+{"current_steps": 236, "total_steps": 586, "loss": 0.8045, "lr": 7.465503946866491e-06, "epoch": 0.4022155943757989, "percentage": 40.27, "elapsed_time": "0:59:05", "remaining_time": "1:27:38"}
+{"current_steps": 238, "total_steps": 586, "loss": 0.8149, "lr": 7.413468498571199e-06, "epoch": 0.4056242011077972, "percentage": 40.61, "elapsed_time": "0:59:34", "remaining_time": "1:27:06"}
+{"current_steps": 240, "total_steps": 586, "loss": 0.8038, "lr": 7.361089986394863e-06, "epoch": 0.4090328078397955, "percentage": 40.96, "elapsed_time": "1:00:10", "remaining_time": "1:26:44"}
+{"current_steps": 242, "total_steps": 586, "loss": 0.8203, "lr": 7.308375855711508e-06, "epoch": 0.4124414145717938, "percentage": 41.3, "elapsed_time": "1:00:40", "remaining_time": "1:26:14"}
+{"current_steps": 244, "total_steps": 586, "loss": 0.8096, "lr": 7.2553335996018485e-06, "epoch": 0.41585002130379206, "percentage": 41.64, "elapsed_time": "1:01:10", "remaining_time": "1:25:44"}
+{"current_steps": 246, "total_steps": 586, "loss": 0.7692, "lr": 7.201970757788172e-06, "epoch": 0.4192586280357904, "percentage": 41.98, "elapsed_time": "1:01:36", "remaining_time": "1:25:08"}
+{"current_steps": 248, "total_steps": 586, "loss": 0.7941, "lr": 7.148294915562617e-06, "epoch": 0.42266723476778867, "percentage": 42.32, "elapsed_time": "1:02:05", "remaining_time": "1:24:38"}
+{"current_steps": 250, "total_steps": 586, "loss": 0.795, "lr": 7.09431370270894e-06, "epoch": 0.42607584149978694, "percentage": 42.66, "elapsed_time": "1:02:40", "remaining_time": "1:24:13"}
+{"current_steps": 252, "total_steps": 586, "loss": 0.7854, "lr": 7.040034792417986e-06, "epoch": 0.4294844482317853, "percentage": 43.0, "elapsed_time": "1:03:10", "remaining_time": "1:23:44"}
+{"current_steps": 254, "total_steps": 586, "loss": 0.8445, "lr": 6.985465900196971e-06, "epoch": 0.43289305496378355, "percentage": 43.34, "elapsed_time": "1:03:39", "remaining_time": "1:23:12"}
+{"current_steps": 256, "total_steps": 586, "loss": 0.8372, "lr": 6.930614782772766e-06, "epoch": 0.43630166169578183, "percentage": 43.69, "elapsed_time": "1:04:06", "remaining_time": "1:22:39"}
+{"current_steps": 258, "total_steps": 586, "loss": 0.82, "lr": 6.875489236989306e-06, "epoch": 0.43971026842778016, "percentage": 44.03, "elapsed_time": "1:04:39", "remaining_time": "1:22:12"}
+{"current_steps": 260, "total_steps": 586, "loss": 0.8208, "lr": 6.8200970986993e-06, "epoch": 0.44311887515977844, "percentage": 44.37, "elapsed_time": "1:05:09", "remaining_time": "1:21:42"}
+{"current_steps": 262, "total_steps": 586, "loss": 0.8073, "lr": 6.764446241650411e-06, "epoch": 0.4465274818917767, "percentage": 44.71, "elapsed_time": "1:05:37", "remaining_time": "1:21:09"}
+{"current_steps": 264, "total_steps": 586, "loss": 0.8231, "lr": 6.708544576366024e-06, "epoch": 0.44993608862377504, "percentage": 45.05, "elapsed_time": "1:06:09", "remaining_time": "1:20:42"}
+{"current_steps": 266, "total_steps": 586, "loss": 0.8065, "lr": 6.65240004902081e-06, "epoch": 0.4533446953557733, "percentage": 45.39, "elapsed_time": "1:06:39", "remaining_time": "1:20:10"}
+{"current_steps": 268, "total_steps": 586, "loss": 0.7485, "lr": 6.5960206403112045e-06, "epoch": 0.45675330208777165, "percentage": 45.73, "elapsed_time": "1:07:10", "remaining_time": "1:19:42"}
+{"current_steps": 270, "total_steps": 586, "loss": 0.779, "lr": 6.539414364320997e-06, "epoch": 0.4601619088197699, "percentage": 46.08, "elapsed_time": "1:07:42", "remaining_time": "1:19:15"}
+{"current_steps": 272, "total_steps": 586, "loss": 0.794, "lr": 6.4825892673821556e-06, "epoch": 0.4635705155517682, "percentage": 46.42, "elapsed_time": "1:08:16", "remaining_time": "1:18:48"}
+{"current_steps": 274, "total_steps": 586, "loss": 0.7618, "lr": 6.425553426931075e-06, "epoch": 0.46697912228376653, "percentage": 46.76, "elapsed_time": "1:08:44", "remaining_time": "1:18:16"}
+{"current_steps": 276, "total_steps": 586, "loss": 0.7785, "lr": 6.368314950360416e-06, "epoch": 0.4703877290157648, "percentage": 47.1, "elapsed_time": "1:09:12", "remaining_time": "1:17:44"}
+{"current_steps": 278, "total_steps": 586, "loss": 0.765, "lr": 6.31088197386666e-06, "epoch": 0.4737963357477631, "percentage": 47.44, "elapsed_time": "1:09:42", "remaining_time": "1:17:13"}
+{"current_steps": 280, "total_steps": 586, "loss": 0.7977, "lr": 6.2532626612936035e-06, "epoch": 0.4772049424797614, "percentage": 47.78, "elapsed_time": "1:10:21", "remaining_time": "1:16:53"}
+{"current_steps": 282, "total_steps": 586, "loss": 0.7637, "lr": 6.195465202971883e-06, "epoch": 0.4806135492117597, "percentage": 48.12, "elapsed_time": "1:10:53", "remaining_time": "1:16:25"}
+{"current_steps": 284, "total_steps": 586, "loss": 0.7974, "lr": 6.137497814554773e-06, "epoch": 0.48402215594375797, "percentage": 48.46, "elapsed_time": "1:11:21", "remaining_time": "1:15:52"}
+{"current_steps": 286, "total_steps": 586, "loss": 0.78, "lr": 6.079368735850355e-06, "epoch": 0.4874307626757563, "percentage": 48.81, "elapsed_time": "1:11:52", "remaining_time": "1:15:23"}
+{"current_steps": 288, "total_steps": 586, "loss": 0.78, "lr": 6.021086229650273e-06, "epoch": 0.4908393694077546, "percentage": 49.15, "elapsed_time": "1:12:19", "remaining_time": "1:14:49"}
+{"current_steps": 290, "total_steps": 586, "loss": 0.8101, "lr": 5.96265858055521e-06, "epoch": 0.49424797613975285, "percentage": 49.49, "elapsed_time": "1:12:49", "remaining_time": "1:14:20"}
+{"current_steps": 292, "total_steps": 586, "loss": 0.7854, "lr": 5.904094093797274e-06, "epoch": 0.4976565828717512, "percentage": 49.83, "elapsed_time": "1:13:18", "remaining_time": "1:13:48"}
+{"current_steps": 294, "total_steps": 586, "loss": 0.8233, "lr": 5.845401094059439e-06, "epoch": 0.5010651896037495, "percentage": 50.17, "elapsed_time": "1:13:45", "remaining_time": "1:13:15"}
+{"current_steps": 296, "total_steps": 586, "loss": 0.8072, "lr": 5.786587924292228e-06, "epoch": 0.5044737963357477, "percentage": 50.51, "elapsed_time": "1:14:18", "remaining_time": "1:12:47"}
+{"current_steps": 298, "total_steps": 586, "loss": 0.8236, "lr": 5.727662944527808e-06, "epoch": 0.507882403067746, "percentage": 50.85, "elapsed_time": "1:14:47", "remaining_time": "1:12:17"}
+{"current_steps": 300, "total_steps": 586, "loss": 0.7829, "lr": 5.668634530691639e-06, "epoch": 0.5112910097997444, "percentage": 51.19, "elapsed_time": "1:15:16", "remaining_time": "1:11:45"}
+{"current_steps": 302, "total_steps": 586, "loss": 0.8069, "lr": 5.609511073411881e-06, "epoch": 0.5146996165317427, "percentage": 51.54, "elapsed_time": "1:15:42", "remaining_time": "1:11:11"}
+{"current_steps": 304, "total_steps": 586, "loss": 0.7978, "lr": 5.550300976826697e-06, "epoch": 0.518108223263741, "percentage": 51.88, "elapsed_time": "1:16:12", "remaining_time": "1:10:41"}
+{"current_steps": 306, "total_steps": 586, "loss": 0.8143, "lr": 5.491012657389644e-06, "epoch": 0.5215168299957392, "percentage": 52.22, "elapsed_time": "1:16:42", "remaining_time": "1:10:11"}
+{"current_steps": 308, "total_steps": 586, "loss": 0.8184, "lr": 5.431654542673315e-06, "epoch": 0.5249254367277375, "percentage": 52.56, "elapsed_time": "1:17:10", "remaining_time": "1:09:39"}
+{"current_steps": 310, "total_steps": 586, "loss": 0.7976, "lr": 5.372235070171387e-06, "epoch": 0.5283340434597358, "percentage": 52.9, "elapsed_time": "1:17:38", "remaining_time": "1:09:07"}
+{"current_steps": 312, "total_steps": 586, "loss": 0.7726, "lr": 5.312762686099282e-06, "epoch": 0.5317426501917342, "percentage": 53.24, "elapsed_time": "1:18:06", "remaining_time": "1:08:35"}
+{"current_steps": 314, "total_steps": 586, "loss": 0.791, "lr": 5.253245844193564e-06, "epoch": 0.5351512569237324, "percentage": 53.58, "elapsed_time": "1:18:34", "remaining_time": "1:08:03"}
+{"current_steps": 316, "total_steps": 586, "loss": 0.7654, "lr": 5.193693004510284e-06, "epoch": 0.5385598636557307, "percentage": 53.92, "elapsed_time": "1:19:03", "remaining_time": "1:07:32"}
+{"current_steps": 318, "total_steps": 586, "loss": 0.7509, "lr": 5.1341126322224145e-06, "epoch": 0.541968470387729, "percentage": 54.27, "elapsed_time": "1:19:32", "remaining_time": "1:07:01"}
+{"current_steps": 320, "total_steps": 586, "loss": 0.7737, "lr": 5.0745131964165686e-06, "epoch": 0.5453770771197273, "percentage": 54.61, "elapsed_time": "1:20:01", "remaining_time": "1:06:31"}
+{"current_steps": 322, "total_steps": 586, "loss": 0.7814, "lr": 5.014903168889155e-06, "epoch": 0.5487856838517257, "percentage": 54.95, "elapsed_time": "1:20:29", "remaining_time": "1:05:59"}
+{"current_steps": 324, "total_steps": 586, "loss": 0.7782, "lr": 4.955291022942146e-06, "epoch": 0.5521942905837239, "percentage": 55.29, "elapsed_time": "1:20:57", "remaining_time": "1:05:27"}
+{"current_steps": 326, "total_steps": 586, "loss": 0.802, "lr": 4.8956852321786394e-06, "epoch": 0.5556028973157222, "percentage": 55.63, "elapsed_time": "1:21:29", "remaining_time": "1:04:59"}
+{"current_steps": 328, "total_steps": 586, "loss": 0.7798, "lr": 4.836094269298373e-06, "epoch": 0.5590115040477205, "percentage": 55.97, "elapsed_time": "1:21:56", "remaining_time": "1:04:27"}
+{"current_steps": 330, "total_steps": 586, "loss": 0.8098, "lr": 4.7765266048933626e-06, "epoch": 0.5624201107797188, "percentage": 56.31, "elapsed_time": "1:22:24", "remaining_time": "1:03:56"}
+{"current_steps": 332, "total_steps": 586, "loss": 0.7728, "lr": 4.7169907062438556e-06, "epoch": 0.565828717511717, "percentage": 56.66, "elapsed_time": "1:22:54", "remaining_time": "1:03:25"}
+{"current_steps": 334, "total_steps": 586, "loss": 0.7721, "lr": 4.657495036114731e-06, "epoch": 0.5692373242437154, "percentage": 57.0, "elapsed_time": "1:23:21", "remaining_time": "1:02:53"}
+{"current_steps": 336, "total_steps": 586, "loss": 0.8186, "lr": 4.598048051552563e-06, "epoch": 0.5726459309757137, "percentage": 57.34, "elapsed_time": "1:23:49", "remaining_time": "1:02:22"}
+{"current_steps": 338, "total_steps": 586, "loss": 0.7503, "lr": 4.53865820268349e-06, "epoch": 0.576054537707712, "percentage": 57.68, "elapsed_time": "1:24:20", "remaining_time": "1:01:53"}
+{"current_steps": 340, "total_steps": 586, "loss": 0.7915, "lr": 4.479333931512064e-06, "epoch": 0.5794631444397103, "percentage": 58.02, "elapsed_time": "1:24:49", "remaining_time": "1:01:22"}
+{"current_steps": 342, "total_steps": 586, "loss": 0.7754, "lr": 4.4200836707212525e-06, "epoch": 0.5828717511717085, "percentage": 58.36, "elapsed_time": "1:25:19", "remaining_time": "1:00:52"}
+{"current_steps": 344, "total_steps": 586, "loss": 0.7543, "lr": 4.360915842473778e-06, "epoch": 0.5862803579037068, "percentage": 58.7, "elapsed_time": "1:25:50", "remaining_time": "1:00:23"}
+{"current_steps": 346, "total_steps": 586, "loss": 0.7629, "lr": 4.301838857214944e-06, "epoch": 0.5896889646357052, "percentage": 59.04, "elapsed_time": "1:26:20", "remaining_time": "0:59:53"}
