Upload 21 files

.gitattributes

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

README.md

@@ -1,3 +1,25 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
+---
+
+# Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
+
+This is the official model released for the paper **[Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning](https://openreview.net/pdf?id=kyzHM557gE)**.
+
+## Abstract
+
+Any entity in the visual world can be hierarchically grouped based on shared characteristics and mapped to fine-grained sub-categories. While Multi-modal Large Language Models (MLLMs) achieve strong performance on coarse-grained visual tasks, they often struggle with Fine-Grained Visual Recognition (FGVR). Adapting general-purpose MLLMs to FGVR typically requires large amounts of annotated data, which is costly to obtain, leaving a substantial performance gap compared to contrastive CLIP models dedicated for discriminative tasks. Moreover, MLLMs tend to overfit to seen sub-categories and generalize poorly to unseen ones. To address these challenges, we propose Fine-R1, an MLLM tailored for FGVR through an R1-style training framework: (1) Chain-of-Thought Supervised Fine-tuning, where we construct a high-quality FGVR CoT dataset with rationales of "visual analysis, candidate sub-categories, comparison, and prediction", transition the model into a strong open-world classifier; and (2) Triplet Augmented Policy Optimization, where Intra-class Augmentation mixes trajectories from anchor and positive images within the same category to improve robustness to intra-class variance, while Inter-class Augmentation maximizes the response distinction conditioned on images across sub-categories to enhance discriminative ability. With only 4-shot training, Fine-R1 outperforms existing general MLLMs, reasoning MLLMs, and even contrastive CLIP models in identifying both seen and unseen sub-categories, showing promise in working in knowledge-intensive domains where gathering expert annotations for all sub-categories is arduous.
+
+
+## GitHub Repository
+
+[https://github.com/PKU-ICST-MIPL/FineR1_ICLR2026](https://github.com/PKU-ICST-MIPL/FineR1_ICLR2026)
+
+## Model Version
+Fine-R1-7B-Stage1 (Checkpoints after CoT SFT)
+
+## Usage
+
+This model can be used with the Hugging Face `transformers` library. For detailed usage examples and how to integrate it into your projects, please refer to the official [GitHub Repository](https://github.com/PKU-ICST-MIPL/FineR1_ICLR2026).

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.235294117647058,
+    "total_flos": 27074593947648.0,
+    "train_loss": 0.388430199213326,
+    "train_runtime": 2487.6221,
+    "train_samples_per_second": 1.624,
+    "train_steps_per_second": 0.048
+}

chat_template.json

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

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "/data/hehulingxiao/code/ICCV/models/Qwen2.5-VL-7B-Instruct",
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "model_type": "qwen2_5_vl",
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2,
+    "torch_dtype": "float32"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad5d56128a8d6adc4267d9c94d06d612e1b51c8b597fc8b99be58dab4d2b115
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0610f31402629f30566642a93e8abad62626d701dac7851c59a3af127fd9fa
