Upload my folder using huggingface_hub

.gitattributes

@@ -33,3 +33,11 @@ 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
+EXP_1.1_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+EXP_1.2_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+EXP_2.1_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+EXP_3.1_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+EXP_3.2_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+EXP_4.1_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+EXP_4.2_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+EXP_4.3_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

EXP_1.1_3b/README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: other
+base_model: /mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: EXP_1.1_3b
+  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. -->
+
+# EXP_1.1_3b
+
+This model is a fine-tuned version of [/mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct](https://huggingface.co//mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct) on the multimodal-open-r1-8k-verified_vision-r1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6923
+
+## 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: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- 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: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.705         | 0.6161 | 500  | 0.7098          |
+| 0.5925        | 1.2317 | 1000 | 0.6842          |
+| 0.5739        | 1.8478 | 1500 | 0.6650          |
+| 0.4637        | 2.4633 | 2000 | 0.6939          |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

EXP_1.1_3b/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
+}

EXP_1.1_3b/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6922884583473206,
+    "eval_runtime": 292.8509,
+    "eval_samples_per_second": 19.699,
+    "eval_steps_per_second": 2.465,
+    "total_flos": 598743726292992.0,
+    "train_loss": 0.6124914906099317,
+    "train_runtime": 9399.7215,
+    "train_samples_per_second": 16.571,
+    "train_steps_per_second": 0.259
+}

EXP_1.1_3b/chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

EXP_1.1_3b/config.json

@@ -0,0 +1,105 @@
+{
+  "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,
+  "text_config": {
+    "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": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 128000,
+    "max_window_layers": 70,
+    "model_type": "qwen2_5_vl_text",
+    "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": "float32",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "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,
+    "initializer_range": 0.02,
+    "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": "float32",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

EXP_1.1_3b/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6922884583473206,
+    "eval_runtime": 292.8509,
+    "eval_samples_per_second": 19.699,
+    "eval_steps_per_second": 2.465
+}

EXP_1.1_3b/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": "4.52.4"
+}

EXP_1.1_3b/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feef36fe2a7a4052196322b7ed49c3067cda293d7686323b4a8afd6604364848
+size 4997750760

EXP_1.1_3b/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cdcaf4c1e4c5d2e450d5c9a6cb01c20c7ece20c9500874b86ec6f6a582403c
+size 2511587184

EXP_1.1_3b/model.safetensors.index.json

@@ -0,0 +1,831 @@
+{
+  "metadata": {
+    "total_size": 7509245952
+  },
+  "weight_map": {
+    "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"
+  }
+}

EXP_1.1_3b/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
+}

EXP_1.1_3b/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
+  }
+}

EXP_1.1_3b/swanlab_public_config.json

@@ -0,0 +1,13 @@
+{
+  "project_name": "LLaMA-Factory",
+  "version": "0.6.1",
+  "run_id": "run-20250610_130347-a3b1799d",
+  "swanlog_dir": "/mnt/nvme/hyz/LLaMA-Factory/swanlog",
+  "run_dir": "/mnt/nvme/hyz/LLaMA-Factory/swanlog/run-20250610_130347-a3b1799d",
+  "cloud": {
+    "project_name": "LLaMA-Factory",
+    "project_url": "https://swanlab.cn/@huyuanze/LLaMA-Factory",
+    "experiment_name": "/mnt/nvme/hyz/mm_homework/checkpoints_full/EXP_1.1_3b",
+    "experiment_url": "https://swanlab.cn/@huyuanze/LLaMA-Factory/runs/s4avvpm017ngll7xxeef0"
+  }
+}

EXP_1.1_3b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

EXP_1.1_3b/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

EXP_1.1_3b/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 598743726292992.0,
+    "train_loss": 0.6124914906099317,
+    "train_runtime": 9399.7215,
+    "train_samples_per_second": 16.571,
+    "train_steps_per_second": 0.259
+}