+{"current_steps": 348, "total_steps": 586, "loss": 0.7919, "lr": 4.2428611124771184e-06, "epoch": 0.5930975713677035, "percentage": 59.39, "elapsed_time": "1:26:47", "remaining_time": "0:59:21"}
+{"current_steps": 350, "total_steps": 586, "loss": 0.7853, "lr": 4.183990991686071e-06, "epoch": 0.5965061780997017, "percentage": 59.73, "elapsed_time": "1:27:14", "remaining_time": "0:58:49"}
+{"current_steps": 352, "total_steps": 586, "loss": 0.7695, "lr": 4.125236862969304e-06, "epoch": 0.5999147848317, "percentage": 60.07, "elapsed_time": "1:27:42", "remaining_time": "0:58:18"}
+{"current_steps": 354, "total_steps": 586, "loss": 0.7395, "lr": 4.066607077966559e-06, "epoch": 0.6033233915636983, "percentage": 60.41, "elapsed_time": "1:28:20", "remaining_time": "0:57:53"}
+{"current_steps": 356, "total_steps": 586, "loss": 0.787, "lr": 4.008109970642665e-06, "epoch": 0.6067319982956967, "percentage": 60.75, "elapsed_time": "1:28:48", "remaining_time": "0:57:22"}
+{"current_steps": 358, "total_steps": 586, "loss": 0.7393, "lr": 3.949753856102909e-06, "epoch": 0.610140605027695, "percentage": 61.09, "elapsed_time": "1:29:17", "remaining_time": "0:56:52"}
+{"current_steps": 360, "total_steps": 586, "loss": 0.8053, "lr": 3.891547029411074e-06, "epoch": 0.6135492117596932, "percentage": 61.43, "elapsed_time": "1:29:45", "remaining_time": "0:56:21"}
+{"current_steps": 362, "total_steps": 586, "loss": 0.7674, "lr": 3.833497764410336e-06, "epoch": 0.6169578184916915, "percentage": 61.77, "elapsed_time": "1:30:11", "remaining_time": "0:55:48"}
+{"current_steps": 364, "total_steps": 586, "loss": 0.7489, "lr": 3.7756143125471745e-06, "epoch": 0.6203664252236898, "percentage": 62.12, "elapsed_time": "1:30:40", "remaining_time": "0:55:18"}
+{"current_steps": 366, "total_steps": 586, "loss": 0.7757, "lr": 3.7179049016984616e-06, "epoch": 0.6237750319556881, "percentage": 62.46, "elapsed_time": "1:31:12", "remaining_time": "0:54:49"}
+{"current_steps": 368, "total_steps": 586, "loss": 0.7656, "lr": 3.660377735001911e-06, "epoch": 0.6271836386876865, "percentage": 62.8, "elapsed_time": "1:31:40", "remaining_time": "0:54:18"}
+{"current_steps": 370, "total_steps": 586, "loss": 0.7731, "lr": 3.6030409896900333e-06, "epoch": 0.6305922454196847, "percentage": 63.14, "elapsed_time": "1:32:06", "remaining_time": "0:53:46"}
+{"current_steps": 372, "total_steps": 586, "loss": 0.7564, "lr": 3.545902815927783e-06, "epoch": 0.634000852151683, "percentage": 63.48, "elapsed_time": "1:32:33", "remaining_time": "0:53:14"}
+{"current_steps": 374, "total_steps": 586, "loss": 0.7556, "lr": 3.4889713356540435e-06, "epoch": 0.6374094588836813, "percentage": 63.82, "elapsed_time": "1:33:05", "remaining_time": "0:52:45"}
+{"current_steps": 376, "total_steps": 586, "loss": 0.7754, "lr": 3.432254641427136e-06, "epoch": 0.6408180656156796, "percentage": 64.16, "elapsed_time": "1:33:35", "remaining_time": "0:52:16"}
+{"current_steps": 378, "total_steps": 586, "loss": 0.7745, "lr": 3.375760795274493e-06, "epoch": 0.6442266723476778, "percentage": 64.51, "elapsed_time": "1:34:10", "remaining_time": "0:51:49"}
+{"current_steps": 380, "total_steps": 586, "loss": 0.7649, "lr": 3.3194978275466755e-06, "epoch": 0.6476352790796762, "percentage": 64.85, "elapsed_time": "1:34:38", "remaining_time": "0:51:18"}
+{"current_steps": 382, "total_steps": 586, "loss": 0.74, "lr": 3.2634737357758994e-06, "epoch": 0.6510438858116745, "percentage": 65.19, "elapsed_time": "1:35:07", "remaining_time": "0:50:48"}
+{"current_steps": 384, "total_steps": 586, "loss": 0.7611, "lr": 3.207696483539219e-06, "epoch": 0.6544524925436728, "percentage": 65.53, "elapsed_time": "1:35:34", "remaining_time": "0:50:16"}
+{"current_steps": 386, "total_steps": 586, "loss": 0.7675, "lr": 3.152173999326537e-06, "epoch": 0.657861099275671, "percentage": 65.87, "elapsed_time": "1:36:04", "remaining_time": "0:49:46"}
+{"current_steps": 388, "total_steps": 586, "loss": 0.7685, "lr": 3.096914175413611e-06, "epoch": 0.6612697060076693, "percentage": 66.21, "elapsed_time": "1:36:31", "remaining_time": "0:49:15"}
+{"current_steps": 390, "total_steps": 586, "loss": 0.7505, "lr": 3.041924866740197e-06, "epoch": 0.6646783127396677, "percentage": 66.55, "elapsed_time": "1:36:59", "remaining_time": "0:48:44"}
+{"current_steps": 392, "total_steps": 586, "loss": 0.7792, "lr": 2.987213889793502e-06, "epoch": 0.668086919471666, "percentage": 66.89, "elapsed_time": "1:37:32", "remaining_time": "0:48:16"}
+{"current_steps": 394, "total_steps": 586, "loss": 0.7661, "lr": 2.9327890214971135e-06, "epoch": 0.6714955262036643, "percentage": 67.24, "elapsed_time": "1:38:04", "remaining_time": "0:47:47"}
+{"current_steps": 396, "total_steps": 586, "loss": 0.7587, "lr": 2.878657998105533e-06, "epoch": 0.6749041329356625, "percentage": 67.58, "elapsed_time": "1:38:35", "remaining_time": "0:47:18"}
+{"current_steps": 398, "total_steps": 586, "loss": 0.8067, "lr": 2.824828514104512e-06, "epoch": 0.6783127396676608, "percentage": 67.92, "elapsed_time": "1:39:03", "remaining_time": "0:46:47"}
+{"current_steps": 400, "total_steps": 586, "loss": 0.7478, "lr": 2.771308221117309e-06, "epoch": 0.6817213463996591, "percentage": 68.26, "elapsed_time": "1:39:31", "remaining_time": "0:46:16"}
+{"current_steps": 402, "total_steps": 586, "loss": 0.8071, "lr": 2.7181047268170436e-06, "epoch": 0.6851299531316575, "percentage": 68.6, "elapsed_time": "1:39:59", "remaining_time": "0:45:46"}
+{"current_steps": 404, "total_steps": 586, "loss": 0.7799, "lr": 2.665225593845307e-06, "epoch": 0.6885385598636558, "percentage": 68.94, "elapsed_time": "1:40:27", "remaining_time": "0:45:15"}
+{"current_steps": 406, "total_steps": 586, "loss": 0.7471, "lr": 2.6126783387371545e-06, "epoch": 0.691947166595654, "percentage": 69.28, "elapsed_time": "1:40:56", "remaining_time": "0:44:45"}
+{"current_steps": 408, "total_steps": 586, "loss": 0.7716, "lr": 2.5604704308526784e-06, "epoch": 0.6953557733276523, "percentage": 69.62, "elapsed_time": "1:41:23", "remaining_time": "0:44:14"}
+{"current_steps": 410, "total_steps": 586, "loss": 0.8003, "lr": 2.5086092913152533e-06, "epoch": 0.6987643800596506, "percentage": 69.97, "elapsed_time": "1:41:56", "remaining_time": "0:43:45"}
+{"current_steps": 412, "total_steps": 586, "loss": 0.7463, "lr": 2.4571022919566747e-06, "epoch": 0.702172986791649, "percentage": 70.31, "elapsed_time": "1:42:27", "remaining_time": "0:43:16"}
+{"current_steps": 414, "total_steps": 586, "loss": 0.7329, "lr": 2.4059567542692688e-06, "epoch": 0.7055815935236472, "percentage": 70.65, "elapsed_time": "1:42:57", "remaining_time": "0:42:46"}
+{"current_steps": 416, "total_steps": 586, "loss": 0.7557, "lr": 2.3551799483651894e-06, "epoch": 0.7089902002556455, "percentage": 70.99, "elapsed_time": "1:43:26", "remaining_time": "0:42:16"}
+{"current_steps": 418, "total_steps": 586, "loss": 0.7618, "lr": 2.3047790919429895e-06, "epoch": 0.7123988069876438, "percentage": 71.33, "elapsed_time": "1:43:55", "remaining_time": "0:41:46"}
+{"current_steps": 420, "total_steps": 586, "loss": 0.7307, "lr": 2.254761349261676e-06, "epoch": 0.7158074137196421, "percentage": 71.67, "elapsed_time": "1:44:27", "remaining_time": "0:41:17"}
+{"current_steps": 422, "total_steps": 586, "loss": 0.7536, "lr": 2.2051338301223187e-06, "epoch": 0.7192160204516403, "percentage": 72.01, "elapsed_time": "1:44:59", "remaining_time": "0:40:47"}
+{"current_steps": 424, "total_steps": 586, "loss": 0.7139, "lr": 2.1559035888574433e-06, "epoch": 0.7226246271836387, "percentage": 72.35, "elapsed_time": "1:45:28", "remaining_time": "0:40:17"}
+{"current_steps": 426, "total_steps": 586, "loss": 0.7335, "lr": 2.107077623328275e-06, "epoch": 0.726033233915637, "percentage": 72.7, "elapsed_time": "1:45:54", "remaining_time": "0:39:46"}
+{"current_steps": 428, "total_steps": 586, "loss": 0.7752, "lr": 2.0586628739300386e-06, "epoch": 0.7294418406476353, "percentage": 73.04, "elapsed_time": "1:46:22", "remaining_time": "0:39:16"}
+{"current_steps": 430, "total_steps": 586, "loss": 0.7814, "lr": 2.0106662226053924e-06, "epoch": 0.7328504473796336, "percentage": 73.38, "elapsed_time": "1:46:55", "remaining_time": "0:38:47"}
+{"current_steps": 432, "total_steps": 586, "loss": 0.7552, "lr": 1.9630944918662122e-06, "epoch": 0.7362590541116318, "percentage": 73.72, "elapsed_time": "1:47:25", "remaining_time": "0:38:17"}
+{"current_steps": 434, "total_steps": 586, "loss": 0.7602, "lr": 1.9159544438237797e-06, "epoch": 0.7396676608436301, "percentage": 74.06, "elapsed_time": "1:47:52", "remaining_time": "0:37:47"}
+{"current_steps": 436, "total_steps": 586, "loss": 0.7695, "lr": 1.8692527792276e-06, "epoch": 0.7430762675756285, "percentage": 74.4, "elapsed_time": "1:48:19", "remaining_time": "0:37:16"}
+{"current_steps": 438, "total_steps": 586, "loss": 0.732, "lr": 1.8229961365128985e-06, "epoch": 0.7464848743076268, "percentage": 74.74, "elapsed_time": "1:48:52", "remaining_time": "0:36:47"}
+{"current_steps": 440, "total_steps": 586, "loss": 0.7566, "lr": 1.7771910908570156e-06, "epoch": 0.749893481039625, "percentage": 75.09, "elapsed_time": "1:49:24", "remaining_time": "0:36:18"}
+{"current_steps": 442, "total_steps": 586, "loss": 0.8073, "lr": 1.7318441532447555e-06, "epoch": 0.7533020877716233, "percentage": 75.43, "elapsed_time": "1:49:55", "remaining_time": "0:35:48"}
+{"current_steps": 444, "total_steps": 586, "loss": 0.7579, "lr": 1.6869617695429024e-06, "epoch": 0.7567106945036216, "percentage": 75.77, "elapsed_time": "1:50:23", "remaining_time": "0:35:18"}
+{"current_steps": 446, "total_steps": 586, "loss": 0.8201, "lr": 1.6425503195839416e-06, "epoch": 0.76011930123562, "percentage": 76.11, "elapsed_time": "1:50:54", "remaining_time": "0:34:48"}
+{"current_steps": 448, "total_steps": 586, "loss": 0.7515, "lr": 1.5986161162592173e-06, "epoch": 0.7635279079676183, "percentage": 76.45, "elapsed_time": "1:51:23", "remaining_time": "0:34:18"}
+{"current_steps": 450, "total_steps": 586, "loss": 0.7684, "lr": 1.555165404621567e-06, "epoch": 0.7669365146996165, "percentage": 76.79, "elapsed_time": "1:51:57", "remaining_time": "0:33:50"}
+{"current_steps": 452, "total_steps": 586, "loss": 0.7335, "lr": 1.5122043609976282e-06, "epoch": 0.7703451214316148, "percentage": 77.13, "elapsed_time": "1:52:25", "remaining_time": "0:33:19"}
+{"current_steps": 454, "total_steps": 586, "loss": 0.7848, "lr": 1.4697390921098886e-06, "epoch": 0.7737537281636131, "percentage": 77.47, "elapsed_time": "1:52:51", "remaining_time": "0:32:48"}
+{"current_steps": 456, "total_steps": 586, "loss": 0.7757, "lr": 1.4277756342086524e-06, "epoch": 0.7771623348956114, "percentage": 77.82, "elapsed_time": "1:53:21", "remaining_time": "0:32:18"}
+{"current_steps": 458, "total_steps": 586, "loss": 0.8031, "lr": 1.3863199522140053e-06, "epoch": 0.7805709416276098, "percentage": 78.16, "elapsed_time": "1:53:48", "remaining_time": "0:31:48"}
+{"current_steps": 460, "total_steps": 586, "loss": 0.7826, "lr": 1.3453779388679378e-06, "epoch": 0.783979548359608, "percentage": 78.5, "elapsed_time": "1:54:15", "remaining_time": "0:31:17"}
