upload the model

.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: henryhe0123/pc-agent-7b
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-VL-7B-sft-40
+  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. -->
+
+# Qwen2.5-VL-7B-sft-40
+
+This model is a fine-tuned version of [/inspire/hdd/global_user/liupengfei-24025/yhhe/model/Qwen2.5-VL-7B-Instruct](https://huggingface.co//inspire/hdd/global_user/liupengfei-24025/yhhe/model/Qwen2.5-VL-7B-Instruct) on the pcagent40 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: 2e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- 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: 0.05
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9949177877428999,
+    "total_flos": 862605439369216.0,
+    "train_loss": 0.715426175948678,
+    "train_runtime": 10328.0995,
+    "train_samples_per_second": 5.181,
+    "train_steps_per_second": 0.04
+}

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 +1,50 @@
+{
+  "_name_or_path": "/inspire/hdd/global_user/liupengfei-24025/yhhe/model/Qwen2.5-VL-7B-Instruct",
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "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": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_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.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "model_type": "qwen2_5_vl",
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2,
+    "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 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2e54612cc0951ec27d57040e1e20b9e7421ba296887e6da06288095d8d68a1
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861dbf13334dd4f516e5a7c76ef6080737a2aed4bd934110aa11f7cae6525827
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4744a669aa1ff85bd8a796b244bd66311c19e4db35d0e4dcf853283eae49075f
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f855a33d272b17422ea29d2b1bb7ad5f04fdf1771c4d754cfecc7d2cc7aed2
+size 1691924384

model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "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.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "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": "Qwen2_5_VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9949177877428999,
+    "total_flos": 862605439369216.0,
+    "train_loss": 0.715426175948678,
+    "train_runtime": 10328.0995,
+    "train_samples_per_second": 5.181,
+    "train_steps_per_second": 0.04
+}

trainer_log.jsonl

@@ -0,0 +1,419 @@
+{"current_steps": 1, "total_steps": 418, "loss": 1.2153, "lr": 9.523809523809523e-08, "epoch": 0.004783258594917788, "percentage": 0.24, "elapsed_time": "0:00:36", "remaining_time": "4:13:49"}
+{"current_steps": 2, "total_steps": 418, "loss": 1.1666, "lr": 1.9047619047619045e-07, "epoch": 0.009566517189835576, "percentage": 0.48, "elapsed_time": "0:01:00", "remaining_time": "3:29:37"}
+{"current_steps": 3, "total_steps": 418, "loss": 1.1641, "lr": 2.857142857142857e-07, "epoch": 0.014349775784753363, "percentage": 0.72, "elapsed_time": "0:01:24", "remaining_time": "3:15:26"}
+{"current_steps": 4, "total_steps": 418, "loss": 1.1522, "lr": 3.809523809523809e-07, "epoch": 0.019133034379671152, "percentage": 0.96, "elapsed_time": "0:01:49", "remaining_time": "3:09:06"}
+{"current_steps": 5, "total_steps": 418, "loss": 1.1849, "lr": 4.761904761904761e-07, "epoch": 0.02391629297458894, "percentage": 1.2, "elapsed_time": "0:02:13", "remaining_time": "3:04:24"}
+{"current_steps": 6, "total_steps": 418, "loss": 1.1832, "lr": 5.714285714285714e-07, "epoch": 0.028699551569506727, "percentage": 1.44, "elapsed_time": "0:02:38", "remaining_time": "3:01:12"}
+{"current_steps": 7, "total_steps": 418, "loss": 1.1646, "lr": 6.666666666666666e-07, "epoch": 0.03348281016442452, "percentage": 1.67, "elapsed_time": "0:03:02", "remaining_time": "2:59:04"}
+{"current_steps": 8, "total_steps": 418, "loss": 1.1492, "lr": 7.619047619047618e-07, "epoch": 0.038266068759342305, "percentage": 1.91, "elapsed_time": "0:03:26", "remaining_time": "2:56:32"}
+{"current_steps": 9, "total_steps": 418, "loss": 1.1356, "lr": 8.57142857142857e-07, "epoch": 0.04304932735426009, "percentage": 2.15, "elapsed_time": "0:03:51", "remaining_time": "2:55:01"}
+{"current_steps": 10, "total_steps": 418, "loss": 1.1373, "lr": 9.523809523809522e-07, "epoch": 0.04783258594917788, "percentage": 2.39, "elapsed_time": "0:04:15", "remaining_time": "2:53:27"}
+{"current_steps": 11, "total_steps": 418, "loss": 1.1133, "lr": 1.0476190476190476e-06, "epoch": 0.052615844544095666, "percentage": 2.63, "elapsed_time": "0:04:38", "remaining_time": "2:52:00"}
+{"current_steps": 12, "total_steps": 418, "loss": 1.1025, "lr": 1.1428571428571428e-06, "epoch": 0.05739910313901345, "percentage": 2.87, "elapsed_time": "0:05:02", "remaining_time": "2:50:28"}
+{"current_steps": 13, "total_steps": 418, "loss": 1.1102, "lr": 1.238095238095238e-06, "epoch": 0.06218236173393124, "percentage": 3.11, "elapsed_time": "0:05:25", "remaining_time": "2:49:13"}
+{"current_steps": 14, "total_steps": 418, "loss": 1.0716, "lr": 1.3333333333333332e-06, "epoch": 0.06696562032884903, "percentage": 3.35, "elapsed_time": "0:05:49", "remaining_time": "2:48:11"}
+{"current_steps": 15, "total_steps": 418, "loss": 1.0198, "lr": 1.4285714285714286e-06, "epoch": 0.07174887892376682, "percentage": 3.59, "elapsed_time": "0:06:13", "remaining_time": "2:47:08"}
+{"current_steps": 16, "total_steps": 418, "loss": 1.0402, "lr": 1.5238095238095236e-06, "epoch": 0.07653213751868461, "percentage": 3.83, "elapsed_time": "0:06:37", "remaining_time": "2:46:17"}
+{"current_steps": 17, "total_steps": 418, "loss": 1.0027, "lr": 1.619047619047619e-06, "epoch": 0.08131539611360239, "percentage": 4.07, "elapsed_time": "0:07:02", "remaining_time": "2:45:59"}
+{"current_steps": 18, "total_steps": 418, "loss": 1.0022, "lr": 1.714285714285714e-06, "epoch": 0.08609865470852018, "percentage": 4.31, "elapsed_time": "0:07:27", "remaining_time": "2:45:39"}
+{"current_steps": 19, "total_steps": 418, "loss": 1.0272, "lr": 1.8095238095238095e-06, "epoch": 0.09088191330343796, "percentage": 4.55, "elapsed_time": "0:07:51", "remaining_time": "2:44:55"}
+{"current_steps": 20, "total_steps": 418, "loss": 0.9569, "lr": 1.9047619047619045e-06, "epoch": 0.09566517189835576, "percentage": 4.78, "elapsed_time": "0:08:15", "remaining_time": "2:44:22"}
+{"current_steps": 21, "total_steps": 418, "loss": 0.9848, "lr": 2e-06, "epoch": 0.10044843049327354, "percentage": 5.02, "elapsed_time": "0:08:39", "remaining_time": "2:43:41"}
+{"current_steps": 22, "total_steps": 418, "loss": 0.9581, "lr": 1.9999686897547167e-06, "epoch": 0.10523168908819133, "percentage": 5.26, "elapsed_time": "0:09:03", "remaining_time": "2:43:06"}
+{"current_steps": 23, "total_steps": 418, "loss": 0.9478, "lr": 1.9998747609795305e-06, "epoch": 0.11001494768310911, "percentage": 5.5, "elapsed_time": "0:09:28", "remaining_time": "2:42:41"}
+{"current_steps": 24, "total_steps": 418, "loss": 0.9834, "lr": 1.999718219556307e-06, "epoch": 0.1147982062780269, "percentage": 5.74, "elapsed_time": "0:09:52", "remaining_time": "2:42:01"}
+{"current_steps": 25, "total_steps": 418, "loss": 0.9852, "lr": 1.999499075287747e-06, "epoch": 0.11958146487294469, "percentage": 5.98, "elapsed_time": "0:10:16", "remaining_time": "2:41:27"}
+{"current_steps": 26, "total_steps": 418, "loss": 0.9549, "lr": 1.999217341896772e-06, "epoch": 0.12436472346786248, "percentage": 6.22, "elapsed_time": "0:10:40", "remaining_time": "2:41:03"}
+{"current_steps": 27, "total_steps": 418, "loss": 0.9395, "lr": 1.998873037025665e-06, "epoch": 0.12914798206278028, "percentage": 6.46, "elapsed_time": "0:11:04", "remaining_time": "2:40:23"}
+{"current_steps": 28, "total_steps": 418, "loss": 0.9124, "lr": 1.9984661822349665e-06, "epoch": 0.13393124065769807, "percentage": 6.7, "elapsed_time": "0:11:28", "remaining_time": "2:39:46"}
+{"current_steps": 29, "total_steps": 418, "loss": 0.9306, "lr": 1.997996803002123e-06, "epoch": 0.13871449925261584, "percentage": 6.94, "elapsed_time": "0:11:51", "remaining_time": "2:39:08"}
+{"current_steps": 30, "total_steps": 418, "loss": 0.8882, "lr": 1.9974649287198914e-06, "epoch": 0.14349775784753363, "percentage": 7.18, "elapsed_time": "0:12:15", "remaining_time": "2:38:35"}
+{"current_steps": 31, "total_steps": 418, "loss": 0.8699, "lr": 1.9968705926945013e-06, "epoch": 0.14828101644245142, "percentage": 7.42, "elapsed_time": "0:12:39", "remaining_time": "2:38:02"}
+{"current_steps": 32, "total_steps": 418, "loss": 0.8919, "lr": 1.9962138321435656e-06, "epoch": 0.15306427503736922, "percentage": 7.66, "elapsed_time": "0:13:03", "remaining_time": "2:37:33"}
+{"current_steps": 33, "total_steps": 418, "loss": 0.8985, "lr": 1.9954946881937524e-06, "epoch": 0.15784753363228698, "percentage": 7.89, "elapsed_time": "0:13:27", "remaining_time": "2:37:05"}
+{"current_steps": 34, "total_steps": 418, "loss": 0.8504, "lr": 1.994713205878208e-06, "epoch": 0.16263079222720478, "percentage": 8.13, "elapsed_time": "0:13:51", "remaining_time": "2:36:28"}
+{"current_steps": 35, "total_steps": 418, "loss": 0.8743, "lr": 1.9938694341337393e-06, "epoch": 0.16741405082212257, "percentage": 8.37, "elapsed_time": "0:14:15", "remaining_time": "2:36:03"}
+{"current_steps": 36, "total_steps": 418, "loss": 0.857, "lr": 1.9929634257977467e-06, "epoch": 0.17219730941704037, "percentage": 8.61, "elapsed_time": "0:14:39", "remaining_time": "2:35:33"}
+{"current_steps": 37, "total_steps": 418, "loss": 0.8487, "lr": 1.991995237604916e-06, "epoch": 0.17698056801195813, "percentage": 8.85, "elapsed_time": "0:15:03", "remaining_time": "2:35:06"}
+{"current_steps": 38, "total_steps": 418, "loss": 0.8692, "lr": 1.9909649301836674e-06, "epoch": 0.18176382660687593, "percentage": 9.09, "elapsed_time": "0:15:27", "remaining_time": "2:34:31"}
+{"current_steps": 39, "total_steps": 418, "loss": 0.8679, "lr": 1.9898725680523566e-06, "epoch": 0.18654708520179372, "percentage": 9.33, "elapsed_time": "0:15:50", "remaining_time": "2:34:01"}
+{"current_steps": 40, "total_steps": 418, "loss": 0.8504, "lr": 1.9887182196152367e-06, "epoch": 0.19133034379671152, "percentage": 9.57, "elapsed_time": "0:16:14", "remaining_time": "2:33:30"}
+{"current_steps": 41, "total_steps": 418, "loss": 0.8125, "lr": 1.9875019571581726e-06, "epoch": 0.1961136023916293, "percentage": 9.81, "elapsed_time": "0:16:38", "remaining_time": "2:33:05"}
+{"current_steps": 42, "total_steps": 418, "loss": 0.8257, "lr": 1.9862238568441165e-06, "epoch": 0.20089686098654708, "percentage": 10.05, "elapsed_time": "0:17:03", "remaining_time": "2:32:45"}
+{"current_steps": 43, "total_steps": 418, "loss": 0.8329, "lr": 1.9848839987083364e-06, "epoch": 0.20568011958146487, "percentage": 10.29, "elapsed_time": "0:17:28", "remaining_time": "2:32:22"}
+{"current_steps": 44, "total_steps": 418, "loss": 0.8409, "lr": 1.983482466653407e-06, "epoch": 0.21046337817638266, "percentage": 10.53, "elapsed_time": "0:17:52", "remaining_time": "2:31:56"}
+{"current_steps": 45, "total_steps": 418, "loss": 0.8323, "lr": 1.982019348443952e-06, "epoch": 0.21524663677130046, "percentage": 10.77, "elapsed_time": "0:18:17", "remaining_time": "2:31:35"}
+{"current_steps": 46, "total_steps": 418, "loss": 0.8673, "lr": 1.9804947357011523e-06, "epoch": 0.22002989536621823, "percentage": 11.0, "elapsed_time": "0:18:41", "remaining_time": "2:31:13"}
+{"current_steps": 47, "total_steps": 418, "loss": 0.8192, "lr": 1.978908723897005e-06, "epoch": 0.22481315396113602, "percentage": 11.24, "elapsed_time": "0:19:05", "remaining_time": "2:30:45"}
+{"current_steps": 48, "total_steps": 418, "loss": 0.8384, "lr": 1.9772614123483485e-06, "epoch": 0.2295964125560538, "percentage": 11.48, "elapsed_time": "0:19:30", "remaining_time": "2:30:23"}
+{"current_steps": 49, "total_steps": 418, "loss": 0.7854, "lr": 1.9755529042106393e-06, "epoch": 0.2343796711509716, "percentage": 11.72, "elapsed_time": "0:19:54", "remaining_time": "2:29:57"}
+{"current_steps": 50, "total_steps": 418, "loss": 0.795, "lr": 1.973783306471495e-06, "epoch": 0.23916292974588937, "percentage": 11.96, "elapsed_time": "0:20:18", "remaining_time": "2:29:30"}
+{"current_steps": 51, "total_steps": 418, "loss": 0.783, "lr": 1.971952729943994e-06, "epoch": 0.24394618834080717, "percentage": 12.2, "elapsed_time": "0:20:44", "remaining_time": "2:29:15"}
+{"current_steps": 52, "total_steps": 418, "loss": 0.8059, "lr": 1.9700612892597372e-06, "epoch": 0.24872944693572496, "percentage": 12.44, "elapsed_time": "0:21:08", "remaining_time": "2:28:45"}
+{"current_steps": 53, "total_steps": 418, "loss": 0.7885, "lr": 1.9681091028616676e-06, "epoch": 0.25351270553064276, "percentage": 12.68, "elapsed_time": "0:21:32", "remaining_time": "2:28:20"}
+{"current_steps": 54, "total_steps": 418, "loss": 0.8031, "lr": 1.966096292996655e-06, "epoch": 0.25829596412556055, "percentage": 12.92, "elapsed_time": "0:21:57", "remaining_time": "2:27:58"}
+{"current_steps": 55, "total_steps": 418, "loss": 0.7774, "lr": 1.9640229857078413e-06, "epoch": 0.26307922272047835, "percentage": 13.16, "elapsed_time": "0:22:20", "remaining_time": "2:27:25"}
+{"current_steps": 56, "total_steps": 418, "loss": 0.7949, "lr": 1.9618893108267454e-06, "epoch": 0.26786248131539614, "percentage": 13.4, "elapsed_time": "0:22:44", "remaining_time": "2:26:57"}
+{"current_steps": 57, "total_steps": 418, "loss": 0.7674, "lr": 1.9596954019651354e-06, "epoch": 0.2726457399103139, "percentage": 13.64, "elapsed_time": "0:23:08", "remaining_time": "2:26:36"}
+{"current_steps": 58, "total_steps": 418, "loss": 0.7953, "lr": 1.95744139650666e-06, "epoch": 0.27742899850523167, "percentage": 13.88, "elapsed_time": "0:23:33", "remaining_time": "2:26:14"}
+{"current_steps": 59, "total_steps": 418, "loss": 0.7881, "lr": 1.955127435598247e-06, "epoch": 0.28221225710014947, "percentage": 14.11, "elapsed_time": "0:23:57", "remaining_time": "2:25:46"}
+{"current_steps": 60, "total_steps": 418, "loss": 0.7984, "lr": 1.9527536641412637e-06, "epoch": 0.28699551569506726, "percentage": 14.35, "elapsed_time": "0:24:23", "remaining_time": "2:25:29"}
+{"current_steps": 61, "total_steps": 418, "loss": 0.7666, "lr": 1.950320230782443e-06, "epoch": 0.29177877428998505, "percentage": 14.59, "elapsed_time": "0:24:47", "remaining_time": "2:25:06"}
+{"current_steps": 62, "total_steps": 418, "loss": 0.7809, "lr": 1.9478272879045763e-06, "epoch": 0.29656203288490285, "percentage": 14.83, "elapsed_time": "0:25:12", "remaining_time": "2:24:44"}
+{"current_steps": 63, "total_steps": 418, "loss": 0.7948, "lr": 1.9452749916169685e-06, "epoch": 0.30134529147982064, "percentage": 15.07, "elapsed_time": "0:25:36", "remaining_time": "2:24:18"}
+{"current_steps": 64, "total_steps": 418, "loss": 0.7843, "lr": 1.942663501745666e-06, "epoch": 0.30612855007473844, "percentage": 15.31, "elapsed_time": "0:26:00", "remaining_time": "2:23:54"}
+{"current_steps": 65, "total_steps": 418, "loss": 0.7713, "lr": 1.939992981823445e-06, "epoch": 0.3109118086696562, "percentage": 15.55, "elapsed_time": "0:26:25", "remaining_time": "2:23:28"}
+{"current_steps": 66, "total_steps": 418, "loss": 0.7338, "lr": 1.9372635990795744e-06, "epoch": 0.31569506726457397, "percentage": 15.79, "elapsed_time": "0:26:49", "remaining_time": "2:23:05"}
+{"current_steps": 67, "total_steps": 418, "loss": 0.7651, "lr": 1.934475524429339e-06, "epoch": 0.32047832585949176, "percentage": 16.03, "elapsed_time": "0:27:15", "remaining_time": "2:22:46"}
+{"current_steps": 68, "total_steps": 418, "loss": 0.7743, "lr": 1.9316289324633416e-06, "epoch": 0.32526158445440956, "percentage": 16.27, "elapsed_time": "0:27:38", "remaining_time": "2:22:17"}
+{"current_steps": 69, "total_steps": 418, "loss": 0.7818, "lr": 1.928724001436568e-06, "epoch": 0.33004484304932735, "percentage": 16.51, "elapsed_time": "0:28:02", "remaining_time": "2:21:50"}
+{"current_steps": 70, "total_steps": 418, "loss": 0.7738, "lr": 1.925760913257224e-06, "epoch": 0.33482810164424515, "percentage": 16.75, "elapsed_time": "0:28:27", "remaining_time": "2:21:26"}
+{"current_steps": 71, "total_steps": 418, "loss": 0.7694, "lr": 1.922739853475345e-06, "epoch": 0.33961136023916294, "percentage": 16.99, "elapsed_time": "0:28:51", "remaining_time": "2:21:02"}
+{"current_steps": 72, "total_steps": 418, "loss": 0.7695, "lr": 1.919661011271176e-06, "epoch": 0.34439461883408073, "percentage": 17.22, "elapsed_time": "0:29:16", "remaining_time": "2:20:39"}
+{"current_steps": 73, "total_steps": 418, "loss": 0.7762, "lr": 1.916524579443327e-06, "epoch": 0.34917787742899853, "percentage": 17.46, "elapsed_time": "0:29:39", "remaining_time": "2:20:10"}
+{"current_steps": 74, "total_steps": 418, "loss": 0.7465, "lr": 1.9133307543966972e-06, "epoch": 0.35396113602391627, "percentage": 17.7, "elapsed_time": "0:30:04", "remaining_time": "2:19:47"}
+{"current_steps": 75, "total_steps": 418, "loss": 0.7591, "lr": 1.910079736130178e-06, "epoch": 0.35874439461883406, "percentage": 17.94, "elapsed_time": "0:30:28", "remaining_time": "2:19:23"}
+{"current_steps": 76, "total_steps": 418, "loss": 0.7473, "lr": 1.9067717282241275e-06, "epoch": 0.36352765321375186, "percentage": 18.18, "elapsed_time": "0:30:52", "remaining_time": "2:18:56"}
+{"current_steps": 77, "total_steps": 418, "loss": 0.7899, "lr": 1.9034069378276248e-06, "epoch": 0.36831091180866965, "percentage": 18.42, "elapsed_time": "0:31:15", "remaining_time": "2:18:25"}
+{"current_steps": 78, "total_steps": 418, "loss": 0.759, "lr": 1.8999855756454943e-06, "epoch": 0.37309417040358744, "percentage": 18.66, "elapsed_time": "0:31:40", "remaining_time": "2:18:02"}
+{"current_steps": 79, "total_steps": 418, "loss": 0.765, "lr": 1.8965078559251141e-06, "epoch": 0.37787742899850524, "percentage": 18.9, "elapsed_time": "0:32:04", "remaining_time": "2:17:37"}
+{"current_steps": 80, "total_steps": 418, "loss": 0.7653, "lr": 1.892973996443e-06, "epoch": 0.38266068759342303, "percentage": 19.14, "elapsed_time": "0:32:28", "remaining_time": "2:17:11"}
+{"current_steps": 81, "total_steps": 418, "loss": 0.7585, "lr": 1.8893842184911652e-06, "epoch": 0.3874439461883408, "percentage": 19.38, "elapsed_time": "0:32:52", "remaining_time": "2:16:47"}
+{"current_steps": 82, "total_steps": 418, "loss": 0.7396, "lr": 1.8857387468632673e-06, "epoch": 0.3922272047832586, "percentage": 19.62, "elapsed_time": "0:33:17", "remaining_time": "2:16:23"}
+{"current_steps": 83, "total_steps": 418, "loss": 0.7449, "lr": 1.8820378098405269e-06, "epoch": 0.39701046337817636, "percentage": 19.86, "elapsed_time": "0:33:41", "remaining_time": "2:15:59"}
+{"current_steps": 84, "total_steps": 418, "loss": 0.7536, "lr": 1.878281639177437e-06, "epoch": 0.40179372197309415, "percentage": 20.1, "elapsed_time": "0:34:05", "remaining_time": "2:15:33"}
+{"current_steps": 85, "total_steps": 418, "loss": 0.7695, "lr": 1.874470470087246e-06, "epoch": 0.40657698056801195, "percentage": 20.33, "elapsed_time": "0:34:29", "remaining_time": "2:15:07"}
+{"current_steps": 86, "total_steps": 418, "loss": 0.7804, "lr": 1.8706045412272329e-06, "epoch": 0.41136023916292974, "percentage": 20.57, "elapsed_time": "0:34:54", "remaining_time": "2:14:46"}
+{"current_steps": 87, "total_steps": 418, "loss": 0.7581, "lr": 1.8666840946837588e-06, "epoch": 0.41614349775784754, "percentage": 20.81, "elapsed_time": "0:35:18", "remaining_time": "2:14:20"}
+{"current_steps": 88, "total_steps": 418, "loss": 0.7486, "lr": 1.8627093759571097e-06, "epoch": 0.42092675635276533, "percentage": 21.05, "elapsed_time": "0:35:42", "remaining_time": "2:13:52"}
+{"current_steps": 89, "total_steps": 418, "loss": 0.7393, "lr": 1.8586806339461223e-06, "epoch": 0.4257100149476831, "percentage": 21.29, "elapsed_time": "0:36:05", "remaining_time": "2:13:26"}
+{"current_steps": 90, "total_steps": 418, "loss": 0.7412, "lr": 1.8545981209325974e-06, "epoch": 0.4304932735426009, "percentage": 21.53, "elapsed_time": "0:36:29", "remaining_time": "2:13:00"}