EXP_1.1_3b/trainer_log.jsonl

@@ -0,0 +1,248 @@
+{"current_steps": 10, "total_steps": 2436, "loss": 1.5881, "lr": 3.6885245901639347e-07, "epoch": 0.012322858903265557, "percentage": 0.41, "elapsed_time": "0:00:38", "remaining_time": "2:35:42"}
+{"current_steps": 20, "total_steps": 2436, "loss": 1.6078, "lr": 7.78688524590164e-07, "epoch": 0.024645717806531114, "percentage": 0.82, "elapsed_time": "0:01:10", "remaining_time": "2:22:11"}
+{"current_steps": 30, "total_steps": 2436, "loss": 1.5155, "lr": 1.1885245901639345e-06, "epoch": 0.036968576709796676, "percentage": 1.23, "elapsed_time": "0:01:44", "remaining_time": "2:19:57"}
+{"current_steps": 40, "total_steps": 2436, "loss": 1.3049, "lr": 1.5983606557377053e-06, "epoch": 0.04929143561306223, "percentage": 1.64, "elapsed_time": "0:02:18", "remaining_time": "2:18:25"}
+{"current_steps": 50, "total_steps": 2436, "loss": 1.1069, "lr": 2.0081967213114756e-06, "epoch": 0.061614294516327786, "percentage": 2.05, "elapsed_time": "0:02:52", "remaining_time": "2:16:49"}
+{"current_steps": 60, "total_steps": 2436, "loss": 0.9964, "lr": 2.418032786885246e-06, "epoch": 0.07393715341959335, "percentage": 2.46, "elapsed_time": "0:03:25", "remaining_time": "2:15:39"}
+{"current_steps": 70, "total_steps": 2436, "loss": 0.9526, "lr": 2.8278688524590166e-06, "epoch": 0.0862600123228589, "percentage": 2.87, "elapsed_time": "0:04:01", "remaining_time": "2:15:51"}
+{"current_steps": 80, "total_steps": 2436, "loss": 0.9071, "lr": 3.2377049180327876e-06, "epoch": 0.09858287122612445, "percentage": 3.28, "elapsed_time": "0:04:33", "remaining_time": "2:14:24"}
+{"current_steps": 90, "total_steps": 2436, "loss": 0.8833, "lr": 3.6475409836065577e-06, "epoch": 0.11090573012939002, "percentage": 3.69, "elapsed_time": "0:05:07", "remaining_time": "2:13:34"}
+{"current_steps": 100, "total_steps": 2436, "loss": 0.8617, "lr": 4.057377049180329e-06, "epoch": 0.12322858903265557, "percentage": 4.11, "elapsed_time": "0:05:43", "remaining_time": "2:13:41"}
+{"current_steps": 110, "total_steps": 2436, "loss": 0.8439, "lr": 4.467213114754098e-06, "epoch": 0.13555144793592114, "percentage": 4.52, "elapsed_time": "0:06:18", "remaining_time": "2:13:27"}
+{"current_steps": 120, "total_steps": 2436, "loss": 0.8494, "lr": 4.877049180327869e-06, "epoch": 0.1478743068391867, "percentage": 4.93, "elapsed_time": "0:06:54", "remaining_time": "2:13:27"}
+{"current_steps": 130, "total_steps": 2436, "loss": 0.8114, "lr": 5.286885245901639e-06, "epoch": 0.16019716574245224, "percentage": 5.34, "elapsed_time": "0:07:28", "remaining_time": "2:12:29"}
+{"current_steps": 140, "total_steps": 2436, "loss": 0.7865, "lr": 5.696721311475411e-06, "epoch": 0.1725200246457178, "percentage": 5.75, "elapsed_time": "0:08:01", "remaining_time": "2:11:41"}
+{"current_steps": 150, "total_steps": 2436, "loss": 0.8102, "lr": 6.10655737704918e-06, "epoch": 0.18484288354898337, "percentage": 6.16, "elapsed_time": "0:08:33", "remaining_time": "2:10:30"}
+{"current_steps": 160, "total_steps": 2436, "loss": 0.7978, "lr": 6.516393442622952e-06, "epoch": 0.1971657424522489, "percentage": 6.57, "elapsed_time": "0:09:08", "remaining_time": "2:10:06"}
+{"current_steps": 170, "total_steps": 2436, "loss": 0.7969, "lr": 6.926229508196722e-06, "epoch": 0.20948860135551448, "percentage": 6.98, "elapsed_time": "0:09:44", "remaining_time": "2:09:56"}
+{"current_steps": 180, "total_steps": 2436, "loss": 0.7821, "lr": 7.336065573770492e-06, "epoch": 0.22181146025878004, "percentage": 7.39, "elapsed_time": "0:10:19", "remaining_time": "2:09:18"}
+{"current_steps": 190, "total_steps": 2436, "loss": 0.7654, "lr": 7.745901639344263e-06, "epoch": 0.2341343191620456, "percentage": 7.8, "elapsed_time": "0:10:53", "remaining_time": "2:08:45"}
+{"current_steps": 200, "total_steps": 2436, "loss": 0.7924, "lr": 8.155737704918034e-06, "epoch": 0.24645717806531114, "percentage": 8.21, "elapsed_time": "0:11:28", "remaining_time": "2:08:18"}
+{"current_steps": 210, "total_steps": 2436, "loss": 0.7754, "lr": 8.565573770491804e-06, "epoch": 0.2587800369685767, "percentage": 8.62, "elapsed_time": "0:12:02", "remaining_time": "2:07:38"}
+{"current_steps": 220, "total_steps": 2436, "loss": 0.7685, "lr": 8.975409836065575e-06, "epoch": 0.2711028958718423, "percentage": 9.03, "elapsed_time": "0:12:34", "remaining_time": "2:06:44"}
+{"current_steps": 230, "total_steps": 2436, "loss": 0.766, "lr": 9.385245901639345e-06, "epoch": 0.28342575477510784, "percentage": 9.44, "elapsed_time": "0:13:09", "remaining_time": "2:06:13"}
+{"current_steps": 240, "total_steps": 2436, "loss": 0.7709, "lr": 9.795081967213116e-06, "epoch": 0.2957486136783734, "percentage": 9.85, "elapsed_time": "0:13:42", "remaining_time": "2:05:24"}
+{"current_steps": 250, "total_steps": 2436, "loss": 0.7434, "lr": 9.999871620167532e-06, "epoch": 0.3080714725816389, "percentage": 10.26, "elapsed_time": "0:14:15", "remaining_time": "2:04:41"}
+{"current_steps": 260, "total_steps": 2436, "loss": 0.7559, "lr": 9.998844621062755e-06, "epoch": 0.3203943314849045, "percentage": 10.67, "elapsed_time": "0:14:50", "remaining_time": "2:04:11"}
+{"current_steps": 270, "total_steps": 2436, "loss": 0.7541, "lr": 9.996790833804053e-06, "epoch": 0.33271719038817005, "percentage": 11.08, "elapsed_time": "0:15:22", "remaining_time": "2:03:24"}
+{"current_steps": 280, "total_steps": 2436, "loss": 0.7565, "lr": 9.993710680249788e-06, "epoch": 0.3450400492914356, "percentage": 11.49, "elapsed_time": "0:15:53", "remaining_time": "2:02:23"}
+{"current_steps": 290, "total_steps": 2436, "loss": 0.7488, "lr": 9.989604793079198e-06, "epoch": 0.3573629081947012, "percentage": 11.9, "elapsed_time": "0:16:26", "remaining_time": "2:01:42"}
+{"current_steps": 300, "total_steps": 2436, "loss": 0.7542, "lr": 9.984474015662421e-06, "epoch": 0.36968576709796674, "percentage": 12.32, "elapsed_time": "0:17:00", "remaining_time": "2:01:04"}
+{"current_steps": 310, "total_steps": 2436, "loss": 0.7626, "lr": 9.978319401887287e-06, "epoch": 0.3820086260012323, "percentage": 12.73, "elapsed_time": "0:17:32", "remaining_time": "2:00:16"}
+{"current_steps": 320, "total_steps": 2436, "loss": 0.7445, "lr": 9.971142215942817e-06, "epoch": 0.3943314849044978, "percentage": 13.14, "elapsed_time": "0:18:06", "remaining_time": "1:59:46"}
+{"current_steps": 330, "total_steps": 2436, "loss": 0.7438, "lr": 9.962943932059573e-06, "epoch": 0.4066543438077634, "percentage": 13.55, "elapsed_time": "0:18:41", "remaining_time": "1:59:17"}
+{"current_steps": 340, "total_steps": 2436, "loss": 0.7403, "lr": 9.953726234206835e-06, "epoch": 0.41897720271102895, "percentage": 13.96, "elapsed_time": "0:19:13", "remaining_time": "1:58:33"}
+{"current_steps": 350, "total_steps": 2436, "loss": 0.7459, "lr": 9.943491015746704e-06, "epoch": 0.4313000616142945, "percentage": 14.37, "elapsed_time": "0:19:47", "remaining_time": "1:57:56"}
+{"current_steps": 360, "total_steps": 2436, "loss": 0.7361, "lr": 9.9322403790452e-06, "epoch": 0.4436229205175601, "percentage": 14.78, "elapsed_time": "0:20:22", "remaining_time": "1:57:32"}
+{"current_steps": 370, "total_steps": 2436, "loss": 0.7373, "lr": 9.919976635040425e-06, "epoch": 0.45594577942082565, "percentage": 15.19, "elapsed_time": "0:20:55", "remaining_time": "1:56:49"}
+{"current_steps": 380, "total_steps": 2436, "loss": 0.7279, "lr": 9.906702302767876e-06, "epoch": 0.4682686383240912, "percentage": 15.6, "elapsed_time": "0:21:29", "remaining_time": "1:56:14"}
+{"current_steps": 390, "total_steps": 2436, "loss": 0.7503, "lr": 9.892420108843038e-06, "epoch": 0.4805914972273567, "percentage": 16.01, "elapsed_time": "0:22:03", "remaining_time": "1:55:43"}
+{"current_steps": 400, "total_steps": 2436, "loss": 0.7528, "lr": 9.877132986901306e-06, "epoch": 0.4929143561306223, "percentage": 16.42, "elapsed_time": "0:22:35", "remaining_time": "1:55:00"}
+{"current_steps": 410, "total_steps": 2436, "loss": 0.7472, "lr": 9.860844076995416e-06, "epoch": 0.5052372150338879, "percentage": 16.83, "elapsed_time": "0:23:10", "remaining_time": "1:54:28"}
+{"current_steps": 420, "total_steps": 2436, "loss": 0.7338, "lr": 9.843556724950454e-06, "epoch": 0.5175600739371534, "percentage": 17.24, "elapsed_time": "0:23:44", "remaining_time": "1:53:57"}
+{"current_steps": 430, "total_steps": 2436, "loss": 0.716, "lr": 9.825274481676605e-06, "epoch": 0.529882932840419, "percentage": 17.65, "elapsed_time": "0:24:18", "remaining_time": "1:53:25"}
+{"current_steps": 440, "total_steps": 2436, "loss": 0.7381, "lr": 9.806001102439789e-06, "epoch": 0.5422057917436846, "percentage": 18.06, "elapsed_time": "0:24:49", "remaining_time": "1:52:37"}
+{"current_steps": 450, "total_steps": 2436, "loss": 0.72, "lr": 9.785740546090293e-06, "epoch": 0.5545286506469501, "percentage": 18.47, "elapsed_time": "0:25:22", "remaining_time": "1:51:58"}
+{"current_steps": 460, "total_steps": 2436, "loss": 0.7302, "lr": 9.76449697424962e-06, "epoch": 0.5668515095502157, "percentage": 18.88, "elapsed_time": "0:25:57", "remaining_time": "1:51:29"}
+{"current_steps": 470, "total_steps": 2436, "loss": 0.7165, "lr": 9.742274750455659e-06, "epoch": 0.5791743684534812, "percentage": 19.29, "elapsed_time": "0:26:30", "remaining_time": "1:50:53"}
+{"current_steps": 480, "total_steps": 2436, "loss": 0.715, "lr": 9.719078439266399e-06, "epoch": 0.5914972273567468, "percentage": 19.7, "elapsed_time": "0:27:01", "remaining_time": "1:50:07"}
+{"current_steps": 490, "total_steps": 2436, "loss": 0.7328, "lr": 9.69491280532234e-06, "epoch": 0.6038200862600123, "percentage": 20.11, "elapsed_time": "0:27:33", "remaining_time": "1:49:25"}
+{"current_steps": 500, "total_steps": 2436, "loss": 0.705, "lr": 9.66978281236782e-06, "epoch": 0.6161429451632778, "percentage": 20.53, "elapsed_time": "0:28:09", "remaining_time": "1:49:01"}
+{"current_steps": 500, "total_steps": 2436, "eval_loss": 0.7097772359848022, "epoch": 0.6161429451632778, "percentage": 20.53, "elapsed_time": "0:32:59", "remaining_time": "2:07:42"}
+{"current_steps": 510, "total_steps": 2436, "loss": 0.7196, "lr": 9.643693622231426e-06, "epoch": 0.6284658040665434, "percentage": 20.94, "elapsed_time": "0:33:31", "remaining_time": "2:06:36"}
+{"current_steps": 520, "total_steps": 2436, "loss": 0.7212, "lr": 9.616650593765733e-06, "epoch": 0.640788662969809, "percentage": 21.35, "elapsed_time": "0:34:05", "remaining_time": "2:05:36"}
+{"current_steps": 530, "total_steps": 2436, "loss": 0.7038, "lr": 9.58865928174657e-06, "epoch": 0.6531115218730745, "percentage": 21.76, "elapsed_time": "0:34:36", "remaining_time": "2:04:28"}
+{"current_steps": 540, "total_steps": 2436, "loss": 0.7108, "lr": 9.559725435732042e-06, "epoch": 0.6654343807763401, "percentage": 22.17, "elapsed_time": "0:35:09", "remaining_time": "2:03:28"}
+{"current_steps": 550, "total_steps": 2436, "loss": 0.7164, "lr": 9.529854998881534e-06, "epoch": 0.6777572396796057, "percentage": 22.58, "elapsed_time": "0:35:43", "remaining_time": "2:02:29"}
+{"current_steps": 560, "total_steps": 2436, "loss": 0.7183, "lr": 9.499054106734963e-06, "epoch": 0.6900800985828712, "percentage": 22.99, "elapsed_time": "0:36:13", "remaining_time": "2:01:20"}
+{"current_steps": 570, "total_steps": 2436, "loss": 0.7082, "lr": 9.467329085952505e-06, "epoch": 0.7024029574861368, "percentage": 23.4, "elapsed_time": "0:36:46", "remaining_time": "2:00:23"}
+{"current_steps": 580, "total_steps": 2436, "loss": 0.7136, "lr": 9.434686453015067e-06, "epoch": 0.7147258163894024, "percentage": 23.81, "elapsed_time": "0:37:15", "remaining_time": "1:59:14"}
+{"current_steps": 590, "total_steps": 2436, "loss": 0.7225, "lr": 9.401132912885764e-06, "epoch": 0.7270486752926679, "percentage": 24.22, "elapsed_time": "0:37:47", "remaining_time": "1:58:13"}
+{"current_steps": 600, "total_steps": 2436, "loss": 0.7133, "lr": 9.36667535763269e-06, "epoch": 0.7393715341959335, "percentage": 24.63, "elapsed_time": "0:38:23", "remaining_time": "1:57:29"}
+{"current_steps": 610, "total_steps": 2436, "loss": 0.7063, "lr": 9.331320865013257e-06, "epoch": 0.751694393099199, "percentage": 25.04, "elapsed_time": "0:38:56", "remaining_time": "1:56:34"}
+{"current_steps": 620, "total_steps": 2436, "loss": 0.6986, "lr": 9.295076697020378e-06, "epoch": 0.7640172520024646, "percentage": 25.45, "elapsed_time": "0:39:29", "remaining_time": "1:55:40"}
+{"current_steps": 630, "total_steps": 2436, "loss": 0.706, "lr": 9.257950298390815e-06, "epoch": 0.7763401109057301, "percentage": 25.86, "elapsed_time": "0:40:04", "remaining_time": "1:54:54"}
+{"current_steps": 640, "total_steps": 2436, "loss": 0.7083, "lr": 9.219949295076006e-06, "epoch": 0.7886629698089956, "percentage": 26.27, "elapsed_time": "0:40:39", "remaining_time": "1:54:05"}
+{"current_steps": 650, "total_steps": 2436, "loss": 0.7066, "lr": 9.181081492675645e-06, "epoch": 0.8009858287122612, "percentage": 26.68, "elapsed_time": "0:41:11", "remaining_time": "1:53:11"}
+{"current_steps": 660, "total_steps": 2436, "loss": 0.6922, "lr": 9.141354874834372e-06, "epoch": 0.8133086876155268, "percentage": 27.09, "elapsed_time": "0:41:43", "remaining_time": "1:52:16"}
+{"current_steps": 670, "total_steps": 2436, "loss": 0.686, "lr": 9.100777601601896e-06, "epoch": 0.8256315465187923, "percentage": 27.5, "elapsed_time": "0:42:18", "remaining_time": "1:51:31"}
+{"current_steps": 680, "total_steps": 2436, "loss": 0.7045, "lr": 9.05935800775688e-06, "epoch": 0.8379544054220579, "percentage": 27.91, "elapsed_time": "0:42:54", "remaining_time": "1:50:47"}
+{"current_steps": 690, "total_steps": 2436, "loss": 0.6952, "lr": 9.017104601094927e-06, "epoch": 0.8502772643253235, "percentage": 28.33, "elapsed_time": "0:43:26", "remaining_time": "1:49:56"}
+{"current_steps": 700, "total_steps": 2436, "loss": 0.6905, "lr": 8.974026060681044e-06, "epoch": 0.862600123228589, "percentage": 28.74, "elapsed_time": "0:44:03", "remaining_time": "1:49:15"}
+{"current_steps": 710, "total_steps": 2436, "loss": 0.7148, "lr": 8.930131235066914e-06, "epoch": 0.8749229821318546, "percentage": 29.15, "elapsed_time": "0:44:37", "remaining_time": "1:48:28"}
+{"current_steps": 720, "total_steps": 2436, "loss": 0.693, "lr": 8.885429140473361e-06, "epoch": 0.8872458410351202, "percentage": 29.56, "elapsed_time": "0:45:10", "remaining_time": "1:47:40"}
+{"current_steps": 730, "total_steps": 2436, "loss": 0.7023, "lr": 8.839928958938364e-06, "epoch": 0.8995686999383857, "percentage": 29.97, "elapsed_time": "0:45:43", "remaining_time": "1:46:52"}
+{"current_steps": 740, "total_steps": 2436, "loss": 0.7014, "lr": 8.793640036431036e-06, "epoch": 0.9118915588416513, "percentage": 30.38, "elapsed_time": "0:46:15", "remaining_time": "1:46:02"}
+{"current_steps": 750, "total_steps": 2436, "loss": 0.7153, "lr": 8.746571880931896e-06, "epoch": 0.9242144177449169, "percentage": 30.79, "elapsed_time": "0:46:50", "remaining_time": "1:45:17"}
+{"current_steps": 760, "total_steps": 2436, "loss": 0.7031, "lr": 8.698734160479892e-06, "epoch": 0.9365372766481824, "percentage": 31.2, "elapsed_time": "0:47:23", "remaining_time": "1:44:31"}
+{"current_steps": 770, "total_steps": 2436, "loss": 0.6744, "lr": 8.650136701186537e-06, "epoch": 0.9488601355514479, "percentage": 31.61, "elapsed_time": "0:47:56", "remaining_time": "1:43:43"}
+{"current_steps": 780, "total_steps": 2436, "loss": 0.6921, "lr": 8.60078948521757e-06, "epoch": 0.9611829944547134, "percentage": 32.02, "elapsed_time": "0:48:30", "remaining_time": "1:42:59"}
+{"current_steps": 790, "total_steps": 2436, "loss": 0.6956, "lr": 8.550702648742566e-06, "epoch": 0.973505853357979, "percentage": 32.43, "elapsed_time": "0:49:06", "remaining_time": "1:42:19"}
+{"current_steps": 800, "total_steps": 2436, "loss": 0.7018, "lr": 8.499886479852935e-06, "epoch": 0.9858287122612446, "percentage": 32.84, "elapsed_time": "0:49:39", "remaining_time": "1:41:33"}
+{"current_steps": 810, "total_steps": 2436, "loss": 0.7032, "lr": 8.448351416448664e-06, "epoch": 0.9981515711645101, "percentage": 33.25, "elapsed_time": "0:50:15", "remaining_time": "1:40:52"}
+{"current_steps": 820, "total_steps": 2436, "loss": 0.595, "lr": 8.39610804409435e-06, "epoch": 1.0098582871226125, "percentage": 33.66, "elapsed_time": "0:50:47", "remaining_time": "1:40:06"}
