Add files using upload-large-folder tool

.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 +1,59 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-VL-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: mmo1-math-qwen2.5_vl_3b-sft_mmr1_sft_0503_v10_mathinstruct_onlygemini_ep5
+  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. -->
+
+# mmo1-math-qwen2.5_vl_3b-sft_mmr1_sft_0503_v10_mathinstruct_onlygemini_ep5
+
+This model is a fine-tuned version of [/mnt/amlfs-02/shared/ckpts/models--Qwen--Qwen2.5-VL-3B-Instruct/snapshots/66285546d2b821cf421d4f5eb2576359d3770cd3/](https://huggingface.co//mnt/amlfs-02/shared/ckpts/models--Qwen--Qwen2.5-VL-3B-Instruct/snapshots/66285546d2b821cf421d4f5eb2576359d3770cd3/) on the sft_0503_v10_prompt and the mm_mathinstruct_gemini_withprompt datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 256
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 1024
+- total_eval_batch_size: 2048
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+### Framework versions
+
+- Transformers 4.51.2
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- 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": 4.99952614120992,
+    "total_flos": 3.246606278526417e+20,
+    "train_loss": 0.08344055705064467,
+    "train_runtime": 26260.8831,
+    "train_samples_per_second": 308.537,
+    "train_steps_per_second": 0.301
+}

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 +1,65 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 2048,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

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": "4.51.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a45d6129f0b13bcafe8aaa3cd9457ac70683ac651c98dbf8fc2b376976de1ca
+size 4997750760

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd63e3b7ea8f19cbc60633fc3388bf2727a5c35b191425184b9479b75cd17787
+size 3133917248

model.safetensors.index.json

@@ -0,0 +1,832 @@
+{
+  "metadata": {
+    "total_size": 8131575808
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+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": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "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": 4.99952614120992,
+    "total_flos": 3.246606278526417e+20,
+    "train_loss": 0.08344055705064467,
+    "train_runtime": 26260.8831,
+    "train_samples_per_second": 308.537,
+    "train_steps_per_second": 0.301
+}

trainer_log.jsonl

@@ -0,0 +1,292 @@
+{"current_steps": 5010, "total_steps": 7910, "loss": 0.2292, "lr": 3.567393091166489e-06, "epoch": 3.166798294108356, "percentage": 63.34, "elapsed_time": "0:01:13", "remaining_time": "0:00:42"}
+{"current_steps": 5020, "total_steps": 7910, "loss": 0.2314, "lr": 3.5462673581616298e-06, "epoch": 3.17311641130943, "percentage": 63.46, "elapsed_time": "0:02:46", "remaining_time": "0:01:36"}
+{"current_steps": 5030, "total_steps": 7910, "loss": 0.2314, "lr": 3.5251699355301253e-06, "epoch": 3.179434528510504, "percentage": 63.59, "elapsed_time": "0:04:04", "remaining_time": "0:02:20"}
+{"current_steps": 5040, "total_steps": 7910, "loss": 0.2321, "lr": 3.504101234128757e-06, "epoch": 3.185752645711578, "percentage": 63.72, "elapsed_time": "0:05:33", "remaining_time": "0:03:10"}
+{"current_steps": 5050, "total_steps": 7910, "loss": 0.231, "lr": 3.4830616642549734e-06, "epoch": 3.192070762912652, "percentage": 63.84, "elapsed_time": "0:07:00", "remaining_time": "0:03:57"}
+{"current_steps": 5060, "total_steps": 7910, "loss": 0.2316, "lr": 3.462051635638919e-06, "epoch": 3.198388880113726, "percentage": 63.97, "elapsed_time": "0:08:18", "remaining_time": "0:04:40"}
+{"current_steps": 5070, "total_steps": 7910, "loss": 0.2317, "lr": 3.441071557435438e-06, "epoch": 3.2047069973148004, "percentage": 64.1, "elapsed_time": "0:09:42", "remaining_time": "0:05:26"}
+{"current_steps": 5080, "total_steps": 7910, "loss": 0.2305, "lr": 3.420121838216114e-06, "epoch": 3.2110251145158744, "percentage": 64.22, "elapsed_time": "0:11:15", "remaining_time": "0:06:16"}
+{"current_steps": 5090, "total_steps": 7910, "loss": 0.2308, "lr": 3.39920288596131e-06, "epoch": 3.2173432317169484, "percentage": 64.35, "elapsed_time": "0:12:44", "remaining_time": "0:07:03"}
+{"current_steps": 5100, "total_steps": 7910, "loss": 0.2322, "lr": 3.378315108052227e-06, "epoch": 3.2236613489180224, "percentage": 64.48, "elapsed_time": "0:14:02", "remaining_time": "0:07:44"}
+{"current_steps": 5110, "total_steps": 7910, "loss": 0.2319, "lr": 3.3574589112629683e-06, "epoch": 3.2299794661190964, "percentage": 64.6, "elapsed_time": "0:15:28", "remaining_time": "0:08:29"}
+{"current_steps": 5120, "total_steps": 7910, "loss": 0.2314, "lr": 3.3366347017526162e-06, "epoch": 3.2362975833201704, "percentage": 64.73, "elapsed_time": "0:17:07", "remaining_time": "0:09:19"}
+{"current_steps": 5130, "total_steps": 7910, "loss": 0.2308, "lr": 3.3158428850573273e-06, "epoch": 3.242615700521245, "percentage": 64.85, "elapsed_time": "0:18:37", "remaining_time": "0:10:05"}
+{"current_steps": 5140, "total_steps": 7910, "loss": 0.2298, "lr": 3.295083866082429e-06, "epoch": 3.248933817722319, "percentage": 64.98, "elapsed_time": "0:20:04", "remaining_time": "0:10:49"}
+{"current_steps": 5150, "total_steps": 7910, "loss": 0.231, "lr": 3.274358049094541e-06, "epoch": 3.255251934923393, "percentage": 65.11, "elapsed_time": "0:21:34", "remaining_time": "0:11:33"}
+{"current_steps": 5160, "total_steps": 7910, "loss": 0.2296, "lr": 3.253665837713694e-06, "epoch": 3.261570052124467, "percentage": 65.23, "elapsed_time": "0:23:02", "remaining_time": "0:12:16"}
+{"current_steps": 5170, "total_steps": 7910, "loss": 0.2301, "lr": 3.2330076349054767e-06, "epoch": 3.267888169325541, "percentage": 65.36, "elapsed_time": "0:24:41", "remaining_time": "0:13:05"}
+{"current_steps": 5180, "total_steps": 7910, "loss": 0.2297, "lr": 3.2123838429731858e-06, "epoch": 3.2742062865266153, "percentage": 65.49, "elapsed_time": "0:26:08", "remaining_time": "0:13:46"}
+{"current_steps": 5190, "total_steps": 7910, "loss": 0.2301, "lr": 3.1917948635499956e-06, "epoch": 3.2805244037276893, "percentage": 65.61, "elapsed_time": "0:27:34", "remaining_time": "0:14:26"}
+{"current_steps": 5200, "total_steps": 7910, "loss": 0.2293, "lr": 3.1712410975911224e-06, "epoch": 3.2868425209287633, "percentage": 65.74, "elapsed_time": "0:28:59", "remaining_time": "0:15:06"}
+{"current_steps": 5210, "total_steps": 7910, "loss": 0.2307, "lr": 3.150722945366035e-06, "epoch": 3.2931606381298373, "percentage": 65.87, "elapsed_time": "0:30:27", "remaining_time": "0:15:47"}
+{"current_steps": 5220, "total_steps": 7910, "loss": 0.2288, "lr": 3.1302408064506496e-06, "epoch": 3.2994787553309113, "percentage": 65.99, "elapsed_time": "0:32:02", "remaining_time": "0:16:30"}
+{"current_steps": 5230, "total_steps": 7910, "loss": 0.2329, "lr": 3.109795079719544e-06, "epoch": 3.3057968725319853, "percentage": 66.12, "elapsed_time": "0:33:33", "remaining_time": "0:17:11"}
+{"current_steps": 5240, "total_steps": 7910, "loss": 0.2297, "lr": 3.0893861633382015e-06, "epoch": 3.3121149897330597, "percentage": 66.25, "elapsed_time": "0:34:57", "remaining_time": "0:17:48"}
+{"current_steps": 5250, "total_steps": 7910, "loss": 0.2309, "lr": 3.0690144547552513e-06, "epoch": 3.3184331069341337, "percentage": 66.37, "elapsed_time": "0:36:15", "remaining_time": "0:18:22"}
+{"current_steps": 5260, "total_steps": 7910, "loss": 0.234, "lr": 3.048680350694724e-06, "epoch": 3.3247512241352077, "percentage": 66.5, "elapsed_time": "0:37:51", "remaining_time": "0:19:04"}