+{"current_steps": 91, "total_steps": 418, "loss": 0.7522, "lr": 1.850462092565503e-06, "epoch": 0.43527653213751866, "percentage": 21.77, "elapsed_time": "0:36:53", "remaining_time": "2:12:33"}
+{"current_steps": 92, "total_steps": 418, "loss": 0.7361, "lr": 1.846272807844964e-06, "epoch": 0.44005979073243645, "percentage": 22.01, "elapsed_time": "0:37:18", "remaining_time": "2:12:10"}
+{"current_steps": 93, "total_steps": 418, "loss": 0.7454, "lr": 1.8420305291060453e-06, "epoch": 0.44484304932735425, "percentage": 22.25, "elapsed_time": "0:37:41", "remaining_time": "2:11:44"}
+{"current_steps": 94, "total_steps": 418, "loss": 0.7776, "lr": 1.837735522002322e-06, "epoch": 0.44962630792227204, "percentage": 22.49, "elapsed_time": "0:38:05", "remaining_time": "2:11:18"}
+{"current_steps": 95, "total_steps": 418, "loss": 0.7284, "lr": 1.8333880554892465e-06, "epoch": 0.45440956651718983, "percentage": 22.73, "elapsed_time": "0:38:30", "remaining_time": "2:10:54"}
+{"current_steps": 96, "total_steps": 418, "loss": 0.7275, "lr": 1.828988401807304e-06, "epoch": 0.4591928251121076, "percentage": 22.97, "elapsed_time": "0:38:53", "remaining_time": "2:10:28"}
+{"current_steps": 97, "total_steps": 418, "loss": 0.7176, "lr": 1.8245368364649672e-06, "epoch": 0.4639760837070254, "percentage": 23.21, "elapsed_time": "0:39:17", "remaining_time": "2:10:03"}
+{"current_steps": 98, "total_steps": 418, "loss": 0.7558, "lr": 1.8200336382214404e-06, "epoch": 0.4687593423019432, "percentage": 23.44, "elapsed_time": "0:39:41", "remaining_time": "2:09:37"}
+{"current_steps": 99, "total_steps": 418, "loss": 0.7477, "lr": 1.815479089069208e-06, "epoch": 0.473542600896861, "percentage": 23.68, "elapsed_time": "0:40:05", "remaining_time": "2:09:10"}
+{"current_steps": 100, "total_steps": 418, "loss": 0.7302, "lr": 1.8108734742163714e-06, "epoch": 0.47832585949177875, "percentage": 23.92, "elapsed_time": "0:40:28", "remaining_time": "2:08:43"}
+{"current_steps": 101, "total_steps": 418, "loss": 0.7461, "lr": 1.8062170820687923e-06, "epoch": 0.48310911808669654, "percentage": 24.16, "elapsed_time": "0:41:39", "remaining_time": "2:10:45"}
+{"current_steps": 102, "total_steps": 418, "loss": 0.7374, "lr": 1.8015102042120314e-06, "epoch": 0.48789237668161434, "percentage": 24.4, "elapsed_time": "0:42:04", "remaining_time": "2:10:21"}
+{"current_steps": 103, "total_steps": 418, "loss": 0.753, "lr": 1.796753135393089e-06, "epoch": 0.49267563527653213, "percentage": 24.64, "elapsed_time": "0:42:29", "remaining_time": "2:09:56"}
+{"current_steps": 104, "total_steps": 418, "loss": 0.7172, "lr": 1.791946173501948e-06, "epoch": 0.4974588938714499, "percentage": 24.88, "elapsed_time": "0:42:53", "remaining_time": "2:09:29"}
+{"current_steps": 105, "total_steps": 418, "loss": 0.7157, "lr": 1.7870896195529204e-06, "epoch": 0.5022421524663677, "percentage": 25.12, "elapsed_time": "0:43:18", "remaining_time": "2:09:04"}
+{"current_steps": 106, "total_steps": 418, "loss": 0.7522, "lr": 1.7821837776657967e-06, "epoch": 0.5070254110612855, "percentage": 25.36, "elapsed_time": "0:43:42", "remaining_time": "2:08:39"}
+{"current_steps": 107, "total_steps": 418, "loss": 0.7215, "lr": 1.777228955046803e-06, "epoch": 0.5118086696562033, "percentage": 25.6, "elapsed_time": "0:44:06", "remaining_time": "2:08:13"}
+{"current_steps": 108, "total_steps": 418, "loss": 0.7311, "lr": 1.7722254619693617e-06, "epoch": 0.5165919282511211, "percentage": 25.84, "elapsed_time": "0:44:31", "remaining_time": "2:07:47"}
+{"current_steps": 109, "total_steps": 418, "loss": 0.7242, "lr": 1.7671736117546643e-06, "epoch": 0.5213751868460389, "percentage": 26.08, "elapsed_time": "0:44:55", "remaining_time": "2:07:21"}
+{"current_steps": 110, "total_steps": 418, "loss": 0.7302, "lr": 1.7620737207520498e-06, "epoch": 0.5261584454409567, "percentage": 26.32, "elapsed_time": "0:45:18", "remaining_time": "2:06:52"}
+{"current_steps": 111, "total_steps": 418, "loss": 0.7222, "lr": 1.756926108319194e-06, "epoch": 0.5309417040358745, "percentage": 26.56, "elapsed_time": "0:45:43", "remaining_time": "2:06:27"}
+{"current_steps": 112, "total_steps": 418, "loss": 0.7361, "lr": 1.751731096802113e-06, "epoch": 0.5357249626307923, "percentage": 26.79, "elapsed_time": "0:46:06", "remaining_time": "2:05:59"}
+{"current_steps": 113, "total_steps": 418, "loss": 0.7183, "lr": 1.7464890115149759e-06, "epoch": 0.54050822122571, "percentage": 27.03, "elapsed_time": "0:46:30", "remaining_time": "2:05:32"}
+{"current_steps": 114, "total_steps": 418, "loss": 0.7342, "lr": 1.7412001807197361e-06, "epoch": 0.5452914798206278, "percentage": 27.27, "elapsed_time": "0:46:55", "remaining_time": "2:05:08"}
+{"current_steps": 115, "total_steps": 418, "loss": 0.7251, "lr": 1.735864935605572e-06, "epoch": 0.5500747384155455, "percentage": 27.51, "elapsed_time": "0:47:19", "remaining_time": "2:04:42"}
+{"current_steps": 116, "total_steps": 418, "loss": 0.7081, "lr": 1.7304836102681493e-06, "epoch": 0.5548579970104633, "percentage": 27.75, "elapsed_time": "0:47:43", "remaining_time": "2:04:16"}
+{"current_steps": 117, "total_steps": 418, "loss": 0.742, "lr": 1.7250565416887015e-06, "epoch": 0.5596412556053811, "percentage": 27.99, "elapsed_time": "0:48:08", "remaining_time": "2:03:52"}
+{"current_steps": 118, "total_steps": 418, "loss": 0.7314, "lr": 1.719584069712925e-06, "epoch": 0.5644245142002989, "percentage": 28.23, "elapsed_time": "0:48:32", "remaining_time": "2:03:24"}
+{"current_steps": 119, "total_steps": 418, "loss": 0.7167, "lr": 1.7140665370296992e-06, "epoch": 0.5692077727952167, "percentage": 28.47, "elapsed_time": "0:48:56", "remaining_time": "2:02:58"}
+{"current_steps": 120, "total_steps": 418, "loss": 0.7421, "lr": 1.708504289149628e-06, "epoch": 0.5739910313901345, "percentage": 28.71, "elapsed_time": "0:49:20", "remaining_time": "2:02:32"}
+{"current_steps": 121, "total_steps": 418, "loss": 0.7067, "lr": 1.702897674383402e-06, "epoch": 0.5787742899850523, "percentage": 28.95, "elapsed_time": "0:49:44", "remaining_time": "2:02:06"}
+{"current_steps": 122, "total_steps": 418, "loss": 0.7283, "lr": 1.697247043819988e-06, "epoch": 0.5835575485799701, "percentage": 29.19, "elapsed_time": "0:50:08", "remaining_time": "2:01:40"}
+{"current_steps": 123, "total_steps": 418, "loss": 0.7289, "lr": 1.6915527513046443e-06, "epoch": 0.5883408071748879, "percentage": 29.43, "elapsed_time": "0:50:32", "remaining_time": "2:01:13"}
+{"current_steps": 124, "total_steps": 418, "loss": 0.7258, "lr": 1.6858151534167616e-06, "epoch": 0.5931240657698057, "percentage": 29.67, "elapsed_time": "0:50:57", "remaining_time": "2:00:48"}
+{"current_steps": 125, "total_steps": 418, "loss": 0.7294, "lr": 1.6800346094475346e-06, "epoch": 0.5979073243647235, "percentage": 29.9, "elapsed_time": "0:51:22", "remaining_time": "2:00:24"}
+{"current_steps": 126, "total_steps": 418, "loss": 0.7059, "lr": 1.6742114813774618e-06, "epoch": 0.6026905829596413, "percentage": 30.14, "elapsed_time": "0:51:46", "remaining_time": "1:59:59"}
+{"current_steps": 127, "total_steps": 418, "loss": 0.76, "lr": 1.6683461338536798e-06, "epoch": 0.6074738415545591, "percentage": 30.38, "elapsed_time": "0:52:11", "remaining_time": "1:59:34"}
+{"current_steps": 128, "total_steps": 418, "loss": 0.7199, "lr": 1.6624389341671278e-06, "epoch": 0.6122571001494769, "percentage": 30.62, "elapsed_time": "0:52:35", "remaining_time": "1:59:08"}
+{"current_steps": 129, "total_steps": 418, "loss": 0.71, "lr": 1.656490252229548e-06, "epoch": 0.6170403587443947, "percentage": 30.86, "elapsed_time": "0:52:59", "remaining_time": "1:58:42"}
+{"current_steps": 130, "total_steps": 418, "loss": 0.7297, "lr": 1.6505004605503223e-06, "epoch": 0.6218236173393124, "percentage": 31.1, "elapsed_time": "0:53:23", "remaining_time": "1:58:16"}
+{"current_steps": 131, "total_steps": 418, "loss": 0.7323, "lr": 1.6444699342131428e-06, "epoch": 0.6266068759342301, "percentage": 31.34, "elapsed_time": "0:53:48", "remaining_time": "1:57:52"}
+{"current_steps": 132, "total_steps": 418, "loss": 0.7091, "lr": 1.638399050852528e-06, "epoch": 0.6313901345291479, "percentage": 31.58, "elapsed_time": "0:54:12", "remaining_time": "1:57:27"}
+{"current_steps": 133, "total_steps": 418, "loss": 0.7092, "lr": 1.632288190630172e-06, "epoch": 0.6361733931240657, "percentage": 31.82, "elapsed_time": "0:54:35", "remaining_time": "1:56:58"}
+{"current_steps": 134, "total_steps": 418, "loss": 0.7226, "lr": 1.6261377362111396e-06, "epoch": 0.6409566517189835, "percentage": 32.06, "elapsed_time": "0:54:59", "remaining_time": "1:56:32"}
+{"current_steps": 135, "total_steps": 418, "loss": 0.7313, "lr": 1.6199480727399032e-06, "epoch": 0.6457399103139013, "percentage": 32.3, "elapsed_time": "0:55:24", "remaining_time": "1:56:08"}
+{"current_steps": 136, "total_steps": 418, "loss": 0.7264, "lr": 1.6137195878162267e-06, "epoch": 0.6505231689088191, "percentage": 32.54, "elapsed_time": "0:55:47", "remaining_time": "1:55:41"}
+{"current_steps": 137, "total_steps": 418, "loss": 0.72, "lr": 1.607452671470891e-06, "epoch": 0.6553064275037369, "percentage": 32.78, "elapsed_time": "0:56:12", "remaining_time": "1:55:16"}
+{"current_steps": 138, "total_steps": 418, "loss": 0.7043, "lr": 1.601147716141272e-06, "epoch": 0.6600896860986547, "percentage": 33.01, "elapsed_time": "0:56:36", "remaining_time": "1:54:50"}
+{"current_steps": 139, "total_steps": 418, "loss": 0.7314, "lr": 1.5948051166467657e-06, "epoch": 0.6648729446935725, "percentage": 33.25, "elapsed_time": "0:56:59", "remaining_time": "1:54:24"}
+{"current_steps": 140, "total_steps": 418, "loss": 0.7223, "lr": 1.5884252701640634e-06, "epoch": 0.6696562032884903, "percentage": 33.49, "elapsed_time": "0:57:23", "remaining_time": "1:53:57"}
+{"current_steps": 141, "total_steps": 418, "loss": 0.7145, "lr": 1.5820085762022823e-06, "epoch": 0.6744394618834081, "percentage": 33.73, "elapsed_time": "0:57:47", "remaining_time": "1:53:32"}
+{"current_steps": 142, "total_steps": 418, "loss": 0.712, "lr": 1.5755554365779455e-06, "epoch": 0.6792227204783259, "percentage": 33.97, "elapsed_time": "0:58:11", "remaining_time": "1:53:07"}
+{"current_steps": 143, "total_steps": 418, "loss": 0.7262, "lr": 1.5690662553898222e-06, "epoch": 0.6840059790732437, "percentage": 34.21, "elapsed_time": "0:58:36", "remaining_time": "1:52:42"}
+{"current_steps": 144, "total_steps": 418, "loss": 0.6881, "lr": 1.5625414389936218e-06, "epoch": 0.6887892376681615, "percentage": 34.45, "elapsed_time": "0:59:00", "remaining_time": "1:52:16"}
+{"current_steps": 145, "total_steps": 418, "loss": 0.7023, "lr": 1.555981395976548e-06, "epoch": 0.6935724962630793, "percentage": 34.69, "elapsed_time": "0:59:24", "remaining_time": "1:51:50"}
+{"current_steps": 146, "total_steps": 418, "loss": 0.7041, "lr": 1.5493865371317123e-06, "epoch": 0.6983557548579971, "percentage": 34.93, "elapsed_time": "0:59:48", "remaining_time": "1:51:26"}
+{"current_steps": 147, "total_steps": 418, "loss": 0.7121, "lr": 1.542757275432411e-06, "epoch": 0.7031390134529149, "percentage": 35.17, "elapsed_time": "1:00:12", "remaining_time": "1:50:59"}
+{"current_steps": 148, "total_steps": 418, "loss": 0.7, "lr": 1.5360940260062635e-06, "epoch": 0.7079222720478325, "percentage": 35.41, "elapsed_time": "1:00:37", "remaining_time": "1:50:35"}
+{"current_steps": 149, "total_steps": 418, "loss": 0.7174, "lr": 1.5293972061092185e-06, "epoch": 0.7127055306427503, "percentage": 35.65, "elapsed_time": "1:01:02", "remaining_time": "1:50:11"}
+{"current_steps": 150, "total_steps": 418, "loss": 0.6842, "lr": 1.522667235099422e-06, "epoch": 0.7174887892376681, "percentage": 35.89, "elapsed_time": "1:01:25", "remaining_time": "1:49:44"}
+{"current_steps": 151, "total_steps": 418, "loss": 0.6917, "lr": 1.515904534410961e-06, "epoch": 0.7222720478325859, "percentage": 36.12, "elapsed_time": "1:01:49", "remaining_time": "1:49:18"}
+{"current_steps": 152, "total_steps": 418, "loss": 0.6807, "lr": 1.5091095275274699e-06, "epoch": 0.7270553064275037, "percentage": 36.36, "elapsed_time": "1:02:12", "remaining_time": "1:48:52"}
+{"current_steps": 153, "total_steps": 418, "loss": 0.6938, "lr": 1.5022826399556133e-06, "epoch": 0.7318385650224215, "percentage": 36.6, "elapsed_time": "1:02:37", "remaining_time": "1:48:28"}
+{"current_steps": 154, "total_steps": 418, "loss": 0.7262, "lr": 1.4954242991984396e-06, "epoch": 0.7366218236173393, "percentage": 36.84, "elapsed_time": "1:03:01", "remaining_time": "1:48:03"}
+{"current_steps": 155, "total_steps": 418, "loss": 0.6928, "lr": 1.4885349347286115e-06, "epoch": 0.7414050822122571, "percentage": 37.08, "elapsed_time": "1:03:25", "remaining_time": "1:47:36"}
+{"current_steps": 156, "total_steps": 418, "loss": 0.7041, "lr": 1.4816149779615126e-06, "epoch": 0.7461883408071749, "percentage": 37.32, "elapsed_time": "1:03:49", "remaining_time": "1:47:11"}
+{"current_steps": 157, "total_steps": 418, "loss": 0.7157, "lr": 1.474664862228229e-06, "epoch": 0.7509715994020927, "percentage": 37.56, "elapsed_time": "1:04:13", "remaining_time": "1:46:46"}
+{"current_steps": 158, "total_steps": 418, "loss": 0.7077, "lr": 1.467685022748419e-06, "epoch": 0.7557548579970105, "percentage": 37.8, "elapsed_time": "1:04:38", "remaining_time": "1:46:22"}
+{"current_steps": 159, "total_steps": 418, "loss": 0.6905, "lr": 1.4606758966030534e-06, "epoch": 0.7605381165919283, "percentage": 38.04, "elapsed_time": "1:05:03", "remaining_time": "1:45:58"}
+{"current_steps": 160, "total_steps": 418, "loss": 0.704, "lr": 1.4536379227070509e-06, "epoch": 0.7653213751868461, "percentage": 38.28, "elapsed_time": "1:05:28", "remaining_time": "1:45:34"}
+{"current_steps": 161, "total_steps": 418, "loss": 0.7014, "lr": 1.4465715417817888e-06, "epoch": 0.7701046337817639, "percentage": 38.52, "elapsed_time": "1:05:51", "remaining_time": "1:45:07"}
+{"current_steps": 162, "total_steps": 418, "loss": 0.6711, "lr": 1.4394771963275076e-06, "epoch": 0.7748878923766817, "percentage": 38.76, "elapsed_time": "1:06:16", "remaining_time": "1:44:44"}
+{"current_steps": 163, "total_steps": 418, "loss": 0.704, "lr": 1.4323553305955997e-06, "epoch": 0.7796711509715994, "percentage": 39.0, "elapsed_time": "1:06:40", "remaining_time": "1:44:18"}
+{"current_steps": 164, "total_steps": 418, "loss": 0.6769, "lr": 1.4252063905607909e-06, "epoch": 0.7844544095665172, "percentage": 39.23, "elapsed_time": "1:07:04", "remaining_time": "1:43:52"}
+{"current_steps": 165, "total_steps": 418, "loss": 0.6903, "lr": 1.4180308238932135e-06, "epoch": 0.7892376681614349, "percentage": 39.47, "elapsed_time": "1:07:28", "remaining_time": "1:43:27"}
+{"current_steps": 166, "total_steps": 418, "loss": 0.7126, "lr": 1.410829079930372e-06, "epoch": 0.7940209267563527, "percentage": 39.71, "elapsed_time": "1:07:51", "remaining_time": "1:43:01"}
+{"current_steps": 167, "total_steps": 418, "loss": 0.6936, "lr": 1.4036016096490064e-06, "epoch": 0.7988041853512705, "percentage": 39.95, "elapsed_time": "1:08:15", "remaining_time": "1:42:34"}
+{"current_steps": 168, "total_steps": 418, "loss": 0.6918, "lr": 1.3963488656368517e-06, "epoch": 0.8035874439461883, "percentage": 40.19, "elapsed_time": "1:08:39", "remaining_time": "1:42:10"}
+{"current_steps": 169, "total_steps": 418, "loss": 0.6837, "lr": 1.389071302064295e-06, "epoch": 0.8083707025411061, "percentage": 40.43, "elapsed_time": "1:09:04", "remaining_time": "1:41:46"}
+{"current_steps": 170, "total_steps": 418, "loss": 0.7087, "lr": 1.381769374655938e-06, "epoch": 0.8131539611360239, "percentage": 40.67, "elapsed_time": "1:09:28", "remaining_time": "1:41:21"}
+{"current_steps": 171, "total_steps": 418, "loss": 0.7132, "lr": 1.374443540662057e-06, "epoch": 0.8179372197309417, "percentage": 40.91, "elapsed_time": "1:09:53", "remaining_time": "1:40:57"}
+{"current_steps": 172, "total_steps": 418, "loss": 0.689, "lr": 1.3670942588299705e-06, "epoch": 0.8227204783258595, "percentage": 41.15, "elapsed_time": "1:10:16", "remaining_time": "1:40:31"}
+{"current_steps": 173, "total_steps": 418, "loss": 0.6669, "lr": 1.3597219893753117e-06, "epoch": 0.8275037369207773, "percentage": 41.39, "elapsed_time": "1:10:39", "remaining_time": "1:40:04"}
+{"current_steps": 174, "total_steps": 418, "loss": 0.675, "lr": 1.352327193953211e-06, "epoch": 0.8322869955156951, "percentage": 41.63, "elapsed_time": "1:11:02", "remaining_time": "1:39:37"}
+{"current_steps": 175, "total_steps": 418, "loss": 0.7151, "lr": 1.3449103356293852e-06, "epoch": 0.8370702541106129, "percentage": 41.87, "elapsed_time": "1:11:26", "remaining_time": "1:39:12"}
+{"current_steps": 176, "total_steps": 418, "loss": 0.6819, "lr": 1.337471878851141e-06, "epoch": 0.8418535127055307, "percentage": 42.11, "elapsed_time": "1:11:51", "remaining_time": "1:38:48"}
+{"current_steps": 177, "total_steps": 418, "loss": 0.7063, "lr": 1.3300122894182909e-06, "epoch": 0.8466367713004485, "percentage": 42.34, "elapsed_time": "1:12:14", "remaining_time": "1:38:21"}
+{"current_steps": 178, "total_steps": 418, "loss": 0.7154, "lr": 1.3225320344539842e-06, "epoch": 0.8514200298953662, "percentage": 42.58, "elapsed_time": "1:12:39", "remaining_time": "1:37:57"}
+{"current_steps": 179, "total_steps": 418, "loss": 0.7119, "lr": 1.315031582375457e-06, "epoch": 0.856203288490284, "percentage": 42.82, "elapsed_time": "1:13:02", "remaining_time": "1:37:32"}
+{"current_steps": 180, "total_steps": 418, "loss": 0.6872, "lr": 1.3075114028646974e-06, "epoch": 0.8609865470852018, "percentage": 43.06, "elapsed_time": "1:13:28", "remaining_time": "1:37:08"}
+{"current_steps": 181, "total_steps": 418, "loss": 0.6995, "lr": 1.299971966839036e-06, "epoch": 0.8657698056801196, "percentage": 43.3, "elapsed_time": "1:13:52", "remaining_time": "1:36:43"}
+{"current_steps": 182, "total_steps": 418, "loss": 0.6788, "lr": 1.292413746421655e-06, "epoch": 0.8705530642750373, "percentage": 43.54, "elapsed_time": "1:14:16", "remaining_time": "1:36:18"}
+{"current_steps": 183, "total_steps": 418, "loss": 0.6625, "lr": 1.2848372149120246e-06, "epoch": 0.8753363228699551, "percentage": 43.78, "elapsed_time": "1:14:41", "remaining_time": "1:35:54"}
+{"current_steps": 184, "total_steps": 418, "loss": 0.6993, "lr": 1.2772428467562651e-06, "epoch": 0.8801195814648729, "percentage": 44.02, "elapsed_time": "1:15:05", "remaining_time": "1:35:29"}
+{"current_steps": 185, "total_steps": 418, "loss": 0.6826, "lr": 1.2696311175174357e-06, "epoch": 0.8849028400597907, "percentage": 44.26, "elapsed_time": "1:15:28", "remaining_time": "1:35:03"}
+{"current_steps": 186, "total_steps": 418, "loss": 0.6875, "lr": 1.2620025038457554e-06, "epoch": 0.8896860986547085, "percentage": 44.5, "elapsed_time": "1:15:52", "remaining_time": "1:34:38"}
+{"current_steps": 187, "total_steps": 418, "loss": 0.6763, "lr": 1.254357483448755e-06, "epoch": 0.8944693572496263, "percentage": 44.74, "elapsed_time": "1:16:16", "remaining_time": "1:34:13"}
+{"current_steps": 188, "total_steps": 418, "loss": 0.7191, "lr": 1.2466965350613615e-06, "epoch": 0.8992526158445441, "percentage": 44.98, "elapsed_time": "1:16:40", "remaining_time": "1:33:48"}
+{"current_steps": 189, "total_steps": 418, "loss": 0.7031, "lr": 1.2390201384159219e-06, "epoch": 0.9040358744394619, "percentage": 45.22, "elapsed_time": "1:17:04", "remaining_time": "1:33:22"}
+{"current_steps": 190, "total_steps": 418, "loss": 0.6596, "lr": 1.231328774212159e-06, "epoch": 0.9088191330343797, "percentage": 45.45, "elapsed_time": "1:17:28", "remaining_time": "1:32:57"}
+{"current_steps": 191, "total_steps": 418, "loss": 0.685, "lr": 1.223622924087073e-06, "epoch": 0.9136023916292975, "percentage": 45.69, "elapsed_time": "1:17:51", "remaining_time": "1:32:32"}
+{"current_steps": 192, "total_steps": 418, "loss": 0.6905, "lr": 1.215903070584779e-06, "epoch": 0.9183856502242153, "percentage": 45.93, "elapsed_time": "1:18:14", "remaining_time": "1:32:06"}
+{"current_steps": 193, "total_steps": 418, "loss": 0.6888, "lr": 1.2081696971262903e-06, "epoch": 0.923168908819133, "percentage": 46.17, "elapsed_time": "1:18:38", "remaining_time": "1:31:41"}