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a209e439c9b0d684ff0475788d4a07ea818779e0a73641e70010e166e52d4eb
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:facbaa9e4a6a8d8079e1c1cae6f518b7d84f2541e3df95c79cf9046f8817c386
+size 1691924384

model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.235294117647058,
+    "total_flos": 27074593947648.0,
+    "train_loss": 0.388430199213326,
+    "train_runtime": 2487.6221,
+    "train_samples_per_second": 1.624,
+    "train_steps_per_second": 0.048
+}

trainer_log.jsonl

@@ -0,0 +1,121 @@
+{"current_steps": 1, "total_steps": 120, "loss": 1.1559, "lr": 4.1666666666666667e-07, "epoch": 0.0784313725490196, "percentage": 0.83, "elapsed_time": "0:00:24", "remaining_time": "0:48:15"}
+{"current_steps": 2, "total_steps": 120, "loss": 1.1107, "lr": 8.333333333333333e-07, "epoch": 0.1568627450980392, "percentage": 1.67, "elapsed_time": "0:00:46", "remaining_time": "0:45:57"}
+{"current_steps": 3, "total_steps": 120, "loss": 1.1384, "lr": 1.25e-06, "epoch": 0.23529411764705882, "percentage": 2.5, "elapsed_time": "0:01:05", "remaining_time": "0:42:51"}
+{"current_steps": 4, "total_steps": 120, "loss": 1.1421, "lr": 1.6666666666666667e-06, "epoch": 0.3137254901960784, "percentage": 3.33, "elapsed_time": "0:01:24", "remaining_time": "0:40:58"}
+{"current_steps": 5, "total_steps": 120, "loss": 1.1439, "lr": 2.0833333333333334e-06, "epoch": 0.39215686274509803, "percentage": 4.17, "elapsed_time": "0:01:43", "remaining_time": "0:39:34"}
+{"current_steps": 6, "total_steps": 120, "loss": 1.0618, "lr": 2.5e-06, "epoch": 0.47058823529411764, "percentage": 5.0, "elapsed_time": "0:02:02", "remaining_time": "0:38:40"}
+{"current_steps": 7, "total_steps": 120, "loss": 1.0401, "lr": 2.916666666666667e-06, "epoch": 0.5490196078431373, "percentage": 5.83, "elapsed_time": "0:02:20", "remaining_time": "0:37:50"}
+{"current_steps": 8, "total_steps": 120, "loss": 0.9898, "lr": 3.3333333333333333e-06, "epoch": 0.6274509803921569, "percentage": 6.67, "elapsed_time": "0:02:41", "remaining_time": "0:37:40"}
+{"current_steps": 9, "total_steps": 120, "loss": 1.011, "lr": 3.7500000000000005e-06, "epoch": 0.7058823529411765, "percentage": 7.5, "elapsed_time": "0:03:00", "remaining_time": "0:37:06"}
+{"current_steps": 10, "total_steps": 120, "loss": 0.9935, "lr": 4.166666666666667e-06, "epoch": 0.7843137254901961, "percentage": 8.33, "elapsed_time": "0:03:20", "remaining_time": "0:36:49"}
+{"current_steps": 11, "total_steps": 120, "loss": 0.9037, "lr": 4.583333333333333e-06, "epoch": 0.8627450980392157, "percentage": 9.17, "elapsed_time": "0:03:39", "remaining_time": "0:36:12"}
+{"current_steps": 12, "total_steps": 120, "loss": 0.9095, "lr": 5e-06, "epoch": 0.9411764705882353, "percentage": 10.0, "elapsed_time": "0:03:58", "remaining_time": "0:35:45"}
+{"current_steps": 13, "total_steps": 120, "loss": 0.6715, "lr": 4.998942375205502e-06, "epoch": 1.0, "percentage": 10.83, "elapsed_time": "0:04:14", "remaining_time": "0:34:58"}
+{"current_steps": 14, "total_steps": 120, "loss": 0.8186, "lr": 4.995770395678171e-06, "epoch": 1.0784313725490196, "percentage": 11.67, "elapsed_time": "0:04:33", "remaining_time": "0:34:34"}
+{"current_steps": 15, "total_steps": 120, "loss": 0.7876, "lr": 4.990486745229364e-06, "epoch": 1.156862745098039, "percentage": 12.5, "elapsed_time": "0:04:53", "remaining_time": "0:34:13"}