+{"current_steps": 5270, "total_steps": 7910, "loss": 0.2299, "lr": 3.0283842471483314e-06, "epoch": 3.3310693413362817, "percentage": 66.62, "elapsed_time": "0:39:24", "remaining_time": "0:19:44"}
+{"current_steps": 5280, "total_steps": 7910, "loss": 0.2309, "lr": 3.008126539367754e-06, "epoch": 3.3373874585373557, "percentage": 66.75, "elapsed_time": "0:40:48", "remaining_time": "0:20:19"}
+{"current_steps": 5290, "total_steps": 7910, "loss": 0.2304, "lr": 2.9879076218569426e-06, "epoch": 3.34370557573843, "percentage": 66.88, "elapsed_time": "0:42:04", "remaining_time": "0:20:50"}
+{"current_steps": 5300, "total_steps": 7910, "loss": 0.2289, "lr": 2.9677278883644367e-06, "epoch": 3.350023692939504, "percentage": 67.0, "elapsed_time": "0:43:31", "remaining_time": "0:21:26"}
+{"current_steps": 5310, "total_steps": 7910, "loss": 0.2307, "lr": 2.9475877318756928e-06, "epoch": 3.356341810140578, "percentage": 67.13, "elapsed_time": "0:45:02", "remaining_time": "0:22:03"}
+{"current_steps": 5320, "total_steps": 7910, "loss": 0.2307, "lr": 2.9274875446054397e-06, "epoch": 3.362659927341652, "percentage": 67.26, "elapsed_time": "0:46:31", "remaining_time": "0:22:38"}
+{"current_steps": 5330, "total_steps": 7910, "loss": 0.2302, "lr": 2.9074277179900324e-06, "epoch": 3.368978044542726, "percentage": 67.38, "elapsed_time": "0:48:02", "remaining_time": "0:23:15"}
+{"current_steps": 5340, "total_steps": 7910, "loss": 0.2307, "lr": 2.887408642679825e-06, "epoch": 3.3752961617438, "percentage": 67.51, "elapsed_time": "0:49:24", "remaining_time": "0:23:46"}
+{"current_steps": 5350, "total_steps": 7910, "loss": 0.2293, "lr": 2.867430708531585e-06, "epoch": 3.381614278944874, "percentage": 67.64, "elapsed_time": "0:50:52", "remaining_time": "0:24:20"}
+{"current_steps": 5360, "total_steps": 7910, "loss": 0.2301, "lr": 2.847494304600874e-06, "epoch": 3.3879323961459487, "percentage": 67.76, "elapsed_time": "0:52:15", "remaining_time": "0:24:51"}
+{"current_steps": 5370, "total_steps": 7910, "loss": 0.23, "lr": 2.827599819134489e-06, "epoch": 3.3942505133470227, "percentage": 67.89, "elapsed_time": "0:53:41", "remaining_time": "0:25:23"}
+{"current_steps": 5380, "total_steps": 7910, "loss": 0.2305, "lr": 2.807747639562889e-06, "epoch": 3.4005686305480967, "percentage": 68.02, "elapsed_time": "0:55:09", "remaining_time": "0:25:56"}
+{"current_steps": 5390, "total_steps": 7910, "loss": 0.2311, "lr": 2.7879381524926635e-06, "epoch": 3.4068867477491707, "percentage": 68.14, "elapsed_time": "0:56:27", "remaining_time": "0:26:23"}
+{"current_steps": 5400, "total_steps": 7910, "loss": 0.2307, "lr": 2.7681717436989954e-06, "epoch": 3.4132048649502447, "percentage": 68.27, "elapsed_time": "0:57:55", "remaining_time": "0:26:55"}
+{"current_steps": 5410, "total_steps": 7910, "loss": 0.2301, "lr": 2.748448798118149e-06, "epoch": 3.419522982151319, "percentage": 68.39, "elapsed_time": "0:59:25", "remaining_time": "0:27:27"}
+{"current_steps": 5420, "total_steps": 7910, "loss": 0.2305, "lr": 2.728769699839975e-06, "epoch": 3.425841099352393, "percentage": 68.52, "elapsed_time": "1:01:03", "remaining_time": "0:28:02"}
+{"current_steps": 5430, "total_steps": 7910, "loss": 0.2286, "lr": 2.7091348321004286e-06, "epoch": 3.432159216553467, "percentage": 68.65, "elapsed_time": "1:02:37", "remaining_time": "0:28:36"}
+{"current_steps": 5440, "total_steps": 7910, "loss": 0.2305, "lr": 2.689544577274113e-06, "epoch": 3.438477333754541, "percentage": 68.77, "elapsed_time": "1:04:04", "remaining_time": "0:29:05"}
+{"current_steps": 5450, "total_steps": 7910, "loss": 0.2303, "lr": 2.669999316866819e-06, "epoch": 3.444795450955615, "percentage": 68.9, "elapsed_time": "1:05:34", "remaining_time": "0:29:35"}
+{"current_steps": 5460, "total_steps": 7910, "loss": 0.2295, "lr": 2.6504994315081114e-06, "epoch": 3.451113568156689, "percentage": 69.03, "elapsed_time": "1:07:12", "remaining_time": "0:30:09"}
+{"current_steps": 5470, "total_steps": 7910, "loss": 0.2318, "lr": 2.631045300943904e-06, "epoch": 3.4574316853577636, "percentage": 69.15, "elapsed_time": "1:08:35", "remaining_time": "0:30:35"}
+{"current_steps": 5480, "total_steps": 7910, "loss": 0.2298, "lr": 2.61163730402908e-06, "epoch": 3.4637498025588376, "percentage": 69.28, "elapsed_time": "1:10:05", "remaining_time": "0:31:04"}
+{"current_steps": 5490, "total_steps": 7910, "loss": 0.2292, "lr": 2.5922758187200893e-06, "epoch": 3.4700679197599116, "percentage": 69.41, "elapsed_time": "1:11:35", "remaining_time": "0:31:33"}
+{"current_steps": 5500, "total_steps": 7910, "loss": 0.2287, "lr": 2.572961222067612e-06, "epoch": 3.4763860369609856, "percentage": 69.53, "elapsed_time": "1:13:08", "remaining_time": "0:32:03"}
+{"current_steps": 5510, "total_steps": 7910, "loss": 0.2297, "lr": 2.5536938902092056e-06, "epoch": 3.4827041541620596, "percentage": 69.66, "elapsed_time": "1:14:41", "remaining_time": "0:32:31"}
+{"current_steps": 5520, "total_steps": 7910, "loss": 0.2275, "lr": 2.5344741983619734e-06, "epoch": 3.489022271363134, "percentage": 69.79, "elapsed_time": "1:16:03", "remaining_time": "0:32:55"}
+{"current_steps": 5530, "total_steps": 7910, "loss": 0.2304, "lr": 2.515302520815275e-06, "epoch": 3.495340388564208, "percentage": 69.91, "elapsed_time": "1:17:18", "remaining_time": "0:33:16"}
+{"current_steps": 5540, "total_steps": 7910, "loss": 0.2301, "lr": 2.4961792309234194e-06, "epoch": 3.501658505765282, "percentage": 70.04, "elapsed_time": "1:18:48", "remaining_time": "0:33:42"}
+{"current_steps": 5550, "total_steps": 7910, "loss": 0.2303, "lr": 2.4771047010984066e-06, "epoch": 3.507976622966356, "percentage": 70.16, "elapsed_time": "1:20:24", "remaining_time": "0:34:11"}
+{"current_steps": 5560, "total_steps": 7910, "loss": 0.2283, "lr": 2.4580793028026636e-06, "epoch": 3.51429474016743, "percentage": 70.29, "elapsed_time": "1:21:50", "remaining_time": "0:34:35"}
+{"current_steps": 5570, "total_steps": 7910, "loss": 0.2323, "lr": 2.439103406541821e-06, "epoch": 3.520612857368504, "percentage": 70.42, "elapsed_time": "1:23:14", "remaining_time": "0:34:58"}
+{"current_steps": 5580, "total_steps": 7910, "loss": 0.2305, "lr": 2.4201773818574956e-06, "epoch": 3.526930974569578, "percentage": 70.54, "elapsed_time": "1:24:40", "remaining_time": "0:35:21"}
+{"current_steps": 5590, "total_steps": 7910, "loss": 0.2308, "lr": 2.4013015973200895e-06, "epoch": 3.5332490917706525, "percentage": 70.67, "elapsed_time": "1:26:05", "remaining_time": "0:35:43"}
+{"current_steps": 5600, "total_steps": 7910, "loss": 0.2308, "lr": 2.3824764205216144e-06, "epoch": 3.5395672089717265, "percentage": 70.8, "elapsed_time": "1:27:37", "remaining_time": "0:36:08"}
+{"current_steps": 5610, "total_steps": 7910, "loss": 0.2316, "lr": 2.363702218068535e-06, "epoch": 3.5458853261728005, "percentage": 70.92, "elapsed_time": "1:29:01", "remaining_time": "0:36:29"}
+{"current_steps": 5620, "total_steps": 7910, "loss": 0.2279, "lr": 2.344979355574629e-06, "epoch": 3.5522034433738745, "percentage": 71.05, "elapsed_time": "1:30:20", "remaining_time": "0:36:48"}
+{"current_steps": 5630, "total_steps": 7910, "loss": 0.2283, "lr": 2.326308197653862e-06, "epoch": 3.5585215605749485, "percentage": 71.18, "elapsed_time": "1:31:46", "remaining_time": "0:37:09"}
+{"current_steps": 5640, "total_steps": 7910, "loss": 0.2289, "lr": 2.307689107913295e-06, "epoch": 3.564839677776023, "percentage": 71.3, "elapsed_time": "1:33:12", "remaining_time": "0:37:30"}