+{"current_steps": 830, "total_steps": 2436, "loss": 0.5946, "lr": 8.343167093844847e-06, "epoch": 1.022181146025878, "percentage": 34.07, "elapsed_time": "0:51:21", "remaining_time": "1:39:23"}
+{"current_steps": 840, "total_steps": 2436, "loss": 0.5845, "lr": 8.289539440041066e-06, "epoch": 1.0345040049291436, "percentage": 34.48, "elapsed_time": "0:51:54", "remaining_time": "1:38:38"}
+{"current_steps": 850, "total_steps": 2436, "loss": 0.584, "lr": 8.23523609807633e-06, "epoch": 1.0468268638324092, "percentage": 34.89, "elapsed_time": "0:52:26", "remaining_time": "1:37:51"}
+{"current_steps": 860, "total_steps": 2436, "loss": 0.5847, "lr": 8.180268222133748e-06, "epoch": 1.0591497227356748, "percentage": 35.3, "elapsed_time": "0:53:01", "remaining_time": "1:37:09"}
+{"current_steps": 870, "total_steps": 2436, "loss": 0.5925, "lr": 8.124647102895098e-06, "epoch": 1.0714725816389403, "percentage": 35.71, "elapsed_time": "0:53:35", "remaining_time": "1:36:27"}
+{"current_steps": 880, "total_steps": 2436, "loss": 0.584, "lr": 8.068384165221657e-06, "epoch": 1.083795440542206, "percentage": 36.12, "elapsed_time": "0:54:09", "remaining_time": "1:35:45"}
+{"current_steps": 890, "total_steps": 2436, "loss": 0.5932, "lr": 8.011490965807479e-06, "epoch": 1.0961182994454712, "percentage": 36.54, "elapsed_time": "0:54:42", "remaining_time": "1:35:01"}
+{"current_steps": 900, "total_steps": 2436, "loss": 0.5642, "lr": 7.953979190805587e-06, "epoch": 1.1084411583487368, "percentage": 36.95, "elapsed_time": "0:55:17", "remaining_time": "1:34:21"}
+{"current_steps": 910, "total_steps": 2436, "loss": 0.6045, "lr": 7.89586065342759e-06, "epoch": 1.1207640172520024, "percentage": 37.36, "elapsed_time": "0:55:49", "remaining_time": "1:33:37"}
+{"current_steps": 920, "total_steps": 2436, "loss": 0.5985, "lr": 7.837147291517172e-06, "epoch": 1.133086876155268, "percentage": 37.77, "elapsed_time": "0:56:23", "remaining_time": "1:32:55"}
+{"current_steps": 930, "total_steps": 2436, "loss": 0.5686, "lr": 7.777851165098012e-06, "epoch": 1.1454097350585335, "percentage": 38.18, "elapsed_time": "0:56:54", "remaining_time": "1:32:08"}
+{"current_steps": 940, "total_steps": 2436, "loss": 0.5888, "lr": 7.717984453896585e-06, "epoch": 1.157732593961799, "percentage": 38.59, "elapsed_time": "0:57:30", "remaining_time": "1:31:30"}
+{"current_steps": 950, "total_steps": 2436, "loss": 0.5813, "lr": 7.657559454840386e-06, "epoch": 1.1700554528650646, "percentage": 39.0, "elapsed_time": "0:58:03", "remaining_time": "1:30:49"}
+{"current_steps": 960, "total_steps": 2436, "loss": 0.582, "lr": 7.596588579532087e-06, "epoch": 1.1823783117683302, "percentage": 39.41, "elapsed_time": "0:58:37", "remaining_time": "1:30:08"}
+{"current_steps": 970, "total_steps": 2436, "loss": 0.5855, "lr": 7.535084351700117e-06, "epoch": 1.1947011706715958, "percentage": 39.82, "elapsed_time": "0:59:10", "remaining_time": "1:29:25"}
+{"current_steps": 980, "total_steps": 2436, "loss": 0.5842, "lr": 7.473059404626229e-06, "epoch": 1.2070240295748613, "percentage": 40.23, "elapsed_time": "0:59:43", "remaining_time": "1:28:44"}
+{"current_steps": 990, "total_steps": 2436, "loss": 0.5927, "lr": 7.410526478550568e-06, "epoch": 1.219346888478127, "percentage": 40.64, "elapsed_time": "1:00:18", "remaining_time": "1:28:04"}
+{"current_steps": 1000, "total_steps": 2436, "loss": 0.5925, "lr": 7.34749841805475e-06, "epoch": 1.2316697473813925, "percentage": 41.05, "elapsed_time": "1:00:50", "remaining_time": "1:27:22"}
+{"current_steps": 1000, "total_steps": 2436, "eval_loss": 0.6842279434204102, "epoch": 1.2316697473813925, "percentage": 41.05, "elapsed_time": "1:05:43", "remaining_time": "1:34:22"}
+{"current_steps": 1010, "total_steps": 2436, "loss": 0.6095, "lr": 7.283988169423526e-06, "epoch": 1.243992606284658, "percentage": 41.46, "elapsed_time": "1:06:35", "remaining_time": "1:34:01"}
+{"current_steps": 1020, "total_steps": 2436, "loss": 0.5953, "lr": 7.2200087779855435e-06, "epoch": 1.2563154651879236, "percentage": 41.87, "elapsed_time": "1:07:07", "remaining_time": "1:33:11"}
+{"current_steps": 1030, "total_steps": 2436, "loss": 0.5913, "lr": 7.155573385433772e-06, "epoch": 1.2686383240911892, "percentage": 42.28, "elapsed_time": "1:07:41", "remaining_time": "1:32:24"}
+{"current_steps": 1040, "total_steps": 2436, "loss": 0.6022, "lr": 7.090695227126141e-06, "epoch": 1.2809611829944547, "percentage": 42.69, "elapsed_time": "1:08:15", "remaining_time": "1:31:37"}
+{"current_steps": 1050, "total_steps": 2436, "loss": 0.5891, "lr": 7.025387629366912e-06, "epoch": 1.2932840418977203, "percentage": 43.1, "elapsed_time": "1:08:51", "remaining_time": "1:30:53"}
+{"current_steps": 1060, "total_steps": 2436, "loss": 0.578, "lr": 6.959664006669404e-06, "epoch": 1.3056069008009858, "percentage": 43.51, "elapsed_time": "1:09:22", "remaining_time": "1:30:03"}
+{"current_steps": 1070, "total_steps": 2436, "loss": 0.5837, "lr": 6.893537859000576e-06, "epoch": 1.3179297597042514, "percentage": 43.92, "elapsed_time": "1:09:55", "remaining_time": "1:29:16"}
+{"current_steps": 1080, "total_steps": 2436, "loss": 0.5783, "lr": 6.827022769008068e-06, "epoch": 1.330252618607517, "percentage": 44.33, "elapsed_time": "1:10:30", "remaining_time": "1:28:31"}
+{"current_steps": 1090, "total_steps": 2436, "loss": 0.5882, "lr": 6.7601323992302525e-06, "epoch": 1.3425754775107825, "percentage": 44.75, "elapsed_time": "1:11:02", "remaining_time": "1:27:43"}
+{"current_steps": 1100, "total_steps": 2436, "loss": 0.5889, "lr": 6.692880489289885e-06, "epoch": 1.354898336414048, "percentage": 45.16, "elapsed_time": "1:11:38", "remaining_time": "1:27:00"}
+{"current_steps": 1110, "total_steps": 2436, "loss": 0.5886, "lr": 6.6252808530719095e-06, "epoch": 1.3672211953173137, "percentage": 45.57, "elapsed_time": "1:12:12", "remaining_time": "1:26:15"}
+{"current_steps": 1120, "total_steps": 2436, "loss": 0.5737, "lr": 6.557347375886022e-06, "epoch": 1.3795440542205792, "percentage": 45.98, "elapsed_time": "1:12:45", "remaining_time": "1:25:29"}
+{"current_steps": 1130, "total_steps": 2436, "loss": 0.5876, "lr": 6.489094011614553e-06, "epoch": 1.3918669131238448, "percentage": 46.39, "elapsed_time": "1:13:18", "remaining_time": "1:24:43"}
+{"current_steps": 1140, "total_steps": 2436, "loss": 0.5917, "lr": 6.4205347798462704e-06, "epoch": 1.4041897720271104, "percentage": 46.8, "elapsed_time": "1:13:53", "remaining_time": "1:24:00"}
+{"current_steps": 1150, "total_steps": 2436, "loss": 0.5836, "lr": 6.351683762996681e-06, "epoch": 1.416512630930376, "percentage": 47.21, "elapsed_time": "1:14:27", "remaining_time": "1:23:15"}
+{"current_steps": 1160, "total_steps": 2436, "loss": 0.5783, "lr": 6.282555103415438e-06, "epoch": 1.4288354898336415, "percentage": 47.62, "elapsed_time": "1:15:03", "remaining_time": "1:22:34"}
+{"current_steps": 1170, "total_steps": 2436, "loss": 0.5723, "lr": 6.213163000481428e-06, "epoch": 1.441158348736907, "percentage": 48.03, "elapsed_time": "1:15:37", "remaining_time": "1:21:49"}
+{"current_steps": 1180, "total_steps": 2436, "loss": 0.6022, "lr": 6.143521707686137e-06, "epoch": 1.4534812076401726, "percentage": 48.44, "elapsed_time": "1:16:10", "remaining_time": "1:21:05"}
+{"current_steps": 1190, "total_steps": 2436, "loss": 0.5917, "lr": 6.073645529705926e-06, "epoch": 1.4658040665434382, "percentage": 48.85, "elapsed_time": "1:16:45", "remaining_time": "1:20:22"}
+{"current_steps": 1200, "total_steps": 2436, "loss": 0.5833, "lr": 6.0035488194637645e-06, "epoch": 1.4781269254467038, "percentage": 49.26, "elapsed_time": "1:17:16", "remaining_time": "1:19:35"}
+{"current_steps": 1210, "total_steps": 2436, "loss": 0.5898, "lr": 5.933245975181074e-06, "epoch": 1.4904497843499693, "percentage": 49.67, "elapsed_time": "1:17:50", "remaining_time": "1:18:51"}
+{"current_steps": 1220, "total_steps": 2436, "loss": 0.5842, "lr": 5.8627514374202596e-06, "epoch": 1.502772643253235, "percentage": 50.08, "elapsed_time": "1:18:23", "remaining_time": "1:18:08"}
+{"current_steps": 1230, "total_steps": 2436, "loss": 0.5839, "lr": 5.79207968611854e-06, "epoch": 1.5150955021565005, "percentage": 50.49, "elapsed_time": "1:18:55", "remaining_time": "1:17:23"}
+{"current_steps": 1240, "total_steps": 2436, "loss": 0.5764, "lr": 5.721245237613704e-06, "epoch": 1.527418361059766, "percentage": 50.9, "elapsed_time": "1:19:27", "remaining_time": "1:16:38"}
+{"current_steps": 1250, "total_steps": 2436, "loss": 0.586, "lr": 5.650262641662367e-06, "epoch": 1.5397412199630314, "percentage": 51.31, "elapsed_time": "1:20:00", "remaining_time": "1:15:54"}
+{"current_steps": 1260, "total_steps": 2436, "loss": 0.5702, "lr": 5.5791464784513905e-06, "epoch": 1.552064078866297, "percentage": 51.72, "elapsed_time": "1:20:34", "remaining_time": "1:15:11"}
+{"current_steps": 1270, "total_steps": 2436, "loss": 0.5833, "lr": 5.50791135560303e-06, "epoch": 1.5643869377695625, "percentage": 52.13, "elapsed_time": "1:21:08", "remaining_time": "1:14:29"}
+{"current_steps": 1280, "total_steps": 2436, "loss": 0.5738, "lr": 5.4365719051744556e-06, "epoch": 1.576709796672828, "percentage": 52.55, "elapsed_time": "1:21:40", "remaining_time": "1:13:45"}
+{"current_steps": 1290, "total_steps": 2436, "loss": 0.5811, "lr": 5.365142780652255e-06, "epoch": 1.5890326555760936, "percentage": 52.96, "elapsed_time": "1:22:13", "remaining_time": "1:13:02"}
+{"current_steps": 1300, "total_steps": 2436, "loss": 0.6035, "lr": 5.2936386539425325e-06, "epoch": 1.6013555144793592, "percentage": 53.37, "elapsed_time": "1:22:49", "remaining_time": "1:12:22"}
+{"current_steps": 1310, "total_steps": 2436, "loss": 0.5767, "lr": 5.222074212357221e-06, "epoch": 1.6136783733826248, "percentage": 53.78, "elapsed_time": "1:23:23", "remaining_time": "1:11:40"}
+{"current_steps": 1320, "total_steps": 2436, "loss": 0.5798, "lr": 5.150464155597239e-06, "epoch": 1.6260012322858903, "percentage": 54.19, "elapsed_time": "1:23:55", "remaining_time": "1:10:57"}
+{"current_steps": 1330, "total_steps": 2436, "loss": 0.5757, "lr": 5.0788231927330924e-06, "epoch": 1.638324091189156, "percentage": 54.6, "elapsed_time": "1:24:28", "remaining_time": "1:10:15"}
+{"current_steps": 1340, "total_steps": 2436, "loss": 0.5762, "lr": 5.007166039183561e-06, "epoch": 1.6506469500924215, "percentage": 55.01, "elapsed_time": "1:25:01", "remaining_time": "1:09:32"}
+{"current_steps": 1350, "total_steps": 2436, "loss": 0.5758, "lr": 4.935507413693071e-06, "epoch": 1.662969808995687, "percentage": 55.42, "elapsed_time": "1:25:34", "remaining_time": "1:08:50"}
+{"current_steps": 1360, "total_steps": 2436, "loss": 0.5727, "lr": 4.863862035308392e-06, "epoch": 1.6752926678989526, "percentage": 55.83, "elapsed_time": "1:26:09", "remaining_time": "1:08:10"}
+{"current_steps": 1370, "total_steps": 2436, "loss": 0.5723, "lr": 4.792244620355275e-06, "epoch": 1.6876155268022182, "percentage": 56.24, "elapsed_time": "1:26:43", "remaining_time": "1:07:29"}
+{"current_steps": 1380, "total_steps": 2436, "loss": 0.58, "lr": 4.720669879415637e-06, "epoch": 1.6999383857054837, "percentage": 56.65, "elapsed_time": "1:27:16", "remaining_time": "1:06:47"}
+{"current_steps": 1390, "total_steps": 2436, "loss": 0.5831, "lr": 4.649152514305934e-06, "epoch": 1.712261244608749, "percentage": 57.06, "elapsed_time": "1:27:50", "remaining_time": "1:06:05"}
+{"current_steps": 1400, "total_steps": 2436, "loss": 0.5647, "lr": 4.5777072150573355e-06, "epoch": 1.7245841035120146, "percentage": 57.47, "elapsed_time": "1:28:21", "remaining_time": "1:05:22"}
+{"current_steps": 1410, "total_steps": 2436, "loss": 0.5631, "lr": 4.506348656898316e-06, "epoch": 1.7369069624152802, "percentage": 57.88, "elapsed_time": "1:28:57", "remaining_time": "1:04:43"}
+{"current_steps": 1420, "total_steps": 2436, "loss": 0.5855, "lr": 4.435091497240287e-06, "epoch": 1.7492298213185458, "percentage": 58.29, "elapsed_time": "1:29:29", "remaining_time": "1:04:01"}
+{"current_steps": 1430, "total_steps": 2436, "loss": 0.5714, "lr": 4.363950372666896e-06, "epoch": 1.7615526802218113, "percentage": 58.7, "elapsed_time": "1:30:02", "remaining_time": "1:03:20"}
+{"current_steps": 1440, "total_steps": 2436, "loss": 0.5754, "lr": 4.292939895927587e-06, "epoch": 1.773875539125077, "percentage": 59.11, "elapsed_time": "1:30:33", "remaining_time": "1:02:38"}
+{"current_steps": 1450, "total_steps": 2436, "loss": 0.5876, "lr": 4.2220746529360745e-06, "epoch": 1.7861983980283425, "percentage": 59.52, "elapsed_time": "1:31:06", "remaining_time": "1:01:56"}
+{"current_steps": 1460, "total_steps": 2436, "loss": 0.5787, "lr": 4.151369199774325e-06, "epoch": 1.798521256931608, "percentage": 59.93, "elapsed_time": "1:31:39", "remaining_time": "1:01:16"}
+{"current_steps": 1470, "total_steps": 2436, "loss": 0.5798, "lr": 4.080838059702656e-06, "epoch": 1.8108441158348736, "percentage": 60.34, "elapsed_time": "1:32:10", "remaining_time": "1:00:34"}
+{"current_steps": 1480, "total_steps": 2436, "loss": 0.5813, "lr": 4.0104957201765874e-06, "epoch": 1.8231669747381392, "percentage": 60.76, "elapsed_time": "1:32:44", "remaining_time": "0:59:54"}
+{"current_steps": 1490, "total_steps": 2436, "loss": 0.5737, "lr": 3.940356629871051e-06, "epoch": 1.8354898336414047, "percentage": 61.17, "elapsed_time": "1:33:17", "remaining_time": "0:59:13"}
+{"current_steps": 1500, "total_steps": 2436, "loss": 0.5739, "lr": 3.870435195712547e-06, "epoch": 1.8478126925446703, "percentage": 61.58, "elapsed_time": "1:33:50", "remaining_time": "0:58:33"}
+{"current_steps": 1500, "total_steps": 2436, "eval_loss": 0.6650247573852539, "epoch": 1.8478126925446703, "percentage": 61.58, "elapsed_time": "1:38:44", "remaining_time": "1:01:36"}
+{"current_steps": 1510, "total_steps": 2436, "loss": 0.5996, "lr": 3.8007457799198977e-06, "epoch": 1.8601355514479359, "percentage": 61.99, "elapsed_time": "1:39:19", "remaining_time": "1:00:54"}
+{"current_steps": 1520, "total_steps": 2436, "loss": 0.5686, "lr": 3.7313026970541687e-06, "epoch": 1.8724584103512014, "percentage": 62.4, "elapsed_time": "1:39:52", "remaining_time": "1:00:11"}
+{"current_steps": 1530, "total_steps": 2436, "loss": 0.5814, "lr": 3.662120211078385e-06, "epoch": 1.884781269254467, "percentage": 62.81, "elapsed_time": "1:40:25", "remaining_time": "0:59:28"}
+{"current_steps": 1540, "total_steps": 2436, "loss": 0.5821, "lr": 3.5932125324276524e-06, "epoch": 1.8971041281577325, "percentage": 63.22, "elapsed_time": "1:40:59", "remaining_time": "0:58:45"}
+{"current_steps": 1550, "total_steps": 2436, "loss": 0.5753, "lr": 3.524593815090241e-06, "epoch": 1.9094269870609981, "percentage": 63.63, "elapsed_time": "1:41:34", "remaining_time": "0:58:03"}
+{"current_steps": 1560, "total_steps": 2436, "loss": 0.5659, "lr": 3.4562781537003e-06, "epoch": 1.9217498459642637, "percentage": 64.04, "elapsed_time": "1:42:05", "remaining_time": "0:57:19"}
+{"current_steps": 1570, "total_steps": 2436, "loss": 0.5705, "lr": 3.3882795806427437e-06, "epoch": 1.9340727048675292, "percentage": 64.45, "elapsed_time": "1:42:39", "remaining_time": "0:56:37"}
+{"current_steps": 1580, "total_steps": 2436, "loss": 0.573, "lr": 3.320612063170926e-06, "epoch": 1.9463955637707948, "percentage": 64.86, "elapsed_time": "1:43:15", "remaining_time": "0:55:56"}
+{"current_steps": 1590, "total_steps": 2436, "loss": 0.5594, "lr": 3.2532895005376943e-06, "epoch": 1.9587184226740604, "percentage": 65.27, "elapsed_time": "1:43:48", "remaining_time": "0:55:14"}
+{"current_steps": 1600, "total_steps": 2436, "loss": 0.5682, "lr": 3.18632572114042e-06, "epoch": 1.971041281577326, "percentage": 65.68, "elapsed_time": "1:44:24", "remaining_time": "0:54:32"}
+{"current_steps": 1610, "total_steps": 2436, "loss": 0.5642, "lr": 3.1197344796805675e-06, "epoch": 1.9833641404805915, "percentage": 66.09, "elapsed_time": "1:44:56", "remaining_time": "0:53:50"}
+{"current_steps": 1620, "total_steps": 2436, "loss": 0.5691, "lr": 3.0535294543384074e-06, "epoch": 1.995686999383857, "percentage": 66.5, "elapsed_time": "1:45:31", "remaining_time": "0:53:08"}