+{"current_steps": 16, "total_steps": 120, "loss": 0.7498, "lr": 4.983095894354858e-06, "epoch": 1.2352941176470589, "percentage": 13.33, "elapsed_time": "0:05:12", "remaining_time": "0:33:48"}
+{"current_steps": 17, "total_steps": 120, "loss": 0.7377, "lr": 4.973604096452361e-06, "epoch": 1.3137254901960784, "percentage": 14.17, "elapsed_time": "0:05:32", "remaining_time": "0:33:36"}
+{"current_steps": 18, "total_steps": 120, "loss": 0.6722, "lr": 4.962019382530521e-06, "epoch": 1.392156862745098, "percentage": 15.0, "elapsed_time": "0:05:54", "remaining_time": "0:33:30"}
+{"current_steps": 19, "total_steps": 120, "loss": 0.6785, "lr": 4.948351554413879e-06, "epoch": 1.4705882352941178, "percentage": 15.83, "elapsed_time": "0:06:16", "remaining_time": "0:33:20"}
+{"current_steps": 20, "total_steps": 120, "loss": 0.6873, "lr": 4.93261217644956e-06, "epoch": 1.5490196078431373, "percentage": 16.67, "elapsed_time": "0:06:36", "remaining_time": "0:33:00"}
+{"current_steps": 21, "total_steps": 120, "loss": 0.659, "lr": 4.914814565722671e-06, "epoch": 1.6274509803921569, "percentage": 17.5, "elapsed_time": "0:06:53", "remaining_time": "0:32:31"}
+{"current_steps": 22, "total_steps": 120, "loss": 0.6438, "lr": 4.894973780788722e-06, "epoch": 1.7058823529411766, "percentage": 18.33, "elapsed_time": "0:07:13", "remaining_time": "0:32:10"}
+{"current_steps": 23, "total_steps": 120, "loss": 0.6467, "lr": 4.873106608932585e-06, "epoch": 1.784313725490196, "percentage": 19.17, "elapsed_time": "0:07:33", "remaining_time": "0:31:52"}
+{"current_steps": 24, "total_steps": 120, "loss": 0.6004, "lr": 4.849231551964771e-06, "epoch": 1.8627450980392157, "percentage": 20.0, "elapsed_time": "0:07:54", "remaining_time": "0:31:36"}
+{"current_steps": 25, "total_steps": 120, "loss": 0.6608, "lr": 4.823368810567056e-06, "epoch": 1.9411764705882353, "percentage": 20.83, "elapsed_time": "0:08:13", "remaining_time": "0:31:14"}
+{"current_steps": 26, "total_steps": 120, "loss": 0.4767, "lr": 4.7955402672006855e-06, "epoch": 2.0, "percentage": 21.67, "elapsed_time": "0:08:30", "remaining_time": "0:30:45"}
+{"current_steps": 27, "total_steps": 120, "loss": 0.5677, "lr": 4.765769467591626e-06, "epoch": 2.0784313725490198, "percentage": 22.5, "elapsed_time": "0:08:52", "remaining_time": "0:30:34"}
+{"current_steps": 28, "total_steps": 120, "loss": 0.5875, "lr": 4.734081600808531e-06, "epoch": 2.156862745098039, "percentage": 23.33, "elapsed_time": "0:09:12", "remaining_time": "0:30:14"}
+{"current_steps": 29, "total_steps": 120, "loss": 0.5528, "lr": 4.700503477950278e-06, "epoch": 2.235294117647059, "percentage": 24.17, "elapsed_time": "0:09:30", "remaining_time": "0:29:49"}
+{"current_steps": 30, "total_steps": 120, "loss": 0.5471, "lr": 4.665063509461098e-06, "epoch": 2.313725490196078, "percentage": 25.0, "elapsed_time": "0:09:49", "remaining_time": "0:29:28"}
+{"current_steps": 31, "total_steps": 120, "loss": 0.5058, "lr": 4.627791681092499e-06, "epoch": 2.392156862745098, "percentage": 25.83, "elapsed_time": "0:10:10", "remaining_time": "0:29:13"}
+{"current_steps": 32, "total_steps": 120, "loss": 0.5226, "lr": 4.588719528532342e-06, "epoch": 2.4705882352941178, "percentage": 26.67, "elapsed_time": "0:10:29", "remaining_time": "0:28:49"}