+{"current_steps": 5650, "total_steps": 7910, "loss": 0.2293, "lr": 2.289122448945997e-06, "epoch": 3.571157794977097, "percentage": 71.43, "elapsed_time": "1:34:43", "remaining_time": "0:37:53"}
+{"current_steps": 5660, "total_steps": 7910, "loss": 0.2283, "lr": 2.270608582323992e-06, "epoch": 3.577475912178171, "percentage": 71.55, "elapsed_time": "1:36:04", "remaining_time": "0:38:11"}
+{"current_steps": 5670, "total_steps": 7910, "loss": 0.2279, "lr": 2.2521478685912027e-06, "epoch": 3.583794029379245, "percentage": 71.68, "elapsed_time": "1:37:43", "remaining_time": "0:38:36"}
+{"current_steps": 5680, "total_steps": 7910, "loss": 0.2264, "lr": 2.233740667256446e-06, "epoch": 3.590112146580319, "percentage": 71.81, "elapsed_time": "1:39:12", "remaining_time": "0:38:57"}
+{"current_steps": 5690, "total_steps": 7910, "loss": 0.2307, "lr": 2.2153873367864203e-06, "epoch": 3.596430263781393, "percentage": 71.93, "elapsed_time": "1:40:38", "remaining_time": "0:39:16"}
+{"current_steps": 5700, "total_steps": 7910, "loss": 0.2304, "lr": 2.19708823459873e-06, "epoch": 3.602748380982467, "percentage": 72.06, "elapsed_time": "1:42:12", "remaining_time": "0:39:37"}
+{"current_steps": 5710, "total_steps": 7910, "loss": 0.229, "lr": 2.178843717054923e-06, "epoch": 3.6090664981835414, "percentage": 72.19, "elapsed_time": "1:43:32", "remaining_time": "0:39:53"}
+{"current_steps": 5720, "total_steps": 7910, "loss": 0.2276, "lr": 2.1606541394535528e-06, "epoch": 3.6153846153846154, "percentage": 72.31, "elapsed_time": "1:45:00", "remaining_time": "0:40:12"}
+{"current_steps": 5730, "total_steps": 7910, "loss": 0.2286, "lr": 2.1425198560232585e-06, "epoch": 3.6217027325856894, "percentage": 72.44, "elapsed_time": "1:46:33", "remaining_time": "0:40:32"}
+{"current_steps": 5740, "total_steps": 7910, "loss": 0.2299, "lr": 2.12444121991586e-06, "epoch": 3.6280208497867634, "percentage": 72.57, "elapsed_time": "1:48:13", "remaining_time": "0:40:54"}
+{"current_steps": 5750, "total_steps": 7910, "loss": 0.231, "lr": 2.106418583199493e-06, "epoch": 3.634338966987838, "percentage": 72.69, "elapsed_time": "1:49:35", "remaining_time": "0:41:10"}
+{"current_steps": 5760, "total_steps": 7910, "loss": 0.2299, "lr": 2.088452296851744e-06, "epoch": 3.640657084188912, "percentage": 72.82, "elapsed_time": "1:51:04", "remaining_time": "0:41:27"}
+{"current_steps": 5770, "total_steps": 7910, "loss": 0.2282, "lr": 2.070542710752818e-06, "epoch": 3.646975201389986, "percentage": 72.95, "elapsed_time": "1:52:34", "remaining_time": "0:41:45"}
+{"current_steps": 5780, "total_steps": 7910, "loss": 0.2287, "lr": 2.052690173678724e-06, "epoch": 3.65329331859106, "percentage": 73.07, "elapsed_time": "1:54:12", "remaining_time": "0:42:05"}
+{"current_steps": 5790, "total_steps": 7910, "loss": 0.2299, "lr": 2.034895033294483e-06, "epoch": 3.659611435792134, "percentage": 73.2, "elapsed_time": "1:55:45", "remaining_time": "0:42:23"}
+{"current_steps": 5800, "total_steps": 7910, "loss": 0.2282, "lr": 2.0171576361473587e-06, "epoch": 3.665929552993208, "percentage": 73.32, "elapsed_time": "1:57:00", "remaining_time": "0:42:33"}
+{"current_steps": 5810, "total_steps": 7910, "loss": 0.2294, "lr": 1.999478327660109e-06, "epoch": 3.672247670194282, "percentage": 73.45, "elapsed_time": "1:58:35", "remaining_time": "0:42:51"}
+{"current_steps": 5820, "total_steps": 7910, "loss": 0.2306, "lr": 1.9818574521242507e-06, "epoch": 3.6785657873953563, "percentage": 73.58, "elapsed_time": "1:59:55", "remaining_time": "0:43:03"}
+{"current_steps": 5830, "total_steps": 7910, "loss": 0.2273, "lr": 1.9642953526933685e-06, "epoch": 3.6848839045964303, "percentage": 73.7, "elapsed_time": "2:01:22", "remaining_time": "0:43:18"}
+{"current_steps": 5840, "total_steps": 7910, "loss": 0.2285, "lr": 1.9467923713764296e-06, "epoch": 3.6912020217975043, "percentage": 73.83, "elapsed_time": "2:02:49", "remaining_time": "0:43:32"}
+{"current_steps": 5850, "total_steps": 7910, "loss": 0.2297, "lr": 1.9293488490311085e-06, "epoch": 3.6975201389985783, "percentage": 73.96, "elapsed_time": "2:04:17", "remaining_time": "0:43:46"}
+{"current_steps": 5860, "total_steps": 7910, "loss": 0.2301, "lr": 1.9119651253571676e-06, "epoch": 3.7038382561996523, "percentage": 74.08, "elapsed_time": "2:05:44", "remaining_time": "0:43:59"}
+{"current_steps": 5870, "total_steps": 7910, "loss": 0.2303, "lr": 1.894641538889832e-06, "epoch": 3.710156373400727, "percentage": 74.21, "elapsed_time": "2:07:05", "remaining_time": "0:44:10"}
+{"current_steps": 5880, "total_steps": 7910, "loss": 0.2268, "lr": 1.877378426993201e-06, "epoch": 3.716474490601801, "percentage": 74.34, "elapsed_time": "2:08:25", "remaining_time": "0:44:20"}
+{"current_steps": 5890, "total_steps": 7910, "loss": 0.2293, "lr": 1.86017612585367e-06, "epoch": 3.722792607802875, "percentage": 74.46, "elapsed_time": "2:09:56", "remaining_time": "0:44:33"}
+{"current_steps": 5900, "total_steps": 7910, "loss": 0.2307, "lr": 1.843034970473398e-06, "epoch": 3.729110725003949, "percentage": 74.59, "elapsed_time": "2:11:18", "remaining_time": "0:44:44"}
+{"current_steps": 5910, "total_steps": 7910, "loss": 0.2292, "lr": 1.82595529466377e-06, "epoch": 3.735428842205023, "percentage": 74.72, "elapsed_time": "2:12:47", "remaining_time": "0:44:56"}
+{"current_steps": 5920, "total_steps": 7910, "loss": 0.2306, "lr": 1.8089374310389052e-06, "epoch": 3.741746959406097, "percentage": 74.84, "elapsed_time": "2:14:12", "remaining_time": "0:45:06"}
+{"current_steps": 5930, "total_steps": 7910, "loss": 0.2314, "lr": 1.7919817110091691e-06, "epoch": 3.748065076607171, "percentage": 74.97, "elapsed_time": "2:15:41", "remaining_time": "0:45:18"}
+{"current_steps": 5940, "total_steps": 7910, "loss": 0.231, "lr": 1.775088464774734e-06, "epoch": 3.7543831938082453, "percentage": 75.09, "elapsed_time": "2:17:12", "remaining_time": "0:45:30"}
+{"current_steps": 5950, "total_steps": 7910, "loss": 0.2281, "lr": 1.7582580213191381e-06, "epoch": 3.7607013110093193, "percentage": 75.22, "elapsed_time": "2:18:41", "remaining_time": "0:45:41"}
+{"current_steps": 5960, "total_steps": 7910, "loss": 0.2265, "lr": 1.7414907084028804e-06, "epoch": 3.7670194282103933, "percentage": 75.35, "elapsed_time": "2:20:10", "remaining_time": "0:45:51"}
+{"current_steps": 5970, "total_steps": 7910, "loss": 0.2307, "lr": 1.724786852557041e-06, "epoch": 3.7733375454114673, "percentage": 75.47, "elapsed_time": "2:21:32", "remaining_time": "0:45:59"}
+{"current_steps": 5980, "total_steps": 7910, "loss": 0.2309, "lr": 1.70814677907692e-06, "epoch": 3.7796556626125417, "percentage": 75.6, "elapsed_time": "2:22:56", "remaining_time": "0:46:07"}
+{"current_steps": 5990, "total_steps": 7910, "loss": 0.2283, "lr": 1.6915708120157042e-06, "epoch": 3.7859737798136157, "percentage": 75.73, "elapsed_time": "2:24:34", "remaining_time": "0:46:20"}
+{"current_steps": 6000, "total_steps": 7910, "loss": 0.2284, "lr": 1.6750592741781496e-06, "epoch": 3.7922918970146897, "percentage": 75.85, "elapsed_time": "2:25:51", "remaining_time": "0:46:26"}
+{"current_steps": 6010, "total_steps": 7910, "loss": 0.2307, "lr": 1.6586124871143062e-06, "epoch": 3.7986100142157637, "percentage": 75.98, "elapsed_time": "2:27:37", "remaining_time": "0:46:40"}
+{"current_steps": 6020, "total_steps": 7910, "loss": 0.23, "lr": 1.6422307711132462e-06, "epoch": 3.8049281314168377, "percentage": 76.11, "elapsed_time": "2:29:08", "remaining_time": "0:46:49"}