+{"current_steps": 1630, "total_steps": 2436, "loss": 0.4903, "lr": 2.987724243963458e-06, "epoch": 2.0073937153419594, "percentage": 66.91, "elapsed_time": "1:46:04", "remaining_time": "0:52:27"}
+{"current_steps": 1640, "total_steps": 2436, "loss": 0.4882, "lr": 2.922332365281201e-06, "epoch": 2.019716574245225, "percentage": 67.32, "elapsed_time": "1:46:40", "remaining_time": "0:51:46"}
+{"current_steps": 1650, "total_steps": 2436, "loss": 0.4714, "lr": 2.857367250116682e-06, "epoch": 2.0320394331484906, "percentage": 67.73, "elapsed_time": "1:47:13", "remaining_time": "0:51:04"}
+{"current_steps": 1660, "total_steps": 2436, "loss": 0.4748, "lr": 2.7928422426355554e-06, "epoch": 2.044362292051756, "percentage": 68.14, "elapsed_time": "1:47:45", "remaining_time": "0:50:22"}
+{"current_steps": 1670, "total_steps": 2436, "loss": 0.4764, "lr": 2.728770596603105e-06, "epoch": 2.0566851509550217, "percentage": 68.56, "elapsed_time": "1:48:20", "remaining_time": "0:49:41"}
+{"current_steps": 1680, "total_steps": 2436, "loss": 0.4735, "lr": 2.665165472661866e-06, "epoch": 2.0690080098582873, "percentage": 68.97, "elapsed_time": "1:48:55", "remaining_time": "0:49:00"}
+{"current_steps": 1690, "total_steps": 2436, "loss": 0.4578, "lr": 2.6020399356283586e-06, "epoch": 2.081330868761553, "percentage": 69.38, "elapsed_time": "1:49:30", "remaining_time": "0:48:20"}
+{"current_steps": 1700, "total_steps": 2436, "loss": 0.4737, "lr": 2.539406951809512e-06, "epoch": 2.0936537276648184, "percentage": 69.79, "elapsed_time": "1:50:01", "remaining_time": "0:47:38"}
+{"current_steps": 1710, "total_steps": 2436, "loss": 0.4695, "lr": 2.477279386339309e-06, "epoch": 2.105976586568084, "percentage": 70.2, "elapsed_time": "1:50:36", "remaining_time": "0:46:57"}
+{"current_steps": 1720, "total_steps": 2436, "loss": 0.4785, "lr": 2.4156700005362384e-06, "epoch": 2.1182994454713495, "percentage": 70.61, "elapsed_time": "1:51:09", "remaining_time": "0:46:16"}
+{"current_steps": 1730, "total_steps": 2436, "loss": 0.4723, "lr": 2.3545914492820366e-06, "epoch": 2.130622304374615, "percentage": 71.02, "elapsed_time": "1:51:44", "remaining_time": "0:45:35"}
+{"current_steps": 1740, "total_steps": 2436, "loss": 0.4672, "lr": 2.2940562784223224e-06, "epoch": 2.1429451632778806, "percentage": 71.43, "elapsed_time": "1:52:15", "remaining_time": "0:44:54"}
+{"current_steps": 1750, "total_steps": 2436, "loss": 0.4734, "lr": 2.234076922189613e-06, "epoch": 2.155268022181146, "percentage": 71.84, "elapsed_time": "1:52:49", "remaining_time": "0:44:13"}
+{"current_steps": 1760, "total_steps": 2436, "loss": 0.4512, "lr": 2.174665700649267e-06, "epoch": 2.167590881084412, "percentage": 72.25, "elapsed_time": "1:53:23", "remaining_time": "0:43:33"}
+{"current_steps": 1770, "total_steps": 2436, "loss": 0.4678, "lr": 2.1158348171688888e-06, "epoch": 2.1799137399876773, "percentage": 72.66, "elapsed_time": "1:53:56", "remaining_time": "0:42:52"}
+{"current_steps": 1780, "total_steps": 2436, "loss": 0.4719, "lr": 2.0575963559116823e-06, "epoch": 2.1922365988909425, "percentage": 73.07, "elapsed_time": "1:54:29", "remaining_time": "0:42:11"}
+{"current_steps": 1790, "total_steps": 2436, "loss": 0.4539, "lr": 1.999962279354311e-06, "epoch": 2.2045594577942085, "percentage": 73.48, "elapsed_time": "1:55:03", "remaining_time": "0:41:31"}
+{"current_steps": 1800, "total_steps": 2436, "loss": 0.4759, "lr": 1.942944425829741e-06, "epoch": 2.2168823166974736, "percentage": 73.89, "elapsed_time": "1:55:35", "remaining_time": "0:40:50"}
+{"current_steps": 1810, "total_steps": 2436, "loss": 0.4633, "lr": 1.8865545070955882e-06, "epoch": 2.229205175600739, "percentage": 74.3, "elapsed_time": "1:56:07", "remaining_time": "0:40:09"}
+{"current_steps": 1820, "total_steps": 2436, "loss": 0.4683, "lr": 1.8308041059284621e-06, "epoch": 2.2415280345040047, "percentage": 74.71, "elapsed_time": "1:56:41", "remaining_time": "0:39:29"}
+{"current_steps": 1830, "total_steps": 2436, "loss": 0.477, "lr": 1.775704673744809e-06, "epoch": 2.2538508934072703, "percentage": 75.12, "elapsed_time": "1:57:14", "remaining_time": "0:38:49"}
+{"current_steps": 1840, "total_steps": 2436, "loss": 0.4792, "lr": 1.7212675282487269e-06, "epoch": 2.266173752310536, "percentage": 75.53, "elapsed_time": "1:57:50", "remaining_time": "0:38:10"}
+{"current_steps": 1850, "total_steps": 2436, "loss": 0.4704, "lr": 1.6675038511072518e-06, "epoch": 2.2784966112138014, "percentage": 75.94, "elapsed_time": "1:58:21", "remaining_time": "0:37:29"}
+{"current_steps": 1860, "total_steps": 2436, "loss": 0.4685, "lr": 1.6144246856535933e-06, "epoch": 2.290819470117067, "percentage": 76.35, "elapsed_time": "1:58:55", "remaining_time": "0:36:49"}
+{"current_steps": 1870, "total_steps": 2436, "loss": 0.4786, "lr": 1.5620409346187697e-06, "epoch": 2.3031423290203326, "percentage": 76.77, "elapsed_time": "1:59:30", "remaining_time": "0:36:10"}
+{"current_steps": 1880, "total_steps": 2436, "loss": 0.469, "lr": 1.510363357892133e-06, "epoch": 2.315465187923598, "percentage": 77.18, "elapsed_time": "2:00:03", "remaining_time": "0:35:30"}
+{"current_steps": 1890, "total_steps": 2436, "loss": 0.4706, "lr": 1.4594025703112397e-06, "epoch": 2.3277880468268637, "percentage": 77.59, "elapsed_time": "2:00:34", "remaining_time": "0:34:50"}
+{"current_steps": 1900, "total_steps": 2436, "loss": 0.4586, "lr": 1.4091690394814989e-06, "epoch": 2.3401109057301293, "percentage": 78.0, "elapsed_time": "2:01:07", "remaining_time": "0:34:10"}
+{"current_steps": 1910, "total_steps": 2436, "loss": 0.4679, "lr": 1.359673083626079e-06, "epoch": 2.352433764633395, "percentage": 78.41, "elapsed_time": "2:01:41", "remaining_time": "0:33:30"}
+{"current_steps": 1920, "total_steps": 2436, "loss": 0.4688, "lr": 1.3109248694664917e-06, "epoch": 2.3647566235366604, "percentage": 78.82, "elapsed_time": "2:02:17", "remaining_time": "0:32:52"}
+{"current_steps": 1930, "total_steps": 2436, "loss": 0.4692, "lr": 1.262934410134292e-06, "epoch": 2.377079482439926, "percentage": 79.23, "elapsed_time": "2:02:52", "remaining_time": "0:32:12"}
+{"current_steps": 1940, "total_steps": 2436, "loss": 0.4734, "lr": 1.2157115631143384e-06, "epoch": 2.3894023413431915, "percentage": 79.64, "elapsed_time": "2:03:27", "remaining_time": "0:31:33"}
+{"current_steps": 1950, "total_steps": 2436, "loss": 0.4789, "lr": 1.169266028220004e-06, "epoch": 2.401725200246457, "percentage": 80.05, "elapsed_time": "2:03:58", "remaining_time": "0:30:53"}
+{"current_steps": 1960, "total_steps": 2436, "loss": 0.4761, "lr": 1.1236073456007928e-06, "epoch": 2.4140480591497226, "percentage": 80.46, "elapsed_time": "2:04:32", "remaining_time": "0:30:14"}
+{"current_steps": 1970, "total_steps": 2436, "loss": 0.4506, "lr": 1.0787448937827428e-06, "epoch": 2.426370918052988, "percentage": 80.87, "elapsed_time": "2:05:07", "remaining_time": "0:29:35"}
+{"current_steps": 1980, "total_steps": 2436, "loss": 0.4661, "lr": 1.034687887742028e-06, "epoch": 2.438693776956254, "percentage": 81.28, "elapsed_time": "2:05:41", "remaining_time": "0:28:56"}
+{"current_steps": 1990, "total_steps": 2436, "loss": 0.4535, "lr": 9.914453770121557e-07, "epoch": 2.4510166358595193, "percentage": 81.69, "elapsed_time": "2:06:14", "remaining_time": "0:28:17"}
+{"current_steps": 2000, "total_steps": 2436, "loss": 0.4637, "lr": 9.490262438251496e-07, "epoch": 2.463339494762785, "percentage": 82.1, "elapsed_time": "2:06:45", "remaining_time": "0:27:38"}
+{"current_steps": 2000, "total_steps": 2436, "eval_loss": 0.6939365267753601, "epoch": 2.463339494762785, "percentage": 82.1, "elapsed_time": "2:11:36", "remaining_time": "0:28:41"}
+{"current_steps": 2010, "total_steps": 2436, "loss": 0.4673, "lr": 9.07439201287088e-07, "epoch": 2.4756623536660505, "percentage": 82.51, "elapsed_time": "2:12:35", "remaining_time": "0:28:06"}
+{"current_steps": 2020, "total_steps": 2436, "loss": 0.4594, "lr": 8.666927915883905e-07, "epoch": 2.487985212569316, "percentage": 82.92, "elapsed_time": "2:13:08", "remaining_time": "0:27:25"}
+{"current_steps": 2030, "total_steps": 2436, "loss": 0.4633, "lr": 8.2679538424921e-07, "epoch": 2.5003080714725816, "percentage": 83.33, "elapsed_time": "2:13:39", "remaining_time": "0:26:43"}
+{"current_steps": 2040, "total_steps": 2436, "loss": 0.4716, "lr": 7.877551744002881e-07, "epoch": 2.512630930375847, "percentage": 83.74, "elapsed_time": "2:14:11", "remaining_time": "0:26:03"}
+{"current_steps": 2050, "total_steps": 2436, "loss": 0.4748, "lr": 7.495801810996334e-07, "epoch": 2.5249537892791127, "percentage": 84.15, "elapsed_time": "2:14:45", "remaining_time": "0:25:22"}
+{"current_steps": 2060, "total_steps": 2436, "loss": 0.4714, "lr": 7.122782456853722e-07, "epoch": 2.5372766481823783, "percentage": 84.56, "elapsed_time": "2:15:18", "remaining_time": "0:24:41"}
+{"current_steps": 2070, "total_steps": 2436, "loss": 0.4745, "lr": 6.758570301650869e-07, "epoch": 2.549599507085644, "percentage": 84.98, "elapsed_time": "2:15:51", "remaining_time": "0:24:01"}
+{"current_steps": 2080, "total_steps": 2436, "loss": 0.4633, "lr": 6.403240156420087e-07, "epoch": 2.5619223659889094, "percentage": 85.39, "elapsed_time": "2:16:25", "remaining_time": "0:23:20"}
+{"current_steps": 2090, "total_steps": 2436, "loss": 0.4674, "lr": 6.056865007783602e-07, "epoch": 2.574245224892175, "percentage": 85.8, "elapsed_time": "2:16:58", "remaining_time": "0:22:40"}
+{"current_steps": 2100, "total_steps": 2436, "loss": 0.4636, "lr": 5.7195160029617e-07, "epoch": 2.5865680837954406, "percentage": 86.21, "elapsed_time": "2:17:33", "remaining_time": "0:22:00"}
+{"current_steps": 2110, "total_steps": 2436, "loss": 0.4612, "lr": 5.391262435158722e-07, "epoch": 2.598890942698706, "percentage": 86.62, "elapsed_time": "2:18:05", "remaining_time": "0:21:20"}
+{"current_steps": 2120, "total_steps": 2436, "loss": 0.4548, "lr": 5.072171729329944e-07, "epoch": 2.6112138016019717, "percentage": 87.03, "elapsed_time": "2:18:39", "remaining_time": "0:20:40"}
+{"current_steps": 2130, "total_steps": 2436, "loss": 0.4649, "lr": 4.7623094283320905e-07, "epoch": 2.6235366605052373, "percentage": 87.44, "elapsed_time": "2:19:10", "remaining_time": "0:19:59"}
+{"current_steps": 2140, "total_steps": 2436, "loss": 0.4649, "lr": 4.4617391794604946e-07, "epoch": 2.635859519408503, "percentage": 87.85, "elapsed_time": "2:19:44", "remaining_time": "0:19:19"}
+{"current_steps": 2150, "total_steps": 2436, "loss": 0.4729, "lr": 4.170522721375669e-07, "epoch": 2.6481823783117684, "percentage": 88.26, "elapsed_time": "2:20:19", "remaining_time": "0:18:39"}
+{"current_steps": 2160, "total_steps": 2436, "loss": 0.4626, "lr": 3.8887198714218255e-07, "epoch": 2.660505237215034, "percentage": 88.67, "elapsed_time": "2:20:52", "remaining_time": "0:18:00"}
+{"current_steps": 2170, "total_steps": 2436, "loss": 0.4618, "lr": 3.616388513340124e-07, "epoch": 2.6728280961182995, "percentage": 89.08, "elapsed_time": "2:21:24", "remaining_time": "0:17:20"}
+{"current_steps": 2180, "total_steps": 2436, "loss": 0.4576, "lr": 3.3535845853790105e-07, "epoch": 2.685150955021565, "percentage": 89.49, "elapsed_time": "2:21:58", "remaining_time": "0:16:40"}
+{"current_steps": 2190, "total_steps": 2436, "loss": 0.4557, "lr": 3.1003620688042636e-07, "epoch": 2.6974738139248307, "percentage": 89.9, "elapsed_time": "2:22:33", "remaining_time": "0:16:00"}
+{"current_steps": 2200, "total_steps": 2436, "loss": 0.4687, "lr": 2.856772976810929e-07, "epoch": 2.709796672828096, "percentage": 90.31, "elapsed_time": "2:23:07", "remaining_time": "0:15:21"}
+{"current_steps": 2210, "total_steps": 2436, "loss": 0.4617, "lr": 2.6228673438395804e-07, "epoch": 2.722119531731362, "percentage": 90.72, "elapsed_time": "2:23:39", "remaining_time": "0:14:41"}
+{"current_steps": 2220, "total_steps": 2436, "loss": 0.4666, "lr": 2.398693215298953e-07, "epoch": 2.7344423906346274, "percentage": 91.13, "elapsed_time": "2:24:13", "remaining_time": "0:14:01"}
+{"current_steps": 2230, "total_steps": 2436, "loss": 0.4757, "lr": 2.1842966376972142e-07, "epoch": 2.746765249537893, "percentage": 91.54, "elapsed_time": "2:24:48", "remaining_time": "0:13:22"}
+{"current_steps": 2240, "total_steps": 2436, "loss": 0.4634, "lr": 1.9797216491837356e-07, "epoch": 2.7590881084411585, "percentage": 91.95, "elapsed_time": "2:25:23", "remaining_time": "0:12:43"}
+{"current_steps": 2250, "total_steps": 2436, "loss": 0.4694, "lr": 1.7850102705034455e-07, "epoch": 2.771410967344424, "percentage": 92.36, "elapsed_time": "2:25:54", "remaining_time": "0:12:03"}
+{"current_steps": 2260, "total_steps": 2436, "loss": 0.4637, "lr": 1.600202496365566e-07, "epoch": 2.7837338262476896, "percentage": 92.78, "elapsed_time": "2:26:26", "remaining_time": "0:11:24"}
+{"current_steps": 2270, "total_steps": 2436, "loss": 0.4709, "lr": 1.425336287228496e-07, "epoch": 2.796056685150955, "percentage": 93.19, "elapsed_time": "2:27:00", "remaining_time": "0:10:45"}
+{"current_steps": 2280, "total_steps": 2436, "loss": 0.46, "lr": 1.2604475615025092e-07, "epoch": 2.8083795440542207, "percentage": 93.6, "elapsed_time": "2:27:33", "remaining_time": "0:10:05"}
+{"current_steps": 2290, "total_steps": 2436, "loss": 0.4722, "lr": 1.1055701881719838e-07, "epoch": 2.820702402957486, "percentage": 94.01, "elapsed_time": "2:28:08", "remaining_time": "0:09:26"}
+{"current_steps": 2300, "total_steps": 2436, "loss": 0.4677, "lr": 9.607359798384785e-08, "epoch": 2.833025261860752, "percentage": 94.42, "elapsed_time": "2:28:42", "remaining_time": "0:08:47"}
+{"current_steps": 2310, "total_steps": 2436, "loss": 0.4645, "lr": 8.259746861863094e-08, "epoch": 2.845348120764017, "percentage": 94.83, "elapsed_time": "2:29:17", "remaining_time": "0:08:08"}
+{"current_steps": 2320, "total_steps": 2436, "loss": 0.4659, "lr": 7.013139878717934e-08, "epoch": 2.857670979667283, "percentage": 95.24, "elapsed_time": "2:29:50", "remaining_time": "0:07:29"}
+{"current_steps": 2330, "total_steps": 2436, "loss": 0.4717, "lr": 5.8677949083749686e-08, "epoch": 2.869993838570548, "percentage": 95.65, "elapsed_time": "2:30:24", "remaining_time": "0:06:50"}
+{"current_steps": 2340, "total_steps": 2436, "loss": 0.4562, "lr": 4.823947210526647e-08, "epoch": 2.882316697473814, "percentage": 96.06, "elapsed_time": "2:30:58", "remaining_time": "0:06:11"}
+{"current_steps": 2350, "total_steps": 2436, "loss": 0.4784, "lr": 3.8818111968083607e-08, "epoch": 2.8946395563770793, "percentage": 96.47, "elapsed_time": "2:31:32", "remaining_time": "0:05:32"}
+{"current_steps": 2360, "total_steps": 2436, "loss": 0.4736, "lr": 3.041580386757448e-08, "epoch": 2.9069624152803453, "percentage": 96.88, "elapsed_time": "2:32:04", "remaining_time": "0:04:53"}
+{"current_steps": 2370, "total_steps": 2436, "loss": 0.4658, "lr": 2.3034273680632157e-08, "epoch": 2.9192852741836104, "percentage": 97.29, "elapsed_time": "2:32:38", "remaining_time": "0:04:15"}
+{"current_steps": 2380, "total_steps": 2436, "loss": 0.4962, "lr": 1.6675037611165735e-08, "epoch": 2.9316081330868764, "percentage": 97.7, "elapsed_time": "2:33:09", "remaining_time": "0:03:36"}
+{"current_steps": 2390, "total_steps": 2436, "loss": 0.4672, "lr": 1.1339401878663337e-08, "epoch": 2.9439309919901415, "percentage": 98.11, "elapsed_time": "2:33:44", "remaining_time": "0:02:57"}
+{"current_steps": 2400, "total_steps": 2436, "loss": 0.4633, "lr": 7.028462449889528e-09, "epoch": 2.9562538508934075, "percentage": 98.52, "elapsed_time": "2:34:18", "remaining_time": "0:02:18"}
+{"current_steps": 2410, "total_steps": 2436, "loss": 0.4541, "lr": 3.743104813767051e-09, "epoch": 2.9685767097966727, "percentage": 98.93, "elapsed_time": "2:34:50", "remaining_time": "0:01:40"}
+{"current_steps": 2420, "total_steps": 2436, "loss": 0.4567, "lr": 1.4840037994923173e-09, "epoch": 2.9808995686999387, "percentage": 99.34, "elapsed_time": "2:35:22", "remaining_time": "0:01:01"}
+{"current_steps": 2430, "total_steps": 2436, "loss": 0.4601, "lr": 2.516234379235094e-10, "epoch": 2.993222427603204, "percentage": 99.75, "elapsed_time": "2:35:55", "remaining_time": "0:00:23"}
+{"current_steps": 2436, "total_steps": 2436, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:36:36", "remaining_time": "0:00:00"}