+{"current_steps": 462, "total_steps": 586, "loss": 0.7706, "lr": 1.3049554138967052e-06, "epoch": 0.7873881550916063, "percentage": 78.84, "elapsed_time": "1:54:43", "remaining_time": "0:30:47"}
+{"current_steps": 464, "total_steps": 586, "loss": 0.7943, "lr": 1.2650581231835923e-06, "epoch": 0.7907967618236046, "percentage": 79.18, "elapsed_time": "1:55:16", "remaining_time": "0:30:18"}
+{"current_steps": 466, "total_steps": 586, "loss": 0.7558, "lr": 1.225691737952152e-06, "epoch": 0.7942053685556029, "percentage": 79.52, "elapsed_time": "1:55:42", "remaining_time": "0:29:47"}
+{"current_steps": 468, "total_steps": 586, "loss": 0.767, "lr": 1.1868618539600718e-06, "epoch": 0.7976139752876011, "percentage": 79.86, "elapsed_time": "1:56:12", "remaining_time": "0:29:18"}
+{"current_steps": 470, "total_steps": 586, "loss": 0.7838, "lr": 1.1485739907037546e-06, "epoch": 0.8010225820195995, "percentage": 80.2, "elapsed_time": "1:56:42", "remaining_time": "0:28:48"}
+{"current_steps": 472, "total_steps": 586, "loss": 0.7519, "lr": 1.1108335906337559e-06, "epoch": 0.8044311887515978, "percentage": 80.55, "elapsed_time": "1:57:15", "remaining_time": "0:28:19"}
+{"current_steps": 474, "total_steps": 586, "loss": 0.7681, "lr": 1.0736460183811547e-06, "epoch": 0.8078397954835961, "percentage": 80.89, "elapsed_time": "1:57:45", "remaining_time": "0:27:49"}
+{"current_steps": 476, "total_steps": 586, "loss": 0.7552, "lr": 1.0370165599950026e-06, "epoch": 0.8112484022155944, "percentage": 81.23, "elapsed_time": "1:58:15", "remaining_time": "0:27:19"}
+{"current_steps": 478, "total_steps": 586, "loss": 0.7336, "lr": 1.0009504221909284e-06, "epoch": 0.8146570089475926, "percentage": 81.57, "elapsed_time": "1:58:47", "remaining_time": "0:26:50"}
+{"current_steps": 480, "total_steps": 586, "loss": 0.7478, "lr": 9.654527316110323e-07, "epoch": 0.818065615679591, "percentage": 81.91, "elapsed_time": "1:59:18", "remaining_time": "0:26:20"}
+{"current_steps": 482, "total_steps": 586, "loss": 0.7693, "lr": 9.305285340951509e-07, "epoch": 0.8214742224115893, "percentage": 82.25, "elapsed_time": "1:59:47", "remaining_time": "0:25:50"}
+{"current_steps": 484, "total_steps": 586, "loss": 0.762, "lr": 8.961827939636198e-07, "epoch": 0.8248828291435876, "percentage": 82.59, "elapsed_time": "2:00:20", "remaining_time": "0:25:21"}
+{"current_steps": 486, "total_steps": 586, "loss": 0.7517, "lr": 8.624203933116088e-07, "epoch": 0.8282914358755858, "percentage": 82.94, "elapsed_time": "2:00:49", "remaining_time": "0:24:51"}
+{"current_steps": 488, "total_steps": 586, "loss": 0.7814, "lr": 8.292461313151662e-07, "epoch": 0.8317000426075841, "percentage": 83.28, "elapsed_time": "2:01:19", "remaining_time": "0:24:21"}
+{"current_steps": 490, "total_steps": 586, "loss": 0.7988, "lr": 7.966647235490222e-07, "epoch": 0.8351086493395824, "percentage": 83.62, "elapsed_time": "2:01:46", "remaining_time": "0:23:51"}
+{"current_steps": 492, "total_steps": 586, "loss": 0.7871, "lr": 7.646808013163026e-07, "epoch": 0.8385172560715808, "percentage": 83.96, "elapsed_time": "2:02:13", "remaining_time": "0:23:21"}
+{"current_steps": 494, "total_steps": 586, "loss": 0.7471, "lr": 7.332989109902028e-07, "epoch": 0.8419258628035791, "percentage": 84.3, "elapsed_time": "2:02:45", "remaining_time": "0:22:51"}
+{"current_steps": 496, "total_steps": 586, "loss": 0.7793, "lr": 7.025235133677455e-07, "epoch": 0.8453344695355773, "percentage": 84.64, "elapsed_time": "2:03:14", "remaining_time": "0:22:21"}
+{"current_steps": 498, "total_steps": 586, "loss": 0.7587, "lr": 6.723589830356925e-07, "epoch": 0.8487430762675756, "percentage": 84.98, "elapsed_time": "2:03:42", "remaining_time": "0:21:51"}
+{"current_steps": 500, "total_steps": 586, "loss": 0.7256, "lr": 6.428096077487244e-07, "epoch": 0.8521516829995739, "percentage": 85.32, "elapsed_time": "2:04:11", "remaining_time": "0:21:21"}
+{"current_steps": 502, "total_steps": 586, "loss": 0.7346, "lr": 6.138795878199467e-07, "epoch": 0.8555602897315722, "percentage": 85.67, "elapsed_time": "2:07:16", "remaining_time": "0:21:17"}
+{"current_steps": 504, "total_steps": 586, "loss": 0.7389, "lr": 5.855730355238415e-07, "epoch": 0.8589688964635706, "percentage": 86.01, "elapsed_time": "2:07:48", "remaining_time": "0:20:47"}
+{"current_steps": 506, "total_steps": 586, "loss": 0.7626, "lr": 5.578939745117173e-07, "epoch": 0.8623775031955688, "percentage": 86.35, "elapsed_time": "2:08:17", "remaining_time": "0:20:16"}
+{"current_steps": 508, "total_steps": 586, "loss": 0.7471, "lr": 5.308463392397756e-07, "epoch": 0.8657861099275671, "percentage": 86.69, "elapsed_time": "2:08:47", "remaining_time": "0:19:46"}
+{"current_steps": 510, "total_steps": 586, "loss": 0.7919, "lr": 5.044339744098348e-07, "epoch": 0.8691947166595654, "percentage": 87.03, "elapsed_time": "2:09:18", "remaining_time": "0:19:16"}
+{"current_steps": 512, "total_steps": 586, "loss": 0.8001, "lr": 4.786606344228317e-07, "epoch": 0.8726033233915637, "percentage": 87.37, "elapsed_time": "2:09:45", "remaining_time": "0:18:45"}
+{"current_steps": 514, "total_steps": 586, "loss": 0.7693, "lr": 4.5352998284514004e-07, "epoch": 0.876011930123562, "percentage": 87.71, "elapsed_time": "2:10:14", "remaining_time": "0:18:14"}
+{"current_steps": 516, "total_steps": 586, "loss": 0.743, "lr": 4.2904559188782334e-07, "epoch": 0.8794205368555603, "percentage": 88.05, "elapsed_time": "2:10:44", "remaining_time": "0:17:44"}
+{"current_steps": 518, "total_steps": 586, "loss": 0.7204, "lr": 4.05210941898847e-07, "epoch": 0.8828291435875586, "percentage": 88.4, "elapsed_time": "2:11:13", "remaining_time": "0:17:13"}
+{"current_steps": 520, "total_steps": 586, "loss": 0.7572, "lr": 3.82029420868375e-07, "epoch": 0.8862377503195569, "percentage": 88.74, "elapsed_time": "2:11:46", "remaining_time": "0:16:43"}
+{"current_steps": 522, "total_steps": 586, "loss": 0.7451, "lr": 3.5950432394717296e-07, "epoch": 0.8896463570515551, "percentage": 89.08, "elapsed_time": "2:12:15", "remaining_time": "0:16:12"}
+{"current_steps": 524, "total_steps": 586, "loss": 0.7748, "lr": 3.3763885297822153e-07, "epoch": 0.8930549637835534, "percentage": 89.42, "elapsed_time": "2:12:42", "remaining_time": "0:15:42"}
+{"current_steps": 526, "total_steps": 586, "loss": 0.7467, "lr": 3.1643611604158687e-07, "epoch": 0.8964635705155518, "percentage": 89.76, "elapsed_time": "2:13:12", "remaining_time": "0:15:11"}
+{"current_steps": 528, "total_steps": 586, "loss": 0.7316, "lr": 2.958991270126221e-07, "epoch": 0.8998721772475501, "percentage": 90.1, "elapsed_time": "2:13:40", "remaining_time": "0:14:41"}
+{"current_steps": 530, "total_steps": 586, "loss": 0.7546, "lr": 2.760308051335564e-07, "epoch": 0.9032807839795484, "percentage": 90.44, "elapsed_time": "2:14:10", "remaining_time": "0:14:10"}
+{"current_steps": 532, "total_steps": 586, "loss": 0.7064, "lr": 2.5683397459854045e-07, "epoch": 0.9066893907115466, "percentage": 90.78, "elapsed_time": "2:14:39", "remaining_time": "0:13:40"}
+{"current_steps": 534, "total_steps": 586, "loss": 0.747, "lr": 2.383113641521956e-07, "epoch": 0.9100979974435449, "percentage": 91.13, "elapsed_time": "2:15:08", "remaining_time": "0:13:09"}
+{"current_steps": 536, "total_steps": 586, "loss": 0.7447, "lr": 2.2046560670173912e-07, "epoch": 0.9135066041755433, "percentage": 91.47, "elapsed_time": "2:15:38", "remaining_time": "0:12:39"}
+{"current_steps": 538, "total_steps": 586, "loss": 0.7329, "lr": 2.0329923894272463e-07, "epoch": 0.9169152109075416, "percentage": 91.81, "elapsed_time": "2:16:09", "remaining_time": "0:12:08"}
+{"current_steps": 540, "total_steps": 586, "loss": 0.7494, "lr": 1.8681470099846554e-07, "epoch": 0.9203238176395399, "percentage": 92.15, "elapsed_time": "2:16:35", "remaining_time": "0:11:38"}
+{"current_steps": 542, "total_steps": 586, "loss": 0.7251, "lr": 1.710143360731781e-07, "epoch": 0.9237324243715381, "percentage": 92.49, "elapsed_time": "2:17:07", "remaining_time": "0:11:07"}
+{"current_steps": 544, "total_steps": 586, "loss": 0.7689, "lr": 1.559003901189099e-07, "epoch": 0.9271410311035364, "percentage": 92.83, "elapsed_time": "2:17:35", "remaining_time": "0:10:37"}
+{"current_steps": 546, "total_steps": 586, "loss": 0.7592, "lr": 1.4147501151628273e-07, "epoch": 0.9305496378355347, "percentage": 93.17, "elapsed_time": "2:18:03", "remaining_time": "0:10:06"}
+{"current_steps": 548, "total_steps": 586, "loss": 0.7369, "lr": 1.2774025076911445e-07, "epoch": 0.9339582445675331, "percentage": 93.52, "elapsed_time": "2:18:36", "remaining_time": "0:09:36"}
+{"current_steps": 550, "total_steps": 586, "loss": 0.735, "lr": 1.146980602129466e-07, "epoch": 0.9373668512995313, "percentage": 93.86, "elapsed_time": "2:19:05", "remaining_time": "0:09:06"}
+{"current_steps": 552, "total_steps": 586, "loss": 0.7895, "lr": 1.0235029373752758e-07, "epoch": 0.9407754580315296, "percentage": 94.2, "elapsed_time": "2:19:31", "remaining_time": "0:08:35"}
+{"current_steps": 554, "total_steps": 586, "loss": 0.8128, "lr": 9.069870652329283e-08, "epoch": 0.9441840647635279, "percentage": 94.54, "elapsed_time": "2:19:57", "remaining_time": "0:08:05"}
+{"current_steps": 556, "total_steps": 586, "loss": 0.7438, "lr": 7.974495479187271e-08, "epoch": 0.9475926714955262, "percentage": 94.88, "elapsed_time": "2:20:24", "remaining_time": "0:07:34"}
+{"current_steps": 558, "total_steps": 586, "loss": 0.7748, "lr": 6.949059557066596e-08, "epoch": 0.9510012782275244, "percentage": 95.22, "elapsed_time": "2:20:54", "remaining_time": "0:07:04"}
+{"current_steps": 560, "total_steps": 586, "loss": 0.775, "lr": 5.993708647151874e-08, "epoch": 0.9544098849595228, "percentage": 95.56, "elapsed_time": "2:21:23", "remaining_time": "0:06:33"}
+{"current_steps": 562, "total_steps": 586, "loss": 0.7588, "lr": 5.108578548352838e-08, "epoch": 0.9578184916915211, "percentage": 95.9, "elapsed_time": "2:21:52", "remaining_time": "0:06:03"}
+{"current_steps": 564, "total_steps": 586, "loss": 0.7671, "lr": 4.2937950780013174e-08, "epoch": 0.9612270984235194, "percentage": 96.25, "elapsed_time": "2:22:21", "remaining_time": "0:05:33"}
+{"current_steps": 566, "total_steps": 586, "loss": 0.7908, "lr": 3.549474053966828e-08, "epoch": 0.9646357051555177, "percentage": 96.59, "elapsed_time": "2:22:51", "remaining_time": "0:05:02"}
+{"current_steps": 568, "total_steps": 586, "loss": 0.7466, "lr": 2.8757212781935218e-08, "epoch": 0.9680443118875159, "percentage": 96.93, "elapsed_time": "2:23:18", "remaining_time": "0:04:32"}
+{"current_steps": 570, "total_steps": 586, "loss": 0.7697, "lr": 2.2726325216608224e-08, "epoch": 0.9714529186195143, "percentage": 97.27, "elapsed_time": "2:23:44", "remaining_time": "0:04:02"}
+{"current_steps": 572, "total_steps": 586, "loss": 0.7753, "lr": 1.7402935107702634e-08, "epoch": 0.9748615253515126, "percentage": 97.61, "elapsed_time": "2:24:13", "remaining_time": "0:03:31"}