+{"current_steps": 6030, "total_steps": 7910, "loss": 0.2293, "lr": 1.6259144451968383e-06, "epoch": 3.8112462486179117, "percentage": 76.23, "elapsed_time": "2:30:41", "remaining_time": "0:46:59"}
+{"current_steps": 6040, "total_steps": 7910, "loss": 0.2293, "lr": 1.6096638271135172e-06, "epoch": 3.8175643658189857, "percentage": 76.36, "elapsed_time": "2:32:08", "remaining_time": "0:47:06"}
+{"current_steps": 6050, "total_steps": 7910, "loss": 0.2276, "lr": 1.593479233332112e-06, "epoch": 3.82388248302006, "percentage": 76.49, "elapsed_time": "2:33:36", "remaining_time": "0:47:13"}
+{"current_steps": 6060, "total_steps": 7910, "loss": 0.2296, "lr": 1.577360979035678e-06, "epoch": 3.830200600221134, "percentage": 76.61, "elapsed_time": "2:35:15", "remaining_time": "0:47:23"}
+{"current_steps": 6070, "total_steps": 7910, "loss": 0.2292, "lr": 1.5613093781153503e-06, "epoch": 3.836518717422208, "percentage": 76.74, "elapsed_time": "2:36:39", "remaining_time": "0:47:29"}
+{"current_steps": 6080, "total_steps": 7910, "loss": 0.2286, "lr": 1.5453247431642493e-06, "epoch": 3.842836834623282, "percentage": 76.86, "elapsed_time": "2:47:29", "remaining_time": "0:50:24"}
+{"current_steps": 6090, "total_steps": 7910, "loss": 0.2302, "lr": 1.5294073854713754e-06, "epoch": 3.849154951824356, "percentage": 76.99, "elapsed_time": "2:48:53", "remaining_time": "0:50:28"}
+{"current_steps": 6100, "total_steps": 7910, "loss": 0.2303, "lr": 1.5135576150155567e-06, "epoch": 3.8554730690254306, "percentage": 77.12, "elapsed_time": "2:50:22", "remaining_time": "0:50:33"}
+{"current_steps": 6110, "total_steps": 7910, "loss": 0.2282, "lr": 1.4977757404594063e-06, "epoch": 3.8617911862265046, "percentage": 77.24, "elapsed_time": "2:51:51", "remaining_time": "0:50:37"}
+{"current_steps": 6120, "total_steps": 7910, "loss": 0.2298, "lr": 1.4820620691433175e-06, "epoch": 3.8681093034275786, "percentage": 77.37, "elapsed_time": "2:53:12", "remaining_time": "0:50:39"}
+{"current_steps": 6130, "total_steps": 7910, "loss": 0.2301, "lr": 1.4664169070794753e-06, "epoch": 3.8744274206286526, "percentage": 77.5, "elapsed_time": "2:54:37", "remaining_time": "0:50:42"}
+{"current_steps": 6140, "total_steps": 7910, "loss": 0.2299, "lr": 1.4508405589458968e-06, "epoch": 3.8807455378297266, "percentage": 77.62, "elapsed_time": "2:56:09", "remaining_time": "0:50:46"}
+{"current_steps": 6150, "total_steps": 7910, "loss": 0.2263, "lr": 1.4353333280805e-06, "epoch": 3.8870636550308006, "percentage": 77.75, "elapsed_time": "2:57:26", "remaining_time": "0:50:46"}
+{"current_steps": 6160, "total_steps": 7910, "loss": 0.2285, "lr": 1.419895516475192e-06, "epoch": 3.8933817722318746, "percentage": 77.88, "elapsed_time": "2:58:55", "remaining_time": "0:50:49"}
+{"current_steps": 6170, "total_steps": 7910, "loss": 0.2315, "lr": 1.4045274247699957e-06, "epoch": 3.899699889432949, "percentage": 78.0, "elapsed_time": "3:00:09", "remaining_time": "0:50:48"}
+{"current_steps": 6180, "total_steps": 7910, "loss": 0.2304, "lr": 1.3892293522471834e-06, "epoch": 3.906018006634023, "percentage": 78.13, "elapsed_time": "3:01:47", "remaining_time": "0:50:53"}
+{"current_steps": 6190, "total_steps": 7910, "loss": 0.2272, "lr": 1.374001596825461e-06, "epoch": 3.912336123835097, "percentage": 78.26, "elapsed_time": "3:03:17", "remaining_time": "0:50:55"}
+{"current_steps": 6200, "total_steps": 7910, "loss": 0.2313, "lr": 1.3588444550541568e-06, "epoch": 3.918654241036171, "percentage": 78.38, "elapsed_time": "3:04:38", "remaining_time": "0:50:55"}
+{"current_steps": 6210, "total_steps": 7910, "loss": 0.2289, "lr": 1.3437582221074574e-06, "epoch": 3.9249723582372456, "percentage": 78.51, "elapsed_time": "3:06:02", "remaining_time": "0:50:55"}
+{"current_steps": 6220, "total_steps": 7910, "loss": 0.2302, "lr": 1.3287431917786426e-06, "epoch": 3.9312904754383196, "percentage": 78.63, "elapsed_time": "3:07:29", "remaining_time": "0:50:56"}
+{"current_steps": 6230, "total_steps": 7910, "loss": 0.2286, "lr": 1.3137996564743783e-06, "epoch": 3.9376085926393936, "percentage": 78.76, "elapsed_time": "3:08:52", "remaining_time": "0:50:56"}
+{"current_steps": 6240, "total_steps": 7910, "loss": 0.2301, "lr": 1.2989279072090184e-06, "epoch": 3.9439267098404676, "percentage": 78.89, "elapsed_time": "3:10:19", "remaining_time": "0:50:56"}
+{"current_steps": 6250, "total_steps": 7910, "loss": 0.2308, "lr": 1.2841282335989363e-06, "epoch": 3.9502448270415416, "percentage": 79.01, "elapsed_time": "3:11:45", "remaining_time": "0:50:55"}
+{"current_steps": 6260, "total_steps": 7910, "loss": 0.2291, "lr": 1.2694009238568794e-06, "epoch": 3.9565629442426156, "percentage": 79.14, "elapsed_time": "3:13:22", "remaining_time": "0:50:58"}
+{"current_steps": 6270, "total_steps": 7910, "loss": 0.2296, "lr": 1.2547462647863711e-06, "epoch": 3.9628810614436896, "percentage": 79.27, "elapsed_time": "3:14:53", "remaining_time": "0:50:58"}
+{"current_steps": 6280, "total_steps": 7910, "loss": 0.2298, "lr": 1.2401645417761126e-06, "epoch": 3.969199178644764, "percentage": 79.39, "elapsed_time": "3:16:23", "remaining_time": "0:50:58"}
+{"current_steps": 6290, "total_steps": 7910, "loss": 0.2321, "lr": 1.225656038794425e-06, "epoch": 3.975517295845838, "percentage": 79.52, "elapsed_time": "3:18:07", "remaining_time": "0:51:01"}
+{"current_steps": 6300, "total_steps": 7910, "loss": 0.2285, "lr": 1.211221038383728e-06, "epoch": 3.981835413046912, "percentage": 79.65, "elapsed_time": "3:19:29", "remaining_time": "0:50:58"}
+{"current_steps": 6310, "total_steps": 7910, "loss": 0.2278, "lr": 1.1968598216550315e-06, "epoch": 3.988153530247986, "percentage": 79.77, "elapsed_time": "3:20:46", "remaining_time": "0:50:54"}
+{"current_steps": 6320, "total_steps": 7910, "loss": 0.2261, "lr": 1.182572668282463e-06, "epoch": 3.99447164744906, "percentage": 79.9, "elapsed_time": "3:22:17", "remaining_time": "0:50:53"}
+{"current_steps": 6330, "total_steps": 7910, "loss": 0.2443, "lr": 1.1683598564978188e-06, "epoch": 4.001263623440215, "percentage": 80.03, "elapsed_time": "3:23:46", "remaining_time": "0:50:51"}
+{"current_steps": 6340, "total_steps": 7910, "loss": 0.2254, "lr": 1.15422166308515e-06, "epoch": 4.007581740641289, "percentage": 80.15, "elapsed_time": "3:25:29", "remaining_time": "0:50:53"}
+{"current_steps": 6350, "total_steps": 7910, "loss": 0.2218, "lr": 1.1401583633753683e-06, "epoch": 4.013899857842363, "percentage": 80.28, "elapsed_time": "3:26:51", "remaining_time": "0:50:49"}
+{"current_steps": 6360, "total_steps": 7910, "loss": 0.223, "lr": 1.1261702312408867e-06, "epoch": 4.020217975043437, "percentage": 80.4, "elapsed_time": "3:28:22", "remaining_time": "0:50:47"}
+{"current_steps": 6370, "total_steps": 7910, "loss": 0.2233, "lr": 1.1122575390902824e-06, "epoch": 4.026536092244511, "percentage": 80.53, "elapsed_time": "3:29:50", "remaining_time": "0:50:43"}
+{"current_steps": 6380, "total_steps": 7910, "loss": 0.2262, "lr": 1.0984205578629958e-06, "epoch": 4.032854209445585, "percentage": 80.66, "elapsed_time": "3:31:18", "remaining_time": "0:50:40"}
+{"current_steps": 6390, "total_steps": 7910, "loss": 0.2248, "lr": 1.084659557024057e-06, "epoch": 4.03917232664666, "percentage": 80.78, "elapsed_time": "3:32:45", "remaining_time": "0:50:36"}
+{"current_steps": 6400, "total_steps": 7910, "loss": 0.2248, "lr": 1.0709748045588269e-06, "epoch": 4.045490443847734, "percentage": 80.91, "elapsed_time": "3:34:26", "remaining_time": "0:50:35"}