+{"current_steps": 194, "total_steps": 418, "loss": 0.6897, "lr": 1.2004232879792464e-06, "epoch": 0.9279521674140508, "percentage": 46.41, "elapsed_time": "1:19:02", "remaining_time": "1:31:15"}
+{"current_steps": 195, "total_steps": 418, "loss": 0.6808, "lr": 1.1926643282275882e-06, "epoch": 0.9327354260089686, "percentage": 46.65, "elapsed_time": "1:19:26", "remaining_time": "1:30:50"}
+{"current_steps": 196, "total_steps": 418, "loss": 0.6721, "lr": 1.1848933037411825e-06, "epoch": 0.9375186846038864, "percentage": 46.89, "elapsed_time": "1:19:50", "remaining_time": "1:30:26"}
+{"current_steps": 197, "total_steps": 418, "loss": 0.6943, "lr": 1.1771107011453933e-06, "epoch": 0.9423019431988042, "percentage": 47.13, "elapsed_time": "1:20:15", "remaining_time": "1:30:02"}
+{"current_steps": 198, "total_steps": 418, "loss": 0.6989, "lr": 1.1693170077906143e-06, "epoch": 0.947085201793722, "percentage": 47.37, "elapsed_time": "1:20:40", "remaining_time": "1:29:38"}
+{"current_steps": 199, "total_steps": 418, "loss": 0.6705, "lr": 1.1615127117217463e-06, "epoch": 0.9518684603886398, "percentage": 47.61, "elapsed_time": "1:21:03", "remaining_time": "1:29:12"}
+{"current_steps": 200, "total_steps": 418, "loss": 0.679, "lr": 1.1536983016476373e-06, "epoch": 0.9566517189835575, "percentage": 47.85, "elapsed_time": "1:21:28", "remaining_time": "1:28:47"}
+{"current_steps": 201, "total_steps": 418, "loss": 0.6652, "lr": 1.1458742669104803e-06, "epoch": 0.9614349775784753, "percentage": 48.09, "elapsed_time": "1:22:36", "remaining_time": "1:29:11"}
+{"current_steps": 202, "total_steps": 418, "loss": 0.6891, "lr": 1.1380410974551682e-06, "epoch": 0.9662182361733931, "percentage": 48.33, "elapsed_time": "1:23:01", "remaining_time": "1:28:46"}
+{"current_steps": 203, "total_steps": 418, "loss": 0.662, "lr": 1.130199283798615e-06, "epoch": 0.9710014947683109, "percentage": 48.56, "elapsed_time": "1:23:25", "remaining_time": "1:28:21"}
+{"current_steps": 204, "total_steps": 418, "loss": 0.6857, "lr": 1.1223493169990391e-06, "epoch": 0.9757847533632287, "percentage": 48.8, "elapsed_time": "1:23:48", "remaining_time": "1:27:55"}
+{"current_steps": 205, "total_steps": 418, "loss": 0.6693, "lr": 1.1144916886252124e-06, "epoch": 0.9805680119581465, "percentage": 49.04, "elapsed_time": "1:24:13", "remaining_time": "1:27:31"}
+{"current_steps": 206, "total_steps": 418, "loss": 0.689, "lr": 1.1066268907256782e-06, "epoch": 0.9853512705530643, "percentage": 49.28, "elapsed_time": "1:24:37", "remaining_time": "1:27:05"}
+{"current_steps": 207, "total_steps": 418, "loss": 0.6795, "lr": 1.098755415797939e-06, "epoch": 0.9901345291479821, "percentage": 49.52, "elapsed_time": "1:25:02", "remaining_time": "1:26:40"}
+{"current_steps": 208, "total_steps": 418, "loss": 0.697, "lr": 1.0908777567576168e-06, "epoch": 0.9949177877428999, "percentage": 49.76, "elapsed_time": "1:25:25", "remaining_time": "1:26:15"}
+{"current_steps": 209, "total_steps": 418, "loss": 0.6913, "lr": 1.0829944069075847e-06, "epoch": 0.9997010463378176, "percentage": 50.0, "elapsed_time": "1:25:50", "remaining_time": "1:25:50"}
+{"current_steps": 210, "total_steps": 418, "loss": 0.0398, "lr": 1.0751058599070781e-06, "epoch": 1.0, "percentage": 50.24, "elapsed_time": "1:25:51", "remaining_time": "1:25:02"}
+{"current_steps": 211, "total_steps": 418, "loss": 0.6558, "lr": 1.0672126097407795e-06, "epoch": 1.0047832585949177, "percentage": 50.48, "elapsed_time": "1:26:16", "remaining_time": "1:24:38"}
+{"current_steps": 212, "total_steps": 418, "loss": 0.6742, "lr": 1.0593151506878865e-06, "epoch": 1.0095665171898356, "percentage": 50.72, "elapsed_time": "1:26:40", "remaining_time": "1:24:13"}
+{"current_steps": 213, "total_steps": 418, "loss": 0.6589, "lr": 1.0514139772911597e-06, "epoch": 1.0143497757847533, "percentage": 50.96, "elapsed_time": "1:27:04", "remaining_time": "1:23:48"}
+{"current_steps": 214, "total_steps": 418, "loss": 0.6526, "lr": 1.043509584325953e-06, "epoch": 1.0191330343796712, "percentage": 51.2, "elapsed_time": "1:27:27", "remaining_time": "1:23:22"}
+{"current_steps": 215, "total_steps": 418, "loss": 0.6849, "lr": 1.0356024667692314e-06, "epoch": 1.0239162929745889, "percentage": 51.44, "elapsed_time": "1:27:51", "remaining_time": "1:22:57"}
+{"current_steps": 216, "total_steps": 418, "loss": 0.6947, "lr": 1.0276931197685753e-06, "epoch": 1.0286995515695068, "percentage": 51.67, "elapsed_time": "1:28:16", "remaining_time": "1:22:33"}
+{"current_steps": 217, "total_steps": 418, "loss": 0.6692, "lr": 1.0197820386111737e-06, "epoch": 1.0334828101644244, "percentage": 51.91, "elapsed_time": "1:28:40", "remaining_time": "1:22:08"}
+{"current_steps": 218, "total_steps": 418, "loss": 0.6481, "lr": 1.0118697186928105e-06, "epoch": 1.0382660687593424, "percentage": 52.15, "elapsed_time": "1:29:04", "remaining_time": "1:21:43"}
+{"current_steps": 219, "total_steps": 418, "loss": 0.6561, "lr": 1.0039566554868392e-06, "epoch": 1.04304932735426, "percentage": 52.39, "elapsed_time": "1:29:28", "remaining_time": "1:21:18"}
+{"current_steps": 220, "total_steps": 418, "loss": 0.6727, "lr": 9.960433445131607e-07, "epoch": 1.047832585949178, "percentage": 52.63, "elapsed_time": "1:29:53", "remaining_time": "1:20:54"}
+{"current_steps": 221, "total_steps": 418, "loss": 0.6786, "lr": 9.881302813071896e-07, "epoch": 1.0526158445440956, "percentage": 52.87, "elapsed_time": "1:30:17", "remaining_time": "1:20:29"}
+{"current_steps": 222, "total_steps": 418, "loss": 0.6492, "lr": 9.802179613888262e-07, "epoch": 1.0573991031390135, "percentage": 53.11, "elapsed_time": "1:30:41", "remaining_time": "1:20:04"}
+{"current_steps": 223, "total_steps": 418, "loss": 0.6435, "lr": 9.723068802314246e-07, "epoch": 1.0621823617339312, "percentage": 53.35, "elapsed_time": "1:31:06", "remaining_time": "1:19:39"}
+{"current_steps": 224, "total_steps": 418, "loss": 0.6693, "lr": 9.643975332307687e-07, "epoch": 1.0669656203288491, "percentage": 53.59, "elapsed_time": "1:31:30", "remaining_time": "1:19:14"}
+{"current_steps": 225, "total_steps": 418, "loss": 0.6554, "lr": 9.564904156740471e-07, "epoch": 1.0717488789237668, "percentage": 53.83, "elapsed_time": "1:31:53", "remaining_time": "1:18:49"}
+{"current_steps": 226, "total_steps": 418, "loss": 0.6524, "lr": 9.485860227088405e-07, "epoch": 1.0765321375186847, "percentage": 54.07, "elapsed_time": "1:32:17", "remaining_time": "1:18:24"}
+{"current_steps": 227, "total_steps": 418, "loss": 0.6598, "lr": 9.406848493121134e-07, "epoch": 1.0813153961136024, "percentage": 54.31, "elapsed_time": "1:32:42", "remaining_time": "1:18:00"}
+{"current_steps": 228, "total_steps": 418, "loss": 0.6546, "lr": 9.327873902592205e-07, "epoch": 1.08609865470852, "percentage": 54.55, "elapsed_time": "1:33:06", "remaining_time": "1:17:35"}
+{"current_steps": 229, "total_steps": 418, "loss": 0.6659, "lr": 9.248941400929222e-07, "epoch": 1.090881913303438, "percentage": 54.78, "elapsed_time": "1:33:30", "remaining_time": "1:17:10"}
+{"current_steps": 230, "total_steps": 418, "loss": 0.6789, "lr": 9.17005593092415e-07, "epoch": 1.0956651718983557, "percentage": 55.02, "elapsed_time": "1:33:55", "remaining_time": "1:16:46"}
+{"current_steps": 231, "total_steps": 418, "loss": 0.6395, "lr": 9.09122243242383e-07, "epoch": 1.1004484304932736, "percentage": 55.26, "elapsed_time": "1:34:19", "remaining_time": "1:16:21"}
+{"current_steps": 232, "total_steps": 418, "loss": 0.6351, "lr": 9.01244584202061e-07, "epoch": 1.1052316890881912, "percentage": 55.5, "elapsed_time": "1:34:43", "remaining_time": "1:15:56"}
+{"current_steps": 233, "total_steps": 418, "loss": 0.6843, "lr": 8.933731092743219e-07, "epoch": 1.1100149476831092, "percentage": 55.74, "elapsed_time": "1:35:08", "remaining_time": "1:15:32"}
+{"current_steps": 234, "total_steps": 418, "loss": 0.6533, "lr": 8.855083113747875e-07, "epoch": 1.1147982062780268, "percentage": 55.98, "elapsed_time": "1:35:32", "remaining_time": "1:15:07"}
+{"current_steps": 235, "total_steps": 418, "loss": 0.6529, "lr": 8.776506830009607e-07, "epoch": 1.1195814648729447, "percentage": 56.22, "elapsed_time": "1:35:56", "remaining_time": "1:14:42"}
+{"current_steps": 236, "total_steps": 418, "loss": 0.6622, "lr": 8.698007162013849e-07, "epoch": 1.1243647234678624, "percentage": 56.46, "elapsed_time": "1:36:21", "remaining_time": "1:14:18"}
+{"current_steps": 237, "total_steps": 418, "loss": 0.6698, "lr": 8.619589025448318e-07, "epoch": 1.1291479820627803, "percentage": 56.7, "elapsed_time": "1:36:44", "remaining_time": "1:13:53"}
+{"current_steps": 238, "total_steps": 418, "loss": 0.6397, "lr": 8.541257330895197e-07, "epoch": 1.133931240657698, "percentage": 56.94, "elapsed_time": "1:37:08", "remaining_time": "1:13:28"}
+{"current_steps": 239, "total_steps": 418, "loss": 0.6724, "lr": 8.463016983523627e-07, "epoch": 1.138714499252616, "percentage": 57.18, "elapsed_time": "1:37:33", "remaining_time": "1:13:04"}
+{"current_steps": 240, "total_steps": 418, "loss": 0.6651, "lr": 8.384872882782541e-07, "epoch": 1.1434977578475336, "percentage": 57.42, "elapsed_time": "1:37:58", "remaining_time": "1:12:39"}
+{"current_steps": 241, "total_steps": 418, "loss": 0.6482, "lr": 8.306829922093857e-07, "epoch": 1.1482810164424515, "percentage": 57.66, "elapsed_time": "1:38:22", "remaining_time": "1:12:14"}
+{"current_steps": 242, "total_steps": 418, "loss": 0.6532, "lr": 8.228892988546067e-07, "epoch": 1.1530642750373692, "percentage": 57.89, "elapsed_time": "1:38:46", "remaining_time": "1:11:50"}
+{"current_steps": 243, "total_steps": 418, "loss": 0.6458, "lr": 8.15106696258818e-07, "epoch": 1.157847533632287, "percentage": 58.13, "elapsed_time": "1:39:10", "remaining_time": "1:11:25"}
+{"current_steps": 244, "total_steps": 418, "loss": 0.6476, "lr": 8.073356717724115e-07, "epoch": 1.1626307922272048, "percentage": 58.37, "elapsed_time": "1:39:33", "remaining_time": "1:10:59"}
+{"current_steps": 245, "total_steps": 418, "loss": 0.6542, "lr": 7.995767120207536e-07, "epoch": 1.1674140508221225, "percentage": 58.61, "elapsed_time": "1:39:58", "remaining_time": "1:10:35"}
+{"current_steps": 246, "total_steps": 418, "loss": 0.6444, "lr": 7.918303028737096e-07, "epoch": 1.1721973094170404, "percentage": 58.85, "elapsed_time": "1:40:21", "remaining_time": "1:10:10"}
+{"current_steps": 247, "total_steps": 418, "loss": 0.6546, "lr": 7.840969294152211e-07, "epoch": 1.176980568011958, "percentage": 59.09, "elapsed_time": "1:40:45", "remaining_time": "1:09:45"}
+{"current_steps": 248, "total_steps": 418, "loss": 0.6483, "lr": 7.763770759129269e-07, "epoch": 1.181763826606876, "percentage": 59.33, "elapsed_time": "1:41:09", "remaining_time": "1:09:20"}
+{"current_steps": 249, "total_steps": 418, "loss": 0.6607, "lr": 7.68671225787841e-07, "epoch": 1.1865470852017936, "percentage": 59.57, "elapsed_time": "1:41:33", "remaining_time": "1:08:55"}
+{"current_steps": 250, "total_steps": 418, "loss": 0.6632, "lr": 7.609798615840785e-07, "epoch": 1.1913303437967115, "percentage": 59.81, "elapsed_time": "1:41:57", "remaining_time": "1:08:31"}
+{"current_steps": 251, "total_steps": 418, "loss": 0.6271, "lr": 7.533034649386384e-07, "epoch": 1.1961136023916292, "percentage": 60.05, "elapsed_time": "1:42:21", "remaining_time": "1:08:06"}
+{"current_steps": 252, "total_steps": 418, "loss": 0.649, "lr": 7.456425165512452e-07, "epoch": 1.2008968609865471, "percentage": 60.29, "elapsed_time": "1:42:45", "remaining_time": "1:07:41"}
+{"current_steps": 253, "total_steps": 418, "loss": 0.6744, "lr": 7.379974961542447e-07, "epoch": 1.2056801195814648, "percentage": 60.53, "elapsed_time": "1:43:09", "remaining_time": "1:07:16"}
+{"current_steps": 254, "total_steps": 418, "loss": 0.6608, "lr": 7.303688824825646e-07, "epoch": 1.2104633781763827, "percentage": 60.77, "elapsed_time": "1:43:33", "remaining_time": "1:06:52"}
+{"current_steps": 255, "total_steps": 418, "loss": 0.652, "lr": 7.227571532437349e-07, "epoch": 1.2152466367713004, "percentage": 61.0, "elapsed_time": "1:43:57", "remaining_time": "1:06:27"}
+{"current_steps": 256, "total_steps": 418, "loss": 0.6543, "lr": 7.151627850879755e-07, "epoch": 1.2200298953662183, "percentage": 61.24, "elapsed_time": "1:44:22", "remaining_time": "1:06:02"}
+{"current_steps": 257, "total_steps": 418, "loss": 0.6337, "lr": 7.075862535783453e-07, "epoch": 1.224813153961136, "percentage": 61.48, "elapsed_time": "1:44:45", "remaining_time": "1:05:37"}
+{"current_steps": 258, "total_steps": 418, "loss": 0.6839, "lr": 7.00028033160964e-07, "epoch": 1.229596412556054, "percentage": 61.72, "elapsed_time": "1:45:09", "remaining_time": "1:05:12"}
+{"current_steps": 259, "total_steps": 418, "loss": 0.6669, "lr": 6.924885971353026e-07, "epoch": 1.2343796711509716, "percentage": 61.96, "elapsed_time": "1:45:33", "remaining_time": "1:04:48"}
+{"current_steps": 260, "total_steps": 418, "loss": 0.6314, "lr": 6.849684176245431e-07, "epoch": 1.2391629297458895, "percentage": 62.2, "elapsed_time": "1:45:58", "remaining_time": "1:04:24"}
+{"current_steps": 261, "total_steps": 418, "loss": 0.6449, "lr": 6.774679655460158e-07, "epoch": 1.2439461883408072, "percentage": 62.44, "elapsed_time": "1:46:22", "remaining_time": "1:03:59"}
+{"current_steps": 262, "total_steps": 418, "loss": 0.6502, "lr": 6.699877105817092e-07, "epoch": 1.2487294469357249, "percentage": 62.68, "elapsed_time": "1:46:46", "remaining_time": "1:03:34"}
+{"current_steps": 263, "total_steps": 418, "loss": 0.6686, "lr": 6.625281211488591e-07, "epoch": 1.2535127055306428, "percentage": 62.92, "elapsed_time": "1:47:10", "remaining_time": "1:03:10"}
+{"current_steps": 264, "total_steps": 418, "loss": 0.6695, "lr": 6.55089664370615e-07, "epoch": 1.2582959641255607, "percentage": 63.16, "elapsed_time": "1:47:35", "remaining_time": "1:02:45"}
+{"current_steps": 265, "total_steps": 418, "loss": 0.6451, "lr": 6.476728060467888e-07, "epoch": 1.2630792227204783, "percentage": 63.4, "elapsed_time": "1:47:59", "remaining_time": "1:02:21"}
+{"current_steps": 266, "total_steps": 418, "loss": 0.6532, "lr": 6.402780106246884e-07, "epoch": 1.267862481315396, "percentage": 63.64, "elapsed_time": "1:48:25", "remaining_time": "1:01:57"}
+{"current_steps": 267, "total_steps": 418, "loss": 0.6673, "lr": 6.329057411700298e-07, "epoch": 1.272645739910314, "percentage": 63.88, "elapsed_time": "1:48:49", "remaining_time": "1:01:32"}
+{"current_steps": 268, "total_steps": 418, "loss": 0.6672, "lr": 6.255564593379429e-07, "epoch": 1.2774289985052316, "percentage": 64.11, "elapsed_time": "1:49:13", "remaining_time": "1:01:08"}
+{"current_steps": 269, "total_steps": 418, "loss": 0.6395, "lr": 6.182306253440619e-07, "epoch": 1.2822122571001495, "percentage": 64.35, "elapsed_time": "1:49:37", "remaining_time": "1:00:43"}
+{"current_steps": 270, "total_steps": 418, "loss": 0.6637, "lr": 6.109286979357051e-07, "epoch": 1.2869955156950672, "percentage": 64.59, "elapsed_time": "1:50:01", "remaining_time": "1:00:18"}
+{"current_steps": 271, "total_steps": 418, "loss": 0.6455, "lr": 6.036511343631488e-07, "epoch": 1.291778774289985, "percentage": 64.83, "elapsed_time": "1:50:24", "remaining_time": "0:59:53"}
+{"current_steps": 272, "total_steps": 418, "loss": 0.6638, "lr": 5.963983903509935e-07, "epoch": 1.2965620328849028, "percentage": 65.07, "elapsed_time": "1:50:49", "remaining_time": "0:59:29"}
+{"current_steps": 273, "total_steps": 418, "loss": 0.6548, "lr": 5.89170920069628e-07, "epoch": 1.3013452914798207, "percentage": 65.31, "elapsed_time": "1:51:13", "remaining_time": "0:59:04"}
+{"current_steps": 274, "total_steps": 418, "loss": 0.6388, "lr": 5.819691761067865e-07, "epoch": 1.3061285500747384, "percentage": 65.55, "elapsed_time": "1:51:37", "remaining_time": "0:58:39"}
+{"current_steps": 275, "total_steps": 418, "loss": 0.6435, "lr": 5.747936094392089e-07, "epoch": 1.310911808669656, "percentage": 65.79, "elapsed_time": "1:52:02", "remaining_time": "0:58:15"}
+{"current_steps": 276, "total_steps": 418, "loss": 0.638, "lr": 5.676446694044002e-07, "epoch": 1.315695067264574, "percentage": 66.03, "elapsed_time": "1:52:26", "remaining_time": "0:57:51"}
+{"current_steps": 277, "total_steps": 418, "loss": 0.6502, "lr": 5.605228036724927e-07, "epoch": 1.3204783258594919, "percentage": 66.27, "elapsed_time": "1:52:50", "remaining_time": "0:57:26"}
+{"current_steps": 278, "total_steps": 418, "loss": 0.6511, "lr": 5.534284582182114e-07, "epoch": 1.3252615844544096, "percentage": 66.51, "elapsed_time": "1:53:15", "remaining_time": "0:57:02"}
+{"current_steps": 279, "total_steps": 418, "loss": 0.6325, "lr": 5.463620772929494e-07, "epoch": 1.3300448430493272, "percentage": 66.75, "elapsed_time": "1:53:40", "remaining_time": "0:56:37"}
+{"current_steps": 280, "total_steps": 418, "loss": 0.6418, "lr": 5.393241033969466e-07, "epoch": 1.3348281016442451, "percentage": 66.99, "elapsed_time": "1:54:05", "remaining_time": "0:56:13"}
+{"current_steps": 281, "total_steps": 418, "loss": 0.6372, "lr": 5.323149772515812e-07, "epoch": 1.339611360239163, "percentage": 67.22, "elapsed_time": "1:54:29", "remaining_time": "0:55:49"}
+{"current_steps": 282, "total_steps": 418, "loss": 0.6504, "lr": 5.253351377717706e-07, "epoch": 1.3443946188340807, "percentage": 67.46, "elapsed_time": "1:54:53", "remaining_time": "0:55:24"}
+{"current_steps": 283, "total_steps": 418, "loss": 0.6461, "lr": 5.183850220384873e-07, "epoch": 1.3491778774289984, "percentage": 67.7, "elapsed_time": "1:55:18", "remaining_time": "0:55:00"}
+{"current_steps": 284, "total_steps": 418, "loss": 0.6542, "lr": 5.114650652713884e-07, "epoch": 1.3539611360239163, "percentage": 67.94, "elapsed_time": "1:55:42", "remaining_time": "0:54:35"}
+{"current_steps": 285, "total_steps": 418, "loss": 0.6627, "lr": 5.045757008015606e-07, "epoch": 1.358744394618834, "percentage": 68.18, "elapsed_time": "1:56:06", "remaining_time": "0:54:10"}
+{"current_steps": 286, "total_steps": 418, "loss": 0.6447, "lr": 4.977173600443868e-07, "epoch": 1.363527653213752, "percentage": 68.42, "elapsed_time": "1:56:30", "remaining_time": "0:53:46"}
+{"current_steps": 287, "total_steps": 418, "loss": 0.651, "lr": 4.908904724725299e-07, "epoch": 1.3683109118086696, "percentage": 68.66, "elapsed_time": "1:56:55", "remaining_time": "0:53:22"}
+{"current_steps": 288, "total_steps": 418, "loss": 0.6518, "lr": 4.840954655890391e-07, "epoch": 1.3730941704035875, "percentage": 68.9, "elapsed_time": "1:57:19", "remaining_time": "0:52:57"}
+{"current_steps": 289, "total_steps": 418, "loss": 0.6712, "lr": 4.773327649005777e-07, "epoch": 1.3778774289985052, "percentage": 69.14, "elapsed_time": "1:57:44", "remaining_time": "0:52:33"}
+{"current_steps": 290, "total_steps": 418, "loss": 0.6594, "lr": 4.7060279389078184e-07, "epoch": 1.382660687593423, "percentage": 69.38, "elapsed_time": "1:58:07", "remaining_time": "0:52:08"}
+{"current_steps": 291, "total_steps": 418, "loss": 0.6311, "lr": 4.6390597399373644e-07, "epoch": 1.3874439461883408, "percentage": 69.62, "elapsed_time": "1:58:31", "remaining_time": "0:51:43"}
+{"current_steps": 292, "total_steps": 418, "loss": 0.6524, "lr": 4.5724272456758907e-07, "epoch": 1.3922272047832587, "percentage": 69.86, "elapsed_time": "1:58:56", "remaining_time": "0:51:19"}
+{"current_steps": 293, "total_steps": 418, "loss": 0.6515, "lr": 4.506134628682877e-07, "epoch": 1.3970104633781764, "percentage": 70.1, "elapsed_time": "1:59:19", "remaining_time": "0:50:54"}
+{"current_steps": 294, "total_steps": 418, "loss": 0.6487, "lr": 4.440186040234524e-07, "epoch": 1.4017937219730943, "percentage": 70.33, "elapsed_time": "1:59:43", "remaining_time": "0:50:29"}
+{"current_steps": 295, "total_steps": 418, "loss": 0.629, "lr": 4.3745856100637834e-07, "epoch": 1.406576980568012, "percentage": 70.57, "elapsed_time": "2:00:06", "remaining_time": "0:50:04"}
+{"current_steps": 296, "total_steps": 418, "loss": 0.6466, "lr": 4.3093374461017785e-07, "epoch": 1.4113602391629296, "percentage": 70.81, "elapsed_time": "2:00:31", "remaining_time": "0:49:40"}