+{"current_steps": 574, "total_steps": 586, "loss": 0.7234, "lr": 1.2787799151596225e-08, "epoch": 0.9782701320835109, "percentage": 97.95, "elapsed_time": "2:24:44", "remaining_time": "0:03:01"}
+{"current_steps": 576, "total_steps": 586, "loss": 0.7403, "lr": 8.881573369469153e-09, "epoch": 0.9816787388155092, "percentage": 98.29, "elapsed_time": "2:25:21", "remaining_time": "0:02:31"}
+{"current_steps": 578, "total_steps": 586, "loss": 0.7659, "lr": 5.684813014052437e-09, "epoch": 0.9850873455475074, "percentage": 98.63, "elapsed_time": "2:25:46", "remaining_time": "0:02:01"}
+{"current_steps": 580, "total_steps": 586, "loss": 0.7572, "lr": 3.197972490704415e-09, "epoch": 0.9884959522795057, "percentage": 98.98, "elapsed_time": "2:26:15", "remaining_time": "0:01:30"}
+{"current_steps": 582, "total_steps": 586, "loss": 0.7572, "lr": 1.421405292813538e-09, "epoch": 0.9919045590115041, "percentage": 99.32, "elapsed_time": "2:26:43", "remaining_time": "0:01:00"}
+{"current_steps": 584, "total_steps": 586, "loss": 0.752, "lr": 3.553639515574414e-10, "epoch": 0.9953131657435024, "percentage": 99.66, "elapsed_time": "2:27:10", "remaining_time": "0:00:30"}
+{"current_steps": 586, "total_steps": 586, "loss": 0.7504, "lr": 0.0, "epoch": 0.9987217724755006, "percentage": 100.0, "elapsed_time": "2:27:40", "remaining_time": "0:00:00"}
+{"current_steps": 586, "total_steps": 586, "epoch": 0.9987217724755006, "percentage": 100.0, "elapsed_time": "2:30:50", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2093 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9987217724755006,
+  "eval_steps": 500,
+  "global_step": 586,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0034086067319982955,
+      "grad_norm": 7.117070422384071,
+      "learning_rate": 3.3898305084745766e-07,
+      "loss": 1.5934,
+      "step": 2
+    },
+    {
+      "epoch": 0.006817213463996591,
+      "grad_norm": 7.58934528658197,
+      "learning_rate": 6.779661016949153e-07,
+      "loss": 1.6231,
+      "step": 4
+    },
+    {
+      "epoch": 0.010225820195994887,
+      "grad_norm": 6.51402630995005,
+      "learning_rate": 1.016949152542373e-06,
+      "loss": 1.5692,
+      "step": 6
+    },
+    {
+      "epoch": 0.013634426927993182,
+      "grad_norm": 5.957629945500037,
+      "learning_rate": 1.3559322033898307e-06,
+      "loss": 1.5249,
+      "step": 8
+    },
+    {
+      "epoch": 0.017043033659991477,
+      "grad_norm": 4.594385046827305,
+      "learning_rate": 1.6949152542372882e-06,
+      "loss": 1.5132,
+      "step": 10
+    },
+    {
+      "epoch": 0.020451640391989774,
+      "grad_norm": 3.4805968864154875,
+      "learning_rate": 2.033898305084746e-06,
+      "loss": 1.4339,
+      "step": 12
+    },
+    {
+      "epoch": 0.02386024712398807,
+      "grad_norm": 3.672492727269049,
+      "learning_rate": 2.372881355932204e-06,
+      "loss": 1.3733,
+      "step": 14
+    },
+    {
+      "epoch": 0.027268853855986364,
+      "grad_norm": 3.5696770668674653,
+      "learning_rate": 2.7118644067796613e-06,
+      "loss": 1.2981,
+      "step": 16
+    },
+    {
+      "epoch": 0.03067746058798466,
+      "grad_norm": 3.721066217222145,
+      "learning_rate": 3.0508474576271192e-06,
+      "loss": 1.2152,
+      "step": 18
+    },
+    {
+      "epoch": 0.034086067319982954,
+      "grad_norm": 3.3165399160593765,
+      "learning_rate": 3.3898305084745763e-06,
+      "loss": 1.1972,
+      "step": 20
+    },
+    {
+      "epoch": 0.03749467405198125,
+      "grad_norm": 3.0704960315045087,
+      "learning_rate": 3.7288135593220342e-06,
+      "loss": 1.1098,
+      "step": 22
+    },
+    {
+      "epoch": 0.04090328078397955,
+      "grad_norm": 3.0249632466321708,
+      "learning_rate": 4.067796610169492e-06,
+      "loss": 1.1101,
+      "step": 24
+    },
+    {
+      "epoch": 0.044311887515977845,
+      "grad_norm": 2.51223844701648,
+      "learning_rate": 4.40677966101695e-06,
+      "loss": 1.0707,
+      "step": 26
+    },
+    {
+      "epoch": 0.04772049424797614,
+      "grad_norm": 2.337756418129475,
+      "learning_rate": 4.745762711864408e-06,
+      "loss": 1.0054,
+      "step": 28
+    },
+    {
+      "epoch": 0.05112910097997444,
+      "grad_norm": 2.507569726418487,
+      "learning_rate": 5.084745762711865e-06,
+      "loss": 0.9751,
+      "step": 30
+    },
+    {
+      "epoch": 0.05453770771197273,
+      "grad_norm": 2.8133808280998664,
+      "learning_rate": 5.423728813559323e-06,
+      "loss": 1.0073,
+      "step": 32
+    },
+    {
+      "epoch": 0.057946314443971025,
+      "grad_norm": 2.259104843714805,
+      "learning_rate": 5.7627118644067805e-06,
+      "loss": 0.9816,
+      "step": 34
+    },
+    {
+      "epoch": 0.06135492117596932,
+      "grad_norm": 2.489954458392594,
+      "learning_rate": 6.1016949152542385e-06,
+      "loss": 0.9969,
+      "step": 36
+    },
+    {
+      "epoch": 0.06476352790796762,
+      "grad_norm": 2.489196411046845,
+      "learning_rate": 6.440677966101695e-06,
+      "loss": 0.9751,
+      "step": 38
+    },
+    {
+      "epoch": 0.06817213463996591,
+      "grad_norm": 2.328531532406521,
+      "learning_rate": 6.779661016949153e-06,
+      "loss": 0.9063,
+      "step": 40
+    },
+    {
+      "epoch": 0.07158074137196421,
+      "grad_norm": 1.8777822207540218,
+      "learning_rate": 7.1186440677966106e-06,
+      "loss": 0.9076,
+      "step": 42
+    },
+    {
+      "epoch": 0.0749893481039625,
+      "grad_norm": 2.3564822959993403,
+      "learning_rate": 7.4576271186440685e-06,
+      "loss": 0.9544,
+      "step": 44
+    },
+    {
+      "epoch": 0.0783979548359608,
+      "grad_norm": 2.0258103744170604,
+      "learning_rate": 7.796610169491526e-06,
+      "loss": 0.9056,
+      "step": 46
+    },
+    {
+      "epoch": 0.0818065615679591,
+      "grad_norm": 2.156862728985429,
+      "learning_rate": 8.135593220338983e-06,
+      "loss": 0.853,
+      "step": 48
+    },
+    {
+      "epoch": 0.08521516829995739,
+      "grad_norm": 2.34893762869447,
+      "learning_rate": 8.47457627118644e-06,
+      "loss": 0.8894,
+      "step": 50
+    },
+    {
+      "epoch": 0.08862377503195569,
+      "grad_norm": 2.315393254315105,
+      "learning_rate": 8.8135593220339e-06,
+      "loss": 0.9133,
+      "step": 52
+    },
+    {
+      "epoch": 0.09203238176395398,
+      "grad_norm": 2.301164621363547,
+      "learning_rate": 9.152542372881356e-06,
+      "loss": 0.8895,
+      "step": 54
+    },
+    {
+      "epoch": 0.09544098849595228,
+      "grad_norm": 2.2398380284062425,
+      "learning_rate": 9.491525423728815e-06,
+      "loss": 0.8563,
+      "step": 56
+    },
+    {
+      "epoch": 0.09884959522795057,
+      "grad_norm": 2.029764049433947,
+      "learning_rate": 9.830508474576272e-06,
+      "loss": 0.8813,
+      "step": 58
+    },
+    {
+      "epoch": 0.10225820195994888,
+      "grad_norm": 2.0880574238328387,
+      "learning_rate": 9.999911158222826e-06,
+      "loss": 0.9337,
+      "step": 60
+    },
+    {
+      "epoch": 0.10566680869194717,
+      "grad_norm": 2.3366310826461993,
+      "learning_rate": 9.999200442948178e-06,
+      "loss": 0.924,
+      "step": 62
+    },
+    {
+      "epoch": 0.10907541542394546,
+      "grad_norm": 2.344634528525901,
+      "learning_rate": 9.997779113423916e-06,
+      "loss": 0.9312,
+      "step": 64
+    },
+    {
+      "epoch": 0.11248402215594376,
+      "grad_norm": 2.551521533584163,
+      "learning_rate": 9.99564737168575e-06,
+      "loss": 0.9062,
+      "step": 66
+    },
+    {
+      "epoch": 0.11589262888794205,
+      "grad_norm": 2.2111244932074,
+      "learning_rate": 9.992805520751352e-06,
+      "loss": 0.9032,
+      "step": 68
+    },
+    {
+      "epoch": 0.11930123561994035,
+      "grad_norm": 2.2310561621390463,
+      "learning_rate": 9.989253964577267e-06,
+      "loss": 0.8851,
+      "step": 70
+    },
+    {
+      "epoch": 0.12270984235193864,
+      "grad_norm": 2.1278482556209153,
+      "learning_rate": 9.984993208001513e-06,
+      "loss": 0.8663,
+      "step": 72
+    },
+    {
+      "epoch": 0.12611844908393693,
+      "grad_norm": 2.173728187499986,
+      "learning_rate": 9.980023856671805e-06,
+      "loss": 0.889,
+      "step": 74
+    },
+    {
+      "epoch": 0.12952705581593524,
+      "grad_norm": 2.0928351193635026,
+      "learning_rate": 9.974346616959476e-06,
+      "loss": 0.8293,
+      "step": 76
+    },
+    {
+      "epoch": 0.13293566254793354,
+      "grad_norm": 2.8128383896971902,
+      "learning_rate": 9.96796229585906e-06,
+      "loss": 0.8746,
+      "step": 78
+    },
+    {
+      "epoch": 0.13634426927993182,
+      "grad_norm": 2.0208631286469254,
+      "learning_rate": 9.960871800873586e-06,
+      "loss": 0.9004,
+      "step": 80
+    },
+    {
+      "epoch": 0.13975287601193012,
+      "grad_norm": 2.1974668712171157,
+      "learning_rate": 9.953076139885581e-06,
+      "loss": 0.9384,
+      "step": 82
+    },
+    {
+      "epoch": 0.14316148274392843,
+      "grad_norm": 2.3881999042131516,
+      "learning_rate": 9.944576421013804e-06,
+      "loss": 0.8679,
+      "step": 84
+    },
+    {
+      "epoch": 0.1465700894759267,
+      "grad_norm": 1.9809033021368312,
+      "learning_rate": 9.935373852455724e-06,
+      "loss": 0.855,
+      "step": 86
+    },
+    {
+      "epoch": 0.149978696207925,
+      "grad_norm": 2.063145920288984,
+      "learning_rate": 9.925469742315799e-06,
+      "loss": 0.8509,
+      "step": 88
+    },
+    {
+      "epoch": 0.1533873029399233,
+      "grad_norm": 2.1854349522591248,
+      "learning_rate": 9.91486549841951e-06,
+      "loss": 0.8774,
+      "step": 90
+    },
+    {
+      "epoch": 0.1567959096719216,
+      "grad_norm": 1.9442802721360337,
+      "learning_rate": 9.903562628113266e-06,
+      "loss": 0.9293,
+      "step": 92
+    },
+    {
+      "epoch": 0.1602045164039199,
+      "grad_norm": 1.9595403019093638,
+      "learning_rate": 9.891562738050127e-06,
+      "loss": 0.835,
+      "step": 94
+    },
+    {
+      "epoch": 0.1636131231359182,
+      "grad_norm": 2.001941381433757,
+      "learning_rate": 9.878867533961434e-06,
+      "loss": 0.8594,
+      "step": 96
+    },
+    {
+      "epoch": 0.1670217298679165,
+      "grad_norm": 2.24822151912714,
+      "learning_rate": 9.865478820414344e-06,
+      "loss": 0.85,
+      "step": 98
+    },
+    {
+      "epoch": 0.17043033659991477,
+      "grad_norm": 1.8987704947701014,
+      "learning_rate": 9.851398500555321e-06,
+      "loss": 0.8647,
+      "step": 100
+    },
+    {
+      "epoch": 0.17383894333191308,
+      "grad_norm": 1.9294894488605314,
+      "learning_rate": 9.8366285758396e-06,
+      "loss": 0.8374,
+      "step": 102
+    },
+    {
+      "epoch": 0.17724755006391138,
+      "grad_norm": 2.0659769053985455,
+      "learning_rate": 9.82117114574671e-06,