+{"current_steps": 6410, "total_steps": 7910, "loss": 0.2246, "lr": 1.057366566967789e-06, "epoch": 4.051808561048808, "percentage": 81.04, "elapsed_time": "3:35:48", "remaining_time": "0:50:30"}
+{"current_steps": 6420, "total_steps": 7910, "loss": 0.2241, "lr": 1.043835109261357e-06, "epoch": 4.058126678249882, "percentage": 81.16, "elapsed_time": "3:37:30", "remaining_time": "0:50:28"}
+{"current_steps": 6430, "total_steps": 7910, "loss": 0.224, "lr": 1.0303806949547118e-06, "epoch": 4.064444795450956, "percentage": 81.29, "elapsed_time": "3:38:58", "remaining_time": "0:50:24"}
+{"current_steps": 6440, "total_steps": 7910, "loss": 0.2262, "lr": 1.0170035860626676e-06, "epoch": 4.07076291265203, "percentage": 81.42, "elapsed_time": "3:40:19", "remaining_time": "0:50:17"}
+{"current_steps": 6450, "total_steps": 7910, "loss": 0.2254, "lr": 1.0037040430945782e-06, "epoch": 4.077081029853104, "percentage": 81.54, "elapsed_time": "3:41:54", "remaining_time": "0:50:13"}
+{"current_steps": 6460, "total_steps": 7910, "loss": 0.2258, "lr": 9.904823250492546e-07, "epoch": 4.083399147054178, "percentage": 81.67, "elapsed_time": "3:43:15", "remaining_time": "0:50:06"}
+{"current_steps": 6470, "total_steps": 7910, "loss": 0.2234, "lr": 9.773386894099269e-07, "epoch": 4.089717264255252, "percentage": 81.8, "elapsed_time": "3:44:51", "remaining_time": "0:50:02"}
+{"current_steps": 6480, "total_steps": 7910, "loss": 0.2252, "lr": 9.642733921392233e-07, "epoch": 4.096035381456326, "percentage": 81.92, "elapsed_time": "3:46:13", "remaining_time": "0:49:55"}
+{"current_steps": 6490, "total_steps": 7910, "loss": 0.2231, "lr": 9.512866876741949e-07, "epoch": 4.1023534986574, "percentage": 82.05, "elapsed_time": "3:47:47", "remaining_time": "0:49:50"}
+{"current_steps": 6500, "total_steps": 7910, "loss": 0.225, "lr": 9.383788289213541e-07, "epoch": 4.108671615858475, "percentage": 82.17, "elapsed_time": "3:49:32", "remaining_time": "0:49:47"}
+{"current_steps": 6510, "total_steps": 7910, "loss": 0.2242, "lr": 9.255500672517497e-07, "epoch": 4.114989733059549, "percentage": 82.3, "elapsed_time": "3:51:01", "remaining_time": "0:49:40"}
+{"current_steps": 6520, "total_steps": 7910, "loss": 0.2249, "lr": 9.128006524960747e-07, "epoch": 4.121307850260623, "percentage": 82.43, "elapsed_time": "3:52:30", "remaining_time": "0:49:34"}
+{"current_steps": 6530, "total_steps": 7910, "loss": 0.2214, "lr": 9.001308329397996e-07, "epoch": 4.127625967461697, "percentage": 82.55, "elapsed_time": "3:53:54", "remaining_time": "0:49:25"}
+{"current_steps": 6540, "total_steps": 7910, "loss": 0.2249, "lr": 8.875408553183357e-07, "epoch": 4.133944084662771, "percentage": 82.68, "elapsed_time": "3:55:22", "remaining_time": "0:49:18"}
+{"current_steps": 6550, "total_steps": 7910, "loss": 0.2264, "lr": 8.750309648122307e-07, "epoch": 4.140262201863845, "percentage": 82.81, "elapsed_time": "3:56:50", "remaining_time": "0:49:10"}
+{"current_steps": 6560, "total_steps": 7910, "loss": 0.2245, "lr": 8.62601405042397e-07, "epoch": 4.146580319064919, "percentage": 82.93, "elapsed_time": "3:58:11", "remaining_time": "0:49:01"}
+{"current_steps": 6570, "total_steps": 7910, "loss": 0.2272, "lr": 8.502524180653632e-07, "epoch": 4.152898436265993, "percentage": 83.06, "elapsed_time": "3:59:43", "remaining_time": "0:48:53"}
+{"current_steps": 6580, "total_steps": 7910, "loss": 0.2259, "lr": 8.379842443685626e-07, "epoch": 4.159216553467067, "percentage": 83.19, "elapsed_time": "4:01:10", "remaining_time": "0:48:44"}
+{"current_steps": 6590, "total_steps": 7910, "loss": 0.224, "lr": 8.257971228656502e-07, "epoch": 4.165534670668141, "percentage": 83.31, "elapsed_time": "4:02:35", "remaining_time": "0:48:35"}
+{"current_steps": 6600, "total_steps": 7910, "loss": 0.2251, "lr": 8.136912908918482e-07, "epoch": 4.171852787869215, "percentage": 83.44, "elapsed_time": "4:04:00", "remaining_time": "0:48:25"}
+{"current_steps": 6610, "total_steps": 7910, "loss": 0.2241, "lr": 8.016669841993258e-07, "epoch": 4.178170905070289, "percentage": 83.57, "elapsed_time": "4:05:43", "remaining_time": "0:48:19"}
+{"current_steps": 6620, "total_steps": 7910, "loss": 0.2249, "lr": 7.897244369526036e-07, "epoch": 4.1844890222713635, "percentage": 83.69, "elapsed_time": "4:07:05", "remaining_time": "0:48:09"}
+{"current_steps": 6630, "total_steps": 7910, "loss": 0.2264, "lr": 7.778638817240042e-07, "epoch": 4.1908071394724375, "percentage": 83.82, "elapsed_time": "4:08:35", "remaining_time": "0:47:59"}
+{"current_steps": 6640, "total_steps": 7910, "loss": 0.222, "lr": 7.660855494891107e-07, "epoch": 4.1971252566735116, "percentage": 83.94, "elapsed_time": "4:09:59", "remaining_time": "0:47:48"}
+{"current_steps": 6650, "total_steps": 7910, "loss": 0.2247, "lr": 7.543896696222763e-07, "epoch": 4.2034433738745856, "percentage": 84.07, "elapsed_time": "4:11:26", "remaining_time": "0:47:38"}
+{"current_steps": 6660, "total_steps": 7910, "loss": 0.2239, "lr": 7.427764698921519e-07, "epoch": 4.20976149107566, "percentage": 84.2, "elapsed_time": "4:12:59", "remaining_time": "0:47:28"}
+{"current_steps": 6670, "total_steps": 7910, "loss": 0.2231, "lr": 7.312461764572571e-07, "epoch": 4.216079608276734, "percentage": 84.32, "elapsed_time": "4:14:37", "remaining_time": "0:47:20"}
+{"current_steps": 6680, "total_steps": 7910, "loss": 0.2247, "lr": 7.197990138615712e-07, "epoch": 4.222397725477808, "percentage": 84.45, "elapsed_time": "4:16:10", "remaining_time": "0:47:10"}
+{"current_steps": 6690, "total_steps": 7910, "loss": 0.2257, "lr": 7.084352050301607e-07, "epoch": 4.228715842678882, "percentage": 84.58, "elapsed_time": "4:17:39", "remaining_time": "0:46:59"}
+{"current_steps": 6700, "total_steps": 7910, "loss": 0.2242, "lr": 6.971549712648401e-07, "epoch": 4.235033959879956, "percentage": 84.7, "elapsed_time": "4:19:11", "remaining_time": "0:46:48"}
+{"current_steps": 6710, "total_steps": 7910, "loss": 0.2238, "lr": 6.859585322398605e-07, "epoch": 4.24135207708103, "percentage": 84.83, "elapsed_time": "4:20:35", "remaining_time": "0:46:36"}
+{"current_steps": 6720, "total_steps": 7910, "loss": 0.2235, "lr": 6.74846105997633e-07, "epoch": 4.247670194282104, "percentage": 84.96, "elapsed_time": "4:22:01", "remaining_time": "0:46:24"}
+{"current_steps": 6730, "total_steps": 7910, "loss": 0.2253, "lr": 6.638179089444791e-07, "epoch": 4.2539883114831785, "percentage": 85.08, "elapsed_time": "4:23:21", "remaining_time": "0:46:10"}
+{"current_steps": 6740, "total_steps": 7910, "loss": 0.2232, "lr": 6.528741558464207e-07, "epoch": 4.2603064286842525, "percentage": 85.21, "elapsed_time": "4:24:47", "remaining_time": "0:45:57"}
+{"current_steps": 6750, "total_steps": 7910, "loss": 0.2244, "lr": 6.420150598249947e-07, "epoch": 4.2666245458853265, "percentage": 85.34, "elapsed_time": "4:26:17", "remaining_time": "0:45:45"}
+{"current_steps": 6760, "total_steps": 7910, "loss": 0.2246, "lr": 6.312408323531083e-07, "epoch": 4.2729426630864005, "percentage": 85.46, "elapsed_time": "4:27:46", "remaining_time": "0:45:33"}
+{"current_steps": 6770, "total_steps": 7910, "loss": 0.2239, "lr": 6.205516832509089e-07, "epoch": 4.2792607802874745, "percentage": 85.59, "elapsed_time": "4:29:25", "remaining_time": "0:45:22"}
+{"current_steps": 6780, "total_steps": 7910, "loss": 0.2249, "lr": 6.0994782068171e-07, "epoch": 4.2855788974885485, "percentage": 85.71, "elapsed_time": "4:31:05", "remaining_time": "0:45:10"}