+{"current_steps": 297, "total_steps": 418, "loss": 0.6504, "lr": 4.244445634220545e-07, "epoch": 1.4161434977578475, "percentage": 71.05, "elapsed_time": "2:00:56", "remaining_time": "0:49:16"}
+{"current_steps": 298, "total_steps": 418, "loss": 0.6675, "lr": 4.1799142379771766e-07, "epoch": 1.4209267563527654, "percentage": 71.29, "elapsed_time": "2:01:21", "remaining_time": "0:48:52"}
+{"current_steps": 299, "total_steps": 418, "loss": 0.6379, "lr": 4.115747298359363e-07, "epoch": 1.4257100149476831, "percentage": 71.53, "elapsed_time": "2:01:45", "remaining_time": "0:48:27"}
+{"current_steps": 300, "total_steps": 418, "loss": 0.6684, "lr": 4.0519488335323415e-07, "epoch": 1.4304932735426008, "percentage": 71.77, "elapsed_time": "2:02:09", "remaining_time": "0:48:03"}
+{"current_steps": 301, "total_steps": 418, "loss": 0.6345, "lr": 3.9885228385872806e-07, "epoch": 1.4352765321375187, "percentage": 72.01, "elapsed_time": "2:03:17", "remaining_time": "0:47:55"}
+{"current_steps": 302, "total_steps": 418, "loss": 0.6419, "lr": 3.925473285291091e-07, "epoch": 1.4400597907324364, "percentage": 72.25, "elapsed_time": "2:03:42", "remaining_time": "0:47:30"}
+{"current_steps": 303, "total_steps": 418, "loss": 0.6568, "lr": 3.862804121837733e-07, "epoch": 1.4448430493273543, "percentage": 72.49, "elapsed_time": "2:04:06", "remaining_time": "0:47:06"}
+{"current_steps": 304, "total_steps": 418, "loss": 0.6526, "lr": 3.8005192726009663e-07, "epoch": 1.449626307922272, "percentage": 72.73, "elapsed_time": "2:04:30", "remaining_time": "0:46:41"}
+{"current_steps": 305, "total_steps": 418, "loss": 0.6554, "lr": 3.738622637888608e-07, "epoch": 1.45440956651719, "percentage": 72.97, "elapsed_time": "2:04:53", "remaining_time": "0:46:16"}
+{"current_steps": 306, "total_steps": 418, "loss": 0.639, "lr": 3.677118093698278e-07, "epoch": 1.4591928251121076, "percentage": 73.21, "elapsed_time": "2:05:18", "remaining_time": "0:45:51"}
+{"current_steps": 307, "total_steps": 418, "loss": 0.6534, "lr": 3.61600949147472e-07, "epoch": 1.4639760837070255, "percentage": 73.44, "elapsed_time": "2:05:43", "remaining_time": "0:45:27"}
+{"current_steps": 308, "total_steps": 418, "loss": 0.6364, "lr": 3.5553006578685706e-07, "epoch": 1.4687593423019432, "percentage": 73.68, "elapsed_time": "2:06:07", "remaining_time": "0:45:02"}
+{"current_steps": 309, "total_steps": 418, "loss": 0.6438, "lr": 3.494995394496778e-07, "epoch": 1.473542600896861, "percentage": 73.92, "elapsed_time": "2:06:32", "remaining_time": "0:44:38"}
+{"current_steps": 310, "total_steps": 418, "loss": 0.6159, "lr": 3.435097477704517e-07, "epoch": 1.4783258594917787, "percentage": 74.16, "elapsed_time": "2:06:56", "remaining_time": "0:44:13"}
+{"current_steps": 311, "total_steps": 418, "loss": 0.6692, "lr": 3.3756106583287205e-07, "epoch": 1.4831091180866967, "percentage": 74.4, "elapsed_time": "2:07:21", "remaining_time": "0:43:49"}
+{"current_steps": 312, "total_steps": 418, "loss": 0.6704, "lr": 3.316538661463204e-07, "epoch": 1.4878923766816143, "percentage": 74.64, "elapsed_time": "2:07:45", "remaining_time": "0:43:24"}
+{"current_steps": 313, "total_steps": 418, "loss": 0.6582, "lr": 3.2578851862253796e-07, "epoch": 1.492675635276532, "percentage": 74.88, "elapsed_time": "2:08:09", "remaining_time": "0:42:59"}
+{"current_steps": 314, "total_steps": 418, "loss": 0.6353, "lr": 3.199653905524654e-07, "epoch": 1.49745889387145, "percentage": 75.12, "elapsed_time": "2:08:34", "remaining_time": "0:42:34"}
+{"current_steps": 315, "total_steps": 418, "loss": 0.6566, "lr": 3.1418484658323806e-07, "epoch": 1.5022421524663678, "percentage": 75.36, "elapsed_time": "2:08:57", "remaining_time": "0:42:10"}
+{"current_steps": 316, "total_steps": 418, "loss": 0.6437, "lr": 3.0844724869535577e-07, "epoch": 1.5070254110612855, "percentage": 75.6, "elapsed_time": "2:09:22", "remaining_time": "0:41:45"}
+{"current_steps": 317, "total_steps": 418, "loss": 0.6541, "lr": 3.027529561800117e-07, "epoch": 1.5118086696562032, "percentage": 75.84, "elapsed_time": "2:09:46", "remaining_time": "0:41:20"}
+{"current_steps": 318, "total_steps": 418, "loss": 0.6429, "lr": 2.971023256165983e-07, "epoch": 1.516591928251121, "percentage": 76.08, "elapsed_time": "2:10:10", "remaining_time": "0:40:56"}
+{"current_steps": 319, "total_steps": 418, "loss": 0.6536, "lr": 2.9149571085037215e-07, "epoch": 1.521375186846039, "percentage": 76.32, "elapsed_time": "2:10:34", "remaining_time": "0:40:31"}
+{"current_steps": 320, "total_steps": 418, "loss": 0.6448, "lr": 2.8593346297030073e-07, "epoch": 1.5261584454409567, "percentage": 76.56, "elapsed_time": "2:10:58", "remaining_time": "0:40:06"}
+{"current_steps": 321, "total_steps": 418, "loss": 0.6361, "lr": 2.804159302870751e-07, "epoch": 1.5309417040358744, "percentage": 76.79, "elapsed_time": "2:11:22", "remaining_time": "0:39:42"}
+{"current_steps": 322, "total_steps": 418, "loss": 0.6275, "lr": 2.7494345831129837e-07, "epoch": 1.5357249626307923, "percentage": 77.03, "elapsed_time": "2:11:47", "remaining_time": "0:39:17"}
+{"current_steps": 323, "total_steps": 418, "loss": 0.6528, "lr": 2.6951638973185073e-07, "epoch": 1.54050822122571, "percentage": 77.27, "elapsed_time": "2:12:10", "remaining_time": "0:38:52"}
+{"current_steps": 324, "total_steps": 418, "loss": 0.6632, "lr": 2.64135064394428e-07, "epoch": 1.5452914798206279, "percentage": 77.51, "elapsed_time": "2:12:35", "remaining_time": "0:38:28"}
+{"current_steps": 325, "total_steps": 418, "loss": 0.6306, "lr": 2.587998192802638e-07, "epoch": 1.5500747384155455, "percentage": 77.75, "elapsed_time": "2:12:59", "remaining_time": "0:38:03"}
+{"current_steps": 326, "total_steps": 418, "loss": 0.6511, "lr": 2.5351098848502386e-07, "epoch": 1.5548579970104632, "percentage": 77.99, "elapsed_time": "2:13:24", "remaining_time": "0:37:38"}
+{"current_steps": 327, "total_steps": 418, "loss": 0.6533, "lr": 2.482689031978872e-07, "epoch": 1.5596412556053811, "percentage": 78.23, "elapsed_time": "2:13:49", "remaining_time": "0:37:14"}
+{"current_steps": 328, "total_steps": 418, "loss": 0.6603, "lr": 2.4307389168080606e-07, "epoch": 1.564424514200299, "percentage": 78.47, "elapsed_time": "2:14:13", "remaining_time": "0:36:49"}
+{"current_steps": 329, "total_steps": 418, "loss": 0.6818, "lr": 2.3792627924795038e-07, "epoch": 1.5692077727952167, "percentage": 78.71, "elapsed_time": "2:14:37", "remaining_time": "0:36:25"}
+{"current_steps": 330, "total_steps": 418, "loss": 0.6531, "lr": 2.3282638824533529e-07, "epoch": 1.5739910313901344, "percentage": 78.95, "elapsed_time": "2:15:02", "remaining_time": "0:36:00"}
+{"current_steps": 331, "total_steps": 418, "loss": 0.6795, "lr": 2.277745380306383e-07, "epoch": 1.5787742899850523, "percentage": 79.19, "elapsed_time": "2:15:26", "remaining_time": "0:35:36"}
+{"current_steps": 332, "total_steps": 418, "loss": 0.6778, "lr": 2.227710449531971e-07, "epoch": 1.5835575485799702, "percentage": 79.43, "elapsed_time": "2:15:50", "remaining_time": "0:35:11"}
+{"current_steps": 333, "total_steps": 418, "loss": 0.6404, "lr": 2.178162223342035e-07, "epoch": 1.588340807174888, "percentage": 79.67, "elapsed_time": "2:16:14", "remaining_time": "0:34:46"}
+{"current_steps": 334, "total_steps": 418, "loss": 0.6528, "lr": 2.1291038044707965e-07, "epoch": 1.5931240657698056, "percentage": 79.9, "elapsed_time": "2:16:38", "remaining_time": "0:34:21"}
+{"current_steps": 335, "total_steps": 418, "loss": 0.6461, "lr": 2.0805382649805225e-07, "epoch": 1.5979073243647235, "percentage": 80.14, "elapsed_time": "2:17:03", "remaining_time": "0:33:57"}
+{"current_steps": 336, "total_steps": 418, "loss": 0.6425, "lr": 2.032468646069112e-07, "epoch": 1.6026905829596414, "percentage": 80.38, "elapsed_time": "2:17:27", "remaining_time": "0:33:32"}
+{"current_steps": 337, "total_steps": 418, "loss": 0.6548, "lr": 1.9848979578796865e-07, "epoch": 1.607473841554559, "percentage": 80.62, "elapsed_time": "2:17:51", "remaining_time": "0:33:08"}
+{"current_steps": 338, "total_steps": 418, "loss": 0.6633, "lr": 1.937829179312076e-07, "epoch": 1.6122571001494768, "percentage": 80.86, "elapsed_time": "2:18:16", "remaining_time": "0:32:43"}
+{"current_steps": 339, "total_steps": 418, "loss": 0.653, "lr": 1.8912652578362853e-07, "epoch": 1.6170403587443947, "percentage": 81.1, "elapsed_time": "2:18:40", "remaining_time": "0:32:18"}
+{"current_steps": 340, "total_steps": 418, "loss": 0.6405, "lr": 1.8452091093079215e-07, "epoch": 1.6218236173393124, "percentage": 81.34, "elapsed_time": "2:19:05", "remaining_time": "0:31:54"}
+{"current_steps": 341, "total_steps": 418, "loss": 0.6776, "lr": 1.7996636177855928e-07, "epoch": 1.6266068759342303, "percentage": 81.58, "elapsed_time": "2:19:29", "remaining_time": "0:31:29"}
+{"current_steps": 342, "total_steps": 418, "loss": 0.6579, "lr": 1.75463163535033e-07, "epoch": 1.631390134529148, "percentage": 81.82, "elapsed_time": "2:19:53", "remaining_time": "0:31:05"}
+{"current_steps": 343, "total_steps": 418, "loss": 0.6432, "lr": 1.7101159819269583e-07, "epoch": 1.6361733931240656, "percentage": 82.06, "elapsed_time": "2:20:18", "remaining_time": "0:30:40"}
+{"current_steps": 344, "total_steps": 418, "loss": 0.6628, "lr": 1.6661194451075345e-07, "epoch": 1.6409566517189835, "percentage": 82.3, "elapsed_time": "2:20:42", "remaining_time": "0:30:16"}
+{"current_steps": 345, "total_steps": 418, "loss": 0.6306, "lr": 1.6226447799767772e-07, "epoch": 1.6457399103139014, "percentage": 82.54, "elapsed_time": "2:21:06", "remaining_time": "0:29:51"}
+{"current_steps": 346, "total_steps": 418, "loss": 0.6462, "lr": 1.5796947089395475e-07, "epoch": 1.6505231689088191, "percentage": 82.78, "elapsed_time": "2:21:30", "remaining_time": "0:29:26"}
+{"current_steps": 347, "total_steps": 418, "loss": 0.6309, "lr": 1.5372719215503582e-07, "epoch": 1.6553064275037368, "percentage": 83.01, "elapsed_time": "2:21:54", "remaining_time": "0:29:02"}
+{"current_steps": 348, "total_steps": 418, "loss": 0.6631, "lr": 1.4953790743449702e-07, "epoch": 1.6600896860986547, "percentage": 83.25, "elapsed_time": "2:22:18", "remaining_time": "0:28:37"}
+{"current_steps": 349, "total_steps": 418, "loss": 0.6285, "lr": 1.4540187906740241e-07, "epoch": 1.6648729446935726, "percentage": 83.49, "elapsed_time": "2:22:43", "remaining_time": "0:28:13"}
+{"current_steps": 350, "total_steps": 418, "loss": 0.6731, "lr": 1.4131936605387762e-07, "epoch": 1.6696562032884903, "percentage": 83.73, "elapsed_time": "2:23:08", "remaining_time": "0:27:48"}
+{"current_steps": 351, "total_steps": 418, "loss": 0.6729, "lr": 1.3729062404289017e-07, "epoch": 1.674439461883408, "percentage": 83.97, "elapsed_time": "2:23:34", "remaining_time": "0:27:24"}
+{"current_steps": 352, "total_steps": 418, "loss": 0.6515, "lr": 1.3331590531624115e-07, "epoch": 1.6792227204783259, "percentage": 84.21, "elapsed_time": "2:23:59", "remaining_time": "0:26:59"}
+{"current_steps": 353, "total_steps": 418, "loss": 0.6452, "lr": 1.2939545877276726e-07, "epoch": 1.6840059790732438, "percentage": 84.45, "elapsed_time": "2:24:22", "remaining_time": "0:26:35"}
+{"current_steps": 354, "total_steps": 418, "loss": 0.6477, "lr": 1.25529529912754e-07, "epoch": 1.6887892376681615, "percentage": 84.69, "elapsed_time": "2:24:47", "remaining_time": "0:26:10"}
+{"current_steps": 355, "total_steps": 418, "loss": 0.6678, "lr": 1.2171836082256316e-07, "epoch": 1.6935724962630792, "percentage": 84.93, "elapsed_time": "2:25:11", "remaining_time": "0:25:45"}
+{"current_steps": 356, "total_steps": 418, "loss": 0.6515, "lr": 1.1796219015947285e-07, "epoch": 1.698355754857997, "percentage": 85.17, "elapsed_time": "2:25:35", "remaining_time": "0:25:21"}
+{"current_steps": 357, "total_steps": 418, "loss": 0.6645, "lr": 1.1426125313673285e-07, "epoch": 1.703139013452915, "percentage": 85.41, "elapsed_time": "2:26:00", "remaining_time": "0:24:56"}
+{"current_steps": 358, "total_steps": 418, "loss": 0.6092, "lr": 1.1061578150883444e-07, "epoch": 1.7079222720478326, "percentage": 85.65, "elapsed_time": "2:26:24", "remaining_time": "0:24:32"}
+{"current_steps": 359, "total_steps": 418, "loss": 0.6539, "lr": 1.070260035570002e-07, "epoch": 1.7127055306427503, "percentage": 85.89, "elapsed_time": "2:26:48", "remaining_time": "0:24:07"}
+{"current_steps": 360, "total_steps": 418, "loss": 0.6454, "lr": 1.0349214407488571e-07, "epoch": 1.717488789237668, "percentage": 86.12, "elapsed_time": "2:27:13", "remaining_time": "0:23:43"}
+{"current_steps": 361, "total_steps": 418, "loss": 0.6486, "lr": 1.000144243545058e-07, "epoch": 1.722272047832586, "percentage": 86.36, "elapsed_time": "2:27:37", "remaining_time": "0:23:18"}
+{"current_steps": 362, "total_steps": 418, "loss": 0.6402, "lr": 9.659306217237517e-08, "epoch": 1.7270553064275038, "percentage": 86.6, "elapsed_time": "2:28:01", "remaining_time": "0:22:53"}
+{"current_steps": 363, "total_steps": 418, "loss": 0.6469, "lr": 9.322827177587212e-08, "epoch": 1.7318385650224215, "percentage": 86.84, "elapsed_time": "2:28:25", "remaining_time": "0:22:29"}
+{"current_steps": 364, "total_steps": 418, "loss": 0.6535, "lr": 8.992026386982221e-08, "epoch": 1.7366218236173392, "percentage": 87.08, "elapsed_time": "2:28:50", "remaining_time": "0:22:04"}
+{"current_steps": 365, "total_steps": 418, "loss": 0.648, "lr": 8.66692456033029e-08, "epoch": 1.741405082212257, "percentage": 87.32, "elapsed_time": "2:29:13", "remaining_time": "0:21:40"}
+{"current_steps": 366, "total_steps": 418, "loss": 0.6529, "lr": 8.347542055667311e-08, "epoch": 1.746188340807175, "percentage": 87.56, "elapsed_time": "2:29:37", "remaining_time": "0:21:15"}
+{"current_steps": 367, "total_steps": 418, "loss": 0.6383, "lr": 8.033898872882394e-08, "epoch": 1.7509715994020927, "percentage": 87.8, "elapsed_time": "2:30:02", "remaining_time": "0:20:50"}
+{"current_steps": 368, "total_steps": 418, "loss": 0.6202, "lr": 7.726014652465507e-08, "epoch": 1.7557548579970104, "percentage": 88.04, "elapsed_time": "2:30:25", "remaining_time": "0:20:26"}
+{"current_steps": 369, "total_steps": 418, "loss": 0.6494, "lr": 7.423908674277579e-08, "epoch": 1.7605381165919283, "percentage": 88.28, "elapsed_time": "2:30:50", "remaining_time": "0:20:01"}
+{"current_steps": 370, "total_steps": 418, "loss": 0.6583, "lr": 7.127599856343192e-08, "epoch": 1.7653213751868462, "percentage": 88.52, "elapsed_time": "2:31:14", "remaining_time": "0:19:37"}
+{"current_steps": 371, "total_steps": 418, "loss": 0.666, "lr": 6.837106753665823e-08, "epoch": 1.7701046337817639, "percentage": 88.76, "elapsed_time": "2:31:38", "remaining_time": "0:19:12"}
+{"current_steps": 372, "total_steps": 418, "loss": 0.6464, "lr": 6.552447557066109e-08, "epoch": 1.7748878923766815, "percentage": 89.0, "elapsed_time": "2:32:01", "remaining_time": "0:18:47"}
+{"current_steps": 373, "total_steps": 418, "loss": 0.6367, "lr": 6.273640092042575e-08, "epoch": 1.7796711509715994, "percentage": 89.23, "elapsed_time": "2:32:26", "remaining_time": "0:18:23"}
+{"current_steps": 374, "total_steps": 418, "loss": 0.6259, "lr": 6.000701817655474e-08, "epoch": 1.7844544095665174, "percentage": 89.47, "elapsed_time": "2:32:50", "remaining_time": "0:17:58"}
+{"current_steps": 375, "total_steps": 418, "loss": 0.6316, "lr": 5.733649825433384e-08, "epoch": 1.789237668161435, "percentage": 89.71, "elapsed_time": "2:33:14", "remaining_time": "0:17:34"}
+{"current_steps": 376, "total_steps": 418, "loss": 0.6764, "lr": 5.47250083830314e-08, "epoch": 1.7940209267563527, "percentage": 89.95, "elapsed_time": "2:33:38", "remaining_time": "0:17:09"}
+{"current_steps": 377, "total_steps": 418, "loss": 0.6581, "lr": 5.217271209542384e-08, "epoch": 1.7988041853512704, "percentage": 90.19, "elapsed_time": "2:34:03", "remaining_time": "0:16:45"}
+{"current_steps": 378, "total_steps": 418, "loss": 0.6238, "lr": 4.967976921755679e-08, "epoch": 1.8035874439461883, "percentage": 90.43, "elapsed_time": "2:34:26", "remaining_time": "0:16:20"}
+{"current_steps": 379, "total_steps": 418, "loss": 0.6417, "lr": 4.724633585873627e-08, "epoch": 1.8083707025411062, "percentage": 90.67, "elapsed_time": "2:34:51", "remaining_time": "0:15:56"}
+{"current_steps": 380, "total_steps": 418, "loss": 0.6563, "lr": 4.487256440175291e-08, "epoch": 1.813153961136024, "percentage": 90.91, "elapsed_time": "2:35:15", "remaining_time": "0:15:31"}
+{"current_steps": 381, "total_steps": 418, "loss": 0.6479, "lr": 4.255860349334006e-08, "epoch": 1.8179372197309416, "percentage": 91.15, "elapsed_time": "2:35:39", "remaining_time": "0:15:06"}
+{"current_steps": 382, "total_steps": 418, "loss": 0.6378, "lr": 4.030459803486464e-08, "epoch": 1.8227204783258595, "percentage": 91.39, "elapsed_time": "2:36:03", "remaining_time": "0:14:42"}
+{"current_steps": 383, "total_steps": 418, "loss": 0.6128, "lr": 3.811068917325444e-08, "epoch": 1.8275037369207774, "percentage": 91.63, "elapsed_time": "2:36:27", "remaining_time": "0:14:17"}
+{"current_steps": 384, "total_steps": 418, "loss": 0.6493, "lr": 3.5977014292158495e-08, "epoch": 1.832286995515695, "percentage": 91.87, "elapsed_time": "2:36:51", "remaining_time": "0:13:53"}
+{"current_steps": 385, "total_steps": 418, "loss": 0.6453, "lr": 3.3903707003344774e-08, "epoch": 1.8370702541106128, "percentage": 92.11, "elapsed_time": "2:37:15", "remaining_time": "0:13:28"}
+{"current_steps": 386, "total_steps": 418, "loss": 0.6564, "lr": 3.189089713833226e-08, "epoch": 1.8418535127055307, "percentage": 92.34, "elapsed_time": "2:37:38", "remaining_time": "0:13:04"}
+{"current_steps": 387, "total_steps": 418, "loss": 0.6286, "lr": 2.9938710740262884e-08, "epoch": 1.8466367713004486, "percentage": 92.58, "elapsed_time": "2:38:03", "remaining_time": "0:12:39"}
+{"current_steps": 388, "total_steps": 418, "loss": 0.6431, "lr": 2.8047270056005934e-08, "epoch": 1.8514200298953662, "percentage": 92.82, "elapsed_time": "2:38:28", "remaining_time": "0:12:15"}
+{"current_steps": 389, "total_steps": 418, "loss": 0.6419, "lr": 2.6216693528505195e-08, "epoch": 1.856203288490284, "percentage": 93.06, "elapsed_time": "2:38:52", "remaining_time": "0:11:50"}
+{"current_steps": 390, "total_steps": 418, "loss": 0.6426, "lr": 2.4447095789360884e-08, "epoch": 1.8609865470852018, "percentage": 93.3, "elapsed_time": "2:39:16", "remaining_time": "0:11:26"}
+{"current_steps": 391, "total_steps": 418, "loss": 0.6418, "lr": 2.2738587651651487e-08, "epoch": 1.8657698056801197, "percentage": 93.54, "elapsed_time": "2:39:39", "remaining_time": "0:11:01"}
+{"current_steps": 392, "total_steps": 418, "loss": 0.6534, "lr": 2.109127610299466e-08, "epoch": 1.8705530642750374, "percentage": 93.78, "elapsed_time": "2:40:04", "remaining_time": "0:10:37"}
+{"current_steps": 393, "total_steps": 418, "loss": 0.6385, "lr": 1.950526429884769e-08, "epoch": 1.875336322869955, "percentage": 94.02, "elapsed_time": "2:40:28", "remaining_time": "0:10:12"}
+{"current_steps": 394, "total_steps": 418, "loss": 0.6533, "lr": 1.7980651556048e-08, "epoch": 1.8801195814648728, "percentage": 94.26, "elapsed_time": "2:40:52", "remaining_time": "0:09:47"}
+{"current_steps": 395, "total_steps": 418, "loss": 0.6533, "lr": 1.6517533346593226e-08, "epoch": 1.8849028400597907, "percentage": 94.5, "elapsed_time": "2:41:17", "remaining_time": "0:09:23"}
+{"current_steps": 396, "total_steps": 418, "loss": 0.686, "lr": 1.5116001291663462e-08, "epoch": 1.8896860986547086, "percentage": 94.74, "elapsed_time": "2:41:41", "remaining_time": "0:08:58"}
+{"current_steps": 397, "total_steps": 418, "loss": 0.6265, "lr": 1.3776143155883491e-08, "epoch": 1.8944693572496263, "percentage": 94.98, "elapsed_time": "2:42:06", "remaining_time": "0:08:34"}
+{"current_steps": 398, "total_steps": 418, "loss": 0.6444, "lr": 1.2498042841827317e-08, "epoch": 1.899252615844544, "percentage": 95.22, "elapsed_time": "2:42:30", "remaining_time": "0:08:09"}