+      "loss": 0.8625,
+      "step": 104
+    },
+    {
+      "epoch": 0.18065615679590968,
+      "grad_norm": 2.1086334049039044,
+      "learning_rate": 9.805028407482027e-06,
+      "loss": 0.8418,
+      "step": 106
+    },
+    {
+      "epoch": 0.18406476352790796,
+      "grad_norm": 1.9093180149494513,
+      "learning_rate": 9.78820265566445e-06,
+      "loss": 0.8378,
+      "step": 108
+    },
+    {
+      "epoch": 0.18747337025990626,
+      "grad_norm": 2.108586166296398,
+      "learning_rate": 9.770696282000245e-06,
+      "loss": 0.8717,
+      "step": 110
+    },
+    {
+      "epoch": 0.19088197699190457,
+      "grad_norm": 1.9600773842942703,
+      "learning_rate": 9.75251177494306e-06,
+      "loss": 0.8626,
+      "step": 112
+    },
+    {
+      "epoch": 0.19429058372390284,
+      "grad_norm": 2.2720190152376425,
+      "learning_rate": 9.733651719340207e-06,
+      "loss": 0.8714,
+      "step": 114
+    },
+    {
+      "epoch": 0.19769919045590115,
+      "grad_norm": 1.9850702888722942,
+      "learning_rate": 9.714118796065243e-06,
+      "loss": 0.8529,
+      "step": 116
+    },
+    {
+      "epoch": 0.20110779718789945,
+      "grad_norm": 2.0995202528398234,
+      "learning_rate": 9.693915781636887e-06,
+      "loss": 0.8508,
+      "step": 118
+    },
+    {
+      "epoch": 0.20451640391989775,
+      "grad_norm": 2.191390132974462,
+      "learning_rate": 9.673045547824356e-06,
+      "loss": 0.8699,
+      "step": 120
+    },
+    {
+      "epoch": 0.20792501065189603,
+      "grad_norm": 1.92525268724109,
+      "learning_rate": 9.651511061239151e-06,
+      "loss": 0.8746,
+      "step": 122
+    },
+    {
+      "epoch": 0.21133361738389433,
+      "grad_norm": 2.1743856429859765,
+      "learning_rate": 9.62931538291337e-06,
+      "loss": 0.8643,
+      "step": 124
+    },
+    {
+      "epoch": 0.21474222411589264,
+      "grad_norm": 2.2545723733622642,
+      "learning_rate": 9.606461667864603e-06,
+      "loss": 0.8518,
+      "step": 126
+    },
+    {
+      "epoch": 0.21815083084789091,
+      "grad_norm": 2.088328769098791,
+      "learning_rate": 9.582953164647438e-06,
+      "loss": 0.8036,
+      "step": 128
+    },
+    {
+      "epoch": 0.22155943757988922,
+      "grad_norm": 1.7154521796104316,
+      "learning_rate": 9.558793214891716e-06,
+      "loss": 0.8749,
+      "step": 130
+    },
+    {
+      "epoch": 0.22496804431188752,
+      "grad_norm": 1.9971816903951989,
+      "learning_rate": 9.533985252827525e-06,
+      "loss": 0.8442,
+      "step": 132
+    },
+    {
+      "epoch": 0.22837665104388583,
+      "grad_norm": 2.0452202203810246,
+      "learning_rate": 9.508532804797035e-06,
+      "loss": 0.8331,
+      "step": 134
+    },
+    {
+      "epoch": 0.2317852577758841,
+      "grad_norm": 1.8873007094774574,
+      "learning_rate": 9.482439488753248e-06,
+      "loss": 0.8404,
+      "step": 136
+    },
+    {
+      "epoch": 0.2351938645078824,
+      "grad_norm": 1.8694505860373616,
+      "learning_rate": 9.455709013745726e-06,
+      "loss": 0.8518,
+      "step": 138
+    },
+    {
+      "epoch": 0.2386024712398807,
+      "grad_norm": 1.8826067133760322,
+      "learning_rate": 9.42834517939336e-06,
+      "loss": 0.8224,
+      "step": 140
+    },
+    {
+      "epoch": 0.24201107797187899,
+      "grad_norm": 1.783995366074571,
+      "learning_rate": 9.400351875344268e-06,
+      "loss": 0.8368,
+      "step": 142
+    },
+    {
+      "epoch": 0.2454196847038773,
+      "grad_norm": 1.9541798533923145,
+      "learning_rate": 9.371733080722911e-06,
+      "loss": 0.8753,
+      "step": 144
+    },
+    {
+      "epoch": 0.2488282914358756,
+      "grad_norm": 1.8725559407975727,
+      "learning_rate": 9.342492863564468e-06,
+      "loss": 0.8382,
+      "step": 146
+    },
+    {
+      "epoch": 0.25223689816787387,
+      "grad_norm": 2.166287610640464,
+      "learning_rate": 9.312635380236582e-06,
+      "loss": 0.8311,
+      "step": 148
+    },
+    {
+      "epoch": 0.2556455048998722,
+      "grad_norm": 2.100500640351814,
+      "learning_rate": 9.282164874848554e-06,
+      "loss": 0.8731,
+      "step": 150
+    },
+    {
+      "epoch": 0.2590541116318705,
+      "grad_norm": 2.269255130053819,
+      "learning_rate": 9.251085678648072e-06,
+      "loss": 0.832,
+      "step": 152
+    },
+    {
+      "epoch": 0.26246271836386875,
+      "grad_norm": 2.019471552415879,
+      "learning_rate": 9.219402209405519e-06,
+      "loss": 0.8715,
+      "step": 154
+    },
+    {
+      "epoch": 0.2658713250958671,
+      "grad_norm": 2.057431118897924,
+      "learning_rate": 9.18711897078603e-06,
+      "loss": 0.8809,
+      "step": 156
+    },
+    {
+      "epoch": 0.26927993182786536,
+      "grad_norm": 1.7964562596950788,
+      "learning_rate": 9.154240551709298e-06,
+      "loss": 0.8159,
+      "step": 158
+    },
+    {
+      "epoch": 0.27268853855986364,
+      "grad_norm": 1.77492002243483,
+      "learning_rate": 9.1207716256973e-06,
+      "loss": 0.8443,
+      "step": 160
+    },
+    {
+      "epoch": 0.27609714529186197,
+      "grad_norm": 2.042551909185088,
+      "learning_rate": 9.08671695020995e-06,
+      "loss": 0.8718,
+      "step": 162
+    },
+    {
+      "epoch": 0.27950575202386024,
+      "grad_norm": 1.9983795965696414,
+      "learning_rate": 9.052081365968873e-06,
+      "loss": 0.827,
+      "step": 164
+    },
+    {
+      "epoch": 0.2829143587558585,
+      "grad_norm": 2.052158753663356,
+      "learning_rate": 9.016869796269299e-06,
+      "loss": 0.8478,
+      "step": 166
+    },
+    {
+      "epoch": 0.28632296548785685,
+      "grad_norm": 1.8439668797771172,
+      "learning_rate": 8.981087246280246e-06,
+      "loss": 0.8063,
+      "step": 168
+    },
+    {
+      "epoch": 0.2897315722198551,
+      "grad_norm": 1.8391702615486196,
+      "learning_rate": 8.944738802333062e-06,
+      "loss": 0.8345,
+      "step": 170
+    },
+    {
+      "epoch": 0.2931401789518534,
+      "grad_norm": 1.832576311204302,
+      "learning_rate": 8.907829631198412e-06,
+      "loss": 0.7921,
+      "step": 172
+    },
+    {
+      "epoch": 0.29654878568385173,
+      "grad_norm": 1.9349714568402026,
+      "learning_rate": 8.870364979351862e-06,
+      "loss": 0.8122,
+      "step": 174
+    },
+    {
+      "epoch": 0.29995739241585,
+      "grad_norm": 2.4339551873431104,
+      "learning_rate": 8.832350172228099e-06,
+      "loss": 0.82,
+      "step": 176
+    },
+    {
+      "epoch": 0.30336599914784834,
+      "grad_norm": 1.5892853144502257,
+      "learning_rate": 8.793790613463956e-06,
+      "loss": 0.8362,
+      "step": 178
+    },
+    {
+      "epoch": 0.3067746058798466,
+      "grad_norm": 1.7805951409311684,
+      "learning_rate": 8.754691784130298e-06,
+      "loss": 0.8283,
+      "step": 180
+    },
+    {
+      "epoch": 0.3101832126118449,
+      "grad_norm": 1.6741127801982758,
+      "learning_rate": 8.715059241952925e-06,
+      "loss": 0.8055,
+      "step": 182
+    },
+    {
+      "epoch": 0.3135918193438432,
+      "grad_norm": 1.7776583452428674,
+      "learning_rate": 8.674898620522558e-06,
+      "loss": 0.8238,
+      "step": 184
+    },
+    {
+      "epoch": 0.3170004260758415,
+      "grad_norm": 1.7939673520888073,
+      "learning_rate": 8.634215628494044e-06,
+      "loss": 0.7946,
+      "step": 186
+    },
+    {
+      "epoch": 0.3204090328078398,
+      "grad_norm": 1.9491996130141838,
+      "learning_rate": 8.593016048774911e-06,
+      "loss": 0.8269,
+      "step": 188
+    },
+    {
+      "epoch": 0.3238176395398381,
+      "grad_norm": 2.0260518716817355,
+      "learning_rate": 8.551305737703338e-06,
+      "loss": 0.8205,
+      "step": 190
+    },
+    {
+      "epoch": 0.3272262462718364,
+      "grad_norm": 2.0407011387236915,
+      "learning_rate": 8.509090624215708e-06,
+      "loss": 0.7965,
+      "step": 192
+    },
+    {
+      "epoch": 0.33063485300383466,
+      "grad_norm": 1.885729706338136,
+      "learning_rate": 8.466376709003841e-06,
+      "loss": 0.8444,
+      "step": 194
+    },
+    {
+      "epoch": 0.334043459735833,
+      "grad_norm": 1.8594029276174733,
+      "learning_rate": 8.423170063662014e-06,
+      "loss": 0.8301,
+      "step": 196
+    },
+    {
+      "epoch": 0.33745206646783127,
+      "grad_norm": 2.0661661167934775,
+      "learning_rate": 8.379476829823919e-06,
+      "loss": 0.8194,
+      "step": 198
+    },
+    {
+      "epoch": 0.34086067319982954,
+      "grad_norm": 1.843312820214377,
+      "learning_rate": 8.335303218289645e-06,
+      "loss": 0.8223,
+      "step": 200
+    },
+    {
+      "epoch": 0.3442692799318279,
+      "grad_norm": 1.9237357576874556,
+      "learning_rate": 8.290655508142855e-06,
+      "loss": 0.8066,
+      "step": 202
+    },
+    {
+      "epoch": 0.34767788666382615,
+      "grad_norm": 1.8680286378652424,
+      "learning_rate": 8.245540045858229e-06,
+      "loss": 0.8035,
+      "step": 204
+    },
+    {
+      "epoch": 0.3510864933958245,
+      "grad_norm": 1.7375474557232102,
+      "learning_rate": 8.199963244399351e-06,
+      "loss": 0.8115,
+      "step": 206
+    },
+    {
+      "epoch": 0.35449510012782276,
+      "grad_norm": 1.8317920240540273,
+      "learning_rate": 8.153931582307124e-06,
+      "loss": 0.8333,
+      "step": 208
+    },
+    {
+      "epoch": 0.35790370685982104,
+      "grad_norm": 1.8807672342031,
+      "learning_rate": 8.107451602778887e-06,
+      "loss": 0.8114,
+      "step": 210
+    },
+    {
+      "epoch": 0.36131231359181937,
+      "grad_norm": 1.8233277253885543,
+      "learning_rate": 8.060529912738316e-06,
+      "loss": 0.8084,
+      "step": 212
+    },
+    {
+      "epoch": 0.36472092032381764,
+      "grad_norm": 1.8018328218174473,
+      "learning_rate": 8.013173181896283e-06,
+      "loss": 0.8036,
+      "step": 214
+    },
+    {
+      "epoch": 0.3681295270558159,
+      "grad_norm": 1.7500277066768286,
+      "learning_rate": 7.965388141802792e-06,
+      "loss": 0.8493,
+      "step": 216
+    },
+    {
+      "epoch": 0.37153813378781425,
+      "grad_norm": 1.8202749968468963,
+      "learning_rate": 7.917181584890113e-06,
+      "loss": 0.8666,
+      "step": 218
+    },
+    {
+      "epoch": 0.3749467405198125,
+      "grad_norm": 1.7463930119282958,
+      "learning_rate": 7.868560363507268e-06,
+      "loss": 0.8104,
+      "step": 220
+    },
+    {
+      "epoch": 0.3783553472518108,
+      "grad_norm": 1.687535685348095,
+      "learning_rate": 7.819531388946e-06,
+      "loss": 0.7423,
+      "step": 222
+    },
+    {
+      "epoch": 0.38176395398380913,
+      "grad_norm": 1.8780292088928865,
+      "learning_rate": 7.770101630458364e-06,
+      "loss": 0.7817,
+      "step": 224
+    },
+    {
+      "epoch": 0.3851725607158074,
+      "grad_norm": 1.7870199236678057,
+      "learning_rate": 7.720278114266084e-06,