+{"current_steps": 6790, "total_steps": 7910, "loss": 0.2264, "lr": 5.99429451147932e-07, "epoch": 4.2918970146896225, "percentage": 85.84, "elapsed_time": "4:32:24", "remaining_time": "0:44:55"}
+{"current_steps": 6800, "total_steps": 7910, "loss": 0.2244, "lr": 5.889967794870794e-07, "epoch": 4.2982151318906965, "percentage": 85.97, "elapsed_time": "4:33:44", "remaining_time": "0:44:41"}
+{"current_steps": 6810, "total_steps": 7910, "loss": 0.2262, "lr": 5.786500088677543e-07, "epoch": 4.3045332490917705, "percentage": 86.09, "elapsed_time": "4:35:17", "remaining_time": "0:44:28"}
+{"current_steps": 6820, "total_steps": 7910, "loss": 0.2234, "lr": 5.683893407857027e-07, "epoch": 4.3108513662928445, "percentage": 86.22, "elapsed_time": "4:36:41", "remaining_time": "0:44:13"}
+{"current_steps": 6830, "total_steps": 7910, "loss": 0.2229, "lr": 5.582149750598842e-07, "epoch": 4.3171694834939185, "percentage": 86.35, "elapsed_time": "4:38:12", "remaining_time": "0:43:59"}
+{"current_steps": 6840, "total_steps": 7910, "loss": 0.2262, "lr": 5.481271098285818e-07, "epoch": 4.3234876006949925, "percentage": 86.47, "elapsed_time": "4:39:44", "remaining_time": "0:43:45"}
+{"current_steps": 6850, "total_steps": 7910, "loss": 0.2241, "lr": 5.381259415455475e-07, "epoch": 4.329805717896067, "percentage": 86.6, "elapsed_time": "4:41:08", "remaining_time": "0:43:30"}
+{"current_steps": 6860, "total_steps": 7910, "loss": 0.2225, "lr": 5.282116649761738e-07, "epoch": 4.336123835097141, "percentage": 86.73, "elapsed_time": "4:42:31", "remaining_time": "0:43:14"}
+{"current_steps": 6870, "total_steps": 7910, "loss": 0.2238, "lr": 5.183844731937004e-07, "epoch": 4.342441952298215, "percentage": 86.85, "elapsed_time": "4:44:05", "remaining_time": "0:43:00"}
+{"current_steps": 6880, "total_steps": 7910, "loss": 0.2249, "lr": 5.086445575754551e-07, "epoch": 4.348760069499289, "percentage": 86.98, "elapsed_time": "4:45:36", "remaining_time": "0:42:45"}
+{"current_steps": 6890, "total_steps": 7910, "loss": 0.2253, "lr": 4.989921077991272e-07, "epoch": 4.355078186700363, "percentage": 87.1, "elapsed_time": "4:47:17", "remaining_time": "0:42:31"}
+{"current_steps": 6900, "total_steps": 7910, "loss": 0.2232, "lr": 4.89427311839073e-07, "epoch": 4.361396303901437, "percentage": 87.23, "elapsed_time": "4:48:35", "remaining_time": "0:42:14"}
+{"current_steps": 6910, "total_steps": 7910, "loss": 0.2231, "lr": 4.799503559626528e-07, "epoch": 4.367714421102511, "percentage": 87.36, "elapsed_time": "4:49:56", "remaining_time": "0:41:57"}
+{"current_steps": 6920, "total_steps": 7910, "loss": 0.2226, "lr": 4.7056142472660993e-07, "epoch": 4.374032538303585, "percentage": 87.48, "elapsed_time": "4:51:22", "remaining_time": "0:41:41"}
+{"current_steps": 6930, "total_steps": 7910, "loss": 0.2242, "lr": 4.6126070097346933e-07, "epoch": 4.380350655504659, "percentage": 87.61, "elapsed_time": "4:52:41", "remaining_time": "0:41:23"}
+{"current_steps": 6940, "total_steps": 7910, "loss": 0.2223, "lr": 4.520483658279817e-07, "epoch": 4.386668772705733, "percentage": 87.74, "elapsed_time": "4:54:14", "remaining_time": "0:41:07"}
+{"current_steps": 6950, "total_steps": 7910, "loss": 0.2253, "lr": 4.4292459869359484e-07, "epoch": 4.392986889906807, "percentage": 87.86, "elapsed_time": "4:55:40", "remaining_time": "0:40:50"}
+{"current_steps": 6960, "total_steps": 7910, "loss": 0.2246, "lr": 4.3388957724895874e-07, "epoch": 4.399305007107882, "percentage": 87.99, "elapsed_time": "4:57:11", "remaining_time": "0:40:33"}
+{"current_steps": 6970, "total_steps": 7910, "loss": 0.2235, "lr": 4.249434774444672e-07, "epoch": 4.405623124308956, "percentage": 88.12, "elapsed_time": "4:58:40", "remaining_time": "0:40:16"}
+{"current_steps": 6980, "total_steps": 7910, "loss": 0.2234, "lr": 4.1608647349883123e-07, "epoch": 4.41194124151003, "percentage": 88.24, "elapsed_time": "5:00:20", "remaining_time": "0:40:00"}
+{"current_steps": 6990, "total_steps": 7910, "loss": 0.2258, "lr": 4.073187378956811e-07, "epoch": 4.418259358711104, "percentage": 88.37, "elapsed_time": "5:01:48", "remaining_time": "0:39:43"}
+{"current_steps": 7000, "total_steps": 7910, "loss": 0.2238, "lr": 3.9864044138021915e-07, "epoch": 4.424577475912178, "percentage": 88.5, "elapsed_time": "5:03:09", "remaining_time": "0:39:24"}
+{"current_steps": 7010, "total_steps": 7910, "loss": 0.2269, "lr": 3.9005175295588227e-07, "epoch": 4.430895593113252, "percentage": 88.62, "elapsed_time": "5:04:58", "remaining_time": "0:39:09"}
+{"current_steps": 7020, "total_steps": 7910, "loss": 0.2239, "lr": 3.815528398810553e-07, "epoch": 4.437213710314326, "percentage": 88.75, "elapsed_time": "5:06:29", "remaining_time": "0:38:51"}
+{"current_steps": 7030, "total_steps": 7910, "loss": 0.2245, "lr": 3.7314386766581725e-07, "epoch": 4.4435318275154, "percentage": 88.87, "elapsed_time": "5:08:04", "remaining_time": "0:38:33"}
+{"current_steps": 7040, "total_steps": 7910, "loss": 0.2235, "lr": 3.6482500006871315e-07, "epoch": 4.449849944716474, "percentage": 89.0, "elapsed_time": "5:09:29", "remaining_time": "0:38:14"}
+{"current_steps": 7050, "total_steps": 7910, "loss": 0.2238, "lr": 3.5659639909356725e-07, "epoch": 4.456168061917548, "percentage": 89.13, "elapsed_time": "5:10:57", "remaining_time": "0:37:55"}
+{"current_steps": 7060, "total_steps": 7910, "loss": 0.2255, "lr": 3.4845822498632773e-07, "epoch": 4.462486179118622, "percentage": 89.25, "elapsed_time": "5:12:29", "remaining_time": "0:37:37"}
+{"current_steps": 7070, "total_steps": 7910, "loss": 0.2244, "lr": 3.4041063623194705e-07, "epoch": 4.468804296319696, "percentage": 89.38, "elapsed_time": "5:14:01", "remaining_time": "0:37:18"}
+{"current_steps": 7080, "total_steps": 7910, "loss": 0.2248, "lr": 3.3245378955129306e-07, "epoch": 4.475122413520771, "percentage": 89.51, "elapsed_time": "5:15:34", "remaining_time": "0:36:59"}
+{"current_steps": 7090, "total_steps": 7910, "loss": 0.2238, "lr": 3.245878398980995e-07, "epoch": 4.481440530721845, "percentage": 89.63, "elapsed_time": "5:17:07", "remaining_time": "0:36:40"}
+{"current_steps": 7100, "total_steps": 7910, "loss": 0.2232, "lr": 3.168129404559467e-07, "epoch": 4.487758647922919, "percentage": 89.76, "elapsed_time": "5:18:41", "remaining_time": "0:36:21"}
+{"current_steps": 7110, "total_steps": 7910, "loss": 0.2226, "lr": 3.0912924263527934e-07, "epoch": 4.494076765123993, "percentage": 89.89, "elapsed_time": "5:20:17", "remaining_time": "0:36:02"}
+{"current_steps": 7120, "total_steps": 7910, "loss": 0.2238, "lr": 3.015368960704584e-07, "epoch": 4.500394882325067, "percentage": 90.01, "elapsed_time": "5:21:42", "remaining_time": "0:35:41"}
+{"current_steps": 7130, "total_steps": 7910, "loss": 0.2245, "lr": 2.940360486168453e-07, "epoch": 4.506712999526141, "percentage": 90.14, "elapsed_time": "5:23:17", "remaining_time": "0:35:21"}
+{"current_steps": 7140, "total_steps": 7910, "loss": 0.2261, "lr": 2.8662684634792436e-07, "epoch": 4.513031116727215, "percentage": 90.27, "elapsed_time": "5:24:45", "remaining_time": "0:35:01"}
+{"current_steps": 7150, "total_steps": 7910, "loss": 0.2236, "lr": 2.793094335524571e-07, "epoch": 4.519349233928289, "percentage": 90.39, "elapsed_time": "5:26:16", "remaining_time": "0:34:40"}
+{"current_steps": 7160, "total_steps": 7910, "loss": 0.2243, "lr": 2.7208395273167376e-07, "epoch": 4.525667351129363, "percentage": 90.52, "elapsed_time": "5:27:37", "remaining_time": "0:34:19"}