+{"current_steps": 33, "total_steps": 120, "loss": 0.5071, "lr": 4.54788011072248e-06, "epoch": 2.549019607843137, "percentage": 27.5, "elapsed_time": "0:10:49", "remaining_time": "0:28:31"}
+{"current_steps": 34, "total_steps": 120, "loss": 0.4998, "lr": 4.50530798188761e-06, "epoch": 2.627450980392157, "percentage": 28.33, "elapsed_time": "0:11:10", "remaining_time": "0:28:16"}
+{"current_steps": 35, "total_steps": 120, "loss": 0.5009, "lr": 4.46103916229894e-06, "epoch": 2.7058823529411766, "percentage": 29.17, "elapsed_time": "0:11:31", "remaining_time": "0:27:58"}
+{"current_steps": 36, "total_steps": 120, "loss": 0.479, "lr": 4.415111107797445e-06, "epoch": 2.784313725490196, "percentage": 30.0, "elapsed_time": "0:11:49", "remaining_time": "0:27:34"}
+{"current_steps": 37, "total_steps": 120, "loss": 0.5122, "lr": 4.367562678102491e-06, "epoch": 2.8627450980392157, "percentage": 30.83, "elapsed_time": "0:12:06", "remaining_time": "0:27:10"}
+{"current_steps": 38, "total_steps": 120, "loss": 0.4938, "lr": 4.318434103932622e-06, "epoch": 2.9411764705882355, "percentage": 31.67, "elapsed_time": "0:12:27", "remaining_time": "0:26:53"}
+{"current_steps": 39, "total_steps": 120, "loss": 0.3629, "lr": 4.267766952966369e-06, "epoch": 3.0, "percentage": 32.5, "elapsed_time": "0:12:43", "remaining_time": "0:26:26"}
+{"current_steps": 40, "total_steps": 120, "loss": 0.4262, "lr": 4.215604094671835e-06, "epoch": 3.0784313725490198, "percentage": 33.33, "elapsed_time": "0:13:05", "remaining_time": "0:26:11"}
+{"current_steps": 41, "total_steps": 120, "loss": 0.4259, "lr": 4.161989664034844e-06, "epoch": 3.156862745098039, "percentage": 34.17, "elapsed_time": "0:13:23", "remaining_time": "0:25:47"}
+{"current_steps": 42, "total_steps": 120, "loss": 0.4009, "lr": 4.106969024216348e-06, "epoch": 3.235294117647059, "percentage": 35.0, "elapsed_time": "0:13:43", "remaining_time": "0:25:29"}
+{"current_steps": 43, "total_steps": 120, "loss": 0.4082, "lr": 4.0505887281706505e-06, "epoch": 3.313725490196078, "percentage": 35.83, "elapsed_time": "0:14:02", "remaining_time": "0:25:08"}
+{"current_steps": 44, "total_steps": 120, "loss": 0.4012, "lr": 3.992896479256966e-06, "epoch": 3.392156862745098, "percentage": 36.67, "elapsed_time": "0:14:23", "remaining_time": "0:24:51"}
+{"current_steps": 45, "total_steps": 120, "loss": 0.4003, "lr": 3.933941090877615e-06, "epoch": 3.4705882352941178, "percentage": 37.5, "elapsed_time": "0:14:43", "remaining_time": "0:24:33"}
+{"current_steps": 46, "total_steps": 120, "loss": 0.3906, "lr": 3.8737724451770155e-06, "epoch": 3.549019607843137, "percentage": 38.33, "elapsed_time": "0:15:04", "remaining_time": "0:24:14"}
+{"current_steps": 47, "total_steps": 120, "loss": 0.3956, "lr": 3.8124414508364005e-06, "epoch": 3.627450980392157, "percentage": 39.17, "elapsed_time": "0:15:23", "remaining_time": "0:23:54"}
+{"current_steps": 48, "total_steps": 120, "loss": 0.3841, "lr": 3.7500000000000005e-06, "epoch": 3.7058823529411766, "percentage": 40.0, "elapsed_time": "0:15:43", "remaining_time": "0:23:34"}
+{"current_steps": 49, "total_steps": 120, "loss": 0.3998, "lr": 3.6865009243691015e-06, "epoch": 3.784313725490196, "percentage": 40.83, "elapsed_time": "0:16:01", "remaining_time": "0:23:13"}
+{"current_steps": 50, "total_steps": 120, "loss": 0.3947, "lr": 3.621997950501156e-06, "epoch": 3.8627450980392157, "percentage": 41.67, "elapsed_time": "0:16:20", "remaining_time": "0:22:53"}