+      "loss": 0.8055,
+      "step": 226
+    },
+    {
+      "epoch": 0.3885811674478057,
+      "grad_norm": 2.1478936673535522,
+      "learning_rate": 7.670067922561795e-06,
+      "loss": 0.8181,
+      "step": 228
+    },
+    {
+      "epoch": 0.391989774179804,
+      "grad_norm": 1.996195916952366,
+      "learning_rate": 7.619478192502352e-06,
+      "loss": 0.786,
+      "step": 230
+    },
+    {
+      "epoch": 0.3953983809118023,
+      "grad_norm": 1.7607026492930253,
+      "learning_rate": 7.5685161151943066e-06,
+      "loss": 0.7861,
+      "step": 232
+    },
+    {
+      "epoch": 0.39880698764380057,
+      "grad_norm": 1.982916095534787,
+      "learning_rate": 7.5171889346717264e-06,
+      "loss": 0.8314,
+      "step": 234
+    },
+    {
+      "epoch": 0.4022155943757989,
+      "grad_norm": 1.8475361020735406,
+      "learning_rate": 7.465503946866491e-06,
+      "loss": 0.8045,
+      "step": 236
+    },
+    {
+      "epoch": 0.4056242011077972,
+      "grad_norm": 1.6483972591254976,
+      "learning_rate": 7.413468498571199e-06,
+      "loss": 0.8149,
+      "step": 238
+    },
+    {
+      "epoch": 0.4090328078397955,
+      "grad_norm": 1.9862409096042428,
+      "learning_rate": 7.361089986394863e-06,
+      "loss": 0.8038,
+      "step": 240
+    },
+    {
+      "epoch": 0.4124414145717938,
+      "grad_norm": 1.9381151415852729,
+      "learning_rate": 7.308375855711508e-06,
+      "loss": 0.8203,
+      "step": 242
+    },
+    {
+      "epoch": 0.41585002130379206,
+      "grad_norm": 1.8252397931133695,
+      "learning_rate": 7.2553335996018485e-06,
+      "loss": 0.8096,
+      "step": 244
+    },
+    {
+      "epoch": 0.4192586280357904,
+      "grad_norm": 1.8096704344426044,
+      "learning_rate": 7.201970757788172e-06,
+      "loss": 0.7692,
+      "step": 246
+    },
+    {
+      "epoch": 0.42266723476778867,
+      "grad_norm": 1.7220473220530976,
+      "learning_rate": 7.148294915562617e-06,
+      "loss": 0.7941,
+      "step": 248
+    },
+    {
+      "epoch": 0.42607584149978694,
+      "grad_norm": 1.6560074887380722,
+      "learning_rate": 7.09431370270894e-06,
+      "loss": 0.795,
+      "step": 250
+    },
+    {
+      "epoch": 0.4294844482317853,
+      "grad_norm": 1.6420030994162023,
+      "learning_rate": 7.040034792417986e-06,
+      "loss": 0.7854,
+      "step": 252
+    },
+    {
+      "epoch": 0.43289305496378355,
+      "grad_norm": 1.8777722598215576,
+      "learning_rate": 6.985465900196971e-06,
+      "loss": 0.8445,
+      "step": 254
+    },
+    {
+      "epoch": 0.43630166169578183,
+      "grad_norm": 1.8421388677475183,
+      "learning_rate": 6.930614782772766e-06,
+      "loss": 0.8372,
+      "step": 256
+    },
+    {
+      "epoch": 0.43971026842778016,
+      "grad_norm": 1.9176127454855982,
+      "learning_rate": 6.875489236989306e-06,
+      "loss": 0.82,
+      "step": 258
+    },
+    {
+      "epoch": 0.44311887515977844,
+      "grad_norm": 1.8186020984518791,
+      "learning_rate": 6.8200970986993e-06,
+      "loss": 0.8208,
+      "step": 260
+    },
+    {
+      "epoch": 0.4465274818917767,
+      "grad_norm": 1.9882080130853592,
+      "learning_rate": 6.764446241650411e-06,
+      "loss": 0.8073,
+      "step": 262
+    },
+    {
+      "epoch": 0.44993608862377504,
+      "grad_norm": 1.5626224821883135,
+      "learning_rate": 6.708544576366024e-06,
+      "loss": 0.8231,
+      "step": 264
+    },
+    {
+      "epoch": 0.4533446953557733,
+      "grad_norm": 1.8993741801940567,
+      "learning_rate": 6.65240004902081e-06,
+      "loss": 0.8065,
+      "step": 266
+    },
+    {
+      "epoch": 0.45675330208777165,
+      "grad_norm": 1.7550634910546117,
+      "learning_rate": 6.5960206403112045e-06,
+      "loss": 0.7485,
+      "step": 268
+    },
+    {
+      "epoch": 0.4601619088197699,
+      "grad_norm": 1.9326203800829964,
+      "learning_rate": 6.539414364320997e-06,
+      "loss": 0.779,
+      "step": 270
+    },
+    {
+      "epoch": 0.4635705155517682,
+      "grad_norm": 1.6516836712807916,
+      "learning_rate": 6.4825892673821556e-06,
+      "loss": 0.794,
+      "step": 272
+    },
+    {
+      "epoch": 0.46697912228376653,
+      "grad_norm": 2.003145254209738,
+      "learning_rate": 6.425553426931075e-06,
+      "loss": 0.7618,
+      "step": 274
+    },
+    {
+      "epoch": 0.4703877290157648,
+      "grad_norm": 1.6246913128967992,
+      "learning_rate": 6.368314950360416e-06,
+      "loss": 0.7785,
+      "step": 276
+    },
+    {
+      "epoch": 0.4737963357477631,
+      "grad_norm": 1.8754262243075055,
+      "learning_rate": 6.31088197386666e-06,
+      "loss": 0.765,
+      "step": 278
+    },
+    {
+      "epoch": 0.4772049424797614,
+      "grad_norm": 1.6448889983604882,
+      "learning_rate": 6.2532626612936035e-06,
+      "loss": 0.7977,
+      "step": 280
+    },
+    {
+      "epoch": 0.4806135492117597,
+      "grad_norm": 1.8537195734950456,
+      "learning_rate": 6.195465202971883e-06,
+      "loss": 0.7637,
+      "step": 282
+    },
+    {
+      "epoch": 0.48402215594375797,
+      "grad_norm": 1.7350572092463452,
+      "learning_rate": 6.137497814554773e-06,
+      "loss": 0.7974,
+      "step": 284
+    },
+    {
+      "epoch": 0.4874307626757563,
+      "grad_norm": 1.659202469943535,
+      "learning_rate": 6.079368735850355e-06,
+      "loss": 0.78,
+      "step": 286
+    },
+    {
+      "epoch": 0.4908393694077546,
+      "grad_norm": 2.0704522103071326,
+      "learning_rate": 6.021086229650273e-06,
+      "loss": 0.78,
+      "step": 288
+    },
+    {
+      "epoch": 0.49424797613975285,
+      "grad_norm": 1.7654110381757835,
+      "learning_rate": 5.96265858055521e-06,
+      "loss": 0.8101,
+      "step": 290
+    },
+    {
+      "epoch": 0.4976565828717512,
+      "grad_norm": 1.6744010674594727,
+      "learning_rate": 5.904094093797274e-06,
+      "loss": 0.7854,
+      "step": 292
+    },
+    {
+      "epoch": 0.5010651896037495,
+      "grad_norm": 1.672935281461675,
+      "learning_rate": 5.845401094059439e-06,
+      "loss": 0.8233,
+      "step": 294
+    },
+    {
+      "epoch": 0.5044737963357477,
+      "grad_norm": 1.7571827575826455,
+      "learning_rate": 5.786587924292228e-06,
+      "loss": 0.8072,
+      "step": 296
+    },
+    {
+      "epoch": 0.507882403067746,
+      "grad_norm": 1.7879627913914475,
+      "learning_rate": 5.727662944527808e-06,
+      "loss": 0.8236,
+      "step": 298
+    },
+    {
+      "epoch": 0.5112910097997444,
+      "grad_norm": 1.6693554243950373,
+      "learning_rate": 5.668634530691639e-06,
+      "loss": 0.7829,
+      "step": 300
+    },
+    {
+      "epoch": 0.5146996165317427,
+      "grad_norm": 1.7885967539315661,
+      "learning_rate": 5.609511073411881e-06,
+      "loss": 0.8069,
+      "step": 302
+    },
+    {
+      "epoch": 0.518108223263741,
+      "grad_norm": 1.8927285112086825,
+      "learning_rate": 5.550300976826697e-06,
+      "loss": 0.7978,
+      "step": 304
+    },
+    {
+      "epoch": 0.5215168299957392,
+      "grad_norm": 1.9422631435450946,
+      "learning_rate": 5.491012657389644e-06,
+      "loss": 0.8143,
+      "step": 306
+    },
+    {
+      "epoch": 0.5249254367277375,
+      "grad_norm": 1.8664920158914793,
+      "learning_rate": 5.431654542673315e-06,
+      "loss": 0.8184,
+      "step": 308
+    },
+    {
+      "epoch": 0.5283340434597358,
+      "grad_norm": 1.7545208791954934,
+      "learning_rate": 5.372235070171387e-06,
+      "loss": 0.7976,
+      "step": 310
+    },
+    {
+      "epoch": 0.5317426501917342,
+      "grad_norm": 1.8345783742469912,
+      "learning_rate": 5.312762686099282e-06,
+      "loss": 0.7726,
+      "step": 312
+    },
+    {
+      "epoch": 0.5351512569237324,
+      "grad_norm": 1.777874135882686,
+      "learning_rate": 5.253245844193564e-06,
+      "loss": 0.791,
+      "step": 314
+    },
+    {
+      "epoch": 0.5385598636557307,
+      "grad_norm": 1.7559490288145514,
+      "learning_rate": 5.193693004510284e-06,
+      "loss": 0.7654,
+      "step": 316
+    },
+    {
+      "epoch": 0.541968470387729,
+      "grad_norm": 1.7582347301570869,
+      "learning_rate": 5.1341126322224145e-06,
+      "loss": 0.7509,
+      "step": 318
+    },
+    {
+      "epoch": 0.5453770771197273,
+      "grad_norm": 1.6309306234524417,
+      "learning_rate": 5.0745131964165686e-06,
+      "loss": 0.7737,
+      "step": 320
+    },
+    {
+      "epoch": 0.5487856838517257,
+      "grad_norm": 1.6033761601218945,
+      "learning_rate": 5.014903168889155e-06,
+      "loss": 0.7814,
+      "step": 322
+    },
+    {
+      "epoch": 0.5521942905837239,
+      "grad_norm": 1.9401976205946008,
+      "learning_rate": 4.955291022942146e-06,
+      "loss": 0.7782,
+      "step": 324
+    },
+    {
+      "epoch": 0.5556028973157222,
+      "grad_norm": 1.8683852058875654,
+      "learning_rate": 4.8956852321786394e-06,
+      "loss": 0.802,
+      "step": 326
+    },
+    {
+      "epoch": 0.5590115040477205,
+      "grad_norm": 1.859200797460236,
+      "learning_rate": 4.836094269298373e-06,
+      "loss": 0.7798,
+      "step": 328
+    },
+    {
+      "epoch": 0.5624201107797188,
+      "grad_norm": 1.803688727471679,
+      "learning_rate": 4.7765266048933626e-06,
+      "loss": 0.8098,
+      "step": 330
+    },
+    {
+      "epoch": 0.565828717511717,
+      "grad_norm": 1.7851903640220046,
+      "learning_rate": 4.7169907062438556e-06,
+      "loss": 0.7728,
+      "step": 332
+    },
+    {
+      "epoch": 0.5692373242437154,
+      "grad_norm": 1.6343651082668207,
+      "learning_rate": 4.657495036114731e-06,
+      "loss": 0.7721,
+      "step": 334
+    },
+    {
+      "epoch": 0.5726459309757137,
+      "grad_norm": 1.6586804458742679,
+      "learning_rate": 4.598048051552563e-06,
+      "loss": 0.8186,
+      "step": 336
+    },
+    {
+      "epoch": 0.576054537707712,
+      "grad_norm": 1.750348106992188,
+      "learning_rate": 4.53865820268349e-06,
+      "loss": 0.7503,
+      "step": 338
+    },
+    {
+      "epoch": 0.5794631444397103,
+      "grad_norm": 1.7165597335606,
+      "learning_rate": 4.479333931512064e-06,
+      "loss": 0.7915,
+      "step": 340
+    },
+    {
+      "epoch": 0.5828717511717085,
+      "grad_norm": 1.7582639909981337,
+      "learning_rate": 4.4200836707212525e-06,
+      "loss": 0.7754,
+      "step": 342
+    },
+    {
+      "epoch": 0.5862803579037068,
+      "grad_norm": 1.6838798515151536,
+      "learning_rate": 4.360915842473778e-06,
+      "loss": 0.7543,
+      "step": 344
+    },
+    {
+      "epoch": 0.5896889646357052,
+      "grad_norm": 1.4519358598788679,
+      "learning_rate": 4.301838857214944e-06,
+      "loss": 0.7629,
+      "step": 346
+    },
+    {
+      "epoch": 0.5930975713677035,
+      "grad_norm": 1.6951153457921704,
+      "learning_rate": 4.2428611124771184e-06,
+      "loss": 0.7919,