+{"current_steps": 7170, "total_steps": 7910, "loss": 0.224, "lr": 2.6495054459649285e-07, "epoch": 4.531985468330437, "percentage": 90.64, "elapsed_time": "5:29:11", "remaining_time": "0:33:58"}
+{"current_steps": 7180, "total_steps": 7910, "loss": 0.2241, "lr": 2.5790934806479095e-07, "epoch": 4.538303585531511, "percentage": 90.77, "elapsed_time": "5:30:52", "remaining_time": "0:33:38"}
+{"current_steps": 7190, "total_steps": 7910, "loss": 0.2233, "lr": 2.5096050025868734e-07, "epoch": 4.544621702732586, "percentage": 90.9, "elapsed_time": "5:32:21", "remaining_time": "0:33:16"}
+{"current_steps": 7200, "total_steps": 7910, "loss": 0.2251, "lr": 2.4410413650188035e-07, "epoch": 4.55093981993366, "percentage": 91.02, "elapsed_time": "5:33:51", "remaining_time": "0:32:55"}
+{"current_steps": 7210, "total_steps": 7910, "loss": 0.2246, "lr": 2.3734039031700684e-07, "epoch": 4.557257937134734, "percentage": 91.15, "elapsed_time": "5:35:13", "remaining_time": "0:32:32"}
+{"current_steps": 7220, "total_steps": 7910, "loss": 0.2216, "lr": 2.3066939342304696e-07, "epoch": 4.563576054335808, "percentage": 91.28, "elapsed_time": "5:36:30", "remaining_time": "0:32:09"}
+{"current_steps": 7230, "total_steps": 7910, "loss": 0.2248, "lr": 2.240912757327557e-07, "epoch": 4.569894171536882, "percentage": 91.4, "elapsed_time": "5:37:58", "remaining_time": "0:31:47"}
+{"current_steps": 7240, "total_steps": 7910, "loss": 0.2242, "lr": 2.176061653501338e-07, "epoch": 4.576212288737956, "percentage": 91.53, "elapsed_time": "5:39:21", "remaining_time": "0:31:24"}
+{"current_steps": 7250, "total_steps": 7910, "loss": 0.2245, "lr": 2.1121418856793363e-07, "epoch": 4.58253040593903, "percentage": 91.66, "elapsed_time": "5:40:43", "remaining_time": "0:31:01"}
+{"current_steps": 7260, "total_steps": 7910, "loss": 0.2229, "lr": 2.0491546986519896e-07, "epoch": 4.588848523140104, "percentage": 91.78, "elapsed_time": "5:42:15", "remaining_time": "0:30:38"}
+{"current_steps": 7270, "total_steps": 7910, "loss": 0.2245, "lr": 1.987101319048418e-07, "epoch": 4.595166640341178, "percentage": 91.91, "elapsed_time": "5:43:53", "remaining_time": "0:30:16"}
+{"current_steps": 7280, "total_steps": 7910, "loss": 0.2221, "lr": 1.925982955312511e-07, "epoch": 4.601484757542252, "percentage": 92.04, "elapsed_time": "5:45:23", "remaining_time": "0:29:53"}
+{"current_steps": 7290, "total_steps": 7910, "loss": 0.226, "lr": 1.8658007976794235e-07, "epoch": 4.607802874743326, "percentage": 92.16, "elapsed_time": "5:46:52", "remaining_time": "0:29:30"}
+{"current_steps": 7300, "total_steps": 7910, "loss": 0.2225, "lr": 1.8065560181523889e-07, "epoch": 4.6141209919444, "percentage": 92.29, "elapsed_time": "5:48:11", "remaining_time": "0:29:05"}
+{"current_steps": 7310, "total_steps": 7910, "loss": 0.2246, "lr": 1.748249770479893e-07, "epoch": 4.620439109145474, "percentage": 92.41, "elapsed_time": "5:49:28", "remaining_time": "0:28:41"}
+{"current_steps": 7320, "total_steps": 7910, "loss": 0.2279, "lr": 1.6908831901331968e-07, "epoch": 4.626757226346549, "percentage": 92.54, "elapsed_time": "5:50:53", "remaining_time": "0:28:16"}
+{"current_steps": 7330, "total_steps": 7910, "loss": 0.2248, "lr": 1.6344573942842333e-07, "epoch": 4.633075343547623, "percentage": 92.67, "elapsed_time": "5:52:25", "remaining_time": "0:27:53"}
+{"current_steps": 7340, "total_steps": 7910, "loss": 0.2237, "lr": 1.5789734817838577e-07, "epoch": 4.639393460748697, "percentage": 92.79, "elapsed_time": "5:53:57", "remaining_time": "0:27:29"}
+{"current_steps": 7350, "total_steps": 7910, "loss": 0.2232, "lr": 1.5244325331404242e-07, "epoch": 4.645711577949771, "percentage": 92.92, "elapsed_time": "5:55:26", "remaining_time": "0:27:04"}
+{"current_steps": 7360, "total_steps": 7910, "loss": 0.2217, "lr": 1.470835610498761e-07, "epoch": 4.652029695150845, "percentage": 93.05, "elapsed_time": "5:56:54", "remaining_time": "0:26:40"}
+{"current_steps": 7370, "total_steps": 7910, "loss": 0.2235, "lr": 1.4181837576195179e-07, "epoch": 4.658347812351919, "percentage": 93.17, "elapsed_time": "5:58:24", "remaining_time": "0:26:15"}
+{"current_steps": 7380, "total_steps": 7910, "loss": 0.2251, "lr": 1.366477999858773e-07, "epoch": 4.664665929552993, "percentage": 93.3, "elapsed_time": "6:00:01", "remaining_time": "0:25:51"}
+{"current_steps": 7390, "total_steps": 7910, "loss": 0.2233, "lr": 1.315719344148092e-07, "epoch": 4.670984046754067, "percentage": 93.43, "elapsed_time": "6:01:33", "remaining_time": "0:25:26"}
+{"current_steps": 7400, "total_steps": 7910, "loss": 0.2238, "lr": 1.2659087789749557e-07, "epoch": 4.677302163955141, "percentage": 93.55, "elapsed_time": "6:02:57", "remaining_time": "0:25:00"}
+{"current_steps": 7410, "total_steps": 7910, "loss": 0.2218, "lr": 1.2170472743634588e-07, "epoch": 4.683620281156215, "percentage": 93.68, "elapsed_time": "6:04:29", "remaining_time": "0:24:35"}
+{"current_steps": 7420, "total_steps": 7910, "loss": 0.226, "lr": 1.1691357818554405e-07, "epoch": 4.68993839835729, "percentage": 93.81, "elapsed_time": "6:05:58", "remaining_time": "0:24:10"}
+{"current_steps": 7430, "total_steps": 7910, "loss": 0.2252, "lr": 1.1221752344919679e-07, "epoch": 4.696256515558364, "percentage": 93.93, "elapsed_time": "6:07:23", "remaining_time": "0:23:44"}
+{"current_steps": 7440, "total_steps": 7910, "loss": 0.2232, "lr": 1.0761665467951321e-07, "epoch": 4.702574632759438, "percentage": 94.06, "elapsed_time": "6:08:51", "remaining_time": "0:23:18"}
+{"current_steps": 7450, "total_steps": 7910, "loss": 0.223, "lr": 1.0311106147502747e-07, "epoch": 4.708892749960512, "percentage": 94.18, "elapsed_time": "6:10:32", "remaining_time": "0:22:52"}
+{"current_steps": 7460, "total_steps": 7910, "loss": 0.2248, "lr": 9.870083157885068e-08, "epoch": 4.715210867161586, "percentage": 94.31, "elapsed_time": "6:11:59", "remaining_time": "0:22:26"}
+{"current_steps": 7470, "total_steps": 7910, "loss": 0.2223, "lr": 9.43860508769645e-08, "epoch": 4.72152898436266, "percentage": 94.44, "elapsed_time": "6:13:13", "remaining_time": "0:21:59"}
+{"current_steps": 7480, "total_steps": 7910, "loss": 0.223, "lr": 9.01668033965486e-08, "epoch": 4.727847101563734, "percentage": 94.56, "elapsed_time": "6:14:50", "remaining_time": "0:21:32"}
+{"current_steps": 7490, "total_steps": 7910, "loss": 0.2242, "lr": 8.604317130434137e-08, "epoch": 4.734165218764808, "percentage": 94.69, "elapsed_time": "6:16:25", "remaining_time": "0:21:06"}
+{"current_steps": 7500, "total_steps": 7910, "loss": 0.2232, "lr": 8.201523490504404e-08, "epoch": 4.740483335965882, "percentage": 94.82, "elapsed_time": "6:17:53", "remaining_time": "0:20:39"}
+{"current_steps": 7510, "total_steps": 7910, "loss": 0.2244, "lr": 7.808307263975301e-08, "epoch": 4.746801453166956, "percentage": 94.94, "elapsed_time": "6:19:21", "remaining_time": "0:20:12"}
+{"current_steps": 7520, "total_steps": 7910, "loss": 0.2248, "lr": 7.424676108443551e-08, "epoch": 4.75311957036803, "percentage": 95.07, "elapsed_time": "6:20:49", "remaining_time": "0:19:45"}
+{"current_steps": 7530, "total_steps": 7910, "loss": 0.225, "lr": 7.050637494843526e-08, "epoch": 4.759437687569104, "percentage": 95.2, "elapsed_time": "6:22:14", "remaining_time": "0:19:17"}
+{"current_steps": 7540, "total_steps": 7910, "loss": 0.2256, "lr": 6.686198707301861e-08, "epoch": 4.765755804770178, "percentage": 95.32, "elapsed_time": "6:23:40", "remaining_time": "0:18:49"}