+{"current_steps": 399, "total_steps": 418, "loss": 0.643, "lr": 1.128178038476324e-08, "epoch": 1.9040358744394619, "percentage": 95.45, "elapsed_time": "2:42:53", "remaining_time": "0:07:45"}
+{"current_steps": 400, "total_steps": 418, "loss": 0.643, "lr": 1.0127431947643316e-08, "epoch": 1.9088191330343798, "percentage": 95.69, "elapsed_time": "2:43:18", "remaining_time": "0:07:20"}
+{"current_steps": 401, "total_steps": 418, "loss": 0.6312, "lr": 9.035069816332619e-09, "epoch": 1.9136023916292975, "percentage": 95.93, "elapsed_time": "2:44:28", "remaining_time": "0:06:58"}
+{"current_steps": 402, "total_steps": 418, "loss": 0.629, "lr": 8.004762395083963e-09, "epoch": 1.9183856502242151, "percentage": 96.17, "elapsed_time": "2:44:52", "remaining_time": "0:06:33"}
+{"current_steps": 403, "total_steps": 418, "loss": 0.6706, "lr": 7.036574202253343e-09, "epoch": 1.923168908819133, "percentage": 96.41, "elapsed_time": "2:45:16", "remaining_time": "0:06:09"}
+{"current_steps": 404, "total_steps": 418, "loss": 0.65, "lr": 6.130565866260484e-09, "epoch": 1.927952167414051, "percentage": 96.65, "elapsed_time": "2:45:40", "remaining_time": "0:05:44"}
+{"current_steps": 405, "total_steps": 418, "loss": 0.6574, "lr": 5.286794121791782e-09, "epoch": 1.9327354260089686, "percentage": 96.89, "elapsed_time": "2:46:05", "remaining_time": "0:05:19"}
+{"current_steps": 406, "total_steps": 418, "loss": 0.6322, "lr": 4.5053118062478025e-09, "epoch": 1.9375186846038863, "percentage": 97.13, "elapsed_time": "2:46:29", "remaining_time": "0:04:55"}
+{"current_steps": 407, "total_steps": 418, "loss": 0.6634, "lr": 3.786167856434375e-09, "epoch": 1.9423019431988042, "percentage": 97.37, "elapsed_time": "2:46:53", "remaining_time": "0:04:30"}
+{"current_steps": 408, "total_steps": 418, "loss": 0.6418, "lr": 3.1294073054987102e-09, "epoch": 1.9470852017937221, "percentage": 97.61, "elapsed_time": "2:47:18", "remaining_time": "0:04:06"}
+{"current_steps": 409, "total_steps": 418, "loss": 0.631, "lr": 2.5350712801084363e-09, "epoch": 1.9518684603886398, "percentage": 97.85, "elapsed_time": "2:47:42", "remaining_time": "0:03:41"}
+{"current_steps": 410, "total_steps": 418, "loss": 0.6405, "lr": 2.003196997877099e-09, "epoch": 1.9566517189835575, "percentage": 98.09, "elapsed_time": "2:48:07", "remaining_time": "0:03:16"}
+{"current_steps": 411, "total_steps": 418, "loss": 0.631, "lr": 1.5338177650332517e-09, "epoch": 1.9614349775784752, "percentage": 98.33, "elapsed_time": "2:48:31", "remaining_time": "0:02:52"}
+{"current_steps": 412, "total_steps": 418, "loss": 0.6433, "lr": 1.1269629743346777e-09, "epoch": 1.966218236173393, "percentage": 98.56, "elapsed_time": "2:48:56", "remaining_time": "0:02:27"}
+{"current_steps": 413, "total_steps": 418, "loss": 0.6422, "lr": 7.826581032279734e-10, "epoch": 1.971001494768311, "percentage": 98.8, "elapsed_time": "2:49:20", "remaining_time": "0:02:03"}
+{"current_steps": 414, "total_steps": 418, "loss": 0.6645, "lr": 5.00924712252937e-10, "epoch": 1.9757847533632287, "percentage": 99.04, "elapsed_time": "2:49:45", "remaining_time": "0:01:38"}
+{"current_steps": 415, "total_steps": 418, "loss": 0.6495, "lr": 2.8178044369286945e-10, "epoch": 1.9805680119581464, "percentage": 99.28, "elapsed_time": "2:50:10", "remaining_time": "0:01:13"}
+{"current_steps": 416, "total_steps": 418, "loss": 0.6238, "lr": 1.2523902046934763e-10, "epoch": 1.9853512705530643, "percentage": 99.52, "elapsed_time": "2:50:33", "remaining_time": "0:00:49"}
+{"current_steps": 417, "total_steps": 418, "loss": 0.6478, "lr": 3.131024528302273e-11, "epoch": 1.9901345291479822, "percentage": 99.76, "elapsed_time": "2:50:56", "remaining_time": "0:00:24"}
+{"current_steps": 418, "total_steps": 418, "loss": 0.6557, "lr": 0.0, "epoch": 1.9949177877428999, "percentage": 100.0, "elapsed_time": "2:51:19", "remaining_time": "0:00:00"}
+{"current_steps": 418, "total_steps": 418, "epoch": 1.9949177877428999, "percentage": 100.0, "elapsed_time": "2:52:05", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2968 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9949177877428999,
+  "eval_steps": 500,
+  "global_step": 418,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004783258594917788,
+      "grad_norm": 0.709558174057161,
+      "learning_rate": 9.523809523809523e-08,
+      "loss": 1.2153,
+      "step": 1
+    },
+    {
+      "epoch": 0.009566517189835576,
+      "grad_norm": 0.7136115199943648,
+      "learning_rate": 1.9047619047619045e-07,
+      "loss": 1.1666,
+      "step": 2
+    },
+    {
+      "epoch": 0.014349775784753363,
+      "grad_norm": 0.675693723617585,
+      "learning_rate": 2.857142857142857e-07,
+      "loss": 1.1641,
+      "step": 3
+    },
+    {
+      "epoch": 0.019133034379671152,
+      "grad_norm": 0.6920682930548318,
+      "learning_rate": 3.809523809523809e-07,
+      "loss": 1.1522,
+      "step": 4
+    },
+    {
+      "epoch": 0.02391629297458894,
+      "grad_norm": 0.7102565482472595,
+      "learning_rate": 4.761904761904761e-07,
+      "loss": 1.1849,
+      "step": 5
+    },
+    {
+      "epoch": 0.028699551569506727,
+      "grad_norm": 0.7063832004098226,
+      "learning_rate": 5.714285714285714e-07,
+      "loss": 1.1832,
+      "step": 6
+    },
+    {
+      "epoch": 0.03348281016442452,
+      "grad_norm": 0.7273064919061014,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 1.1646,
+      "step": 7
+    },
+    {
+      "epoch": 0.038266068759342305,
+      "grad_norm": 0.6515215643931184,
+      "learning_rate": 7.619047619047618e-07,
+      "loss": 1.1492,
+      "step": 8
+    },
+    {
+      "epoch": 0.04304932735426009,
+      "grad_norm": 0.662055704210126,
+      "learning_rate": 8.57142857142857e-07,
+      "loss": 1.1356,
+      "step": 9
+    },
+    {
+      "epoch": 0.04783258594917788,
+      "grad_norm": 0.6717882944749636,
+      "learning_rate": 9.523809523809522e-07,
+      "loss": 1.1373,
+      "step": 10
+    },
+    {
+      "epoch": 0.052615844544095666,
+      "grad_norm": 0.5448741661939914,
+      "learning_rate": 1.0476190476190476e-06,
+      "loss": 1.1133,
+      "step": 11
+    },
+    {
+      "epoch": 0.05739910313901345,
+      "grad_norm": 0.5462157636865493,
+      "learning_rate": 1.1428571428571428e-06,
+      "loss": 1.1025,
+      "step": 12
+    },
+    {
+      "epoch": 0.06218236173393124,
+      "grad_norm": 0.5384420206966651,
+      "learning_rate": 1.238095238095238e-06,
+      "loss": 1.1102,
+      "step": 13
+    },
+    {
+      "epoch": 0.06696562032884903,
+      "grad_norm": 0.5199166835309963,
+      "learning_rate": 1.3333333333333332e-06,
+      "loss": 1.0716,
+      "step": 14
+    },
+    {
+      "epoch": 0.07174887892376682,
+      "grad_norm": 0.3132434598969462,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.0198,
+      "step": 15
+    },
+    {
+      "epoch": 0.07653213751868461,
+      "grad_norm": 0.2906366968418868,
+      "learning_rate": 1.5238095238095236e-06,
+      "loss": 1.0402,
+      "step": 16
+    },
+    {
+      "epoch": 0.08131539611360239,
+      "grad_norm": 0.27762786913003945,
+      "learning_rate": 1.619047619047619e-06,
+      "loss": 1.0027,
+      "step": 17
+    },
+    {
+      "epoch": 0.08609865470852018,
+      "grad_norm": 0.27399342611565175,
+      "learning_rate": 1.714285714285714e-06,
+      "loss": 1.0022,
+      "step": 18
+    },
+    {
+      "epoch": 0.09088191330343796,
+      "grad_norm": 0.24537662923792491,
+      "learning_rate": 1.8095238095238095e-06,
+      "loss": 1.0272,
+      "step": 19
+    },
+    {
+      "epoch": 0.09566517189835576,
+      "grad_norm": 0.20010147123002528,
+      "learning_rate": 1.9047619047619045e-06,
+      "loss": 0.9569,
+      "step": 20
+    },
+    {
+      "epoch": 0.10044843049327354,
+      "grad_norm": 0.25587399010113915,
+      "learning_rate": 2e-06,
+      "loss": 0.9848,
+      "step": 21
+    },
+    {
+      "epoch": 0.10523168908819133,
+      "grad_norm": 0.3007962756012024,
+      "learning_rate": 1.9999686897547167e-06,
+      "loss": 0.9581,
+      "step": 22
+    },
+    {
+      "epoch": 0.11001494768310911,
+      "grad_norm": 0.3006848188189002,
+      "learning_rate": 1.9998747609795305e-06,
+      "loss": 0.9478,
+      "step": 23
+    },
+    {
+      "epoch": 0.1147982062780269,
+      "grad_norm": 0.30781981272131237,
+      "learning_rate": 1.999718219556307e-06,
+      "loss": 0.9834,
+      "step": 24
+    },
+    {
+      "epoch": 0.11958146487294469,
+      "grad_norm": 0.3118837626745979,
+      "learning_rate": 1.999499075287747e-06,
+      "loss": 0.9852,
+      "step": 25
+    },
+    {
+      "epoch": 0.12436472346786248,
+      "grad_norm": 0.26545213805928825,
+      "learning_rate": 1.999217341896772e-06,
+      "loss": 0.9549,
+      "step": 26
+    },
+    {
+      "epoch": 0.12914798206278028,
+      "grad_norm": 0.28369668711343804,
+      "learning_rate": 1.998873037025665e-06,
+      "loss": 0.9395,
+      "step": 27
+    },
+    {
+      "epoch": 0.13393124065769807,
+      "grad_norm": 0.228056096803738,
+      "learning_rate": 1.9984661822349665e-06,
+      "loss": 0.9124,
+      "step": 28
+    },
+    {
+      "epoch": 0.13871449925261584,
+      "grad_norm": 0.23393624794141885,
+      "learning_rate": 1.997996803002123e-06,
+      "loss": 0.9306,
+      "step": 29
+    },
+    {
+      "epoch": 0.14349775784753363,
+      "grad_norm": 0.20376330319941563,
+      "learning_rate": 1.9974649287198914e-06,
+      "loss": 0.8882,
+      "step": 30
+    },
+    {
+      "epoch": 0.14828101644245142,
+      "grad_norm": 0.19033042713450593,
+      "learning_rate": 1.9968705926945013e-06,
+      "loss": 0.8699,
+      "step": 31
+    },
+    {
+      "epoch": 0.15306427503736922,
+      "grad_norm": 0.20517384186395837,
+      "learning_rate": 1.9962138321435656e-06,
+      "loss": 0.8919,
+      "step": 32
+    },
+    {
+      "epoch": 0.15784753363228698,
+      "grad_norm": 0.19219397333283395,
+      "learning_rate": 1.9954946881937524e-06,
+      "loss": 0.8985,
+      "step": 33
+    },
+    {
+      "epoch": 0.16263079222720478,
+      "grad_norm": 0.18095506989716384,
+      "learning_rate": 1.994713205878208e-06,
+      "loss": 0.8504,
+      "step": 34
+    },
+    {
+      "epoch": 0.16741405082212257,
+      "grad_norm": 0.1722529909885032,
+      "learning_rate": 1.9938694341337393e-06,
+      "loss": 0.8743,
+      "step": 35
+    },
+    {
+      "epoch": 0.17219730941704037,
+      "grad_norm": 0.16508567356320156,
+      "learning_rate": 1.9929634257977467e-06,
+      "loss": 0.857,
+      "step": 36
+    },
+    {
+      "epoch": 0.17698056801195813,
+      "grad_norm": 0.15380307949646846,
+      "learning_rate": 1.991995237604916e-06,
+      "loss": 0.8487,
+      "step": 37
+    },
+    {
+      "epoch": 0.18176382660687593,
+      "grad_norm": 0.14856130486975244,
+      "learning_rate": 1.9909649301836674e-06,
+      "loss": 0.8692,
+      "step": 38
+    },
+    {
+      "epoch": 0.18654708520179372,
+      "grad_norm": 0.1518842900714723,
+      "learning_rate": 1.9898725680523566e-06,
+      "loss": 0.8679,
+      "step": 39
+    },
+    {
+      "epoch": 0.19133034379671152,
+      "grad_norm": 0.1443106182213824,
+      "learning_rate": 1.9887182196152367e-06,
+      "loss": 0.8504,
+      "step": 40
+    },
+    {
+      "epoch": 0.1961136023916293,
+      "grad_norm": 0.14664015617981188,
+      "learning_rate": 1.9875019571581726e-06,
+      "loss": 0.8125,
+      "step": 41
+    },
+    {
+      "epoch": 0.20089686098654708,
+      "grad_norm": 0.14692793192413753,
+      "learning_rate": 1.9862238568441165e-06,
+      "loss": 0.8257,
+      "step": 42
+    },
+    {
+      "epoch": 0.20568011958146487,
+      "grad_norm": 0.13896889627771705,
+      "learning_rate": 1.9848839987083364e-06,
+      "loss": 0.8329,
+      "step": 43
+    },
+    {
+      "epoch": 0.21046337817638266,
+      "grad_norm": 0.14943974659921427,
+      "learning_rate": 1.983482466653407e-06,
+      "loss": 0.8409,
+      "step": 44
+    },
+    {
+      "epoch": 0.21524663677130046,
+      "grad_norm": 0.138210028938997,
+      "learning_rate": 1.982019348443952e-06,
+      "loss": 0.8323,
+      "step": 45
+    },
+    {
+      "epoch": 0.22002989536621823,
+      "grad_norm": 0.1250406305407292,
+      "learning_rate": 1.9804947357011523e-06,
+      "loss": 0.8673,
+      "step": 46
+    },
+    {
+      "epoch": 0.22481315396113602,
+      "grad_norm": 0.12719252526959784,
+      "learning_rate": 1.978908723897005e-06,
+      "loss": 0.8192,
+      "step": 47
+    },
+    {
+      "epoch": 0.2295964125560538,
+      "grad_norm": 0.10853106729801387,
+      "learning_rate": 1.9772614123483485e-06,
+      "loss": 0.8384,
+      "step": 48
+    },
+    {
+      "epoch": 0.2343796711509716,
+      "grad_norm": 0.11375286279894396,
+      "learning_rate": 1.9755529042106393e-06,
+      "loss": 0.7854,
+      "step": 49
+    },
+    {
+      "epoch": 0.23916292974588937,
+      "grad_norm": 0.11326113932314119,
+      "learning_rate": 1.973783306471495e-06,
+      "loss": 0.795,
+      "step": 50
+    },
+    {
+      "epoch": 0.24394618834080717,
+      "grad_norm": 0.12664705711535487,
+      "learning_rate": 1.971952729943994e-06,
+      "loss": 0.783,
+      "step": 51
+    },
+    {
+      "epoch": 0.24872944693572496,
+      "grad_norm": 0.11119059988645158,
+      "learning_rate": 1.9700612892597372e-06,
+      "loss": 0.8059,
+      "step": 52
+    },
+    {
+      "epoch": 0.25351270553064276,
+      "grad_norm": 0.10545114737351395,
+      "learning_rate": 1.9681091028616676e-06,
+      "loss": 0.7885,
+      "step": 53
+    },
+    {
+      "epoch": 0.25829596412556055,
+      "grad_norm": 0.11679452392637804,
+      "learning_rate": 1.966096292996655e-06,
+      "loss": 0.8031,
+      "step": 54
+    },
+    {
+      "epoch": 0.26307922272047835,
+      "grad_norm": 0.11363287552532539,
+      "learning_rate": 1.9640229857078413e-06,
+      "loss": 0.7774,
+      "step": 55
+    },
+    {
+      "epoch": 0.26786248131539614,
+      "grad_norm": 0.1164225509000403,
+      "learning_rate": 1.9618893108267454e-06,
+      "loss": 0.7949,
+      "step": 56
+    },
+    {
+      "epoch": 0.2726457399103139,
+      "grad_norm": 0.11077425052933487,
+      "learning_rate": 1.9596954019651354e-06,
+      "loss": 0.7674,
+      "step": 57
+    },
+    {
+      "epoch": 0.27742899850523167,
+      "grad_norm": 0.10576177825898277,
+      "learning_rate": 1.95744139650666e-06,
+      "loss": 0.7953,
+      "step": 58
+    },
+    {
+      "epoch": 0.28221225710014947,
+      "grad_norm": 0.10359885133841641,
+      "learning_rate": 1.955127435598247e-06,
+      "loss": 0.7881,
+      "step": 59
+    },
+    {
+      "epoch": 0.28699551569506726,
+      "grad_norm": 0.10586032252156977,
+      "learning_rate": 1.9527536641412637e-06,
+      "loss": 0.7984,
+      "step": 60
+    },
+    {
+      "epoch": 0.29177877428998505,
+      "grad_norm": 0.10642116844371083,
+      "learning_rate": 1.950320230782443e-06,
+      "loss": 0.7666,
+      "step": 61
+    },
+    {
+      "epoch": 0.29656203288490285,
+      "grad_norm": 0.11202675632435576,
+      "learning_rate": 1.9478272879045763e-06,
+      "loss": 0.7809,
+      "step": 62
+    },
+    {
+      "epoch": 0.30134529147982064,
+      "grad_norm": 0.10728322195233368,
+      "learning_rate": 1.9452749916169685e-06,
+      "loss": 0.7948,
+      "step": 63
+    },
+    {
+      "epoch": 0.30612855007473844,
+      "grad_norm": 0.10427886124668943,
+      "learning_rate": 1.942663501745666e-06,
+      "loss": 0.7843,
+      "step": 64
+    },
+    {
+      "epoch": 0.3109118086696562,
+      "grad_norm": 0.09150641957182463,
+      "learning_rate": 1.939992981823445e-06,
+      "loss": 0.7713,
+      "step": 65
+    },
+    {
+      "epoch": 0.31569506726457397,
+      "grad_norm": 0.10652939965487439,
+      "learning_rate": 1.9372635990795744e-06,
+      "loss": 0.7338,
+      "step": 66
+    },
+    {
+      "epoch": 0.32047832585949176,
+      "grad_norm": 0.12224668990837938,
+      "learning_rate": 1.934475524429339e-06,
+      "loss": 0.7651,
+      "step": 67
+    },
+    {
+      "epoch": 0.32526158445440956,
+      "grad_norm": 0.09554788331952155,
+      "learning_rate": 1.9316289324633416e-06,
+      "loss": 0.7743,
+      "step": 68
+    },
+    {
+      "epoch": 0.33004484304932735,
+      "grad_norm": 0.10311314948775388,
+      "learning_rate": 1.928724001436568e-06,
+      "loss": 0.7818,
+      "step": 69
+    },
+    {
+      "epoch": 0.33482810164424515,
+      "grad_norm": 0.11402809897006772,
+      "learning_rate": 1.925760913257224e-06,
+      "loss": 0.7738,
+      "step": 70
+    },
+    {
+      "epoch": 0.33961136023916294,
+      "grad_norm": 0.10099702778225672,
+      "learning_rate": 1.922739853475345e-06,
+      "loss": 0.7694,
+      "step": 71
+    },
+    {
+      "epoch": 0.34439461883408073,
+      "grad_norm": 0.09669133625846159,
+      "learning_rate": 1.919661011271176e-06,
+      "loss": 0.7695,
+      "step": 72
+    },
+    {
+      "epoch": 0.34917787742899853,
+      "grad_norm": 0.10013746372306316,
+      "learning_rate": 1.916524579443327e-06,
+      "loss": 0.7762,
+      "step": 73
+    },
+    {
+      "epoch": 0.35396113602391627,
+      "grad_norm": 0.09840254254939616,
+      "learning_rate": 1.9133307543966972e-06,
+      "loss": 0.7465,
+      "step": 74
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.10348087475535427,
+      "learning_rate": 1.910079736130178e-06,
+      "loss": 0.7591,
+      "step": 75
+    },
+    {
+      "epoch": 0.36352765321375186,
+      "grad_norm": 0.09831488128647803,
+      "learning_rate": 1.9067717282241275e-06,
+      "loss": 0.7473,
+      "step": 76
+    },
+    {
+      "epoch": 0.36831091180866965,
+      "grad_norm": 0.10747256347092367,
+      "learning_rate": 1.9034069378276248e-06,
+      "loss": 0.7899,
+      "step": 77
+    },
+    {
+      "epoch": 0.37309417040358744,
+      "grad_norm": 0.10145726153107046,
+      "learning_rate": 1.8999855756454943e-06,
+      "loss": 0.759,
+      "step": 78
+    },
+    {
+      "epoch": 0.37787742899850524,
+      "grad_norm": 0.09521749859691808,
+      "learning_rate": 1.8965078559251141e-06,
+      "loss": 0.765,
+      "step": 79
+    },
+    {
+      "epoch": 0.38266068759342303,
+      "grad_norm": 0.09559204768504546,
+      "learning_rate": 1.892973996443e-06,
+      "loss": 0.7653,
+      "step": 80
+    },
+    {
+      "epoch": 0.3874439461883408,
+      "grad_norm": 0.09893961689958143,
+      "learning_rate": 1.8893842184911652e-06,
+      "loss": 0.7585,
+      "step": 81
+    },
+    {
+      "epoch": 0.3922272047832586,
+      "grad_norm": 0.10469293200053865,
+      "learning_rate": 1.8857387468632673e-06,
+      "loss": 0.7396,
+      "step": 82
+    },
+    {
+      "epoch": 0.39701046337817636,
+      "grad_norm": 0.09881168266263542,
+      "learning_rate": 1.8820378098405269e-06,
+      "loss": 0.7449,
+      "step": 83
+    },
+    {
+      "epoch": 0.40179372197309415,
+      "grad_norm": 0.09472923155314936,
+      "learning_rate": 1.878281639177437e-06,
+      "loss": 0.7536,
+      "step": 84
+    },
+    {
+      "epoch": 0.40657698056801195,
+      "grad_norm": 0.09940252508830999,
+      "learning_rate": 1.874470470087246e-06,
+      "loss": 0.7695,
+      "step": 85
+    },
+    {
+      "epoch": 0.41136023916292974,
+      "grad_norm": 0.10835992130612712,
+      "learning_rate": 1.8706045412272329e-06,
+      "loss": 0.7804,
+      "step": 86
+    },
+    {
+      "epoch": 0.41614349775784754,
+      "grad_norm": 0.09850260645852206,
+      "learning_rate": 1.8666840946837588e-06,
+      "loss": 0.7581,
+      "step": 87
+    },
+    {
+      "epoch": 0.42092675635276533,
+      "grad_norm": 0.10663807706116737,
+      "learning_rate": 1.8627093759571097e-06,
+      "loss": 0.7486,
+      "step": 88
+    },
+    {
+      "epoch": 0.4257100149476831,