+      "step": 348
+    },
+    {
+      "epoch": 0.5965061780997017,
+      "grad_norm": 1.716470856323328,
+      "learning_rate": 4.183990991686071e-06,
+      "loss": 0.7853,
+      "step": 350
+    },
+    {
+      "epoch": 0.5999147848317,
+      "grad_norm": 1.8973005312026041,
+      "learning_rate": 4.125236862969304e-06,
+      "loss": 0.7695,
+      "step": 352
+    },
+    {
+      "epoch": 0.6033233915636983,
+      "grad_norm": 1.4862142786601558,
+      "learning_rate": 4.066607077966559e-06,
+      "loss": 0.7395,
+      "step": 354
+    },
+    {
+      "epoch": 0.6067319982956967,
+      "grad_norm": 1.8815334843344234,
+      "learning_rate": 4.008109970642665e-06,
+      "loss": 0.787,
+      "step": 356
+    },
+    {
+      "epoch": 0.610140605027695,
+      "grad_norm": 1.6378926667179599,
+      "learning_rate": 3.949753856102909e-06,
+      "loss": 0.7393,
+      "step": 358
+    },
+    {
+      "epoch": 0.6135492117596932,
+      "grad_norm": 1.7084737118259692,
+      "learning_rate": 3.891547029411074e-06,
+      "loss": 0.8053,
+      "step": 360
+    },
+    {
+      "epoch": 0.6169578184916915,
+      "grad_norm": 1.8544822094338145,
+      "learning_rate": 3.833497764410336e-06,
+      "loss": 0.7674,
+      "step": 362
+    },
+    {
+      "epoch": 0.6203664252236898,
+      "grad_norm": 1.7409266320356052,
+      "learning_rate": 3.7756143125471745e-06,
+      "loss": 0.7489,
+      "step": 364
+    },
+    {
+      "epoch": 0.6237750319556881,
+      "grad_norm": 1.8302377955954783,
+      "learning_rate": 3.7179049016984616e-06,
+      "loss": 0.7757,
+      "step": 366
+    },
+    {
+      "epoch": 0.6271836386876865,
+      "grad_norm": 1.6552784195481047,
+      "learning_rate": 3.660377735001911e-06,
+      "loss": 0.7656,
+      "step": 368
+    },
+    {
+      "epoch": 0.6305922454196847,
+      "grad_norm": 1.8034934811229115,
+      "learning_rate": 3.6030409896900333e-06,
+      "loss": 0.7731,
+      "step": 370
+    },
+    {
+      "epoch": 0.634000852151683,
+      "grad_norm": 1.656497367167841,
+      "learning_rate": 3.545902815927783e-06,
+      "loss": 0.7564,
+      "step": 372
+    },
+    {
+      "epoch": 0.6374094588836813,
+      "grad_norm": 1.6538858927486708,
+      "learning_rate": 3.4889713356540435e-06,
+      "loss": 0.7556,
+      "step": 374
+    },
+    {
+      "epoch": 0.6408180656156796,
+      "grad_norm": 1.7721211559316303,
+      "learning_rate": 3.432254641427136e-06,
+      "loss": 0.7754,
+      "step": 376
+    },
+    {
+      "epoch": 0.6442266723476778,
+      "grad_norm": 2.0169569259903946,
+      "learning_rate": 3.375760795274493e-06,
+      "loss": 0.7745,
+      "step": 378
+    },
+    {
+      "epoch": 0.6476352790796762,
+      "grad_norm": 1.5174685690539855,
+      "learning_rate": 3.3194978275466755e-06,
+      "loss": 0.7649,
+      "step": 380
+    },
+    {
+      "epoch": 0.6510438858116745,
+      "grad_norm": 1.5043926003321177,
+      "learning_rate": 3.2634737357758994e-06,
+      "loss": 0.74,
+      "step": 382
+    },
+    {
+      "epoch": 0.6544524925436728,
+      "grad_norm": 1.6692309306036763,
+      "learning_rate": 3.207696483539219e-06,
+      "loss": 0.7611,
+      "step": 384
+    },
+    {
+      "epoch": 0.657861099275671,
+      "grad_norm": 1.784881350588902,
+      "learning_rate": 3.152173999326537e-06,
+      "loss": 0.7675,
+      "step": 386
+    },
+    {
+      "epoch": 0.6612697060076693,
+      "grad_norm": 1.7444177474948184,
+      "learning_rate": 3.096914175413611e-06,
+      "loss": 0.7685,
+      "step": 388
+    },
+    {
+      "epoch": 0.6646783127396677,
+      "grad_norm": 1.999124406609706,
+      "learning_rate": 3.041924866740197e-06,
+      "loss": 0.7505,
+      "step": 390
+    },
+    {
+      "epoch": 0.668086919471666,
+      "grad_norm": 1.5350179140801363,
+      "learning_rate": 2.987213889793502e-06,
+      "loss": 0.7792,
+      "step": 392
+    },
+    {
+      "epoch": 0.6714955262036643,
+      "grad_norm": 1.7053442818016058,
+      "learning_rate": 2.9327890214971135e-06,
+      "loss": 0.7661,
+      "step": 394
+    },
+    {
+      "epoch": 0.6749041329356625,
+      "grad_norm": 1.6957720054975949,
+      "learning_rate": 2.878657998105533e-06,
+      "loss": 0.7587,
+      "step": 396
+    },
+    {
+      "epoch": 0.6783127396676608,
+      "grad_norm": 1.7615190253028947,
+      "learning_rate": 2.824828514104512e-06,
+      "loss": 0.8067,
+      "step": 398
+    },
+    {
+      "epoch": 0.6817213463996591,
+      "grad_norm": 1.5571276091989836,
+      "learning_rate": 2.771308221117309e-06,
+      "loss": 0.7478,
+      "step": 400
+    },
+    {
+      "epoch": 0.6851299531316575,
+      "grad_norm": 1.5280419708791328,
+      "learning_rate": 2.7181047268170436e-06,
+      "loss": 0.8071,
+      "step": 402
+    },
+    {
+      "epoch": 0.6885385598636558,
+      "grad_norm": 1.6771310372158614,
+      "learning_rate": 2.665225593845307e-06,
+      "loss": 0.7799,
+      "step": 404
+    },
+    {
+      "epoch": 0.691947166595654,
+      "grad_norm": 1.7562403180703012,
+      "learning_rate": 2.6126783387371545e-06,
+      "loss": 0.7471,
+      "step": 406
+    },
+    {
+      "epoch": 0.6953557733276523,
+      "grad_norm": 1.796003576907647,
+      "learning_rate": 2.5604704308526784e-06,
+      "loss": 0.7716,
+      "step": 408
+    },
+    {
+      "epoch": 0.6987643800596506,
+      "grad_norm": 1.6859622044955247,
+      "learning_rate": 2.5086092913152533e-06,
+      "loss": 0.8003,
+      "step": 410
+    },
+    {
+      "epoch": 0.702172986791649,
+      "grad_norm": 1.6580555467710547,
+      "learning_rate": 2.4571022919566747e-06,
+      "loss": 0.7463,
+      "step": 412
+    },
+    {
+      "epoch": 0.7055815935236472,
+      "grad_norm": 1.5775642264745176,
+      "learning_rate": 2.4059567542692688e-06,
+      "loss": 0.7329,
+      "step": 414
+    },
+    {
+      "epoch": 0.7089902002556455,
+      "grad_norm": 1.6145511797148977,
+      "learning_rate": 2.3551799483651894e-06,
+      "loss": 0.7557,
+      "step": 416
+    },
+    {
+      "epoch": 0.7123988069876438,
+      "grad_norm": 1.815641939119739,
+      "learning_rate": 2.3047790919429895e-06,
+      "loss": 0.7618,
+      "step": 418
+    },
+    {
+      "epoch": 0.7158074137196421,
+      "grad_norm": 1.751085671764699,
+      "learning_rate": 2.254761349261676e-06,
+      "loss": 0.7307,
+      "step": 420
+    },
+    {
+      "epoch": 0.7192160204516403,
+      "grad_norm": 1.722113083895161,
+      "learning_rate": 2.2051338301223187e-06,
+      "loss": 0.7536,
+      "step": 422
+    },
+    {
+      "epoch": 0.7226246271836387,
+      "grad_norm": 1.5887620089800378,
+      "learning_rate": 2.1559035888574433e-06,
+      "loss": 0.7139,
+      "step": 424
+    },
+    {
+      "epoch": 0.726033233915637,
+      "grad_norm": 1.792034913644711,
+      "learning_rate": 2.107077623328275e-06,
+      "loss": 0.7335,
+      "step": 426
+    },
+    {
+      "epoch": 0.7294418406476353,
+      "grad_norm": 1.5385202560838132,
+      "learning_rate": 2.0586628739300386e-06,
+      "loss": 0.7752,
+      "step": 428
+    },
+    {
+      "epoch": 0.7328504473796336,
+      "grad_norm": 1.554007093824859,
+      "learning_rate": 2.0106662226053924e-06,
+      "loss": 0.7814,
+      "step": 430
+    },
+    {
+      "epoch": 0.7362590541116318,
+      "grad_norm": 1.60530576083176,
+      "learning_rate": 1.9630944918662122e-06,
+      "loss": 0.7552,
+      "step": 432
+    },
+    {
+      "epoch": 0.7396676608436301,
+      "grad_norm": 1.5045851644291919,
+      "learning_rate": 1.9159544438237797e-06,
+      "loss": 0.7602,
+      "step": 434
+    },
+    {
+      "epoch": 0.7430762675756285,
+      "grad_norm": 1.6227515256198517,
+      "learning_rate": 1.8692527792276e-06,
+      "loss": 0.7695,
+      "step": 436
+    },
+    {
+      "epoch": 0.7464848743076268,
+      "grad_norm": 1.6302337283434762,
+      "learning_rate": 1.8229961365128985e-06,
+      "loss": 0.732,
+      "step": 438
+    },
+    {
+      "epoch": 0.749893481039625,
+      "grad_norm": 1.5834938000524268,
+      "learning_rate": 1.7771910908570156e-06,
+      "loss": 0.7566,
+      "step": 440
+    },
+    {
+      "epoch": 0.7533020877716233,
+      "grad_norm": 1.4483744882069087,
+      "learning_rate": 1.7318441532447555e-06,
+      "loss": 0.8073,
+      "step": 442
+    },
+    {
+      "epoch": 0.7567106945036216,
+      "grad_norm": 1.6825397102814452,
+      "learning_rate": 1.6869617695429024e-06,
+      "loss": 0.7579,
+      "step": 444
+    },
+    {
+      "epoch": 0.76011930123562,
+      "grad_norm": 1.5595787362408242,
+      "learning_rate": 1.6425503195839416e-06,
+      "loss": 0.8201,
+      "step": 446
+    },
+    {
+      "epoch": 0.7635279079676183,
+      "grad_norm": 1.6860253511961054,
+      "learning_rate": 1.5986161162592173e-06,
+      "loss": 0.7515,
+      "step": 448
+    },
+    {
+      "epoch": 0.7669365146996165,
+      "grad_norm": 1.6217349191290344,
+      "learning_rate": 1.555165404621567e-06,
+      "loss": 0.7684,
+      "step": 450
+    },
+    {
+      "epoch": 0.7703451214316148,
+      "grad_norm": 1.7202733697764292,
+      "learning_rate": 1.5122043609976282e-06,
+      "loss": 0.7335,
+      "step": 452
+    },
+    {
+      "epoch": 0.7737537281636131,
+      "grad_norm": 1.7746564761962131,
+      "learning_rate": 1.4697390921098886e-06,
+      "loss": 0.7848,
+      "step": 454
+    },
+    {
+      "epoch": 0.7771623348956114,
+      "grad_norm": 1.5349803625176617,
+      "learning_rate": 1.4277756342086524e-06,
+      "loss": 0.7757,
+      "step": 456
+    },
+    {
+      "epoch": 0.7805709416276098,
+      "grad_norm": 1.6124010704416651,
+      "learning_rate": 1.3863199522140053e-06,
+      "loss": 0.8031,
+      "step": 458
+    },
+    {
+      "epoch": 0.783979548359608,
+      "grad_norm": 1.7539891598801893,
+      "learning_rate": 1.3453779388679378e-06,
+      "loss": 0.7826,
+      "step": 460
+    },
+    {
+      "epoch": 0.7873881550916063,
+      "grad_norm": 1.6197274527555163,
+      "learning_rate": 1.3049554138967052e-06,
+      "loss": 0.7706,
+      "step": 462
+    },
+    {
+      "epoch": 0.7907967618236046,
+      "grad_norm": 1.5679920515099621,
+      "learning_rate": 1.2650581231835923e-06,
+      "loss": 0.7943,
+      "step": 464
+    },
+    {
+      "epoch": 0.7942053685556029,
+      "grad_norm": 1.6044331803289653,
+      "learning_rate": 1.225691737952152e-06,
+      "loss": 0.7558,
+      "step": 466
+    },
+    {
+      "epoch": 0.7976139752876011,
+      "grad_norm": 1.5903299233431156,
+      "learning_rate": 1.1868618539600718e-06,
+      "loss": 0.767,
+      "step": 468
+    },
+    {
+      "epoch": 0.8010225820195995,
+      "grad_norm": 1.5362855174389376,
+      "learning_rate": 1.1485739907037546e-06,