+{"current_steps": 7550, "total_steps": 7910, "loss": 0.2251, "lr": 6.331366842995901e-08, "epoch": 4.772073921971253, "percentage": 95.45, "elapsed_time": "6:24:59", "remaining_time": "0:18:21"}
+{"current_steps": 7560, "total_steps": 7910, "loss": 0.2271, "lr": 5.986148812015036e-08, "epoch": 4.778392039172327, "percentage": 95.58, "elapsed_time": "6:26:23", "remaining_time": "0:17:53"}
+{"current_steps": 7570, "total_steps": 7910, "loss": 0.2247, "lr": 5.650551337226362e-08, "epoch": 4.784710156373401, "percentage": 95.7, "elapsed_time": "6:28:05", "remaining_time": "0:17:25"}
+{"current_steps": 7580, "total_steps": 7910, "loss": 0.225, "lr": 5.324580954143621e-08, "epoch": 4.791028273574475, "percentage": 95.83, "elapsed_time": "6:29:28", "remaining_time": "0:16:57"}
+{"current_steps": 7590, "total_steps": 7910, "loss": 0.2244, "lr": 5.008244010800245e-08, "epoch": 4.797346390775549, "percentage": 95.95, "elapsed_time": "6:30:46", "remaining_time": "0:16:28"}
+{"current_steps": 7600, "total_steps": 7910, "loss": 0.2242, "lr": 4.701546667625401e-08, "epoch": 4.803664507976623, "percentage": 96.08, "elapsed_time": "6:32:05", "remaining_time": "0:15:59"}
+{"current_steps": 7610, "total_steps": 7910, "loss": 0.2241, "lr": 4.4044948973240855e-08, "epoch": 4.809982625177697, "percentage": 96.21, "elapsed_time": "6:33:33", "remaining_time": "0:15:30"}
+{"current_steps": 7620, "total_steps": 7910, "loss": 0.2223, "lr": 4.117094484760942e-08, "epoch": 4.816300742378771, "percentage": 96.33, "elapsed_time": "6:34:59", "remaining_time": "0:15:01"}
+{"current_steps": 7630, "total_steps": 7910, "loss": 0.2245, "lr": 3.8393510268475155e-08, "epoch": 4.822618859579845, "percentage": 96.46, "elapsed_time": "6:36:32", "remaining_time": "0:14:33"}
+{"current_steps": 7640, "total_steps": 7910, "loss": 0.2237, "lr": 3.5712699324331745e-08, "epoch": 4.828936976780919, "percentage": 96.59, "elapsed_time": "6:37:52", "remaining_time": "0:14:03"}
+{"current_steps": 7650, "total_steps": 7910, "loss": 0.2249, "lr": 3.312856422200028e-08, "epoch": 4.835255093981994, "percentage": 96.71, "elapsed_time": "6:39:14", "remaining_time": "0:13:34"}
+{"current_steps": 7660, "total_steps": 7910, "loss": 0.224, "lr": 3.064115528561007e-08, "epoch": 4.841573211183068, "percentage": 96.84, "elapsed_time": "6:40:51", "remaining_time": "0:13:04"}
+{"current_steps": 7670, "total_steps": 7910, "loss": 0.2206, "lr": 2.8250520955618864e-08, "epoch": 4.847891328384142, "percentage": 96.97, "elapsed_time": "6:42:38", "remaining_time": "0:12:35"}
+{"current_steps": 7680, "total_steps": 7910, "loss": 0.2254, "lr": 2.595670778787196e-08, "epoch": 4.854209445585216, "percentage": 97.09, "elapsed_time": "6:44:09", "remaining_time": "0:12:06"}
+{"current_steps": 7690, "total_steps": 7910, "loss": 0.2249, "lr": 2.3759760452691794e-08, "epoch": 4.86052756278629, "percentage": 97.22, "elapsed_time": "6:45:36", "remaining_time": "0:11:36"}
+{"current_steps": 7700, "total_steps": 7910, "loss": 0.2237, "lr": 2.165972173401143e-08, "epoch": 4.866845679987364, "percentage": 97.35, "elapsed_time": "6:47:04", "remaining_time": "0:11:06"}
+{"current_steps": 7710, "total_steps": 7910, "loss": 0.2246, "lr": 1.965663252853911e-08, "epoch": 4.873163797188438, "percentage": 97.47, "elapsed_time": "6:48:34", "remaining_time": "0:10:35"}
+{"current_steps": 7720, "total_steps": 7910, "loss": 0.2245, "lr": 1.7750531844963335e-08, "epoch": 4.879481914389512, "percentage": 97.6, "elapsed_time": "6:49:58", "remaining_time": "0:10:05"}
+{"current_steps": 7730, "total_steps": 7910, "loss": 0.2221, "lr": 1.5941456803191812e-08, "epoch": 4.885800031590586, "percentage": 97.72, "elapsed_time": "6:51:34", "remaining_time": "0:09:35"}
+{"current_steps": 7740, "total_steps": 7910, "loss": 0.2224, "lr": 1.4229442633630353e-08, "epoch": 4.89211814879166, "percentage": 97.85, "elapsed_time": "6:53:01", "remaining_time": "0:09:04"}
+{"current_steps": 7750, "total_steps": 7910, "loss": 0.2217, "lr": 1.2614522676493435e-08, "epoch": 4.898436265992734, "percentage": 97.98, "elapsed_time": "6:54:24", "remaining_time": "0:08:33"}
+{"current_steps": 7760, "total_steps": 7910, "loss": 0.2236, "lr": 1.1096728381160271e-08, "epoch": 4.904754383193808, "percentage": 98.1, "elapsed_time": "6:55:59", "remaining_time": "0:08:02"}
+{"current_steps": 7770, "total_steps": 7910, "loss": 0.2244, "lr": 9.676089305557523e-09, "epoch": 4.911072500394882, "percentage": 98.23, "elapsed_time": "6:57:22", "remaining_time": "0:07:31"}
+{"current_steps": 7780, "total_steps": 7910, "loss": 0.2257, "lr": 8.352633115584764e-09, "epoch": 4.917390617595957, "percentage": 98.36, "elapsed_time": "6:58:42", "remaining_time": "0:06:59"}
+{"current_steps": 7790, "total_steps": 7910, "loss": 0.2231, "lr": 7.1263855845782325e-09, "epoch": 4.923708734797031, "percentage": 98.48, "elapsed_time": "7:00:04", "remaining_time": "0:06:28"}
+{"current_steps": 7800, "total_steps": 7910, "loss": 0.2241, "lr": 5.997370592806251e-09, "epoch": 4.930026851998105, "percentage": 98.61, "elapsed_time": "7:01:32", "remaining_time": "0:05:56"}
+{"current_steps": 7810, "total_steps": 7910, "loss": 0.2229, "lr": 4.965610127004028e-09, "epoch": 4.936344969199179, "percentage": 98.74, "elapsed_time": "7:02:51", "remaining_time": "0:05:24"}
+{"current_steps": 7820, "total_steps": 7910, "loss": 0.2231, "lr": 4.031124279948451e-09, "epoch": 4.942663086400253, "percentage": 98.86, "elapsed_time": "7:04:31", "remaining_time": "0:04:53"}
+{"current_steps": 7830, "total_steps": 7910, "loss": 0.2249, "lr": 3.193931250062843e-09, "epoch": 4.948981203601327, "percentage": 98.99, "elapsed_time": "7:05:52", "remaining_time": "0:04:21"}
+{"current_steps": 7840, "total_steps": 7910, "loss": 0.2253, "lr": 2.45404734106558e-09, "epoch": 4.955299320802401, "percentage": 99.12, "elapsed_time": "7:07:21", "remaining_time": "0:03:48"}
+{"current_steps": 7850, "total_steps": 7910, "loss": 0.2246, "lr": 1.811486961650899e-09, "epoch": 4.961617438003475, "percentage": 99.24, "elapsed_time": "7:08:48", "remaining_time": "0:03:16"}
+{"current_steps": 7860, "total_steps": 7910, "loss": 0.2225, "lr": 1.266262625210235e-09, "epoch": 4.967935555204549, "percentage": 99.37, "elapsed_time": "7:10:17", "remaining_time": "0:02:44"}
+{"current_steps": 7870, "total_steps": 7910, "loss": 0.2237, "lr": 8.183849495851937e-10, "epoch": 4.974253672405623, "percentage": 99.49, "elapsed_time": "7:11:37", "remaining_time": "0:02:11"}
+{"current_steps": 7880, "total_steps": 7910, "loss": 0.223, "lr": 4.678626568649369e-10, "epoch": 4.980571789606698, "percentage": 99.62, "elapsed_time": "7:13:01", "remaining_time": "0:01:38"}
+{"current_steps": 7890, "total_steps": 7910, "loss": 0.2237, "lr": 2.1470257321298815e-10, "epoch": 4.986889906807772, "percentage": 99.75, "elapsed_time": "7:14:22", "remaining_time": "0:01:06"}
+{"current_steps": 7900, "total_steps": 7910, "loss": 0.2235, "lr": 5.890962873456029e-11, "epoch": 4.993208024008846, "percentage": 99.87, "elapsed_time": "7:15:47", "remaining_time": "0:00:33"}
+{"current_steps": 7910, "total_steps": 7910, "loss": 0.2249, "lr": 4.868573838523461e-13, "epoch": 4.99952614120992, "percentage": 100.0, "elapsed_time": "7:17:10", "remaining_time": "0:00:00"}
+{"current_steps": 7910, "total_steps": 7910, "epoch": 4.99952614120992, "percentage": 100.0, "elapsed_time": "7:17:38", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c97426fc4ecb507399844d65d36e1e1ffb0326ae3f92237901eeb13d2827eb
+size 7480