+{"current_steps": 51, "total_steps": 120, "loss": 0.3898, "lr": 3.556545654351749e-06, "epoch": 3.9411764705882355, "percentage": 42.5, "elapsed_time": "0:16:40", "remaining_time": "0:22:33"}
+{"current_steps": 52, "total_steps": 120, "loss": 0.2635, "lr": 3.4901994150978926e-06, "epoch": 4.0, "percentage": 43.33, "elapsed_time": "0:16:57", "remaining_time": "0:22:09"}
+{"current_steps": 53, "total_steps": 120, "loss": 0.3232, "lr": 3.4230153682817112e-06, "epoch": 4.078431372549019, "percentage": 44.17, "elapsed_time": "0:17:15", "remaining_time": "0:21:48"}
+{"current_steps": 54, "total_steps": 120, "loss": 0.2997, "lr": 3.3550503583141726e-06, "epoch": 4.1568627450980395, "percentage": 45.0, "elapsed_time": "0:17:35", "remaining_time": "0:21:30"}
+{"current_steps": 55, "total_steps": 120, "loss": 0.3061, "lr": 3.2863618903790346e-06, "epoch": 4.235294117647059, "percentage": 45.83, "elapsed_time": "0:17:56", "remaining_time": "0:21:11"}
+{"current_steps": 56, "total_steps": 120, "loss": 0.2995, "lr": 3.217008081777726e-06, "epoch": 4.313725490196078, "percentage": 46.67, "elapsed_time": "0:18:15", "remaining_time": "0:20:51"}
+{"current_steps": 57, "total_steps": 120, "loss": 0.2973, "lr": 3.147047612756302e-06, "epoch": 4.392156862745098, "percentage": 47.5, "elapsed_time": "0:18:35", "remaining_time": "0:20:32"}
+{"current_steps": 58, "total_steps": 120, "loss": 0.2987, "lr": 3.0765396768561005e-06, "epoch": 4.470588235294118, "percentage": 48.33, "elapsed_time": "0:18:55", "remaining_time": "0:20:13"}
+{"current_steps": 59, "total_steps": 120, "loss": 0.3132, "lr": 3.0055439308300954e-06, "epoch": 4.549019607843137, "percentage": 49.17, "elapsed_time": "0:19:16", "remaining_time": "0:19:55"}
+{"current_steps": 60, "total_steps": 120, "loss": 0.2929, "lr": 2.9341204441673267e-06, "epoch": 4.627450980392156, "percentage": 50.0, "elapsed_time": "0:19:36", "remaining_time": "0:19:36"}
+{"current_steps": 61, "total_steps": 120, "loss": 0.2794, "lr": 2.862329648268117e-06, "epoch": 4.705882352941177, "percentage": 50.83, "elapsed_time": "0:19:57", "remaining_time": "0:19:18"}
+{"current_steps": 62, "total_steps": 120, "loss": 0.2911, "lr": 2.7902322853130758e-06, "epoch": 4.784313725490196, "percentage": 51.67, "elapsed_time": "0:20:18", "remaining_time": "0:18:59"}
+{"current_steps": 63, "total_steps": 120, "loss": 0.2945, "lr": 2.717889356869146e-06, "epoch": 4.862745098039216, "percentage": 52.5, "elapsed_time": "0:20:37", "remaining_time": "0:18:39"}
+{"current_steps": 64, "total_steps": 120, "loss": 0.3093, "lr": 2.6453620722761897e-06, "epoch": 4.9411764705882355, "percentage": 53.33, "elapsed_time": "0:20:57", "remaining_time": "0:18:20"}
+{"current_steps": 65, "total_steps": 120, "loss": 0.2038, "lr": 2.572711796857779e-06, "epoch": 5.0, "percentage": 54.17, "elapsed_time": "0:21:11", "remaining_time": "0:17:56"}
+{"current_steps": 66, "total_steps": 120, "loss": 0.2457, "lr": 2.5e-06, "epoch": 5.078431372549019, "percentage": 55.0, "elapsed_time": "0:21:32", "remaining_time": "0:17:37"}
+{"current_steps": 67, "total_steps": 120, "loss": 0.2378, "lr": 2.4272882031422216e-06, "epoch": 5.1568627450980395, "percentage": 55.83, "elapsed_time": "0:21:53", "remaining_time": "0:17:19"}
+{"current_steps": 68, "total_steps": 120, "loss": 0.2365, "lr": 2.3546379277238107e-06, "epoch": 5.235294117647059, "percentage": 56.67, "elapsed_time": "0:22:12", "remaining_time": "0:16:58"}