EXP_1.1_3b/trainer_state.json

@@ -0,0 +1,1776 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2436,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012322858903265557,
+      "grad_norm": 8.865929400670435,
+      "learning_rate": 3.6885245901639347e-07,
+      "loss": 1.5881,
+      "step": 10
+    },
+    {
+      "epoch": 0.024645717806531114,
+      "grad_norm": 7.574103078308896,
+      "learning_rate": 7.78688524590164e-07,
+      "loss": 1.6078,
+      "step": 20
+    },
+    {
+      "epoch": 0.036968576709796676,
+      "grad_norm": 6.183109440553045,
+      "learning_rate": 1.1885245901639345e-06,
+      "loss": 1.5155,
+      "step": 30
+    },
+    {
+      "epoch": 0.04929143561306223,
+      "grad_norm": 3.7877912491073786,
+      "learning_rate": 1.5983606557377053e-06,
+      "loss": 1.3049,
+      "step": 40
+    },
+    {
+      "epoch": 0.061614294516327786,
+      "grad_norm": 2.116426567902146,
+      "learning_rate": 2.0081967213114756e-06,
+      "loss": 1.1069,
+      "step": 50
+    },
+    {
+      "epoch": 0.07393715341959335,
+      "grad_norm": 1.9333052226557788,
+      "learning_rate": 2.418032786885246e-06,
+      "loss": 0.9964,
+      "step": 60
+    },
+    {
+      "epoch": 0.0862600123228589,
+      "grad_norm": 1.7274261944769131,
+      "learning_rate": 2.8278688524590166e-06,
+      "loss": 0.9526,
+      "step": 70
+    },
+    {
+      "epoch": 0.09858287122612445,
+      "grad_norm": 1.485084447219836,
+      "learning_rate": 3.2377049180327876e-06,
+      "loss": 0.9071,
+      "step": 80
+    },
+    {
+      "epoch": 0.11090573012939002,
+      "grad_norm": 1.6878869537634686,
+      "learning_rate": 3.6475409836065577e-06,
+      "loss": 0.8833,
+      "step": 90
+    },
+    {
+      "epoch": 0.12322858903265557,
+      "grad_norm": 1.6224576695093869,
+      "learning_rate": 4.057377049180329e-06,
+      "loss": 0.8617,
+      "step": 100
+    },
+    {
+      "epoch": 0.13555144793592114,
+      "grad_norm": 1.5341177753373625,
+      "learning_rate": 4.467213114754098e-06,
+      "loss": 0.8439,
+      "step": 110
+    },
+    {
+      "epoch": 0.1478743068391867,
+      "grad_norm": 1.680475740650815,
+      "learning_rate": 4.877049180327869e-06,
+      "loss": 0.8494,
+      "step": 120
+    },
+    {
+      "epoch": 0.16019716574245224,
+      "grad_norm": 1.8320444027458695,
+      "learning_rate": 5.286885245901639e-06,
+      "loss": 0.8114,
+      "step": 130
+    },
+    {
+      "epoch": 0.1725200246457178,
+      "grad_norm": 1.653101255301024,
+      "learning_rate": 5.696721311475411e-06,
+      "loss": 0.7865,
+      "step": 140
+    },
+    {
+      "epoch": 0.18484288354898337,
+      "grad_norm": 1.845033324261731,
+      "learning_rate": 6.10655737704918e-06,
+      "loss": 0.8102,
+      "step": 150
+    },
+    {
+      "epoch": 0.1971657424522489,
+      "grad_norm": 1.50017872275538,
+      "learning_rate": 6.516393442622952e-06,
+      "loss": 0.7978,
+      "step": 160
+    },
+    {
+      "epoch": 0.20948860135551448,
+      "grad_norm": 1.7319722249969618,
+      "learning_rate": 6.926229508196722e-06,
+      "loss": 0.7969,
+      "step": 170
+    },
+    {
+      "epoch": 0.22181146025878004,
+      "grad_norm": 1.5125736552951485,
+      "learning_rate": 7.336065573770492e-06,
+      "loss": 0.7821,
+      "step": 180
+    },
+    {
+      "epoch": 0.2341343191620456,
+      "grad_norm": 1.8457968609015014,
+      "learning_rate": 7.745901639344263e-06,
+      "loss": 0.7654,
+      "step": 190
+    },
+    {
+      "epoch": 0.24645717806531114,
+      "grad_norm": 1.612579047273975,
+      "learning_rate": 8.155737704918034e-06,
+      "loss": 0.7924,
+      "step": 200
+    },
+    {
+      "epoch": 0.2587800369685767,
+      "grad_norm": 1.7222316881259245,
+      "learning_rate": 8.565573770491804e-06,
+      "loss": 0.7754,
+      "step": 210
+    },
+    {
+      "epoch": 0.2711028958718423,
+      "grad_norm": 1.6823495566135107,
+      "learning_rate": 8.975409836065575e-06,
+      "loss": 0.7685,
+      "step": 220
+    },
+    {
+      "epoch": 0.28342575477510784,
+      "grad_norm": 1.8243123794941252,
+      "learning_rate": 9.385245901639345e-06,
+      "loss": 0.766,
+      "step": 230
+    },
+    {
+      "epoch": 0.2957486136783734,
+      "grad_norm": 1.6969329352168785,
+      "learning_rate": 9.795081967213116e-06,
+      "loss": 0.7709,
+      "step": 240
+    },
+    {
+      "epoch": 0.3080714725816389,
+      "grad_norm": 1.5658877986677437,
+      "learning_rate": 9.999871620167532e-06,
+      "loss": 0.7434,
+      "step": 250
+    },
+    {
+      "epoch": 0.3203943314849045,
+      "grad_norm": 1.7193380497814985,
+      "learning_rate": 9.998844621062755e-06,
+      "loss": 0.7559,
+      "step": 260
+    },
+    {
+      "epoch": 0.33271719038817005,
+      "grad_norm": 1.769267118394799,
+      "learning_rate": 9.996790833804053e-06,
+      "loss": 0.7541,
+      "step": 270
+    },
+    {
+      "epoch": 0.3450400492914356,
+      "grad_norm": 1.6377922328571806,
+      "learning_rate": 9.993710680249788e-06,
+      "loss": 0.7565,
+      "step": 280
+    },
+    {
+      "epoch": 0.3573629081947012,
+      "grad_norm": 1.6202653826059523,
+      "learning_rate": 9.989604793079198e-06,
+      "loss": 0.7488,
+      "step": 290
+    },
+    {
+      "epoch": 0.36968576709796674,
+      "grad_norm": 1.7411263842465872,
+      "learning_rate": 9.984474015662421e-06,
+      "loss": 0.7542,
+      "step": 300
+    },
+    {
+      "epoch": 0.3820086260012323,
+      "grad_norm": 1.7305673660844891,
+      "learning_rate": 9.978319401887287e-06,
+      "loss": 0.7626,
+      "step": 310
+    },
+    {
+      "epoch": 0.3943314849044978,
+      "grad_norm": 1.6891856351420287,
+      "learning_rate": 9.971142215942817e-06,
+      "loss": 0.7445,
+      "step": 320
+    },
+    {
+      "epoch": 0.4066543438077634,
+      "grad_norm": 1.5418334432889922,
+      "learning_rate": 9.962943932059573e-06,
+      "loss": 0.7438,
+      "step": 330
+    },
+    {
+      "epoch": 0.41897720271102895,
+      "grad_norm": 1.5266927582987573,
+      "learning_rate": 9.953726234206835e-06,
+      "loss": 0.7403,
+      "step": 340
+    },
+    {
+      "epoch": 0.4313000616142945,
+      "grad_norm": 1.6404004809298283,
+      "learning_rate": 9.943491015746704e-06,
+      "loss": 0.7459,
+      "step": 350
+    },
+    {
+      "epoch": 0.4436229205175601,
+      "grad_norm": 1.5048534772298556,
+      "learning_rate": 9.9322403790452e-06,
+      "loss": 0.7361,
+      "step": 360
+    },
+    {
+      "epoch": 0.45594577942082565,
+      "grad_norm": 1.6069777870788664,
+      "learning_rate": 9.919976635040425e-06,
+      "loss": 0.7373,
+      "step": 370
+    },
+    {
+      "epoch": 0.4682686383240912,
+      "grad_norm": 1.479252474067406,
+      "learning_rate": 9.906702302767876e-06,
+      "loss": 0.7279,
+      "step": 380
+    },
+    {
+      "epoch": 0.4805914972273567,
+      "grad_norm": 1.54960054924232,
+      "learning_rate": 9.892420108843038e-06,
+      "loss": 0.7503,
+      "step": 390
+    },
+    {
+      "epoch": 0.4929143561306223,
+      "grad_norm": 1.84677255909603,
+      "learning_rate": 9.877132986901306e-06,
+      "loss": 0.7528,
+      "step": 400
+    },
+    {
+      "epoch": 0.5052372150338879,
+      "grad_norm": 1.6037926513380787,
+      "learning_rate": 9.860844076995416e-06,
+      "loss": 0.7472,
+      "step": 410
+    },
+    {
+      "epoch": 0.5175600739371534,
+      "grad_norm": 1.655327892600129,
+      "learning_rate": 9.843556724950454e-06,
+      "loss": 0.7338,
+      "step": 420
+    },
+    {
+      "epoch": 0.529882932840419,
+      "grad_norm": 1.5442494735316896,
+      "learning_rate": 9.825274481676605e-06,
+      "loss": 0.716,
+      "step": 430
+    },
+    {
+      "epoch": 0.5422057917436846,
+      "grad_norm": 1.5124305778248208,
+      "learning_rate": 9.806001102439789e-06,
+      "loss": 0.7381,
+      "step": 440
+    },
+    {
+      "epoch": 0.5545286506469501,
+      "grad_norm": 1.560981504733344,
+      "learning_rate": 9.785740546090293e-06,
+      "loss": 0.72,
+      "step": 450
+    },
+    {
+      "epoch": 0.5668515095502157,
+      "grad_norm": 1.5093735463852636,
+      "learning_rate": 9.76449697424962e-06,
+      "loss": 0.7302,
+      "step": 460
+    },
+    {
+      "epoch": 0.5791743684534812,
+      "grad_norm": 1.5144954032372582,
+      "learning_rate": 9.742274750455659e-06,
+      "loss": 0.7165,
+      "step": 470
+    },
+    {
+      "epoch": 0.5914972273567468,
+      "grad_norm": 1.4515433945811713,
+      "learning_rate": 9.719078439266399e-06,
+      "loss": 0.715,
+      "step": 480
+    },
+    {
+      "epoch": 0.6038200862600123,
+      "grad_norm": 1.5477114404836352,
+      "learning_rate": 9.69491280532234e-06,
+      "loss": 0.7328,
+      "step": 490
+    },
+    {
+      "epoch": 0.6161429451632778,
+      "grad_norm": 1.5020199584697078,
+      "learning_rate": 9.66978281236782e-06,
+      "loss": 0.705,
+      "step": 500
+    },
+    {
+      "epoch": 0.6161429451632778,
+      "eval_loss": 0.7097772359848022,
+      "eval_runtime": 289.5537,
+      "eval_samples_per_second": 19.924,
+      "eval_steps_per_second": 2.493,
+      "step": 500
+    },
+    {
+      "epoch": 0.6284658040665434,
+      "grad_norm": 1.6670022717865285,
+      "learning_rate": 9.643693622231426e-06,
+      "loss": 0.7196,
+      "step": 510
+    },
+    {
+      "epoch": 0.640788662969809,
+      "grad_norm": 1.404510439712067,
+      "learning_rate": 9.616650593765733e-06,
+      "loss": 0.7212,
+      "step": 520
+    },
+    {
+      "epoch": 0.6531115218730745,
+      "grad_norm": 1.5052601371891572,
+      "learning_rate": 9.58865928174657e-06,
+      "loss": 0.7038,
+      "step": 530
+    },
+    {
+      "epoch": 0.6654343807763401,
+      "grad_norm": 1.4958093674390802,
+      "learning_rate": 9.559725435732042e-06,
+      "loss": 0.7108,
+      "step": 540
+    },
+    {
+      "epoch": 0.6777572396796057,
+      "grad_norm": 1.5318847750594449,
+      "learning_rate": 9.529854998881534e-06,
+      "loss": 0.7164,
+      "step": 550
+    },
+    {
+      "epoch": 0.6900800985828712,
+      "grad_norm": 1.5019475478688826,
+      "learning_rate": 9.499054106734963e-06,
+      "loss": 0.7183,
+      "step": 560
+    },
+    {
+      "epoch": 0.7024029574861368,
+      "grad_norm": 1.6065560053372951,
+      "learning_rate": 9.467329085952505e-06,
+      "loss": 0.7082,
+      "step": 570
+    },
+    {
+      "epoch": 0.7147258163894024,
+      "grad_norm": 1.5660643966910845,
+      "learning_rate": 9.434686453015067e-06,
+      "loss": 0.7136,
+      "step": 580
+    },
+    {
+      "epoch": 0.7270486752926679,
+      "grad_norm": 1.5293218100937476,
+      "learning_rate": 9.401132912885764e-06,
+      "loss": 0.7225,
+      "step": 590
+    },
+    {
+      "epoch": 0.7393715341959335,
+      "grad_norm": 1.5434780622861681,
+      "learning_rate": 9.36667535763269e-06,
+      "loss": 0.7133,
+      "step": 600
+    },
+    {
+      "epoch": 0.751694393099199,
+      "grad_norm": 1.6408253382203255,
+      "learning_rate": 9.331320865013257e-06,
+      "loss": 0.7063,
+      "step": 610
+    },
+    {
+      "epoch": 0.7640172520024646,
+      "grad_norm": 1.4072416974078221,
+      "learning_rate": 9.295076697020378e-06,
+      "loss": 0.6986,
+      "step": 620
+    },
+    {
+      "epoch": 0.7763401109057301,
+      "grad_norm": 1.472755575560557,
+      "learning_rate": 9.257950298390815e-06,
+      "loss": 0.706,
+      "step": 630
+    },
+    {
+      "epoch": 0.7886629698089956,
+      "grad_norm": 1.5142987867097109,
+      "learning_rate": 9.219949295076006e-06,
+      "loss": 0.7083,
+      "step": 640
+    },
+    {
+      "epoch": 0.8009858287122612,
+      "grad_norm": 1.7078530382768096,
+      "learning_rate": 9.181081492675645e-06,
+      "loss": 0.7066,
+      "step": 650
+    },
+    {
+      "epoch": 0.8133086876155268,
+      "grad_norm": 1.4156076970190257,
+      "learning_rate": 9.141354874834372e-06,
+      "loss": 0.6922,
+      "step": 660
+    },
+    {
+      "epoch": 0.8256315465187923,
+      "grad_norm": 1.489267836422785,
+      "learning_rate": 9.100777601601896e-06,
+      "loss": 0.686,
+      "step": 670
+    },
+    {
+      "epoch": 0.8379544054220579,
+      "grad_norm": 1.5156823023774049,
+      "learning_rate": 9.05935800775688e-06,
+      "loss": 0.7045,
+      "step": 680
+    },
+    {
+      "epoch": 0.8502772643253235,
+      "grad_norm": 1.4997012195145634,
+      "learning_rate": 9.017104601094927e-06,
+      "loss": 0.6952,
+      "step": 690
+    },
+    {
+      "epoch": 0.862600123228589,
+      "grad_norm": 1.4993129316246536,
+      "learning_rate": 8.974026060681044e-06,
+      "loss": 0.6905,
+      "step": 700
+    },
+    {
+      "epoch": 0.8749229821318546,
+      "grad_norm": 1.4292715251283548,
+      "learning_rate": 8.930131235066914e-06,
+      "loss": 0.7148,
+      "step": 710
+    },
+    {
+      "epoch": 0.8872458410351202,
+      "grad_norm": 1.6096597940014286,
+      "learning_rate": 8.885429140473361e-06,
+      "loss": 0.693,
+      "step": 720
+    },
+    {
+      "epoch": 0.8995686999383857,
+      "grad_norm": 1.353744510033121,
+      "learning_rate": 8.839928958938364e-06,
+      "loss": 0.7023,
+      "step": 730
+    },
+    {
+      "epoch": 0.9118915588416513,
+      "grad_norm": 1.4213815672007308,
+      "learning_rate": 8.793640036431036e-06,
+      "loss": 0.7014,
+      "step": 740
+    },
+    {
+      "epoch": 0.9242144177449169,
+      "grad_norm": 1.4606321089003083,
+      "learning_rate": 8.746571880931896e-06,
+      "loss": 0.7153,
+      "step": 750
+    },
+    {
+      "epoch": 0.9365372766481824,
+      "grad_norm": 1.5281040298725672,
+      "learning_rate": 8.698734160479892e-06,
+      "loss": 0.7031,
+      "step": 760
+    },
+    {
+      "epoch": 0.9488601355514479,
+      "grad_norm": 1.3884649680592567,
+      "learning_rate": 8.650136701186537e-06,
+      "loss": 0.6744,
+      "step": 770
+    },
+    {
+      "epoch": 0.9611829944547134,
+      "grad_norm": 1.4546984091832766,
+      "learning_rate": 8.60078948521757e-06,
+      "loss": 0.6921,
+      "step": 780
+    },
+    {
+      "epoch": 0.973505853357979,
+      "grad_norm": 1.407393171546671,
+      "learning_rate": 8.550702648742566e-06,
+      "loss": 0.6956,
+      "step": 790
+    },
+    {
+      "epoch": 0.9858287122612446,
+      "grad_norm": 1.5419052598370024,
+      "learning_rate": 8.499886479852935e-06,
+      "loss": 0.7018,
+      "step": 800
+    },
+    {
+      "epoch": 0.9981515711645101,
+      "grad_norm": 1.3924572032379763,
+      "learning_rate": 8.448351416448664e-06,
+      "loss": 0.7032,
+      "step": 810
+    },
+    {
+      "epoch": 1.0098582871226125,
+      "grad_norm": 1.469436463403791,
+      "learning_rate": 8.39610804409435e-06,
+      "loss": 0.595,
+      "step": 820
+    },
+    {
+      "epoch": 1.022181146025878,
+      "grad_norm": 1.3472647409260032,
+      "learning_rate": 8.343167093844847e-06,
+      "loss": 0.5946,
+      "step": 830
+    },
+    {
+      "epoch": 1.0345040049291436,
+      "grad_norm": 1.4900881715555114,
+      "learning_rate": 8.289539440041066e-06,
+      "loss": 0.5845,
+      "step": 840
+    },
+    {
+      "epoch": 1.0468268638324092,
+      "grad_norm": 1.536018069046092,
+      "learning_rate": 8.23523609807633e-06,
+      "loss": 0.584,
+      "step": 850
+    },
+    {
+      "epoch": 1.0591497227356748,
+      "grad_norm": 1.3929504918120152,
+      "learning_rate": 8.180268222133748e-06,
+      "loss": 0.5847,
+      "step": 860
+    },
+    {
+      "epoch": 1.0714725816389403,
+      "grad_norm": 1.4359269869911984,
+      "learning_rate": 8.124647102895098e-06,
+      "loss": 0.5925,
+      "step": 870
+    },
+    {
+      "epoch": 1.083795440542206,
+      "grad_norm": 1.5544330412650198,
+      "learning_rate": 8.068384165221657e-06,
+      "loss": 0.584,
+      "step": 880
+    },
+    {
+      "epoch": 1.0961182994454712,
+      "grad_norm": 1.5891555387420517,
+      "learning_rate": 8.011490965807479e-06,
+      "loss": 0.5932,
+      "step": 890
+    },
+    {
+      "epoch": 1.1084411583487368,
+      "grad_norm": 1.3831550373033548,
+      "learning_rate": 7.953979190805587e-06,
+      "loss": 0.5642,
+      "step": 900
+    },
+    {
+      "epoch": 1.1207640172520024,
+      "grad_norm": 1.5096251669733274,
+      "learning_rate": 7.89586065342759e-06,
+      "loss": 0.6045,
+      "step": 910
+    },
+    {
+      "epoch": 1.133086876155268,
+      "grad_norm": 1.5477962613440504,
+      "learning_rate": 7.837147291517172e-06,
+      "loss": 0.5985,
+      "step": 920
+    },
+    {
+      "epoch": 1.1454097350585335,
+      "grad_norm": 1.4777678800069058,
+      "learning_rate": 7.777851165098012e-06,
+      "loss": 0.5686,
+      "step": 930
+    },
+    {
+      "epoch": 1.157732593961799,
+      "grad_norm": 1.4642650138802815,
+      "learning_rate": 7.717984453896585e-06,
+      "loss": 0.5888,
+      "step": 940
+    },
+    {
+      "epoch": 1.1700554528650646,
+      "grad_norm": 1.4714962123924216,
+      "learning_rate": 7.657559454840386e-06,
+      "loss": 0.5813,
+      "step": 950
+    },
+    {
+      "epoch": 1.1823783117683302,
+      "grad_norm": 1.5434418352328334,
+      "learning_rate": 7.596588579532087e-06,
+      "loss": 0.582,
+      "step": 960
+    },
+    {
+      "epoch": 1.1947011706715958,
+      "grad_norm": 1.5260417649961813,
+      "learning_rate": 7.535084351700117e-06,
+      "loss": 0.5855,
+      "step": 970
+    },
+    {
+      "epoch": 1.2070240295748613,
+      "grad_norm": 1.4802498809379745,
+      "learning_rate": 7.473059404626229e-06,
+      "loss": 0.5842,
+      "step": 980
+    },
+    {
+      "epoch": 1.219346888478127,
+      "grad_norm": 1.3297021246491412,
+      "learning_rate": 7.410526478550568e-06,
+      "loss": 0.5927,
+      "step": 990
+    },
+    {
+      "epoch": 1.2316697473813925,
+      "grad_norm": 1.4822236798755983,
+      "learning_rate": 7.34749841805475e-06,
+      "loss": 0.5925,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2316697473813925,
+      "eval_loss": 0.6842279434204102,
+      "eval_runtime": 292.4878,
+      "eval_samples_per_second": 19.724,
+      "eval_steps_per_second": 2.468,
+      "step": 1000
+    },
+    {
+      "epoch": 1.243992606284658,
+      "grad_norm": 1.4439342982568775,
+      "learning_rate": 7.283988169423526e-06,
+      "loss": 0.6095,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2563154651879236,
+      "grad_norm": 1.4717143885943422,
+      "learning_rate": 7.2200087779855435e-06,
+      "loss": 0.5953,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2686383240911892,
+      "grad_norm": 1.3795289662769703,
+      "learning_rate": 7.155573385433772e-06,
+      "loss": 0.5913,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2809611829944547,
+      "grad_norm": 1.4524123662025874,
+      "learning_rate": 7.090695227126141e-06,
+      "loss": 0.6022,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2932840418977203,
+      "grad_norm": 1.490623557265845,
+      "learning_rate": 7.025387629366912e-06,
+      "loss": 0.5891,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3056069008009858,
+      "grad_norm": 1.531349932144773,
+      "learning_rate": 6.959664006669404e-06,
+      "loss": 0.578,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3179297597042514,
+      "grad_norm": 1.530526603204912,
+      "learning_rate": 6.893537859000576e-06,
+      "loss": 0.5837,
+      "step": 1070
+    },
+    {
+      "epoch": 1.330252618607517,
+      "grad_norm": 1.5336378586039672,
+      "learning_rate": 6.827022769008068e-06,
+      "loss": 0.5783,
+      "step": 1080
+    },
+    {
+      "epoch": 1.3425754775107825,
+      "grad_norm": 1.5280710127320882,
+      "learning_rate": 6.7601323992302525e-06,
+      "loss": 0.5882,
+      "step": 1090
+    },
+    {
+      "epoch": 1.354898336414048,
+      "grad_norm": 1.4999675248496456,
+      "learning_rate": 6.692880489289885e-06,
+      "loss": 0.5889,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3672211953173137,
+      "grad_norm": 1.5626649470550829,
+      "learning_rate": 6.6252808530719095e-06,
+      "loss": 0.5886,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3795440542205792,
+      "grad_norm": 1.284249388975707,
+      "learning_rate": 6.557347375886022e-06,
+      "loss": 0.5737,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3918669131238448,
+      "grad_norm": 1.5307650624586169,
+      "learning_rate": 6.489094011614553e-06,
+      "loss": 0.5876,
+      "step": 1130
+    },
+    {
+      "epoch": 1.4041897720271104,
+      "grad_norm": 1.5439204209276158,
+      "learning_rate": 6.4205347798462704e-06,
+      "loss": 0.5917,
+      "step": 1140
+    },
+    {
+      "epoch": 1.416512630930376,
+      "grad_norm": 1.4449420830490325,
+      "learning_rate": 6.351683762996681e-06,
+      "loss": 0.5836,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4288354898336415,
+      "grad_norm": 1.3380998089412088,
+      "learning_rate": 6.282555103415438e-06,
+      "loss": 0.5783,
+      "step": 1160
+    },
+    {
+      "epoch": 1.441158348736907,
+      "grad_norm": 1.5189010531540565,
+      "learning_rate": 6.213163000481428e-06,
+      "loss": 0.5723,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4534812076401726,
+      "grad_norm": 1.4395684252424352,
+      "learning_rate": 6.143521707686137e-06,
+      "loss": 0.6022,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4658040665434382,
+      "grad_norm": 1.4792406947504433,
+      "learning_rate": 6.073645529705926e-06,
+      "loss": 0.5917,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4781269254467038,
+      "grad_norm": 1.3975340017935896,
+      "learning_rate": 6.0035488194637645e-06,
+      "loss": 0.5833,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4904497843499693,
+      "grad_norm": 1.3964019973704387,
+      "learning_rate": 5.933245975181074e-06,
+      "loss": 0.5898,
+      "step": 1210
+    },
+    {
+      "epoch": 1.502772643253235,
+      "grad_norm": 1.4887675284639827,
+      "learning_rate": 5.8627514374202596e-06,
+      "loss": 0.5842,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5150955021565005,
+      "grad_norm": 1.5230001110062263,