+      "grad_norm": 0.09576966700987803,
+      "learning_rate": 1.8586806339461223e-06,
+      "loss": 0.7393,
+      "step": 89
+    },
+    {
+      "epoch": 0.4304932735426009,
+      "grad_norm": 0.13616509255793824,
+      "learning_rate": 1.8545981209325974e-06,
+      "loss": 0.7412,
+      "step": 90
+    },
+    {
+      "epoch": 0.43527653213751866,
+      "grad_norm": 0.10078747049635026,
+      "learning_rate": 1.850462092565503e-06,
+      "loss": 0.7522,
+      "step": 91
+    },
+    {
+      "epoch": 0.44005979073243645,
+      "grad_norm": 0.09590506182617801,
+      "learning_rate": 1.846272807844964e-06,
+      "loss": 0.7361,
+      "step": 92
+    },
+    {
+      "epoch": 0.44484304932735425,
+      "grad_norm": 0.09599938671410663,
+      "learning_rate": 1.8420305291060453e-06,
+      "loss": 0.7454,
+      "step": 93
+    },
+    {
+      "epoch": 0.44962630792227204,
+      "grad_norm": 0.10175459960116054,
+      "learning_rate": 1.837735522002322e-06,
+      "loss": 0.7776,
+      "step": 94
+    },
+    {
+      "epoch": 0.45440956651718983,
+      "grad_norm": 0.10921604960602464,
+      "learning_rate": 1.8333880554892465e-06,
+      "loss": 0.7284,
+      "step": 95
+    },
+    {
+      "epoch": 0.4591928251121076,
+      "grad_norm": 0.10701793438795469,
+      "learning_rate": 1.828988401807304e-06,
+      "loss": 0.7275,
+      "step": 96
+    },
+    {
+      "epoch": 0.4639760837070254,
+      "grad_norm": 0.10671158442373065,
+      "learning_rate": 1.8245368364649672e-06,
+      "loss": 0.7176,
+      "step": 97
+    },
+    {
+      "epoch": 0.4687593423019432,
+      "grad_norm": 0.09323865008012455,
+      "learning_rate": 1.8200336382214404e-06,
+      "loss": 0.7558,
+      "step": 98
+    },
+    {
+      "epoch": 0.473542600896861,
+      "grad_norm": 0.09924243426975013,
+      "learning_rate": 1.815479089069208e-06,
+      "loss": 0.7477,
+      "step": 99
+    },
+    {
+      "epoch": 0.47832585949177875,
+      "grad_norm": 0.10034019533981096,
+      "learning_rate": 1.8108734742163714e-06,
+      "loss": 0.7302,
+      "step": 100
+    },
+    {
+      "epoch": 0.48310911808669654,
+      "grad_norm": 0.09289950458176202,
+      "learning_rate": 1.8062170820687923e-06,
+      "loss": 0.7461,
+      "step": 101
+    },
+    {
+      "epoch": 0.48789237668161434,
+      "grad_norm": 0.10063821105969947,
+      "learning_rate": 1.8015102042120314e-06,
+      "loss": 0.7374,
+      "step": 102
+    },
+    {
+      "epoch": 0.49267563527653213,
+      "grad_norm": 0.10431764482912426,
+      "learning_rate": 1.796753135393089e-06,
+      "loss": 0.753,
+      "step": 103
+    },
+    {
+      "epoch": 0.4974588938714499,
+      "grad_norm": 0.09777703419526715,
+      "learning_rate": 1.791946173501948e-06,
+      "loss": 0.7172,
+      "step": 104
+    },
+    {
+      "epoch": 0.5022421524663677,
+      "grad_norm": 0.09880039694565383,
+      "learning_rate": 1.7870896195529204e-06,
+      "loss": 0.7157,
+      "step": 105
+    },
+    {
+      "epoch": 0.5070254110612855,
+      "grad_norm": 0.10103523012523379,
+      "learning_rate": 1.7821837776657967e-06,
+      "loss": 0.7522,
+      "step": 106
+    },
+    {
+      "epoch": 0.5118086696562033,
+      "grad_norm": 0.09953632352625874,
+      "learning_rate": 1.777228955046803e-06,
+      "loss": 0.7215,
+      "step": 107
+    },
+    {
+      "epoch": 0.5165919282511211,
+      "grad_norm": 0.09448842637214858,
+      "learning_rate": 1.7722254619693617e-06,
+      "loss": 0.7311,
+      "step": 108
+    },
+    {
+      "epoch": 0.5213751868460389,
+      "grad_norm": 0.09926544596139777,
+      "learning_rate": 1.7671736117546643e-06,
+      "loss": 0.7242,
+      "step": 109
+    },
+    {
+      "epoch": 0.5261584454409567,
+      "grad_norm": 0.09420983432319698,
+      "learning_rate": 1.7620737207520498e-06,
+      "loss": 0.7302,
+      "step": 110
+    },
+    {
+      "epoch": 0.5309417040358745,
+      "grad_norm": 0.09391867567605319,
+      "learning_rate": 1.756926108319194e-06,
+      "loss": 0.7222,
+      "step": 111
+    },
+    {
+      "epoch": 0.5357249626307923,
+      "grad_norm": 0.09479652603956866,
+      "learning_rate": 1.751731096802113e-06,
+      "loss": 0.7361,
+      "step": 112
+    },
+    {
+      "epoch": 0.54050822122571,
+      "grad_norm": 0.09440230389077435,
+      "learning_rate": 1.7464890115149759e-06,
+      "loss": 0.7183,
+      "step": 113
+    },
+    {
+      "epoch": 0.5452914798206278,
+      "grad_norm": 0.09514244364363002,
+      "learning_rate": 1.7412001807197361e-06,
+      "loss": 0.7342,
+      "step": 114
+    },
+    {
+      "epoch": 0.5500747384155455,
+      "grad_norm": 0.10939831006494534,
+      "learning_rate": 1.735864935605572e-06,
+      "loss": 0.7251,
+      "step": 115
+    },
+    {
+      "epoch": 0.5548579970104633,
+      "grad_norm": 0.10066676165355973,
+      "learning_rate": 1.7304836102681493e-06,
+      "loss": 0.7081,
+      "step": 116
+    },
+    {
+      "epoch": 0.5596412556053811,
+      "grad_norm": 0.10100361164339053,
+      "learning_rate": 1.7250565416887015e-06,
+      "loss": 0.742,
+      "step": 117
+    },
+    {
+      "epoch": 0.5644245142002989,
+      "grad_norm": 0.09740229601345607,
+      "learning_rate": 1.719584069712925e-06,
+      "loss": 0.7314,
+      "step": 118
+    },
+    {
+      "epoch": 0.5692077727952167,
+      "grad_norm": 0.1012821496567702,
+      "learning_rate": 1.7140665370296992e-06,
+      "loss": 0.7167,
+      "step": 119
+    },
+    {
+      "epoch": 0.5739910313901345,
+      "grad_norm": 0.09994075838359362,
+      "learning_rate": 1.708504289149628e-06,
+      "loss": 0.7421,
+      "step": 120
+    },
+    {
+      "epoch": 0.5787742899850523,
+      "grad_norm": 0.09513046173828367,
+      "learning_rate": 1.702897674383402e-06,
+      "loss": 0.7067,
+      "step": 121
+    },
+    {
+      "epoch": 0.5835575485799701,
+      "grad_norm": 0.10488877885042427,
+      "learning_rate": 1.697247043819988e-06,
+      "loss": 0.7283,
+      "step": 122
+    },
+    {
+      "epoch": 0.5883408071748879,
+      "grad_norm": 0.10017563354892535,
+      "learning_rate": 1.6915527513046443e-06,
+      "loss": 0.7289,
+      "step": 123
+    },
+    {
+      "epoch": 0.5931240657698057,
+      "grad_norm": 0.09910676006320021,
+      "learning_rate": 1.6858151534167616e-06,
+      "loss": 0.7258,
+      "step": 124
+    },
+    {
+      "epoch": 0.5979073243647235,
+      "grad_norm": 0.10226756484228856,
+      "learning_rate": 1.6800346094475346e-06,
+      "loss": 0.7294,
+      "step": 125
+    },
+    {
+      "epoch": 0.6026905829596413,
+      "grad_norm": 0.0941277312513867,
+      "learning_rate": 1.6742114813774618e-06,
+      "loss": 0.7059,
+      "step": 126
+    },
+    {
+      "epoch": 0.6074738415545591,
+      "grad_norm": 0.10468386708851042,
+      "learning_rate": 1.6683461338536798e-06,
+      "loss": 0.76,
+      "step": 127
+    },
+    {
+      "epoch": 0.6122571001494769,
+      "grad_norm": 0.09546912003315239,
+      "learning_rate": 1.6624389341671278e-06,
+      "loss": 0.7199,
+      "step": 128
+    },
+    {
+      "epoch": 0.6170403587443947,
+      "grad_norm": 0.09278710008849092,
+      "learning_rate": 1.656490252229548e-06,
+      "loss": 0.71,
+      "step": 129
+    },
+    {
+      "epoch": 0.6218236173393124,
+      "grad_norm": 0.09629578223078193,
+      "learning_rate": 1.6505004605503223e-06,
+      "loss": 0.7297,
+      "step": 130
+    },
+    {
+      "epoch": 0.6266068759342301,
+      "grad_norm": 0.10564515959559177,
+      "learning_rate": 1.6444699342131428e-06,
+      "loss": 0.7323,
+      "step": 131
+    },
+    {
+      "epoch": 0.6313901345291479,
+      "grad_norm": 0.11359024419098725,
+      "learning_rate": 1.638399050852528e-06,
+      "loss": 0.7091,
+      "step": 132
+    },
+    {
+      "epoch": 0.6361733931240657,
+      "grad_norm": 0.11261022540293862,
+      "learning_rate": 1.632288190630172e-06,
+      "loss": 0.7092,
+      "step": 133
+    },
+    {
+      "epoch": 0.6409566517189835,
+      "grad_norm": 0.11356374624941931,
+      "learning_rate": 1.6261377362111396e-06,
+      "loss": 0.7226,
+      "step": 134
+    },
+    {
+      "epoch": 0.6457399103139013,
+      "grad_norm": 0.09628738165774237,
+      "learning_rate": 1.6199480727399032e-06,
+      "loss": 0.7313,
+      "step": 135
+    },
+    {
+      "epoch": 0.6505231689088191,
+      "grad_norm": 0.09955265729242128,
+      "learning_rate": 1.6137195878162267e-06,
+      "loss": 0.7264,
+      "step": 136
+    },
+    {
+      "epoch": 0.6553064275037369,
+      "grad_norm": 0.10088157860044299,
+      "learning_rate": 1.607452671470891e-06,
+      "loss": 0.72,
+      "step": 137
+    },
+    {
+      "epoch": 0.6600896860986547,
+      "grad_norm": 0.09316854100471951,
+      "learning_rate": 1.601147716141272e-06,
+      "loss": 0.7043,
+      "step": 138
+    },
+    {
+      "epoch": 0.6648729446935725,
+      "grad_norm": 0.09866104920600266,
+      "learning_rate": 1.5948051166467657e-06,
+      "loss": 0.7314,
+      "step": 139
+    },
+    {
+      "epoch": 0.6696562032884903,
+      "grad_norm": 0.09908667617176863,
+      "learning_rate": 1.5884252701640634e-06,
+      "loss": 0.7223,
+      "step": 140
+    },
+    {
+      "epoch": 0.6744394618834081,
+      "grad_norm": 0.10108043693556777,
+      "learning_rate": 1.5820085762022823e-06,
+      "loss": 0.7145,
+      "step": 141
+    },
+    {
+      "epoch": 0.6792227204783259,
+      "grad_norm": 0.09483321797525981,
+      "learning_rate": 1.5755554365779455e-06,
+      "loss": 0.712,
+      "step": 142
+    },
+    {
+      "epoch": 0.6840059790732437,
+      "grad_norm": 0.09772063438530315,
+      "learning_rate": 1.5690662553898222e-06,
+      "loss": 0.7262,
+      "step": 143
+    },
+    {
+      "epoch": 0.6887892376681615,
+      "grad_norm": 0.09547210509162248,
+      "learning_rate": 1.5625414389936218e-06,
+      "loss": 0.6881,
+      "step": 144
+    },
+    {
+      "epoch": 0.6935724962630793,
+      "grad_norm": 0.10198333563773951,
+      "learning_rate": 1.555981395976548e-06,
+      "loss": 0.7023,
+      "step": 145
+    },
+    {
+      "epoch": 0.6983557548579971,
+      "grad_norm": 0.0960216671080163,
+      "learning_rate": 1.5493865371317123e-06,
+      "loss": 0.7041,
+      "step": 146
+    },
+    {
+      "epoch": 0.7031390134529149,
+      "grad_norm": 0.10811878950887173,
+      "learning_rate": 1.542757275432411e-06,
+      "loss": 0.7121,
+      "step": 147
+    },
+    {
+      "epoch": 0.7079222720478325,
+      "grad_norm": 0.09745342759060693,
+      "learning_rate": 1.5360940260062635e-06,
+      "loss": 0.7,
+      "step": 148
+    },
+    {
+      "epoch": 0.7127055306427503,
+      "grad_norm": 0.10002068890855158,
+      "learning_rate": 1.5293972061092185e-06,
+      "loss": 0.7174,
+      "step": 149
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.094440761646848,
+      "learning_rate": 1.522667235099422e-06,
+      "loss": 0.6842,
+      "step": 150
+    },
+    {
+      "epoch": 0.7222720478325859,
+      "grad_norm": 0.09714805521617614,
+      "learning_rate": 1.515904534410961e-06,
+      "loss": 0.6917,
+      "step": 151
+    },
+    {
+      "epoch": 0.7270553064275037,
+      "grad_norm": 0.09206634939711936,
+      "learning_rate": 1.5091095275274699e-06,
+      "loss": 0.6807,
+      "step": 152
+    },
+    {
+      "epoch": 0.7318385650224215,
+      "grad_norm": 0.09811924963451824,
+      "learning_rate": 1.5022826399556133e-06,
+      "loss": 0.6938,
+      "step": 153
+    },
+    {
+      "epoch": 0.7366218236173393,
+      "grad_norm": 0.09469018906462104,
+      "learning_rate": 1.4954242991984396e-06,
+      "loss": 0.7262,
+      "step": 154
+    },
+    {
+      "epoch": 0.7414050822122571,
+      "grad_norm": 0.09900495842570976,
+      "learning_rate": 1.4885349347286115e-06,
+      "loss": 0.6928,
+      "step": 155
+    },
+    {
+      "epoch": 0.7461883408071749,
+      "grad_norm": 0.09813499443182924,
+      "learning_rate": 1.4816149779615126e-06,
+      "loss": 0.7041,
+      "step": 156
+    },
+    {
+      "epoch": 0.7509715994020927,
+      "grad_norm": 0.09285509032551069,
+      "learning_rate": 1.474664862228229e-06,
+      "loss": 0.7157,
+      "step": 157
+    },
+    {
+      "epoch": 0.7557548579970105,
+      "grad_norm": 0.09930227957877516,
+      "learning_rate": 1.467685022748419e-06,
+      "loss": 0.7077,
+      "step": 158
+    },
+    {
+      "epoch": 0.7605381165919283,
+      "grad_norm": 0.09336816965151891,
+      "learning_rate": 1.4606758966030534e-06,
+      "loss": 0.6905,
+      "step": 159
+    },
+    {
+      "epoch": 0.7653213751868461,
+      "grad_norm": 0.09584860785157516,
+      "learning_rate": 1.4536379227070509e-06,
+      "loss": 0.704,
+      "step": 160
+    },
+    {
+      "epoch": 0.7701046337817639,
+      "grad_norm": 0.09906164552724124,
+      "learning_rate": 1.4465715417817888e-06,
+      "loss": 0.7014,
+      "step": 161
+    },
+    {
+      "epoch": 0.7748878923766817,
+      "grad_norm": 0.09920929186360831,
+      "learning_rate": 1.4394771963275076e-06,
+      "loss": 0.6711,
+      "step": 162
+    },
+    {
+      "epoch": 0.7796711509715994,
+      "grad_norm": 0.09312914704123235,
+      "learning_rate": 1.4323553305955997e-06,
+      "loss": 0.704,
+      "step": 163
+    },
+    {
+      "epoch": 0.7844544095665172,
+      "grad_norm": 0.09380001375870357,
+      "learning_rate": 1.4252063905607909e-06,
+      "loss": 0.6769,
+      "step": 164
+    },
+    {
+      "epoch": 0.7892376681614349,
+      "grad_norm": 0.09383108087011895,
+      "learning_rate": 1.4180308238932135e-06,
+      "loss": 0.6903,
+      "step": 165
+    },
+    {
+      "epoch": 0.7940209267563527,
+      "grad_norm": 0.09761627284743495,
+      "learning_rate": 1.410829079930372e-06,
+      "loss": 0.7126,
+      "step": 166
+    },
+    {
+      "epoch": 0.7988041853512705,
+      "grad_norm": 0.09591926993818495,
+      "learning_rate": 1.4036016096490064e-06,
+      "loss": 0.6936,
+      "step": 167
+    },
+    {
+      "epoch": 0.8035874439461883,
+      "grad_norm": 0.09463907898930997,
+      "learning_rate": 1.3963488656368517e-06,
+      "loss": 0.6918,
+      "step": 168
+    },
+    {
+      "epoch": 0.8083707025411061,
+      "grad_norm": 0.10314575539858357,
+      "learning_rate": 1.389071302064295e-06,
+      "loss": 0.6837,
+      "step": 169
+    },
+    {
+      "epoch": 0.8131539611360239,
+      "grad_norm": 0.0964154089668258,
+      "learning_rate": 1.381769374655938e-06,
+      "loss": 0.7087,
+      "step": 170
+    },
+    {
+      "epoch": 0.8179372197309417,
+      "grad_norm": 0.10458955759891816,
+      "learning_rate": 1.374443540662057e-06,
+      "loss": 0.7132,
+      "step": 171
+    },
+    {
+      "epoch": 0.8227204783258595,
+      "grad_norm": 0.11118113052583456,
+      "learning_rate": 1.3670942588299705e-06,
+      "loss": 0.689,
+      "step": 172
+    },
+    {
+      "epoch": 0.8275037369207773,
+      "grad_norm": 0.09430050647819165,
+      "learning_rate": 1.3597219893753117e-06,
+      "loss": 0.6669,
+      "step": 173
+    },
+    {
+      "epoch": 0.8322869955156951,
+      "grad_norm": 0.10018122520539552,
+      "learning_rate": 1.352327193953211e-06,
+      "loss": 0.675,
+      "step": 174
+    },
+    {
+      "epoch": 0.8370702541106129,
+      "grad_norm": 0.1036112926787395,
+      "learning_rate": 1.3449103356293852e-06,
+      "loss": 0.7151,
+      "step": 175
+    },
+    {
+      "epoch": 0.8418535127055307,
+      "grad_norm": 0.09652117392718416,
+      "learning_rate": 1.337471878851141e-06,
+      "loss": 0.6819,
+      "step": 176
+    },
+    {
+      "epoch": 0.8466367713004485,
+      "grad_norm": 0.11467070226240633,
+      "learning_rate": 1.3300122894182909e-06,
+      "loss": 0.7063,
+      "step": 177
+    },
+    {
+      "epoch": 0.8514200298953662,
+      "grad_norm": 0.0974406950357686,
+      "learning_rate": 1.3225320344539842e-06,
+      "loss": 0.7154,
+      "step": 178
+    },
+    {
+      "epoch": 0.856203288490284,
+      "grad_norm": 0.10056923973958724,
+      "learning_rate": 1.315031582375457e-06,
+      "loss": 0.7119,
+      "step": 179
+    },
+    {
+      "epoch": 0.8609865470852018,
+      "grad_norm": 0.10289512917324216,
+      "learning_rate": 1.3075114028646974e-06,
+      "loss": 0.6872,
+      "step": 180
+    },
+    {
+      "epoch": 0.8657698056801196,
+      "grad_norm": 0.10284996024746469,
+      "learning_rate": 1.299971966839036e-06,
+      "loss": 0.6995,
+      "step": 181
+    },
+    {
+      "epoch": 0.8705530642750373,
+      "grad_norm": 0.09442402879665361,
+      "learning_rate": 1.292413746421655e-06,
+      "loss": 0.6788,
+      "step": 182
+    },
+    {
+      "epoch": 0.8753363228699551,
+      "grad_norm": 0.09221585066528634,
+      "learning_rate": 1.2848372149120246e-06,
+      "loss": 0.6625,
+      "step": 183
+    },
+    {
+      "epoch": 0.8801195814648729,
+      "grad_norm": 0.09614590670948946,
+      "learning_rate": 1.2772428467562651e-06,
+      "loss": 0.6993,
+      "step": 184
+    },
+    {
+      "epoch": 0.8849028400597907,
+      "grad_norm": 0.09884964743533457,
+      "learning_rate": 1.2696311175174357e-06,
+      "loss": 0.6826,
+      "step": 185
+    },
+    {
+      "epoch": 0.8896860986547085,
+      "grad_norm": 0.10049262287084837,
+      "learning_rate": 1.2620025038457554e-06,
+      "loss": 0.6875,
+      "step": 186
+    },
+    {
+      "epoch": 0.8944693572496263,
+      "grad_norm": 0.0951319815934962,
+      "learning_rate": 1.254357483448755e-06,
+      "loss": 0.6763,
+      "step": 187
+    },
+    {
+      "epoch": 0.8992526158445441,
+      "grad_norm": 0.0935897850203258,
+      "learning_rate": 1.2466965350613615e-06,
+      "loss": 0.7191,
+      "step": 188
+    },
+    {
+      "epoch": 0.9040358744394619,
+      "grad_norm": 0.10488228598924217,
+      "learning_rate": 1.2390201384159219e-06,
+      "loss": 0.7031,
+      "step": 189
+    },
+    {
+      "epoch": 0.9088191330343797,
+      "grad_norm": 0.09803611282531831,
+      "learning_rate": 1.231328774212159e-06,
+      "loss": 0.6596,
+      "step": 190
+    },
+    {
+      "epoch": 0.9136023916292975,
+      "grad_norm": 0.10982924572402691,
+      "learning_rate": 1.223622924087073e-06,
+      "loss": 0.685,
+      "step": 191
+    },
+    {
+      "epoch": 0.9183856502242153,
+      "grad_norm": 0.0990057467989385,
+      "learning_rate": 1.215903070584779e-06,
+      "loss": 0.6905,
+      "step": 192
+    },
+    {
+      "epoch": 0.923168908819133,
+      "grad_norm": 0.09806799076875558,
+      "learning_rate": 1.2081696971262903e-06,
+      "loss": 0.6888,
+      "step": 193
+    },
+    {
+      "epoch": 0.9279521674140508,
+      "grad_norm": 0.09725950749183558,
+      "learning_rate": 1.2004232879792464e-06,
+      "loss": 0.6897,
+      "step": 194
+    },
+    {
+      "epoch": 0.9327354260089686,
+      "grad_norm": 0.09998658118754998,
+      "learning_rate": 1.1926643282275882e-06,
+      "loss": 0.6808,
+      "step": 195
+    },
+    {
+      "epoch": 0.9375186846038864,
+      "grad_norm": 0.09991311679692257,
+      "learning_rate": 1.1848933037411825e-06,
+      "loss": 0.6721,
+      "step": 196
+    },
+    {
+      "epoch": 0.9423019431988042,
+      "grad_norm": 0.09570773453199784,
+      "learning_rate": 1.1771107011453933e-06,
+      "loss": 0.6943,
+      "step": 197
+    },
+    {
+      "epoch": 0.947085201793722,
+      "grad_norm": 0.09891331359398514,
+      "learning_rate": 1.1693170077906143e-06,
+      "loss": 0.6989,
+      "step": 198
+    },
+    {
+      "epoch": 0.9518684603886398,
+      "grad_norm": 0.09162536810525922,
+      "learning_rate": 1.1615127117217463e-06,
+      "loss": 0.6705,