+      "loss": 0.7838,
+      "step": 470
+    },
+    {
+      "epoch": 0.8044311887515978,
+      "grad_norm": 1.6430906694597753,
+      "learning_rate": 1.1108335906337559e-06,
+      "loss": 0.7519,
+      "step": 472
+    },
+    {
+      "epoch": 0.8078397954835961,
+      "grad_norm": 1.7499785715417322,
+      "learning_rate": 1.0736460183811547e-06,
+      "loss": 0.7681,
+      "step": 474
+    },
+    {
+      "epoch": 0.8112484022155944,
+      "grad_norm": 1.7219048713168092,
+      "learning_rate": 1.0370165599950026e-06,
+      "loss": 0.7552,
+      "step": 476
+    },
+    {
+      "epoch": 0.8146570089475926,
+      "grad_norm": 1.797003265591149,
+      "learning_rate": 1.0009504221909284e-06,
+      "loss": 0.7336,
+      "step": 478
+    },
+    {
+      "epoch": 0.818065615679591,
+      "grad_norm": 1.322267929113636,
+      "learning_rate": 9.654527316110323e-07,
+      "loss": 0.7478,
+      "step": 480
+    },
+    {
+      "epoch": 0.8214742224115893,
+      "grad_norm": 1.6060348997953555,
+      "learning_rate": 9.305285340951509e-07,
+      "loss": 0.7693,
+      "step": 482
+    },
+    {
+      "epoch": 0.8248828291435876,
+      "grad_norm": 1.589739100394995,
+      "learning_rate": 8.961827939636198e-07,
+      "loss": 0.762,
+      "step": 484
+    },
+    {
+      "epoch": 0.8282914358755858,
+      "grad_norm": 1.5977203911776114,
+      "learning_rate": 8.624203933116088e-07,
+      "loss": 0.7517,
+      "step": 486
+    },
+    {
+      "epoch": 0.8317000426075841,
+      "grad_norm": 1.4433282291047127,
+      "learning_rate": 8.292461313151662e-07,
+      "loss": 0.7814,
+      "step": 488
+    },
+    {
+      "epoch": 0.8351086493395824,
+      "grad_norm": 1.5861673926723674,
+      "learning_rate": 7.966647235490222e-07,
+      "loss": 0.7988,
+      "step": 490
+    },
+    {
+      "epoch": 0.8385172560715808,
+      "grad_norm": 1.7785118279929921,
+      "learning_rate": 7.646808013163026e-07,
+      "loss": 0.7871,
+      "step": 492
+    },
+    {
+      "epoch": 0.8419258628035791,
+      "grad_norm": 1.4097703537190163,
+      "learning_rate": 7.332989109902028e-07,
+      "loss": 0.7471,
+      "step": 494
+    },
+    {
+      "epoch": 0.8453344695355773,
+      "grad_norm": 1.6394050318483955,
+      "learning_rate": 7.025235133677455e-07,
+      "loss": 0.7793,
+      "step": 496
+    },
+    {
+      "epoch": 0.8487430762675756,
+      "grad_norm": 1.4882317995688061,
+      "learning_rate": 6.723589830356925e-07,
+      "loss": 0.7587,
+      "step": 498
+    },
+    {
+      "epoch": 0.8521516829995739,
+      "grad_norm": 1.5993598547748789,
+      "learning_rate": 6.428096077487244e-07,
+      "loss": 0.7256,
+      "step": 500
+    },
+    {
+      "epoch": 0.8555602897315722,
+      "grad_norm": 1.8369103578526638,
+      "learning_rate": 6.138795878199467e-07,
+      "loss": 0.7346,
+      "step": 502
+    },
+    {
+      "epoch": 0.8589688964635706,
+      "grad_norm": 1.3809387771101223,
+      "learning_rate": 5.855730355238415e-07,
+      "loss": 0.7389,
+      "step": 504
+    },
+    {
+      "epoch": 0.8623775031955688,
+      "grad_norm": 1.606520808055538,
+      "learning_rate": 5.578939745117173e-07,
+      "loss": 0.7626,
+      "step": 506
+    },
+    {
+      "epoch": 0.8657861099275671,
+      "grad_norm": 1.4252640716496985,
+      "learning_rate": 5.308463392397756e-07,
+      "loss": 0.7471,
+      "step": 508
+    },
+    {
+      "epoch": 0.8691947166595654,
+      "grad_norm": 1.5620326120060357,
+      "learning_rate": 5.044339744098348e-07,
+      "loss": 0.7919,
+      "step": 510
+    },
+    {
+      "epoch": 0.8726033233915637,
+      "grad_norm": 1.582860405051893,
+      "learning_rate": 4.786606344228317e-07,
+      "loss": 0.8001,
+      "step": 512
+    },
+    {
+      "epoch": 0.876011930123562,
+      "grad_norm": 1.6390377107564265,
+      "learning_rate": 4.5352998284514004e-07,
+      "loss": 0.7693,
+      "step": 514
+    },
+    {
+      "epoch": 0.8794205368555603,
+      "grad_norm": 1.5740989498771922,
+      "learning_rate": 4.2904559188782334e-07,
+      "loss": 0.743,
+      "step": 516
+    },
+    {
+      "epoch": 0.8828291435875586,
+      "grad_norm": 1.6277724611514495,
+      "learning_rate": 4.05210941898847e-07,
+      "loss": 0.7204,
+      "step": 518
+    },
+    {
+      "epoch": 0.8862377503195569,
+      "grad_norm": 1.4964610352537944,
+      "learning_rate": 3.82029420868375e-07,
+      "loss": 0.7572,
+      "step": 520
+    },
+    {
+      "epoch": 0.8896463570515551,
+      "grad_norm": 1.5631623729163737,
+      "learning_rate": 3.5950432394717296e-07,
+      "loss": 0.7451,
+      "step": 522
+    },
+    {
+      "epoch": 0.8930549637835534,
+      "grad_norm": 1.6364549935760584,
+      "learning_rate": 3.3763885297822153e-07,
+      "loss": 0.7748,
+      "step": 524
+    },
+    {
+      "epoch": 0.8964635705155518,
+      "grad_norm": 1.901698775456035,
+      "learning_rate": 3.1643611604158687e-07,
+      "loss": 0.7467,
+      "step": 526
+    },
+    {
+      "epoch": 0.8998721772475501,
+      "grad_norm": 1.6649529271504364,
+      "learning_rate": 2.958991270126221e-07,
+      "loss": 0.7316,
+      "step": 528
+    },
+    {
+      "epoch": 0.9032807839795484,
+      "grad_norm": 1.7118286972837617,
+      "learning_rate": 2.760308051335564e-07,
+      "loss": 0.7546,
+      "step": 530
+    },
+    {
+      "epoch": 0.9066893907115466,
+      "grad_norm": 1.5718606351870987,
+      "learning_rate": 2.5683397459854045e-07,
+      "loss": 0.7064,
+      "step": 532
+    },
+    {
+      "epoch": 0.9100979974435449,
+      "grad_norm": 1.3894669570974365,
+      "learning_rate": 2.383113641521956e-07,
+      "loss": 0.747,
+      "step": 534
+    },
+    {
+      "epoch": 0.9135066041755433,
+      "grad_norm": 1.4787818567245852,
+      "learning_rate": 2.2046560670173912e-07,
+      "loss": 0.7447,
+      "step": 536
+    },
+    {
+      "epoch": 0.9169152109075416,
+      "grad_norm": 1.6746803954544742,
+      "learning_rate": 2.0329923894272463e-07,
+      "loss": 0.7329,
+      "step": 538
+    },
+    {
+      "epoch": 0.9203238176395399,
+      "grad_norm": 1.6476225947328762,
+      "learning_rate": 1.8681470099846554e-07,
+      "loss": 0.7494,
+      "step": 540
+    },
+    {
+      "epoch": 0.9237324243715381,
+      "grad_norm": 1.4591813987858449,
+      "learning_rate": 1.710143360731781e-07,
+      "loss": 0.7251,
+      "step": 542
+    },
+    {
+      "epoch": 0.9271410311035364,
+      "grad_norm": 1.6247674197735347,
+      "learning_rate": 1.559003901189099e-07,
+      "loss": 0.7689,
+      "step": 544
+    },
+    {
+      "epoch": 0.9305496378355347,
+      "grad_norm": 1.7245251671767248,
+      "learning_rate": 1.4147501151628273e-07,
+      "loss": 0.7592,
+      "step": 546
+    },
+    {
+      "epoch": 0.9339582445675331,
+      "grad_norm": 1.4107246676973044,
+      "learning_rate": 1.2774025076911445e-07,
+      "loss": 0.7369,
+      "step": 548
+    },
+    {
+      "epoch": 0.9373668512995313,
+      "grad_norm": 1.6265296555944986,
+      "learning_rate": 1.146980602129466e-07,
+      "loss": 0.735,
+      "step": 550
+    },
+    {
+      "epoch": 0.9407754580315296,
+      "grad_norm": 1.7696409777572968,
+      "learning_rate": 1.0235029373752758e-07,
+      "loss": 0.7895,
+      "step": 552
+    },
+    {
+      "epoch": 0.9441840647635279,
+      "grad_norm": 1.6245561044198507,
+      "learning_rate": 9.069870652329283e-08,
+      "loss": 0.8128,
+      "step": 554
+    },
+    {
+      "epoch": 0.9475926714955262,
+      "grad_norm": 1.5989317111370667,
+      "learning_rate": 7.974495479187271e-08,
+      "loss": 0.7438,
+      "step": 556
+    },
+    {
+      "epoch": 0.9510012782275244,
+      "grad_norm": 1.4760047355170607,
+      "learning_rate": 6.949059557066596e-08,
+      "loss": 0.7748,
+      "step": 558
+    },
+    {
+      "epoch": 0.9544098849595228,
+      "grad_norm": 1.7501965543108127,
+      "learning_rate": 5.993708647151874e-08,
+      "loss": 0.775,
+      "step": 560
+    },
+    {
+      "epoch": 0.9578184916915211,
+      "grad_norm": 1.4579885728200068,
+      "learning_rate": 5.108578548352838e-08,
+      "loss": 0.7588,
+      "step": 562
+    },
+    {
+      "epoch": 0.9612270984235194,
+      "grad_norm": 1.5049680408512587,
+      "learning_rate": 4.2937950780013174e-08,
+      "loss": 0.7671,
+      "step": 564
+    },
+    {
+      "epoch": 0.9646357051555177,
+      "grad_norm": 1.6438976356754593,
+      "learning_rate": 3.549474053966828e-08,
+      "loss": 0.7908,
+      "step": 566
+    },
+    {
+      "epoch": 0.9680443118875159,
+      "grad_norm": 1.4470095982360724,
+      "learning_rate": 2.8757212781935218e-08,
+      "loss": 0.7466,
+      "step": 568
+    },
+    {
+      "epoch": 0.9714529186195143,
+      "grad_norm": 1.8960810552290914,
+      "learning_rate": 2.2726325216608224e-08,
+      "loss": 0.7697,
+      "step": 570
+    },
+    {
+      "epoch": 0.9748615253515126,
+      "grad_norm": 1.6811694769201933,
+      "learning_rate": 1.7402935107702634e-08,
+      "loss": 0.7753,
+      "step": 572
+    },
+    {
+      "epoch": 0.9782701320835109,
+      "grad_norm": 1.487143334303855,
+      "learning_rate": 1.2787799151596225e-08,
+      "loss": 0.7234,
+      "step": 574
+    },
+    {
+      "epoch": 0.9816787388155092,
+      "grad_norm": 1.3834640793692283,
+      "learning_rate": 8.881573369469153e-09,
+      "loss": 0.7403,
+      "step": 576
+    },
+    {
+      "epoch": 0.9850873455475074,
+      "grad_norm": 1.6803671958080162,
+      "learning_rate": 5.684813014052437e-09,
+      "loss": 0.7659,
+      "step": 578
+    },
+    {
+      "epoch": 0.9884959522795057,
+      "grad_norm": 1.556690011938104,
+      "learning_rate": 3.197972490704415e-09,
+      "loss": 0.7572,
+      "step": 580
+    },
+    {
+      "epoch": 0.9919045590115041,
+      "grad_norm": 1.7044244176997279,
+      "learning_rate": 1.421405292813538e-09,
+      "loss": 0.7572,
+      "step": 582
+    },
+    {
+      "epoch": 0.9953131657435024,
+      "grad_norm": 1.5088989927512526,
+      "learning_rate": 3.553639515574414e-10,
+      "loss": 0.752,
+      "step": 584
+    },
+    {
+      "epoch": 0.9987217724755006,
+      "grad_norm": 1.4553290863162762,
+      "learning_rate": 0.0,
+      "loss": 0.7504,
+      "step": 586
+    },
+    {
+      "epoch": 0.9987217724755006,
+      "step": 586,
+      "total_flos": 6.719053758464e+16,
+      "train_loss": 0.8281301904863871,
+      "train_runtime": 9052.2037,
+      "train_samples_per_second": 1.037,
+      "train_steps_per_second": 0.065
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 586,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.719053758464e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb18a468775e068b3bebcc98532e5d083e1997b93d35253096d4fd5805b72dc1
+size 7736