+      "learning_rate": 5.79207968611854e-06,
+      "loss": 0.5839,
+      "step": 1230
+    },
+    {
+      "epoch": 1.527418361059766,
+      "grad_norm": 1.6079713389994916,
+      "learning_rate": 5.721245237613704e-06,
+      "loss": 0.5764,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5397412199630314,
+      "grad_norm": 1.4413876513489634,
+      "learning_rate": 5.650262641662367e-06,
+      "loss": 0.586,
+      "step": 1250
+    },
+    {
+      "epoch": 1.552064078866297,
+      "grad_norm": 1.3881515755792924,
+      "learning_rate": 5.5791464784513905e-06,
+      "loss": 0.5702,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5643869377695625,
+      "grad_norm": 1.4305380922203093,
+      "learning_rate": 5.50791135560303e-06,
+      "loss": 0.5833,
+      "step": 1270
+    },
+    {
+      "epoch": 1.576709796672828,
+      "grad_norm": 1.5745707819252874,
+      "learning_rate": 5.4365719051744556e-06,
+      "loss": 0.5738,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5890326555760936,
+      "grad_norm": 1.5326630255795084,
+      "learning_rate": 5.365142780652255e-06,
+      "loss": 0.5811,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6013555144793592,
+      "grad_norm": 1.4817407233445945,
+      "learning_rate": 5.2936386539425325e-06,
+      "loss": 0.6035,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6136783733826248,
+      "grad_norm": 1.5091402086971266,
+      "learning_rate": 5.222074212357221e-06,
+      "loss": 0.5767,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6260012322858903,
+      "grad_norm": 1.3581090409841263,
+      "learning_rate": 5.150464155597239e-06,
+      "loss": 0.5798,
+      "step": 1320
+    },
+    {
+      "epoch": 1.638324091189156,
+      "grad_norm": 1.530635775774838,
+      "learning_rate": 5.0788231927330924e-06,
+      "loss": 0.5757,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6506469500924215,
+      "grad_norm": 1.4118546219588066,
+      "learning_rate": 5.007166039183561e-06,
+      "loss": 0.5762,
+      "step": 1340
+    },
+    {
+      "epoch": 1.662969808995687,
+      "grad_norm": 1.4363769831225472,
+      "learning_rate": 4.935507413693071e-06,
+      "loss": 0.5758,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6752926678989526,
+      "grad_norm": 1.4406194256672695,
+      "learning_rate": 4.863862035308392e-06,
+      "loss": 0.5727,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6876155268022182,
+      "grad_norm": 1.450317318281763,
+      "learning_rate": 4.792244620355275e-06,
+      "loss": 0.5723,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6999383857054837,
+      "grad_norm": 1.3072933545935408,
+      "learning_rate": 4.720669879415637e-06,
+      "loss": 0.58,
+      "step": 1380
+    },
+    {
+      "epoch": 1.712261244608749,
+      "grad_norm": 1.4301648378358092,
+      "learning_rate": 4.649152514305934e-06,
+      "loss": 0.5831,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7245841035120146,
+      "grad_norm": 1.446398014421451,
+      "learning_rate": 4.5777072150573355e-06,
+      "loss": 0.5647,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7369069624152802,
+      "grad_norm": 1.335488005255364,
+      "learning_rate": 4.506348656898316e-06,
+      "loss": 0.5631,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7492298213185458,
+      "grad_norm": 1.4887079476746525,
+      "learning_rate": 4.435091497240287e-06,
+      "loss": 0.5855,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7615526802218113,
+      "grad_norm": 1.3528687038903755,
+      "learning_rate": 4.363950372666896e-06,
+      "loss": 0.5714,
+      "step": 1430
+    },
+    {
+      "epoch": 1.773875539125077,
+      "grad_norm": 1.5010430485235071,
+      "learning_rate": 4.292939895927587e-06,
+      "loss": 0.5754,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7861983980283425,
+      "grad_norm": 1.4967607376486216,
+      "learning_rate": 4.2220746529360745e-06,
+      "loss": 0.5876,
+      "step": 1450
+    },
+    {
+      "epoch": 1.798521256931608,
+      "grad_norm": 1.414501545862856,
+      "learning_rate": 4.151369199774325e-06,
+      "loss": 0.5787,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8108441158348736,
+      "grad_norm": 1.4353512720205093,
+      "learning_rate": 4.080838059702656e-06,
+      "loss": 0.5798,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8231669747381392,
+      "grad_norm": 1.4304133370737042,
+      "learning_rate": 4.0104957201765874e-06,
+      "loss": 0.5813,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8354898336414047,
+      "grad_norm": 1.4767308440844067,
+      "learning_rate": 3.940356629871051e-06,
+      "loss": 0.5737,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8478126925446703,
+      "grad_norm": 1.4076636748109828,
+      "learning_rate": 3.870435195712547e-06,
+      "loss": 0.5739,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8478126925446703,
+      "eval_loss": 0.6650247573852539,
+      "eval_runtime": 293.5128,
+      "eval_samples_per_second": 19.655,
+      "eval_steps_per_second": 2.46,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8601355514479359,
+      "grad_norm": 1.446069322241234,
+      "learning_rate": 3.8007457799198977e-06,
+      "loss": 0.5996,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8724584103512014,
+      "grad_norm": 1.461756871051999,
+      "learning_rate": 3.7313026970541687e-06,
+      "loss": 0.5686,
+      "step": 1520
+    },
+    {
+      "epoch": 1.884781269254467,
+      "grad_norm": 1.3839934073401108,
+      "learning_rate": 3.662120211078385e-06,
+      "loss": 0.5814,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8971041281577325,
+      "grad_norm": 1.430323877887507,
+      "learning_rate": 3.5932125324276524e-06,
+      "loss": 0.5821,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9094269870609981,
+      "grad_norm": 1.547047373146706,
+      "learning_rate": 3.524593815090241e-06,
+      "loss": 0.5753,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9217498459642637,
+      "grad_norm": 1.4286065771891827,
+      "learning_rate": 3.4562781537003e-06,
+      "loss": 0.5659,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9340727048675292,
+      "grad_norm": 1.489813539203223,
+      "learning_rate": 3.3882795806427437e-06,
+      "loss": 0.5705,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9463955637707948,
+      "grad_norm": 1.3797109203901303,
+      "learning_rate": 3.320612063170926e-06,
+      "loss": 0.573,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9587184226740604,
+      "grad_norm": 1.424911376888776,
+      "learning_rate": 3.2532895005376943e-06,
+      "loss": 0.5594,
+      "step": 1590
+    },
+    {
+      "epoch": 1.971041281577326,
+      "grad_norm": 1.4893262359299044,
+      "learning_rate": 3.18632572114042e-06,
+      "loss": 0.5682,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9833641404805915,
+      "grad_norm": 1.5364372251837122,
+      "learning_rate": 3.1197344796805675e-06,
+      "loss": 0.5642,
+      "step": 1610
+    },
+    {
+      "epoch": 1.995686999383857,
+      "grad_norm": 1.3917689573647591,
+      "learning_rate": 3.0535294543384074e-06,
+      "loss": 0.5691,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0073937153419594,
+      "grad_norm": 1.2335683413193184,
+      "learning_rate": 2.987724243963458e-06,
+      "loss": 0.4903,
+      "step": 1630
+    },
+    {
+      "epoch": 2.019716574245225,
+      "grad_norm": 1.4879923707562226,
+      "learning_rate": 2.922332365281201e-06,
+      "loss": 0.4882,
+      "step": 1640
+    },
+    {
+      "epoch": 2.0320394331484906,
+      "grad_norm": 1.470082730902103,
+      "learning_rate": 2.857367250116682e-06,
+      "loss": 0.4714,
+      "step": 1650
+    },
+    {
+      "epoch": 2.044362292051756,
+      "grad_norm": 1.3868059292330677,
+      "learning_rate": 2.7928422426355554e-06,
+      "loss": 0.4748,
+      "step": 1660
+    },
+    {
+      "epoch": 2.0566851509550217,
+      "grad_norm": 1.3074599768704374,
+      "learning_rate": 2.728770596603105e-06,
+      "loss": 0.4764,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0690080098582873,
+      "grad_norm": 1.32948215843512,
+      "learning_rate": 2.665165472661866e-06,
+      "loss": 0.4735,
+      "step": 1680
+    },
+    {
+      "epoch": 2.081330868761553,
+      "grad_norm": 1.288105917381929,
+      "learning_rate": 2.6020399356283586e-06,
+      "loss": 0.4578,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0936537276648184,
+      "grad_norm": 1.5083815524530002,
+      "learning_rate": 2.539406951809512e-06,
+      "loss": 0.4737,
+      "step": 1700
+    },
+    {
+      "epoch": 2.105976586568084,
+      "grad_norm": 1.370643565971273,
+      "learning_rate": 2.477279386339309e-06,
+      "loss": 0.4695,
+      "step": 1710
+    },
+    {
+      "epoch": 2.1182994454713495,
+      "grad_norm": 1.539465680425723,
+      "learning_rate": 2.4156700005362384e-06,
+      "loss": 0.4785,
+      "step": 1720
+    },
+    {
+      "epoch": 2.130622304374615,
+      "grad_norm": 1.3161398723417894,
+      "learning_rate": 2.3545914492820366e-06,
+      "loss": 0.4723,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1429451632778806,
+      "grad_norm": 1.3496232354886113,
+      "learning_rate": 2.2940562784223224e-06,
+      "loss": 0.4672,
+      "step": 1740
+    },
+    {
+      "epoch": 2.155268022181146,
+      "grad_norm": 1.4560762054385992,
+      "learning_rate": 2.234076922189613e-06,
+      "loss": 0.4734,
+      "step": 1750
+    },
+    {
+      "epoch": 2.167590881084412,
+      "grad_norm": 1.4261953514874182,
+      "learning_rate": 2.174665700649267e-06,
+      "loss": 0.4512,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1799137399876773,
+      "grad_norm": 1.402399540780295,
+      "learning_rate": 2.1158348171688888e-06,
+      "loss": 0.4678,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1922365988909425,
+      "grad_norm": 1.5018053091348222,
+      "learning_rate": 2.0575963559116823e-06,
+      "loss": 0.4719,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2045594577942085,
+      "grad_norm": 1.3841680388808222,
+      "learning_rate": 1.999962279354311e-06,
+      "loss": 0.4539,
+      "step": 1790
+    },
+    {
+      "epoch": 2.2168823166974736,
+      "grad_norm": 1.4988666932124328,
+      "learning_rate": 1.942944425829741e-06,
+      "loss": 0.4759,
+      "step": 1800
+    },
+    {
+      "epoch": 2.229205175600739,
+      "grad_norm": 1.4604660741651032,
+      "learning_rate": 1.8865545070955882e-06,
+      "loss": 0.4633,
+      "step": 1810
+    },
+    {
+      "epoch": 2.2415280345040047,
+      "grad_norm": 1.4729154256839592,
+      "learning_rate": 1.8308041059284621e-06,
+      "loss": 0.4683,
+      "step": 1820
+    },
+    {
+      "epoch": 2.2538508934072703,
+      "grad_norm": 1.3951925274071466,
+      "learning_rate": 1.775704673744809e-06,
+      "loss": 0.477,
+      "step": 1830
+    },
+    {
+      "epoch": 2.266173752310536,
+      "grad_norm": 1.3274198340736063,
+      "learning_rate": 1.7212675282487269e-06,
+      "loss": 0.4792,
+      "step": 1840
+    },
+    {
+      "epoch": 2.2784966112138014,
+      "grad_norm": 1.47289795633966,
+      "learning_rate": 1.6675038511072518e-06,
+      "loss": 0.4704,
+      "step": 1850
+    },
+    {
+      "epoch": 2.290819470117067,
+      "grad_norm": 1.464939828470514,
+      "learning_rate": 1.6144246856535933e-06,
+      "loss": 0.4685,
+      "step": 1860
+    },
+    {
+      "epoch": 2.3031423290203326,
+      "grad_norm": 1.5114712361380727,
+      "learning_rate": 1.5620409346187697e-06,
+      "loss": 0.4786,
+      "step": 1870
+    },
+    {
+      "epoch": 2.315465187923598,
+      "grad_norm": 1.470496061687908,
+      "learning_rate": 1.510363357892133e-06,
+      "loss": 0.469,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3277880468268637,
+      "grad_norm": 1.3693122919551104,
+      "learning_rate": 1.4594025703112397e-06,
+      "loss": 0.4706,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3401109057301293,
+      "grad_norm": 1.4248383166060672,
+      "learning_rate": 1.4091690394814989e-06,
+      "loss": 0.4586,
+      "step": 1900
+    },
+    {
+      "epoch": 2.352433764633395,
+      "grad_norm": 1.3906892416250238,
+      "learning_rate": 1.359673083626079e-06,
+      "loss": 0.4679,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3647566235366604,
+      "grad_norm": 1.4984855730756004,
+      "learning_rate": 1.3109248694664917e-06,
+      "loss": 0.4688,
+      "step": 1920
+    },
+    {
+      "epoch": 2.377079482439926,
+      "grad_norm": 1.3070944407719698,
+      "learning_rate": 1.262934410134292e-06,
+      "loss": 0.4692,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3894023413431915,
+      "grad_norm": 1.456513284182291,
+      "learning_rate": 1.2157115631143384e-06,
+      "loss": 0.4734,
+      "step": 1940
+    },
+    {
+      "epoch": 2.401725200246457,
+      "grad_norm": 1.4802761342220625,
+      "learning_rate": 1.169266028220004e-06,
+      "loss": 0.4789,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4140480591497226,
+      "grad_norm": 1.4862600637634056,
+      "learning_rate": 1.1236073456007928e-06,
+      "loss": 0.4761,
+      "step": 1960
+    },
+    {
+      "epoch": 2.426370918052988,
+      "grad_norm": 1.436924860825337,
+      "learning_rate": 1.0787448937827428e-06,
+      "loss": 0.4506,
+      "step": 1970
+    },
+    {
+      "epoch": 2.438693776956254,
+      "grad_norm": 1.4729675955814119,
+      "learning_rate": 1.034687887742028e-06,
+      "loss": 0.4661,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4510166358595193,
+      "grad_norm": 1.4365421186657983,
+      "learning_rate": 9.914453770121557e-07,
+      "loss": 0.4535,
+      "step": 1990
+    },
+    {
+      "epoch": 2.463339494762785,
+      "grad_norm": 1.3393762796043207,
+      "learning_rate": 9.490262438251496e-07,
+      "loss": 0.4637,
+      "step": 2000
+    },
+    {
+      "epoch": 2.463339494762785,
+      "eval_loss": 0.6939365267753601,
+      "eval_runtime": 290.4872,
+      "eval_samples_per_second": 19.86,
+      "eval_steps_per_second": 2.485,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4756623536660505,
+      "grad_norm": 1.318600880357867,
+      "learning_rate": 9.07439201287088e-07,
+      "loss": 0.4673,
+      "step": 2010
+    },
+    {
+      "epoch": 2.487985212569316,
+      "grad_norm": 1.4047247838739947,
+      "learning_rate": 8.666927915883905e-07,
+      "loss": 0.4594,
+      "step": 2020
+    },
+    {
+      "epoch": 2.5003080714725816,
+      "grad_norm": 1.3215657962974705,
+      "learning_rate": 8.2679538424921e-07,
+      "loss": 0.4633,
+      "step": 2030
+    },
+    {
+      "epoch": 2.512630930375847,
+      "grad_norm": 1.3898207583964082,
+      "learning_rate": 7.877551744002881e-07,
+      "loss": 0.4716,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5249537892791127,
+      "grad_norm": 1.467272084224576,
+      "learning_rate": 7.495801810996334e-07,
+      "loss": 0.4748,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5372766481823783,
+      "grad_norm": 1.5209575533016215,
+      "learning_rate": 7.122782456853722e-07,
+      "loss": 0.4714,
+      "step": 2060
+    },
+    {
+      "epoch": 2.549599507085644,
+      "grad_norm": 1.433751017027838,
+      "learning_rate": 6.758570301650869e-07,
+      "loss": 0.4745,
+      "step": 2070
+    },
+    {
+      "epoch": 2.5619223659889094,
+      "grad_norm": 1.3745904975610637,
+      "learning_rate": 6.403240156420087e-07,
+      "loss": 0.4633,
+      "step": 2080
+    },
+    {
+      "epoch": 2.574245224892175,
+      "grad_norm": 1.5462474471731622,
+      "learning_rate": 6.056865007783602e-07,
+      "loss": 0.4674,
+      "step": 2090
+    },
+    {
+      "epoch": 2.5865680837954406,
+      "grad_norm": 1.395318352381848,
+      "learning_rate": 5.7195160029617e-07,
+      "loss": 0.4636,
+      "step": 2100
+    },
+    {
+      "epoch": 2.598890942698706,
+      "grad_norm": 1.4508968784638185,
+      "learning_rate": 5.391262435158722e-07,
+      "loss": 0.4612,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6112138016019717,
+      "grad_norm": 1.5179245072065153,
+      "learning_rate": 5.072171729329944e-07,
+      "loss": 0.4548,
+      "step": 2120
+    },
+    {
+      "epoch": 2.6235366605052373,
+      "grad_norm": 1.4994168181906784,
+      "learning_rate": 4.7623094283320905e-07,
+      "loss": 0.4649,
+      "step": 2130
+    },
+    {
+      "epoch": 2.635859519408503,
+      "grad_norm": 1.4135373611963087,
+      "learning_rate": 4.4617391794604946e-07,
+      "loss": 0.4649,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6481823783117684,
+      "grad_norm": 1.2683747528125564,
+      "learning_rate": 4.170522721375669e-07,
+      "loss": 0.4729,
+      "step": 2150
+    },
+    {
+      "epoch": 2.660505237215034,
+      "grad_norm": 1.3525207032019462,
+      "learning_rate": 3.8887198714218255e-07,
+      "loss": 0.4626,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6728280961182995,
+      "grad_norm": 1.4316798644144118,
+      "learning_rate": 3.616388513340124e-07,
+      "loss": 0.4618,
+      "step": 2170
+    },
+    {
+      "epoch": 2.685150955021565,
+      "grad_norm": 1.506137937558267,
+      "learning_rate": 3.3535845853790105e-07,
+      "loss": 0.4576,
+      "step": 2180
+    },
+    {
+      "epoch": 2.6974738139248307,
+      "grad_norm": 1.2499089130102832,
+      "learning_rate": 3.1003620688042636e-07,
+      "loss": 0.4557,
+      "step": 2190
+    },
+    {
+      "epoch": 2.709796672828096,
+      "grad_norm": 1.5041243905421406,
+      "learning_rate": 2.856772976810929e-07,
+      "loss": 0.4687,
+      "step": 2200
+    },
+    {
+      "epoch": 2.722119531731362,
+      "grad_norm": 1.3256641357947336,
+      "learning_rate": 2.6228673438395804e-07,
+      "loss": 0.4617,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7344423906346274,
+      "grad_norm": 1.516883255523505,
+      "learning_rate": 2.398693215298953e-07,
+      "loss": 0.4666,
+      "step": 2220
+    },
+    {
+      "epoch": 2.746765249537893,
+      "grad_norm": 1.2550064770530165,
+      "learning_rate": 2.1842966376972142e-07,
+      "loss": 0.4757,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7590881084411585,
+      "grad_norm": 1.4223713837529477,
+      "learning_rate": 1.9797216491837356e-07,
+      "loss": 0.4634,
+      "step": 2240
+    },
+    {
+      "epoch": 2.771410967344424,
+      "grad_norm": 1.3606827390943357,
+      "learning_rate": 1.7850102705034455e-07,
+      "loss": 0.4694,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7837338262476896,
+      "grad_norm": 1.4381020424607691,
+      "learning_rate": 1.600202496365566e-07,
+      "loss": 0.4637,
+      "step": 2260
+    },
+    {
+      "epoch": 2.796056685150955,
+      "grad_norm": 1.4541821978517326,
+      "learning_rate": 1.425336287228496e-07,
+      "loss": 0.4709,
+      "step": 2270
+    },
+    {
+      "epoch": 2.8083795440542207,
+      "grad_norm": 1.535729509926539,
+      "learning_rate": 1.2604475615025092e-07,
+      "loss": 0.46,
+      "step": 2280
+    },
+    {
+      "epoch": 2.820702402957486,
+      "grad_norm": 1.4756674292181435,
+      "learning_rate": 1.1055701881719838e-07,
+      "loss": 0.4722,
+      "step": 2290
+    },
+    {
+      "epoch": 2.833025261860752,
+      "grad_norm": 1.365953899712207,
+      "learning_rate": 9.607359798384785e-08,
+      "loss": 0.4677,
+      "step": 2300
+    },
+    {
+      "epoch": 2.845348120764017,
+      "grad_norm": 1.2777787545094819,
+      "learning_rate": 8.259746861863094e-08,
+      "loss": 0.4645,
+      "step": 2310
+    },
+    {
+      "epoch": 2.857670979667283,
+      "grad_norm": 1.4119719950612792,
+      "learning_rate": 7.013139878717934e-08,
+      "loss": 0.4659,
+      "step": 2320
+    },
+    {
+      "epoch": 2.869993838570548,
+      "grad_norm": 1.3219403705325738,
+      "learning_rate": 5.8677949083749686e-08,
+      "loss": 0.4717,
+      "step": 2330
+    },
+    {
+      "epoch": 2.882316697473814,
+      "grad_norm": 1.43452858824685,
+      "learning_rate": 4.823947210526647e-08,
+      "loss": 0.4562,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8946395563770793,
+      "grad_norm": 1.4018883778180602,
+      "learning_rate": 3.8818111968083607e-08,
+      "loss": 0.4784,
+      "step": 2350
+    },
+    {
+      "epoch": 2.9069624152803453,
+      "grad_norm": 1.4362249713543827,
+      "learning_rate": 3.041580386757448e-08,
+      "loss": 0.4736,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9192852741836104,
+      "grad_norm": 1.4667038100350953,
+      "learning_rate": 2.3034273680632157e-08,
+      "loss": 0.4658,
+      "step": 2370
+    },
+    {
+      "epoch": 2.9316081330868764,
+      "grad_norm": 1.4777477329312418,
+      "learning_rate": 1.6675037611165735e-08,
+      "loss": 0.4962,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9439309919901415,
+      "grad_norm": 1.4703683347893792,
+      "learning_rate": 1.1339401878663337e-08,
+      "loss": 0.4672,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9562538508934075,
+      "grad_norm": 1.4130266231255557,
+      "learning_rate": 7.028462449889528e-09,
+      "loss": 0.4633,
+      "step": 2400
+    },
+    {
+      "epoch": 2.9685767097966727,
+      "grad_norm": 1.3914037328445572,
+      "learning_rate": 3.743104813767051e-09,
+      "loss": 0.4541,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9808995686999387,
+      "grad_norm": 1.4673797756485851,
+      "learning_rate": 1.4840037994923173e-09,
+      "loss": 0.4567,
+      "step": 2420
+    },
+    {
+      "epoch": 2.993222427603204,
+      "grad_norm": 1.336412676673849,
+      "learning_rate": 2.516234379235094e-10,
+      "loss": 0.4601,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "step": 2436,
+      "total_flos": 598743726292992.0,
+      "train_loss": 0.6124914906099317,
+      "train_runtime": 9399.7215,
+      "train_samples_per_second": 16.571,
+      "train_steps_per_second": 0.259
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2436,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 598743726292992.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