+{"current_steps": 69, "total_steps": 120, "loss": 0.2273, "lr": 2.2821106431308546e-06, "epoch": 5.313725490196078, "percentage": 57.5, "elapsed_time": "0:22:32", "remaining_time": "0:16:39"}
+{"current_steps": 70, "total_steps": 120, "loss": 0.2251, "lr": 2.2097677146869242e-06, "epoch": 5.392156862745098, "percentage": 58.33, "elapsed_time": "0:22:53", "remaining_time": "0:16:21"}
+{"current_steps": 71, "total_steps": 120, "loss": 0.2199, "lr": 2.1376703517318835e-06, "epoch": 5.470588235294118, "percentage": 59.17, "elapsed_time": "0:23:13", "remaining_time": "0:16:01"}
+{"current_steps": 72, "total_steps": 120, "loss": 0.2275, "lr": 2.0658795558326745e-06, "epoch": 5.549019607843137, "percentage": 60.0, "elapsed_time": "0:23:30", "remaining_time": "0:15:40"}
+{"current_steps": 73, "total_steps": 120, "loss": 0.2219, "lr": 1.994456069169906e-06, "epoch": 5.627450980392156, "percentage": 60.83, "elapsed_time": "0:23:49", "remaining_time": "0:15:20"}
+{"current_steps": 74, "total_steps": 120, "loss": 0.2204, "lr": 1.9234603231439e-06, "epoch": 5.705882352941177, "percentage": 61.67, "elapsed_time": "0:24:09", "remaining_time": "0:15:00"}
+{"current_steps": 75, "total_steps": 120, "loss": 0.22, "lr": 1.852952387243698e-06, "epoch": 5.784313725490196, "percentage": 62.5, "elapsed_time": "0:24:30", "remaining_time": "0:14:42"}
+{"current_steps": 76, "total_steps": 120, "loss": 0.2199, "lr": 1.7829919182222752e-06, "epoch": 5.862745098039216, "percentage": 63.33, "elapsed_time": "0:24:51", "remaining_time": "0:14:23"}
+{"current_steps": 77, "total_steps": 120, "loss": 0.2037, "lr": 1.7136381096209665e-06, "epoch": 5.9411764705882355, "percentage": 64.17, "elapsed_time": "0:25:12", "remaining_time": "0:14:04"}
+{"current_steps": 78, "total_steps": 120, "loss": 0.1583, "lr": 1.6449496416858285e-06, "epoch": 6.0, "percentage": 65.0, "elapsed_time": "0:25:26", "remaining_time": "0:13:41"}
+{"current_steps": 79, "total_steps": 120, "loss": 0.1934, "lr": 1.5769846317182894e-06, "epoch": 6.078431372549019, "percentage": 65.83, "elapsed_time": "0:25:47", "remaining_time": "0:13:23"}
+{"current_steps": 80, "total_steps": 120, "loss": 0.1705, "lr": 1.509800584902108e-06, "epoch": 6.1568627450980395, "percentage": 66.67, "elapsed_time": "0:26:05", "remaining_time": "0:13:02"}
+{"current_steps": 81, "total_steps": 120, "loss": 0.1723, "lr": 1.443454345648252e-06, "epoch": 6.235294117647059, "percentage": 67.5, "elapsed_time": "0:26:27", "remaining_time": "0:12:44"}
+{"current_steps": 82, "total_steps": 120, "loss": 0.1792, "lr": 1.3780020494988447e-06, "epoch": 6.313725490196078, "percentage": 68.33, "elapsed_time": "0:26:47", "remaining_time": "0:12:24"}
+{"current_steps": 83, "total_steps": 120, "loss": 0.1679, "lr": 1.313499075630899e-06, "epoch": 6.392156862745098, "percentage": 69.17, "elapsed_time": "0:27:06", "remaining_time": "0:12:04"}
+{"current_steps": 84, "total_steps": 120, "loss": 0.169, "lr": 1.2500000000000007e-06, "epoch": 6.470588235294118, "percentage": 70.0, "elapsed_time": "0:27:25", "remaining_time": "0:11:45"}
+{"current_steps": 85, "total_steps": 120, "loss": 0.1807, "lr": 1.1875585491636e-06, "epoch": 6.549019607843137, "percentage": 70.83, "elapsed_time": "0:27:45", "remaining_time": "0:11:25"}