+      "step": 199
+    },
+    {
+      "epoch": 0.9566517189835575,
+      "grad_norm": 0.08903988395053124,
+      "learning_rate": 1.1536983016476373e-06,
+      "loss": 0.679,
+      "step": 200
+    },
+    {
+      "epoch": 0.9614349775784753,
+      "grad_norm": 0.09042806424104788,
+      "learning_rate": 1.1458742669104803e-06,
+      "loss": 0.6652,
+      "step": 201
+    },
+    {
+      "epoch": 0.9662182361733931,
+      "grad_norm": 0.10347050843667145,
+      "learning_rate": 1.1380410974551682e-06,
+      "loss": 0.6891,
+      "step": 202
+    },
+    {
+      "epoch": 0.9710014947683109,
+      "grad_norm": 0.0937785288147842,
+      "learning_rate": 1.130199283798615e-06,
+      "loss": 0.662,
+      "step": 203
+    },
+    {
+      "epoch": 0.9757847533632287,
+      "grad_norm": 0.10125646071292,
+      "learning_rate": 1.1223493169990391e-06,
+      "loss": 0.6857,
+      "step": 204
+    },
+    {
+      "epoch": 0.9805680119581465,
+      "grad_norm": 0.09552098120941739,
+      "learning_rate": 1.1144916886252124e-06,
+      "loss": 0.6693,
+      "step": 205
+    },
+    {
+      "epoch": 0.9853512705530643,
+      "grad_norm": 0.0939464203547695,
+      "learning_rate": 1.1066268907256782e-06,
+      "loss": 0.689,
+      "step": 206
+    },
+    {
+      "epoch": 0.9901345291479821,
+      "grad_norm": 0.1083244661837491,
+      "learning_rate": 1.098755415797939e-06,
+      "loss": 0.6795,
+      "step": 207
+    },
+    {
+      "epoch": 0.9949177877428999,
+      "grad_norm": 0.09671011359258122,
+      "learning_rate": 1.0908777567576168e-06,
+      "loss": 0.697,
+      "step": 208
+    },
+    {
+      "epoch": 0.9997010463378176,
+      "grad_norm": 0.09491067631505212,
+      "learning_rate": 1.0829944069075847e-06,
+      "loss": 0.6913,
+      "step": 209
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.09491067631505212,
+      "learning_rate": 1.0751058599070781e-06,
+      "loss": 0.0398,
+      "step": 210
+    },
+    {
+      "epoch": 1.0047832585949177,
+      "grad_norm": 0.09568291564665689,
+      "learning_rate": 1.0672126097407795e-06,
+      "loss": 0.6558,
+      "step": 211
+    },
+    {
+      "epoch": 1.0095665171898356,
+      "grad_norm": 0.0890899262566247,
+      "learning_rate": 1.0593151506878865e-06,
+      "loss": 0.6742,
+      "step": 212
+    },
+    {
+      "epoch": 1.0143497757847533,
+      "grad_norm": 0.08951496407842846,
+      "learning_rate": 1.0514139772911597e-06,
+      "loss": 0.6589,
+      "step": 213
+    },
+    {
+      "epoch": 1.0191330343796712,
+      "grad_norm": 0.09303979677050327,
+      "learning_rate": 1.043509584325953e-06,
+      "loss": 0.6526,
+      "step": 214
+    },
+    {
+      "epoch": 1.0239162929745889,
+      "grad_norm": 0.10551892280989528,
+      "learning_rate": 1.0356024667692314e-06,
+      "loss": 0.6849,
+      "step": 215
+    },
+    {
+      "epoch": 1.0286995515695068,
+      "grad_norm": 0.10560698057117009,
+      "learning_rate": 1.0276931197685753e-06,
+      "loss": 0.6947,
+      "step": 216
+    },
+    {
+      "epoch": 1.0334828101644244,
+      "grad_norm": 0.09055248425609617,
+      "learning_rate": 1.0197820386111737e-06,
+      "loss": 0.6692,
+      "step": 217
+    },
+    {
+      "epoch": 1.0382660687593424,
+      "grad_norm": 0.08952534903326591,
+      "learning_rate": 1.0118697186928105e-06,
+      "loss": 0.6481,
+      "step": 218
+    },
+    {
+      "epoch": 1.04304932735426,
+      "grad_norm": 0.0949207133753394,
+      "learning_rate": 1.0039566554868392e-06,
+      "loss": 0.6561,
+      "step": 219
+    },
+    {
+      "epoch": 1.047832585949178,
+      "grad_norm": 0.09247582314260705,
+      "learning_rate": 9.960433445131607e-07,
+      "loss": 0.6727,
+      "step": 220
+    },
+    {
+      "epoch": 1.0526158445440956,
+      "grad_norm": 0.0922431854223743,
+      "learning_rate": 9.881302813071896e-07,
+      "loss": 0.6786,
+      "step": 221
+    },
+    {
+      "epoch": 1.0573991031390135,
+      "grad_norm": 0.09921340856730206,
+      "learning_rate": 9.802179613888262e-07,
+      "loss": 0.6492,
+      "step": 222
+    },
+    {
+      "epoch": 1.0621823617339312,
+      "grad_norm": 0.09405904196612806,
+      "learning_rate": 9.723068802314246e-07,
+      "loss": 0.6435,
+      "step": 223
+    },
+    {
+      "epoch": 1.0669656203288491,
+      "grad_norm": 0.10252064804861775,
+      "learning_rate": 9.643975332307687e-07,
+      "loss": 0.6693,
+      "step": 224
+    },
+    {
+      "epoch": 1.0717488789237668,
+      "grad_norm": 0.09137882604103069,
+      "learning_rate": 9.564904156740471e-07,
+      "loss": 0.6554,
+      "step": 225
+    },
+    {
+      "epoch": 1.0765321375186847,
+      "grad_norm": 0.09506143141231545,
+      "learning_rate": 9.485860227088405e-07,
+      "loss": 0.6524,
+      "step": 226
+    },
+    {
+      "epoch": 1.0813153961136024,
+      "grad_norm": 0.09471266291722098,
+      "learning_rate": 9.406848493121134e-07,
+      "loss": 0.6598,
+      "step": 227
+    },
+    {
+      "epoch": 1.08609865470852,
+      "grad_norm": 0.09374158444399681,
+      "learning_rate": 9.327873902592205e-07,
+      "loss": 0.6546,
+      "step": 228
+    },
+    {
+      "epoch": 1.090881913303438,
+      "grad_norm": 0.0988485463507574,
+      "learning_rate": 9.248941400929222e-07,
+      "loss": 0.6659,
+      "step": 229
+    },
+    {
+      "epoch": 1.0956651718983557,
+      "grad_norm": 0.09989186431558944,
+      "learning_rate": 9.17005593092415e-07,
+      "loss": 0.6789,
+      "step": 230
+    },
+    {
+      "epoch": 1.1004484304932736,
+      "grad_norm": 0.09577210416129449,
+      "learning_rate": 9.09122243242383e-07,
+      "loss": 0.6395,
+      "step": 231
+    },
+    {
+      "epoch": 1.1052316890881912,
+      "grad_norm": 0.09417460653116495,
+      "learning_rate": 9.01244584202061e-07,
+      "loss": 0.6351,
+      "step": 232
+    },
+    {
+      "epoch": 1.1100149476831092,
+      "grad_norm": 0.1060296134876217,
+      "learning_rate": 8.933731092743219e-07,
+      "loss": 0.6843,
+      "step": 233
+    },
+    {
+      "epoch": 1.1147982062780268,
+      "grad_norm": 0.1015156854708665,
+      "learning_rate": 8.855083113747875e-07,
+      "loss": 0.6533,
+      "step": 234
+    },
+    {
+      "epoch": 1.1195814648729447,
+      "grad_norm": 0.09252864648733664,
+      "learning_rate": 8.776506830009607e-07,
+      "loss": 0.6529,
+      "step": 235
+    },
+    {
+      "epoch": 1.1243647234678624,
+      "grad_norm": 0.09810040579156247,
+      "learning_rate": 8.698007162013849e-07,
+      "loss": 0.6622,
+      "step": 236
+    },
+    {
+      "epoch": 1.1291479820627803,
+      "grad_norm": 0.10333456832019272,
+      "learning_rate": 8.619589025448318e-07,
+      "loss": 0.6698,
+      "step": 237
+    },
+    {
+      "epoch": 1.133931240657698,
+      "grad_norm": 0.09369526359642345,
+      "learning_rate": 8.541257330895197e-07,
+      "loss": 0.6397,
+      "step": 238
+    },
+    {
+      "epoch": 1.138714499252616,
+      "grad_norm": 0.0934070849673633,
+      "learning_rate": 8.463016983523627e-07,
+      "loss": 0.6724,
+      "step": 239
+    },
+    {
+      "epoch": 1.1434977578475336,
+      "grad_norm": 0.0968568071003159,
+      "learning_rate": 8.384872882782541e-07,
+      "loss": 0.6651,
+      "step": 240
+    },
+    {
+      "epoch": 1.1482810164424515,
+      "grad_norm": 0.09218848184783551,
+      "learning_rate": 8.306829922093857e-07,
+      "loss": 0.6482,
+      "step": 241
+    },
+    {
+      "epoch": 1.1530642750373692,
+      "grad_norm": 0.09367162146496326,
+      "learning_rate": 8.228892988546067e-07,
+      "loss": 0.6532,
+      "step": 242
+    },
+    {
+      "epoch": 1.157847533632287,
+      "grad_norm": 0.09179870741014423,
+      "learning_rate": 8.15106696258818e-07,
+      "loss": 0.6458,
+      "step": 243
+    },
+    {
+      "epoch": 1.1626307922272048,
+      "grad_norm": 0.10425982157218257,
+      "learning_rate": 8.073356717724115e-07,
+      "loss": 0.6476,
+      "step": 244
+    },
+    {
+      "epoch": 1.1674140508221225,
+      "grad_norm": 0.10785978296392415,
+      "learning_rate": 7.995767120207536e-07,
+      "loss": 0.6542,
+      "step": 245
+    },
+    {
+      "epoch": 1.1721973094170404,
+      "grad_norm": 0.09053925155843066,
+      "learning_rate": 7.918303028737096e-07,
+      "loss": 0.6444,
+      "step": 246
+    },
+    {
+      "epoch": 1.176980568011958,
+      "grad_norm": 0.11054671698924359,
+      "learning_rate": 7.840969294152211e-07,
+      "loss": 0.6546,
+      "step": 247
+    },
+    {
+      "epoch": 1.181763826606876,
+      "grad_norm": 0.09190168624229306,
+      "learning_rate": 7.763770759129269e-07,
+      "loss": 0.6483,
+      "step": 248
+    },
+    {
+      "epoch": 1.1865470852017936,
+      "grad_norm": 0.10112895278117082,
+      "learning_rate": 7.68671225787841e-07,
+      "loss": 0.6607,
+      "step": 249
+    },
+    {
+      "epoch": 1.1913303437967115,
+      "grad_norm": 0.09521368142452571,
+      "learning_rate": 7.609798615840785e-07,
+      "loss": 0.6632,
+      "step": 250
+    },
+    {
+      "epoch": 1.1961136023916292,
+      "grad_norm": 0.09631678500828386,
+      "learning_rate": 7.533034649386384e-07,
+      "loss": 0.6271,
+      "step": 251
+    },
+    {
+      "epoch": 1.2008968609865471,
+      "grad_norm": 0.09402110237205977,
+      "learning_rate": 7.456425165512452e-07,
+      "loss": 0.649,
+      "step": 252
+    },
+    {
+      "epoch": 1.2056801195814648,
+      "grad_norm": 0.10452266128761932,
+      "learning_rate": 7.379974961542447e-07,
+      "loss": 0.6744,
+      "step": 253
+    },
+    {
+      "epoch": 1.2104633781763827,
+      "grad_norm": 0.09522707743392524,
+      "learning_rate": 7.303688824825646e-07,
+      "loss": 0.6608,
+      "step": 254
+    },
+    {
+      "epoch": 1.2152466367713004,
+      "grad_norm": 0.09573208889216732,
+      "learning_rate": 7.227571532437349e-07,
+      "loss": 0.652,
+      "step": 255
+    },
+    {
+      "epoch": 1.2200298953662183,
+      "grad_norm": 0.08917908293059873,
+      "learning_rate": 7.151627850879755e-07,
+      "loss": 0.6543,
+      "step": 256
+    },
+    {
+      "epoch": 1.224813153961136,
+      "grad_norm": 0.09616438435062312,
+      "learning_rate": 7.075862535783453e-07,
+      "loss": 0.6337,
+      "step": 257
+    },
+    {
+      "epoch": 1.229596412556054,
+      "grad_norm": 0.09640367364080155,
+      "learning_rate": 7.00028033160964e-07,
+      "loss": 0.6839,
+      "step": 258
+    },
+    {
+      "epoch": 1.2343796711509716,
+      "grad_norm": 0.09586353497663917,
+      "learning_rate": 6.924885971353026e-07,
+      "loss": 0.6669,
+      "step": 259
+    },
+    {
+      "epoch": 1.2391629297458895,
+      "grad_norm": 0.09267059238961081,
+      "learning_rate": 6.849684176245431e-07,
+      "loss": 0.6314,
+      "step": 260
+    },
+    {
+      "epoch": 1.2439461883408072,
+      "grad_norm": 0.09031407329588002,
+      "learning_rate": 6.774679655460158e-07,
+      "loss": 0.6449,
+      "step": 261
+    },
+    {
+      "epoch": 1.2487294469357249,
+      "grad_norm": 0.09470627715876291,
+      "learning_rate": 6.699877105817092e-07,
+      "loss": 0.6502,
+      "step": 262
+    },
+    {
+      "epoch": 1.2535127055306428,
+      "grad_norm": 0.10074811226580811,
+      "learning_rate": 6.625281211488591e-07,
+      "loss": 0.6686,
+      "step": 263
+    },
+    {
+      "epoch": 1.2582959641255607,
+      "grad_norm": 0.10063396201285223,
+      "learning_rate": 6.55089664370615e-07,
+      "loss": 0.6695,
+      "step": 264
+    },
+    {
+      "epoch": 1.2630792227204783,
+      "grad_norm": 0.0918463846096307,
+      "learning_rate": 6.476728060467888e-07,
+      "loss": 0.6451,
+      "step": 265
+    },
+    {
+      "epoch": 1.267862481315396,
+      "grad_norm": 0.09328601851356563,
+      "learning_rate": 6.402780106246884e-07,
+      "loss": 0.6532,
+      "step": 266
+    },
+    {
+      "epoch": 1.272645739910314,
+      "grad_norm": 0.09424847785405825,
+      "learning_rate": 6.329057411700298e-07,
+      "loss": 0.6673,
+      "step": 267
+    },
+    {
+      "epoch": 1.2774289985052316,
+      "grad_norm": 0.10008134051501576,
+      "learning_rate": 6.255564593379429e-07,
+      "loss": 0.6672,
+      "step": 268
+    },
+    {
+      "epoch": 1.2822122571001495,
+      "grad_norm": 0.09294984655524738,
+      "learning_rate": 6.182306253440619e-07,
+      "loss": 0.6395,
+      "step": 269
+    },
+    {
+      "epoch": 1.2869955156950672,
+      "grad_norm": 0.10285895388747343,
+      "learning_rate": 6.109286979357051e-07,
+      "loss": 0.6637,
+      "step": 270
+    },
+    {
+      "epoch": 1.291778774289985,
+      "grad_norm": 0.11139784795321246,
+      "learning_rate": 6.036511343631488e-07,
+      "loss": 0.6455,
+      "step": 271
+    },
+    {
+      "epoch": 1.2965620328849028,
+      "grad_norm": 0.09212296328590026,
+      "learning_rate": 5.963983903509935e-07,
+      "loss": 0.6638,
+      "step": 272
+    },
+    {
+      "epoch": 1.3013452914798207,
+      "grad_norm": 0.0949968377343012,
+      "learning_rate": 5.89170920069628e-07,
+      "loss": 0.6548,
+      "step": 273
+    },
+    {
+      "epoch": 1.3061285500747384,
+      "grad_norm": 0.09690303299554558,
+      "learning_rate": 5.819691761067865e-07,
+      "loss": 0.6388,
+      "step": 274
+    },
+    {
+      "epoch": 1.310911808669656,
+      "grad_norm": 0.09255296263795812,
+      "learning_rate": 5.747936094392089e-07,
+      "loss": 0.6435,
+      "step": 275
+    },
+    {
+      "epoch": 1.315695067264574,
+      "grad_norm": 0.09503263182638313,
+      "learning_rate": 5.676446694044002e-07,
+      "loss": 0.638,
+      "step": 276
+    },
+    {
+      "epoch": 1.3204783258594919,
+      "grad_norm": 0.09478054996201758,
+      "learning_rate": 5.605228036724927e-07,
+      "loss": 0.6502,
+      "step": 277
+    },
+    {
+      "epoch": 1.3252615844544096,
+      "grad_norm": 0.0933411883471192,
+      "learning_rate": 5.534284582182114e-07,
+      "loss": 0.6511,
+      "step": 278
+    },
+    {
+      "epoch": 1.3300448430493272,
+      "grad_norm": 0.09944351370813859,
+      "learning_rate": 5.463620772929494e-07,
+      "loss": 0.6325,
+      "step": 279
+    },
+    {
+      "epoch": 1.3348281016442451,
+      "grad_norm": 0.10023032726854744,
+      "learning_rate": 5.393241033969466e-07,
+      "loss": 0.6418,
+      "step": 280
+    },
+    {
+      "epoch": 1.339611360239163,
+      "grad_norm": 0.09729398494948012,
+      "learning_rate": 5.323149772515812e-07,
+      "loss": 0.6372,
+      "step": 281
+    },
+    {
+      "epoch": 1.3443946188340807,
+      "grad_norm": 0.09323209082587747,
+      "learning_rate": 5.253351377717706e-07,
+      "loss": 0.6504,
+      "step": 282
+    },
+    {
+      "epoch": 1.3491778774289984,
+      "grad_norm": 0.08940562070783202,
+      "learning_rate": 5.183850220384873e-07,
+      "loss": 0.6461,
+      "step": 283
+    },
+    {
+      "epoch": 1.3539611360239163,
+      "grad_norm": 0.09092518318025446,
+      "learning_rate": 5.114650652713884e-07,
+      "loss": 0.6542,
+      "step": 284
+    },
+    {
+      "epoch": 1.358744394618834,
+      "grad_norm": 0.0957083892879257,
+      "learning_rate": 5.045757008015606e-07,
+      "loss": 0.6627,
+      "step": 285
+    },
+    {
+      "epoch": 1.363527653213752,
+      "grad_norm": 0.09918131125769998,
+      "learning_rate": 4.977173600443868e-07,
+      "loss": 0.6447,
+      "step": 286
+    },
+    {
+      "epoch": 1.3683109118086696,
+      "grad_norm": 0.09079455495976413,
+      "learning_rate": 4.908904724725299e-07,
+      "loss": 0.651,
+      "step": 287
+    },
+    {
+      "epoch": 1.3730941704035875,
+      "grad_norm": 0.09533039778556848,
+      "learning_rate": 4.840954655890391e-07,
+      "loss": 0.6518,
+      "step": 288
+    },
+    {
+      "epoch": 1.3778774289985052,
+      "grad_norm": 0.09328409620590697,
+      "learning_rate": 4.773327649005777e-07,
+      "loss": 0.6712,
+      "step": 289
+    },
+    {
+      "epoch": 1.382660687593423,
+      "grad_norm": 0.10546886430926707,
+      "learning_rate": 4.7060279389078184e-07,
+      "loss": 0.6594,
+      "step": 290
+    },
+    {
+      "epoch": 1.3874439461883408,
+      "grad_norm": 0.09513157037379577,
+      "learning_rate": 4.6390597399373644e-07,
+      "loss": 0.6311,
+      "step": 291
+    },
+    {
+      "epoch": 1.3922272047832587,
+      "grad_norm": 0.0910714399276055,
+      "learning_rate": 4.5724272456758907e-07,
+      "loss": 0.6524,
+      "step": 292
+    },
+    {
+      "epoch": 1.3970104633781764,
+      "grad_norm": 0.08960044994197404,
+      "learning_rate": 4.506134628682877e-07,
+      "loss": 0.6515,
+      "step": 293
+    },
+    {
+      "epoch": 1.4017937219730943,
+      "grad_norm": 0.0939439987196228,
+      "learning_rate": 4.440186040234524e-07,
+      "loss": 0.6487,
+      "step": 294
+    },
+    {
+      "epoch": 1.406576980568012,
+      "grad_norm": 0.10645194425387064,
+      "learning_rate": 4.3745856100637834e-07,
+      "loss": 0.629,
+      "step": 295
+    },
+    {
+      "epoch": 1.4113602391629296,
+      "grad_norm": 0.1047763121754449,
+      "learning_rate": 4.3093374461017785e-07,
+      "loss": 0.6466,
+      "step": 296
+    },
+    {
+      "epoch": 1.4161434977578475,
+      "grad_norm": 0.09982639743024341,
+      "learning_rate": 4.244445634220545e-07,
+      "loss": 0.6504,
+      "step": 297
+    },
+    {
+      "epoch": 1.4209267563527654,
+      "grad_norm": 0.094704337085837,
+      "learning_rate": 4.1799142379771766e-07,
+      "loss": 0.6675,
+      "step": 298
+    },
+    {
+      "epoch": 1.4257100149476831,
+      "grad_norm": 0.09542340607816273,
+      "learning_rate": 4.115747298359363e-07,
+      "loss": 0.6379,
+      "step": 299
+    },
+    {
+      "epoch": 1.4304932735426008,
+      "grad_norm": 0.09975848410849608,
+      "learning_rate": 4.0519488335323415e-07,
+      "loss": 0.6684,
+      "step": 300
+    },
+    {
+      "epoch": 1.4352765321375187,
+      "grad_norm": 0.09564133208363568,
+      "learning_rate": 3.9885228385872806e-07,
+      "loss": 0.6345,
+      "step": 301
+    },
+    {
+      "epoch": 1.4400597907324364,
+      "grad_norm": 0.0955432935737647,
+      "learning_rate": 3.925473285291091e-07,
+      "loss": 0.6419,
+      "step": 302
+    },
+    {
+      "epoch": 1.4448430493273543,
+      "grad_norm": 0.0971708074341661,
+      "learning_rate": 3.862804121837733e-07,
+      "loss": 0.6568,
+      "step": 303
+    },
+    {
+      "epoch": 1.449626307922272,
+      "grad_norm": 0.09654206097129785,
+      "learning_rate": 3.8005192726009663e-07,
+      "loss": 0.6526,
+      "step": 304
+    },
+    {
+      "epoch": 1.45440956651719,
+      "grad_norm": 0.1047844291301578,
+      "learning_rate": 3.738622637888608e-07,
+      "loss": 0.6554,
+      "step": 305
+    },
+    {
+      "epoch": 1.4591928251121076,
+      "grad_norm": 0.10495835343403974,
+      "learning_rate": 3.677118093698278e-07,
+      "loss": 0.639,
+      "step": 306
+    },
+    {
+      "epoch": 1.4639760837070255,
+      "grad_norm": 0.09312185978330073,
+      "learning_rate": 3.61600949147472e-07,
+      "loss": 0.6534,
+      "step": 307
+    },
+    {
+      "epoch": 1.4687593423019432,
+      "grad_norm": 0.0914400067851364,
+      "learning_rate": 3.5553006578685706e-07,
+      "loss": 0.6364,
+      "step": 308
+    },
+    {
+      "epoch": 1.473542600896861,
+      "grad_norm": 0.10168751711517944,
+      "learning_rate": 3.494995394496778e-07,
+      "loss": 0.6438,
+      "step": 309
+    },
+    {
+      "epoch": 1.4783258594917787,
+      "grad_norm": 0.08777082505313431,
+      "learning_rate": 3.435097477704517e-07,
+      "loss": 0.6159,
+      "step": 310