EXP_1.1_3b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00930cc5b9b912ef62d9bf9ecb60388b02022d6fc087abd0690f66ed466b9a7
+size 7953

EXP_1.1_3b/video_preprocessor_config.json

@@ -0,0 +1,86 @@
+{
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

EXP_1.2_3b/README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+base_model: /mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: EXP_1.2_3b
+  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. -->
+
+# EXP_1.2_3b
+
+This model is a fine-tuned version of [/mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct](https://huggingface.co//mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct) on the multimodal-open-r1-8k-verified_train_long_cot dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4758
+
+## 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: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- 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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

EXP_1.2_3b/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
+}

EXP_1.2_3b/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.47578269243240356,
+    "eval_runtime": 39.7643,
+    "eval_samples_per_second": 19.339,
+    "eval_steps_per_second": 2.439,
+    "total_flos": 56487017447424.0,
+    "train_loss": 0.33897173769248007,
+    "train_runtime": 796.6909,
+    "train_samples_per_second": 26.058,
+    "train_steps_per_second": 0.41
+}

EXP_1.2_3b/chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

EXP_1.2_3b/config.json

@@ -0,0 +1,105 @@
+{
+  "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,
+  "text_config": {
+    "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": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 128000,
+    "max_window_layers": 70,
+    "model_type": "qwen2_5_vl_text",
+    "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": "float32",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "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,
+    "initializer_range": 0.02,
+    "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": "float32",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

EXP_1.2_3b/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.47578269243240356,
+    "eval_runtime": 39.7643,
+    "eval_samples_per_second": 19.339,
+    "eval_steps_per_second": 2.439
+}

EXP_1.2_3b/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": "4.52.4"
+}

EXP_1.2_3b/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca91d23c884ea32ec9c9a82275f94153d501c4fdf693c085f5802ee38054a8f
+size 4997750760

EXP_1.2_3b/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79e238572fa6c8a446cc5cd858f7755e96d6326beaa069e56d6ec53d4746cb1
+size 2511587184

EXP_1.2_3b/model.safetensors.index.json

@@ -0,0 +1,831 @@
+{
+  "metadata": {
+    "total_size": 7509245952
+  },
+  "weight_map": {
+    "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"
+  }
+}

EXP_1.2_3b/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
+}

EXP_1.2_3b/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
+  }
+}

EXP_1.2_3b/swanlab_public_config.json

@@ -0,0 +1,13 @@
+{
+  "project_name": "LLaMA-Factory",
+  "version": "0.6.1",
+  "run_id": "run-20250610_121219-a3b1799d",
+  "swanlog_dir": "/mnt/nvme/hyz/LLaMA-Factory/swanlog",
+  "run_dir": "/mnt/nvme/hyz/LLaMA-Factory/swanlog/run-20250610_121219-a3b1799d",
+  "cloud": {
+    "project_name": "LLaMA-Factory",
+    "project_url": "https://swanlab.cn/@huyuanze/LLaMA-Factory",
+    "experiment_name": "/mnt/nvme/hyz/mm_homework/checkpoints_full/EXP_1.2_3b",
+    "experiment_url": "https://swanlab.cn/@huyuanze/LLaMA-Factory/runs/skm5tcynsle1qxupe85cz"
+  }
+}

EXP_1.2_3b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

EXP_1.2_3b/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

EXP_1.2_3b/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 56487017447424.0,
+    "train_loss": 0.33897173769248007,
+    "train_runtime": 796.6909,
+    "train_samples_per_second": 26.058,
+    "train_steps_per_second": 0.41
+}

EXP_1.2_3b/trainer_log.jsonl

@@ -0,0 +1,33 @@
+{"current_steps": 10, "total_steps": 327, "loss": 0.8529, "lr": 2.7272727272727272e-06, "epoch": 0.09216589861751152, "percentage": 3.06, "elapsed_time": "0:00:29", "remaining_time": "0:15:30"}
+{"current_steps": 20, "total_steps": 327, "loss": 0.6404, "lr": 5.7575757575757586e-06, "epoch": 0.18433179723502305, "percentage": 6.12, "elapsed_time": "0:00:52", "remaining_time": "0:13:28"}
+{"current_steps": 30, "total_steps": 327, "loss": 0.5326, "lr": 8.787878787878788e-06, "epoch": 0.2764976958525346, "percentage": 9.17, "elapsed_time": "0:01:17", "remaining_time": "0:12:47"}
+{"current_steps": 40, "total_steps": 327, "loss": 0.4925, "lr": 9.989726963751683e-06, "epoch": 0.3686635944700461, "percentage": 12.23, "elapsed_time": "0:01:40", "remaining_time": "0:11:58"}
+{"current_steps": 50, "total_steps": 327, "loss": 0.4799, "lr": 9.927100106776213e-06, "epoch": 0.4608294930875576, "percentage": 15.29, "elapsed_time": "0:02:03", "remaining_time": "0:11:22"}
+{"current_steps": 60, "total_steps": 327, "loss": 0.4592, "lr": 9.808267184205182e-06, "epoch": 0.5529953917050692, "percentage": 18.35, "elapsed_time": "0:02:26", "remaining_time": "0:10:51"}
+{"current_steps": 70, "total_steps": 327, "loss": 0.455, "lr": 9.63458378673011e-06, "epoch": 0.6451612903225806, "percentage": 21.41, "elapsed_time": "0:02:50", "remaining_time": "0:10:26"}
+{"current_steps": 80, "total_steps": 327, "loss": 0.4417, "lr": 9.408031213740045e-06, "epoch": 0.7373271889400922, "percentage": 24.46, "elapsed_time": "0:03:13", "remaining_time": "0:09:58"}
+{"current_steps": 90, "total_steps": 327, "loss": 0.4463, "lr": 9.131193871579975e-06, "epoch": 0.8294930875576036, "percentage": 27.52, "elapsed_time": "0:03:36", "remaining_time": "0:09:29"}
+{"current_steps": 100, "total_steps": 327, "loss": 0.4508, "lr": 8.807229791845673e-06, "epoch": 0.9216589861751152, "percentage": 30.58, "elapsed_time": "0:04:00", "remaining_time": "0:09:05"}
+{"current_steps": 110, "total_steps": 327, "loss": 0.4024, "lr": 8.439834606028594e-06, "epoch": 1.0092165898617511, "percentage": 33.64, "elapsed_time": "0:04:23", "remaining_time": "0:08:39"}
+{"current_steps": 120, "total_steps": 327, "loss": 0.3197, "lr": 8.033199387471278e-06, "epoch": 1.1013824884792627, "percentage": 36.7, "elapsed_time": "0:04:47", "remaining_time": "0:08:16"}
+{"current_steps": 130, "total_steps": 327, "loss": 0.3219, "lr": 7.591962841552627e-06, "epoch": 1.1935483870967742, "percentage": 39.76, "elapsed_time": "0:05:11", "remaining_time": "0:07:51"}
+{"current_steps": 140, "total_steps": 327, "loss": 0.3195, "lr": 7.121158389495187e-06, "epoch": 1.2857142857142856, "percentage": 42.81, "elapsed_time": "0:05:33", "remaining_time": "0:07:26"}
+{"current_steps": 150, "total_steps": 327, "loss": 0.3175, "lr": 6.626156749437736e-06, "epoch": 1.3778801843317972, "percentage": 45.87, "elapsed_time": "0:05:57", "remaining_time": "0:07:01"}
+{"current_steps": 160, "total_steps": 327, "loss": 0.3065, "lr": 6.112604669781572e-06, "epoch": 1.4700460829493087, "percentage": 48.93, "elapsed_time": "0:06:21", "remaining_time": "0:06:37"}
+{"current_steps": 170, "total_steps": 327, "loss": 0.3157, "lr": 5.586360513712011e-06, "epoch": 1.5622119815668203, "percentage": 51.99, "elapsed_time": "0:06:43", "remaining_time": "0:06:12"}
+{"current_steps": 180, "total_steps": 327, "loss": 0.311, "lr": 5.053427429716867e-06, "epoch": 1.6543778801843319, "percentage": 55.05, "elapsed_time": "0:07:06", "remaining_time": "0:05:48"}
+{"current_steps": 190, "total_steps": 327, "loss": 0.3131, "lr": 4.5198848704615915e-06, "epoch": 1.7465437788018434, "percentage": 58.1, "elapsed_time": "0:07:28", "remaining_time": "0:05:23"}
+{"current_steps": 200, "total_steps": 327, "loss": 0.2933, "lr": 3.991819241221836e-06, "epoch": 1.838709677419355, "percentage": 61.16, "elapsed_time": "0:07:52", "remaining_time": "0:05:00"}
+{"current_steps": 210, "total_steps": 327, "loss": 0.2828, "lr": 3.475254469003865e-06, "epoch": 1.9308755760368663, "percentage": 64.22, "elapsed_time": "0:08:17", "remaining_time": "0:04:37"}
+{"current_steps": 220, "total_steps": 327, "loss": 0.2656, "lr": 2.976083284388031e-06, "epoch": 2.0184331797235022, "percentage": 67.28, "elapsed_time": "0:08:41", "remaining_time": "0:04:13"}
+{"current_steps": 230, "total_steps": 327, "loss": 0.1944, "lr": 2.5000000000000015e-06, "epoch": 2.110599078341014, "percentage": 70.34, "elapsed_time": "0:09:03", "remaining_time": "0:03:49"}
+{"current_steps": 240, "total_steps": 327, "loss": 0.1971, "lr": 2.0524355524417017e-06, "epoch": 2.2027649769585254, "percentage": 73.39, "elapsed_time": "0:09:26", "remaining_time": "0:03:25"}
+{"current_steps": 250, "total_steps": 327, "loss": 0.1971, "lr": 1.6384955486934157e-06, "epoch": 2.294930875576037, "percentage": 76.45, "elapsed_time": "0:09:50", "remaining_time": "0:03:01"}
+{"current_steps": 260, "total_steps": 327, "loss": 0.1934, "lr": 1.2629020237248241e-06, "epoch": 2.3870967741935485, "percentage": 79.51, "elapsed_time": "0:10:15", "remaining_time": "0:02:38"}
+{"current_steps": 270, "total_steps": 327, "loss": 0.1975, "lr": 9.299395737170758e-07, "epoch": 2.47926267281106, "percentage": 82.57, "elapsed_time": "0:10:39", "remaining_time": "0:02:14"}
+{"current_steps": 280, "total_steps": 327, "loss": 0.2041, "lr": 6.43406479383053e-07, "epoch": 2.571428571428571, "percentage": 85.63, "elapsed_time": "0:11:01", "remaining_time": "0:01:51"}
+{"current_steps": 290, "total_steps": 327, "loss": 0.1979, "lr": 4.0657137694820826e-07, "epoch": 2.6635944700460827, "percentage": 88.69, "elapsed_time": "0:11:26", "remaining_time": "0:01:27"}
+{"current_steps": 300, "total_steps": 327, "loss": 0.1919, "lr": 2.2213597106929608e-07, "epoch": 2.7557603686635943, "percentage": 91.74, "elapsed_time": "0:11:48", "remaining_time": "0:01:03"}
+{"current_steps": 310, "total_steps": 327, "loss": 0.1897, "lr": 9.22042150446728e-08, "epoch": 2.847926267281106, "percentage": 94.8, "elapsed_time": "0:12:12", "remaining_time": "0:00:40"}
+{"current_steps": 320, "total_steps": 327, "loss": 0.1877, "lr": 1.8258309893965375e-08, "epoch": 2.9400921658986174, "percentage": 97.86, "elapsed_time": "0:12:37", "remaining_time": "0:00:16"}
+{"current_steps": 327, "total_steps": 327, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:13:14", "remaining_time": "0:00:00"}

EXP_1.2_3b/trainer_state.json

@@ -0,0 +1,267 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 327,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09216589861751152,
+      "grad_norm": 4.912416428745171,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.8529,
+      "step": 10
+    },
+    {
+      "epoch": 0.18433179723502305,
+      "grad_norm": 2.1443951476400227,
+      "learning_rate": 5.7575757575757586e-06,
+      "loss": 0.6404,
+      "step": 20
+    },
+    {
+      "epoch": 0.2764976958525346,
+      "grad_norm": 1.658722389064836,
+      "learning_rate": 8.787878787878788e-06,
+      "loss": 0.5326,
+      "step": 30
+    },
+    {
+      "epoch": 0.3686635944700461,
+      "grad_norm": 1.5618873833827294,
+      "learning_rate": 9.989726963751683e-06,
+      "loss": 0.4925,
+      "step": 40
+    },
+    {
+      "epoch": 0.4608294930875576,
+      "grad_norm": 1.4925009785754748,
+      "learning_rate": 9.927100106776213e-06,
+      "loss": 0.4799,
+      "step": 50
+    },
+    {
+      "epoch": 0.5529953917050692,
+      "grad_norm": 1.322188289534146,
+      "learning_rate": 9.808267184205182e-06,
+      "loss": 0.4592,
+      "step": 60
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 1.4524544851906915,
+      "learning_rate": 9.63458378673011e-06,
+      "loss": 0.455,
+      "step": 70
+    },
+    {
+      "epoch": 0.7373271889400922,
+      "grad_norm": 1.400758206854473,
+      "learning_rate": 9.408031213740045e-06,
+      "loss": 0.4417,
+      "step": 80
+    },
+    {
+      "epoch": 0.8294930875576036,
+      "grad_norm": 1.393729749690361,
+      "learning_rate": 9.131193871579975e-06,
+      "loss": 0.4463,
+      "step": 90
+    },
+    {
+      "epoch": 0.9216589861751152,
+      "grad_norm": 1.4880361350108735,
+      "learning_rate": 8.807229791845673e-06,
+      "loss": 0.4508,
+      "step": 100
+    },
+    {
+      "epoch": 1.0092165898617511,
+      "grad_norm": 1.299774055064554,
+      "learning_rate": 8.439834606028594e-06,
+      "loss": 0.4024,
+      "step": 110
+    },
+    {
+      "epoch": 1.1013824884792627,
+      "grad_norm": 1.298198957499482,
+      "learning_rate": 8.033199387471278e-06,
+      "loss": 0.3197,
+      "step": 120
+    },
+    {
+      "epoch": 1.1935483870967742,
+      "grad_norm": 1.3650000791809225,
+      "learning_rate": 7.591962841552627e-06,
+      "loss": 0.3219,
+      "step": 130
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 1.434265135129886,
+      "learning_rate": 7.121158389495187e-06,
+      "loss": 0.3195,
+      "step": 140
+    },
+    {
+      "epoch": 1.3778801843317972,
+      "grad_norm": 1.495992136082361,
+      "learning_rate": 6.626156749437736e-06,
+      "loss": 0.3175,
+      "step": 150
+    },
+    {
+      "epoch": 1.4700460829493087,
+      "grad_norm": 1.3523477092551237,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.3065,
+      "step": 160
+    },
+    {
+      "epoch": 1.5622119815668203,
+      "grad_norm": 1.2695226148335443,
+      "learning_rate": 5.586360513712011e-06,
+      "loss": 0.3157,
+      "step": 170
+    },
+    {
+      "epoch": 1.6543778801843319,
+      "grad_norm": 1.2984094624484053,
+      "learning_rate": 5.053427429716867e-06,
+      "loss": 0.311,
+      "step": 180
+    },
+    {
+      "epoch": 1.7465437788018434,
+      "grad_norm": 1.465758872280537,
+      "learning_rate": 4.5198848704615915e-06,
+      "loss": 0.3131,
+      "step": 190
+    },
+    {
+      "epoch": 1.838709677419355,
+      "grad_norm": 1.3727910421793548,
+      "learning_rate": 3.991819241221836e-06,
+      "loss": 0.2933,
+      "step": 200
+    },
+    {
+      "epoch": 1.9308755760368663,
+      "grad_norm": 1.2600662931978257,
+      "learning_rate": 3.475254469003865e-06,
+      "loss": 0.2828,
+      "step": 210
+    },
+    {
+      "epoch": 2.0184331797235022,
+      "grad_norm": 1.2847409994029446,
+      "learning_rate": 2.976083284388031e-06,
+      "loss": 0.2656,
+      "step": 220
+    },
+    {
+      "epoch": 2.110599078341014,
+      "grad_norm": 1.4825208018701794,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1944,
+      "step": 230
+    },
+    {
+      "epoch": 2.2027649769585254,
+      "grad_norm": 1.4346771852112512,
+      "learning_rate": 2.0524355524417017e-06,
+      "loss": 0.1971,
+      "step": 240
+    },
+    {
+      "epoch": 2.294930875576037,
+      "grad_norm": 1.2773781048743025,
+      "learning_rate": 1.6384955486934157e-06,
+      "loss": 0.1971,
+      "step": 250
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 1.3513953567558703,
+      "learning_rate": 1.2629020237248241e-06,
+      "loss": 0.1934,
+      "step": 260
+    },
+    {
+      "epoch": 2.47926267281106,
+      "grad_norm": 1.1153786023075227,
+      "learning_rate": 9.299395737170758e-07,
+      "loss": 0.1975,
+      "step": 270
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.255516210757092,
+      "learning_rate": 6.43406479383053e-07,
+      "loss": 0.2041,
+      "step": 280
+    },
+    {
+      "epoch": 2.6635944700460827,
+      "grad_norm": 1.2757448362037527,
+      "learning_rate": 4.0657137694820826e-07,
+      "loss": 0.1979,
+      "step": 290
+    },
+    {
+      "epoch": 2.7557603686635943,
+      "grad_norm": 1.218519400711122,
+      "learning_rate": 2.2213597106929608e-07,
+      "loss": 0.1919,
+      "step": 300
+    },
+    {
+      "epoch": 2.847926267281106,
+      "grad_norm": 1.2928947540930629,
+      "learning_rate": 9.22042150446728e-08,
+      "loss": 0.1897,
+      "step": 310
+    },
+    {
+      "epoch": 2.9400921658986174,
+      "grad_norm": 1.2273178341773785,
+      "learning_rate": 1.8258309893965375e-08,
+      "loss": 0.1877,
+      "step": 320
+    },
+    {
+      "epoch": 3.0,
+      "step": 327,
+      "total_flos": 56487017447424.0,
+      "train_loss": 0.33897173769248007,
+      "train_runtime": 796.6909,
+      "train_samples_per_second": 26.058,
+      "train_steps_per_second": 0.41
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 327,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 56487017447424.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

EXP_1.2_3b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71a34ce7185ab0118e74c9a95e848341684e12450857a06282b8ccf3a277b4d
+size 7953

EXP_1.2_3b/video_preprocessor_config.json

@@ -0,0 +1,86 @@
+{
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

EXP_2.1_3b/README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: other
+base_model: /mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: EXP_2.1_3b
+  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. -->
+
+# EXP_2.1_3b
+
+This model is a fine-tuned version of [/mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct](https://huggingface.co//mnt/nvme/hyz/hf/models/Qwen2.5-VL-3B-Instruct) on the txt_img dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5101
+
+## 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: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- 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: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5338        | 0.7107 | 500  | 0.5341          |
+| 0.4883        | 1.4208 | 1000 | 0.5142          |
+| 0.4397        | 2.1322 | 1500 | 0.5145          |
+| 0.436         | 2.8429 | 2000 | 0.5102          |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

EXP_2.1_3b/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
+}