+    },
+    {
+      "epoch": 1.4831091180866967,
+      "grad_norm": 0.0992483436164171,
+      "learning_rate": 3.3756106583287205e-07,
+      "loss": 0.6692,
+      "step": 311
+    },
+    {
+      "epoch": 1.4878923766816143,
+      "grad_norm": 0.09763140125702534,
+      "learning_rate": 3.316538661463204e-07,
+      "loss": 0.6704,
+      "step": 312
+    },
+    {
+      "epoch": 1.492675635276532,
+      "grad_norm": 0.103958466638517,
+      "learning_rate": 3.2578851862253796e-07,
+      "loss": 0.6582,
+      "step": 313
+    },
+    {
+      "epoch": 1.49745889387145,
+      "grad_norm": 0.09058417960194183,
+      "learning_rate": 3.199653905524654e-07,
+      "loss": 0.6353,
+      "step": 314
+    },
+    {
+      "epoch": 1.5022421524663678,
+      "grad_norm": 0.10131403619552605,
+      "learning_rate": 3.1418484658323806e-07,
+      "loss": 0.6566,
+      "step": 315
+    },
+    {
+      "epoch": 1.5070254110612855,
+      "grad_norm": 0.09681513597634411,
+      "learning_rate": 3.0844724869535577e-07,
+      "loss": 0.6437,
+      "step": 316
+    },
+    {
+      "epoch": 1.5118086696562032,
+      "grad_norm": 0.10073309195120103,
+      "learning_rate": 3.027529561800117e-07,
+      "loss": 0.6541,
+      "step": 317
+    },
+    {
+      "epoch": 1.516591928251121,
+      "grad_norm": 0.09187767379862512,
+      "learning_rate": 2.971023256165983e-07,
+      "loss": 0.6429,
+      "step": 318
+    },
+    {
+      "epoch": 1.521375186846039,
+      "grad_norm": 0.09322468814151724,
+      "learning_rate": 2.9149571085037215e-07,
+      "loss": 0.6536,
+      "step": 319
+    },
+    {
+      "epoch": 1.5261584454409567,
+      "grad_norm": 0.09535864278016615,
+      "learning_rate": 2.8593346297030073e-07,
+      "loss": 0.6448,
+      "step": 320
+    },
+    {
+      "epoch": 1.5309417040358744,
+      "grad_norm": 0.09853757658051235,
+      "learning_rate": 2.804159302870751e-07,
+      "loss": 0.6361,
+      "step": 321
+    },
+    {
+      "epoch": 1.5357249626307923,
+      "grad_norm": 0.08652865663588583,
+      "learning_rate": 2.7494345831129837e-07,
+      "loss": 0.6275,
+      "step": 322
+    },
+    {
+      "epoch": 1.54050822122571,
+      "grad_norm": 0.09209381258321075,
+      "learning_rate": 2.6951638973185073e-07,
+      "loss": 0.6528,
+      "step": 323
+    },
+    {
+      "epoch": 1.5452914798206279,
+      "grad_norm": 0.09568385273192681,
+      "learning_rate": 2.64135064394428e-07,
+      "loss": 0.6632,
+      "step": 324
+    },
+    {
+      "epoch": 1.5500747384155455,
+      "grad_norm": 0.0947277435093391,
+      "learning_rate": 2.587998192802638e-07,
+      "loss": 0.6306,
+      "step": 325
+    },
+    {
+      "epoch": 1.5548579970104632,
+      "grad_norm": 0.0985703474276344,
+      "learning_rate": 2.5351098848502386e-07,
+      "loss": 0.6511,
+      "step": 326
+    },
+    {
+      "epoch": 1.5596412556053811,
+      "grad_norm": 0.09427610648180619,
+      "learning_rate": 2.482689031978872e-07,
+      "loss": 0.6533,
+      "step": 327
+    },
+    {
+      "epoch": 1.564424514200299,
+      "grad_norm": 0.09520925811802433,
+      "learning_rate": 2.4307389168080606e-07,
+      "loss": 0.6603,
+      "step": 328
+    },
+    {
+      "epoch": 1.5692077727952167,
+      "grad_norm": 0.0907369263004915,
+      "learning_rate": 2.3792627924795038e-07,
+      "loss": 0.6818,
+      "step": 329
+    },
+    {
+      "epoch": 1.5739910313901344,
+      "grad_norm": 0.09440279581013306,
+      "learning_rate": 2.3282638824533529e-07,
+      "loss": 0.6531,
+      "step": 330
+    },
+    {
+      "epoch": 1.5787742899850523,
+      "grad_norm": 0.09614745051429147,
+      "learning_rate": 2.277745380306383e-07,
+      "loss": 0.6795,
+      "step": 331
+    },
+    {
+      "epoch": 1.5835575485799702,
+      "grad_norm": 0.09778941686336041,
+      "learning_rate": 2.227710449531971e-07,
+      "loss": 0.6778,
+      "step": 332
+    },
+    {
+      "epoch": 1.588340807174888,
+      "grad_norm": 0.09575250682717351,
+      "learning_rate": 2.178162223342035e-07,
+      "loss": 0.6404,
+      "step": 333
+    },
+    {
+      "epoch": 1.5931240657698056,
+      "grad_norm": 0.09627217057571222,
+      "learning_rate": 2.1291038044707965e-07,
+      "loss": 0.6528,
+      "step": 334
+    },
+    {
+      "epoch": 1.5979073243647235,
+      "grad_norm": 0.09572743591446818,
+      "learning_rate": 2.0805382649805225e-07,
+      "loss": 0.6461,
+      "step": 335
+    },
+    {
+      "epoch": 1.6026905829596414,
+      "grad_norm": 0.09528928099830879,
+      "learning_rate": 2.032468646069112e-07,
+      "loss": 0.6425,
+      "step": 336
+    },
+    {
+      "epoch": 1.607473841554559,
+      "grad_norm": 0.09652866769512121,
+      "learning_rate": 1.9848979578796865e-07,
+      "loss": 0.6548,
+      "step": 337
+    },
+    {
+      "epoch": 1.6122571001494768,
+      "grad_norm": 0.0954083836089715,
+      "learning_rate": 1.937829179312076e-07,
+      "loss": 0.6633,
+      "step": 338
+    },
+    {
+      "epoch": 1.6170403587443947,
+      "grad_norm": 0.09389212828330971,
+      "learning_rate": 1.8912652578362853e-07,
+      "loss": 0.653,
+      "step": 339
+    },
+    {
+      "epoch": 1.6218236173393124,
+      "grad_norm": 0.09323975661872334,
+      "learning_rate": 1.8452091093079215e-07,
+      "loss": 0.6405,
+      "step": 340
+    },
+    {
+      "epoch": 1.6266068759342303,
+      "grad_norm": 0.1030124431981675,
+      "learning_rate": 1.7996636177855928e-07,
+      "loss": 0.6776,
+      "step": 341
+    },
+    {
+      "epoch": 1.631390134529148,
+      "grad_norm": 0.09627742650338285,
+      "learning_rate": 1.75463163535033e-07,
+      "loss": 0.6579,
+      "step": 342
+    },
+    {
+      "epoch": 1.6361733931240656,
+      "grad_norm": 0.09724021609427144,
+      "learning_rate": 1.7101159819269583e-07,
+      "loss": 0.6432,
+      "step": 343
+    },
+    {
+      "epoch": 1.6409566517189835,
+      "grad_norm": 0.09615121849981347,
+      "learning_rate": 1.6661194451075345e-07,
+      "loss": 0.6628,
+      "step": 344
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "grad_norm": 0.11302849698050037,
+      "learning_rate": 1.6226447799767772e-07,
+      "loss": 0.6306,
+      "step": 345
+    },
+    {
+      "epoch": 1.6505231689088191,
+      "grad_norm": 0.10400127614773519,
+      "learning_rate": 1.5796947089395475e-07,
+      "loss": 0.6462,
+      "step": 346
+    },
+    {
+      "epoch": 1.6553064275037368,
+      "grad_norm": 0.08798479350296001,
+      "learning_rate": 1.5372719215503582e-07,
+      "loss": 0.6309,
+      "step": 347
+    },
+    {
+      "epoch": 1.6600896860986547,
+      "grad_norm": 0.09514870211869147,
+      "learning_rate": 1.4953790743449702e-07,
+      "loss": 0.6631,
+      "step": 348
+    },
+    {
+      "epoch": 1.6648729446935726,
+      "grad_norm": 0.09749807157916107,
+      "learning_rate": 1.4540187906740241e-07,
+      "loss": 0.6285,
+      "step": 349
+    },
+    {
+      "epoch": 1.6696562032884903,
+      "grad_norm": 0.0901583318721974,
+      "learning_rate": 1.4131936605387762e-07,
+      "loss": 0.6731,
+      "step": 350
+    },
+    {
+      "epoch": 1.674439461883408,
+      "grad_norm": 0.09526536450165937,
+      "learning_rate": 1.3729062404289017e-07,
+      "loss": 0.6729,
+      "step": 351
+    },
+    {
+      "epoch": 1.6792227204783259,
+      "grad_norm": 0.09836491336123554,
+      "learning_rate": 1.3331590531624115e-07,
+      "loss": 0.6515,
+      "step": 352
+    },
+    {
+      "epoch": 1.6840059790732438,
+      "grad_norm": 0.10075181987095727,
+      "learning_rate": 1.2939545877276726e-07,
+      "loss": 0.6452,
+      "step": 353
+    },
+    {
+      "epoch": 1.6887892376681615,
+      "grad_norm": 0.09365016014154177,
+      "learning_rate": 1.25529529912754e-07,
+      "loss": 0.6477,
+      "step": 354
+    },
+    {
+      "epoch": 1.6935724962630792,
+      "grad_norm": 0.09704957910910289,
+      "learning_rate": 1.2171836082256316e-07,
+      "loss": 0.6678,
+      "step": 355
+    },
+    {
+      "epoch": 1.698355754857997,
+      "grad_norm": 0.0902657671425916,
+      "learning_rate": 1.1796219015947285e-07,
+      "loss": 0.6515,
+      "step": 356
+    },
+    {
+      "epoch": 1.703139013452915,
+      "grad_norm": 0.09237650202510098,
+      "learning_rate": 1.1426125313673285e-07,
+      "loss": 0.6645,
+      "step": 357
+    },
+    {
+      "epoch": 1.7079222720478326,
+      "grad_norm": 0.09196231975892524,
+      "learning_rate": 1.1061578150883444e-07,
+      "loss": 0.6092,
+      "step": 358
+    },
+    {
+      "epoch": 1.7127055306427503,
+      "grad_norm": 0.10378820492061246,
+      "learning_rate": 1.070260035570002e-07,
+      "loss": 0.6539,
+      "step": 359
+    },
+    {
+      "epoch": 1.717488789237668,
+      "grad_norm": 0.09091589756400278,
+      "learning_rate": 1.0349214407488571e-07,
+      "loss": 0.6454,
+      "step": 360
+    },
+    {
+      "epoch": 1.722272047832586,
+      "grad_norm": 0.09881444337923977,
+      "learning_rate": 1.000144243545058e-07,
+      "loss": 0.6486,
+      "step": 361
+    },
+    {
+      "epoch": 1.7270553064275038,
+      "grad_norm": 0.09311309771551186,
+      "learning_rate": 9.659306217237517e-08,
+      "loss": 0.6402,
+      "step": 362
+    },
+    {
+      "epoch": 1.7318385650224215,
+      "grad_norm": 0.09631340848121332,
+      "learning_rate": 9.322827177587212e-08,
+      "loss": 0.6469,
+      "step": 363
+    },
+    {
+      "epoch": 1.7366218236173392,
+      "grad_norm": 0.08882699558772723,
+      "learning_rate": 8.992026386982221e-08,
+      "loss": 0.6535,
+      "step": 364
+    },
+    {
+      "epoch": 1.741405082212257,
+      "grad_norm": 0.09280206311141305,
+      "learning_rate": 8.66692456033029e-08,
+      "loss": 0.648,
+      "step": 365
+    },
+    {
+      "epoch": 1.746188340807175,
+      "grad_norm": 0.0909402496845187,
+      "learning_rate": 8.347542055667311e-08,
+      "loss": 0.6529,
+      "step": 366
+    },
+    {
+      "epoch": 1.7509715994020927,
+      "grad_norm": 0.09512784479004122,
+      "learning_rate": 8.033898872882394e-08,
+      "loss": 0.6383,
+      "step": 367
+    },
+    {
+      "epoch": 1.7557548579970104,
+      "grad_norm": 0.09252600518424785,
+      "learning_rate": 7.726014652465507e-08,
+      "loss": 0.6202,
+      "step": 368
+    },
+    {
+      "epoch": 1.7605381165919283,
+      "grad_norm": 0.09450252582803388,
+      "learning_rate": 7.423908674277579e-08,
+      "loss": 0.6494,
+      "step": 369
+    },
+    {
+      "epoch": 1.7653213751868462,
+      "grad_norm": 0.09089301547199258,
+      "learning_rate": 7.127599856343192e-08,
+      "loss": 0.6583,
+      "step": 370
+    },
+    {
+      "epoch": 1.7701046337817639,
+      "grad_norm": 0.0917284963739844,
+      "learning_rate": 6.837106753665823e-08,
+      "loss": 0.666,
+      "step": 371
+    },
+    {
+      "epoch": 1.7748878923766815,
+      "grad_norm": 0.09493041895710681,
+      "learning_rate": 6.552447557066109e-08,
+      "loss": 0.6464,
+      "step": 372
+    },
+    {
+      "epoch": 1.7796711509715994,
+      "grad_norm": 0.08941486424509316,
+      "learning_rate": 6.273640092042575e-08,
+      "loss": 0.6367,
+      "step": 373
+    },
+    {
+      "epoch": 1.7844544095665174,
+      "grad_norm": 0.08812104207206783,
+      "learning_rate": 6.000701817655474e-08,
+      "loss": 0.6259,
+      "step": 374
+    },
+    {
+      "epoch": 1.789237668161435,
+      "grad_norm": 0.09772722276760373,
+      "learning_rate": 5.733649825433384e-08,
+      "loss": 0.6316,
+      "step": 375
+    },
+    {
+      "epoch": 1.7940209267563527,
+      "grad_norm": 0.09550366242600927,
+      "learning_rate": 5.47250083830314e-08,
+      "loss": 0.6764,
+      "step": 376
+    },
+    {
+      "epoch": 1.7988041853512704,
+      "grad_norm": 0.09529244067030168,
+      "learning_rate": 5.217271209542384e-08,
+      "loss": 0.6581,
+      "step": 377
+    },
+    {
+      "epoch": 1.8035874439461883,
+      "grad_norm": 0.09484969927499808,
+      "learning_rate": 4.967976921755679e-08,
+      "loss": 0.6238,
+      "step": 378
+    },
+    {
+      "epoch": 1.8083707025411062,
+      "grad_norm": 0.0922584352432481,
+      "learning_rate": 4.724633585873627e-08,
+      "loss": 0.6417,
+      "step": 379
+    },
+    {
+      "epoch": 1.813153961136024,
+      "grad_norm": 0.09178466251978876,
+      "learning_rate": 4.487256440175291e-08,
+      "loss": 0.6563,
+      "step": 380
+    },
+    {
+      "epoch": 1.8179372197309416,
+      "grad_norm": 0.0945223759439494,
+      "learning_rate": 4.255860349334006e-08,
+      "loss": 0.6479,
+      "step": 381
+    },
+    {
+      "epoch": 1.8227204783258595,
+      "grad_norm": 0.08929357609354767,
+      "learning_rate": 4.030459803486464e-08,
+      "loss": 0.6378,
+      "step": 382
+    },
+    {
+      "epoch": 1.8275037369207774,
+      "grad_norm": 0.08950252320624025,
+      "learning_rate": 3.811068917325444e-08,
+      "loss": 0.6128,
+      "step": 383
+    },
+    {
+      "epoch": 1.832286995515695,
+      "grad_norm": 0.09959763380863362,
+      "learning_rate": 3.5977014292158495e-08,
+      "loss": 0.6493,
+      "step": 384
+    },
+    {
+      "epoch": 1.8370702541106128,
+      "grad_norm": 0.09877239003895597,
+      "learning_rate": 3.3903707003344774e-08,
+      "loss": 0.6453,
+      "step": 385
+    },
+    {
+      "epoch": 1.8418535127055307,
+      "grad_norm": 0.09253710326481404,
+      "learning_rate": 3.189089713833226e-08,
+      "loss": 0.6564,
+      "step": 386
+    },
+    {
+      "epoch": 1.8466367713004486,
+      "grad_norm": 0.09295026609135121,
+      "learning_rate": 2.9938710740262884e-08,
+      "loss": 0.6286,
+      "step": 387
+    },
+    {
+      "epoch": 1.8514200298953662,
+      "grad_norm": 0.0931563883337063,
+      "learning_rate": 2.8047270056005934e-08,
+      "loss": 0.6431,
+      "step": 388
+    },
+    {
+      "epoch": 1.856203288490284,
+      "grad_norm": 0.10071203031568553,
+      "learning_rate": 2.6216693528505195e-08,
+      "loss": 0.6419,
+      "step": 389
+    },
+    {
+      "epoch": 1.8609865470852018,
+      "grad_norm": 0.0926672982724561,
+      "learning_rate": 2.4447095789360884e-08,
+      "loss": 0.6426,
+      "step": 390
+    },
+    {
+      "epoch": 1.8657698056801197,
+      "grad_norm": 0.10839157436286975,
+      "learning_rate": 2.2738587651651487e-08,
+      "loss": 0.6418,
+      "step": 391
+    },
+    {
+      "epoch": 1.8705530642750374,
+      "grad_norm": 0.09452841812388145,
+      "learning_rate": 2.109127610299466e-08,
+      "loss": 0.6534,
+      "step": 392
+    },
+    {
+      "epoch": 1.875336322869955,
+      "grad_norm": 0.09059164967961951,
+      "learning_rate": 1.950526429884769e-08,
+      "loss": 0.6385,
+      "step": 393
+    },
+    {
+      "epoch": 1.8801195814648728,
+      "grad_norm": 0.09541292286319235,
+      "learning_rate": 1.7980651556048e-08,
+      "loss": 0.6533,
+      "step": 394
+    },
+    {
+      "epoch": 1.8849028400597907,
+      "grad_norm": 0.09352871341544354,
+      "learning_rate": 1.6517533346593226e-08,
+      "loss": 0.6533,
+      "step": 395
+    },
+    {
+      "epoch": 1.8896860986547086,
+      "grad_norm": 0.09830540898676399,
+      "learning_rate": 1.5116001291663462e-08,
+      "loss": 0.686,
+      "step": 396
+    },
+    {
+      "epoch": 1.8944693572496263,
+      "grad_norm": 0.09186784336874675,
+      "learning_rate": 1.3776143155883491e-08,
+      "loss": 0.6265,
+      "step": 397
+    },
+    {
+      "epoch": 1.899252615844544,
+      "grad_norm": 0.0903805903035563,
+      "learning_rate": 1.2498042841827317e-08,
+      "loss": 0.6444,
+      "step": 398
+    },
+    {
+      "epoch": 1.9040358744394619,
+      "grad_norm": 0.09251729842752435,
+      "learning_rate": 1.128178038476324e-08,
+      "loss": 0.643,
+      "step": 399
+    },
+    {
+      "epoch": 1.9088191330343798,
+      "grad_norm": 0.08909847951509034,
+      "learning_rate": 1.0127431947643316e-08,
+      "loss": 0.643,
+      "step": 400
+    },
+    {
+      "epoch": 1.9136023916292975,
+      "grad_norm": 0.09779029431433935,
+      "learning_rate": 9.035069816332619e-09,
+      "loss": 0.6312,
+      "step": 401
+    },
+    {
+      "epoch": 1.9183856502242151,
+      "grad_norm": 0.09602092233428558,
+      "learning_rate": 8.004762395083963e-09,
+      "loss": 0.629,
+      "step": 402
+    },
+    {
+      "epoch": 1.923168908819133,
+      "grad_norm": 0.09003448698278545,
+      "learning_rate": 7.036574202253343e-09,
+      "loss": 0.6706,
+      "step": 403
+    },
+    {
+      "epoch": 1.927952167414051,
+      "grad_norm": 0.09531787472090986,
+      "learning_rate": 6.130565866260484e-09,
+      "loss": 0.65,
+      "step": 404
+    },
+    {
+      "epoch": 1.9327354260089686,
+      "grad_norm": 0.09179251340184746,
+      "learning_rate": 5.286794121791782e-09,
+      "loss": 0.6574,
+      "step": 405
+    },
+    {
+      "epoch": 1.9375186846038863,
+      "grad_norm": 0.09493544791044316,
+      "learning_rate": 4.5053118062478025e-09,
+      "loss": 0.6322,
+      "step": 406
+    },
+    {
+      "epoch": 1.9423019431988042,
+      "grad_norm": 0.09306468796228341,
+      "learning_rate": 3.786167856434375e-09,
+      "loss": 0.6634,
+      "step": 407
+    },
+    {
+      "epoch": 1.9470852017937221,
+      "grad_norm": 0.09006826318963117,
+      "learning_rate": 3.1294073054987102e-09,
+      "loss": 0.6418,
+      "step": 408
+    },
+    {
+      "epoch": 1.9518684603886398,
+      "grad_norm": 0.09638156976673805,
+      "learning_rate": 2.5350712801084363e-09,
+      "loss": 0.631,
+      "step": 409
+    },
+    {
+      "epoch": 1.9566517189835575,
+      "grad_norm": 0.09585138354438733,
+      "learning_rate": 2.003196997877099e-09,
+      "loss": 0.6405,
+      "step": 410
+    },
+    {
+      "epoch": 1.9614349775784752,
+      "grad_norm": 0.0982765637161277,
+      "learning_rate": 1.5338177650332517e-09,
+      "loss": 0.631,
+      "step": 411
+    },
+    {
+      "epoch": 1.966218236173393,
+      "grad_norm": 0.0924075594922873,
+      "learning_rate": 1.1269629743346777e-09,
+      "loss": 0.6433,
+      "step": 412
+    },
+    {
+      "epoch": 1.971001494768311,
+      "grad_norm": 0.09407079001673903,
+      "learning_rate": 7.826581032279734e-10,
+      "loss": 0.6422,
+      "step": 413
+    },
+    {
+      "epoch": 1.9757847533632287,
+      "grad_norm": 0.09103323653600585,
+      "learning_rate": 5.00924712252937e-10,
+      "loss": 0.6645,
+      "step": 414
+    },
+    {
+      "epoch": 1.9805680119581464,
+      "grad_norm": 0.09999729799669839,
+      "learning_rate": 2.8178044369286945e-10,
+      "loss": 0.6495,
+      "step": 415
+    },
+    {
+      "epoch": 1.9853512705530643,
+      "grad_norm": 0.0958229669734574,
+      "learning_rate": 1.2523902046934763e-10,
+      "loss": 0.6238,
+      "step": 416
+    },
+    {
+      "epoch": 1.9901345291479822,
+      "grad_norm": 0.08983387781419207,
+      "learning_rate": 3.131024528302273e-11,
+      "loss": 0.6478,
+      "step": 417
+    },
+    {
+      "epoch": 1.9949177877428999,
+      "grad_norm": 0.09621386225221452,
+      "learning_rate": 0.0,
+      "loss": 0.6557,
+      "step": 418
+    },
+    {
+      "epoch": 1.9949177877428999,
+      "step": 418,
+      "total_flos": 862605439369216.0,
+      "train_loss": 0.715426175948678,
+      "train_runtime": 10328.0995,
+      "train_samples_per_second": 5.181,
+      "train_steps_per_second": 0.04
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 418,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 862605439369216.0,
+  "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:e535fcb69ddd092945b9b9538a6c3932328010b5b25147061ad1689f88a1633c
+size 7672