+{"current_steps": 86, "total_steps": 120, "loss": 0.1735, "lr": 1.1262275548229852e-06, "epoch": 6.627450980392156, "percentage": 71.67, "elapsed_time": "0:28:03", "remaining_time": "0:11:05"}
+{"current_steps": 87, "total_steps": 120, "loss": 0.1728, "lr": 1.0660589091223854e-06, "epoch": 6.705882352941177, "percentage": 72.5, "elapsed_time": "0:28:22", "remaining_time": "0:10:45"}
+{"current_steps": 88, "total_steps": 120, "loss": 0.171, "lr": 1.0071035207430352e-06, "epoch": 6.784313725490196, "percentage": 73.33, "elapsed_time": "0:28:39", "remaining_time": "0:10:25"}
+{"current_steps": 89, "total_steps": 120, "loss": 0.1761, "lr": 9.494112718293503e-07, "epoch": 6.862745098039216, "percentage": 74.17, "elapsed_time": "0:29:00", "remaining_time": "0:10:06"}
+{"current_steps": 90, "total_steps": 120, "loss": 0.1689, "lr": 8.930309757836517e-07, "epoch": 6.9411764705882355, "percentage": 75.0, "elapsed_time": "0:29:22", "remaining_time": "0:09:47"}
+{"current_steps": 91, "total_steps": 120, "loss": 0.1193, "lr": 8.380103359651554e-07, "epoch": 7.0, "percentage": 75.83, "elapsed_time": "0:29:37", "remaining_time": "0:09:26"}
+{"current_steps": 92, "total_steps": 120, "loss": 0.1531, "lr": 7.843959053281663e-07, "epoch": 7.078431372549019, "percentage": 76.67, "elapsed_time": "0:29:56", "remaining_time": "0:09:06"}
+{"current_steps": 93, "total_steps": 120, "loss": 0.1449, "lr": 7.322330470336314e-07, "epoch": 7.1568627450980395, "percentage": 77.5, "elapsed_time": "0:30:16", "remaining_time": "0:08:47"}
+{"current_steps": 94, "total_steps": 120, "loss": 0.1398, "lr": 6.815658960673782e-07, "epoch": 7.235294117647059, "percentage": 78.33, "elapsed_time": "0:30:36", "remaining_time": "0:08:27"}
+{"current_steps": 95, "total_steps": 120, "loss": 0.1487, "lr": 6.324373218975105e-07, "epoch": 7.313725490196078, "percentage": 79.17, "elapsed_time": "0:30:53", "remaining_time": "0:08:07"}
+{"current_steps": 96, "total_steps": 120, "loss": 0.1403, "lr": 5.848888922025553e-07, "epoch": 7.392156862745098, "percentage": 80.0, "elapsed_time": "0:31:12", "remaining_time": "0:07:48"}
+{"current_steps": 97, "total_steps": 120, "loss": 0.1449, "lr": 5.389608377010608e-07, "epoch": 7.470588235294118, "percentage": 80.83, "elapsed_time": "0:31:32", "remaining_time": "0:07:28"}
+{"current_steps": 98, "total_steps": 120, "loss": 0.1451, "lr": 4.946920181123904e-07, "epoch": 7.549019607843137, "percentage": 81.67, "elapsed_time": "0:31:52", "remaining_time": "0:07:09"}
+{"current_steps": 99, "total_steps": 120, "loss": 0.134, "lr": 4.5211988927752026e-07, "epoch": 7.627450980392156, "percentage": 82.5, "elapsed_time": "0:32:14", "remaining_time": "0:06:50"}
+{"current_steps": 100, "total_steps": 120, "loss": 0.1497, "lr": 4.1128047146765936e-07, "epoch": 7.705882352941177, "percentage": 83.33, "elapsed_time": "0:32:34", "remaining_time": "0:06:30"}
+{"current_steps": 101, "total_steps": 120, "loss": 0.1523, "lr": 3.722083189075007e-07, "epoch": 7.784313725490196, "percentage": 84.17, "elapsed_time": "0:32:56", "remaining_time": "0:06:11"}
+{"current_steps": 102, "total_steps": 120, "loss": 0.1406, "lr": 3.3493649053890325e-07, "epoch": 7.862745098039216, "percentage": 85.0, "elapsed_time": "0:33:15", "remaining_time": "0:05:52"}
+{"current_steps": 103, "total_steps": 120, "loss": 0.1414, "lr": 2.9949652204972257e-07, "epoch": 7.9411764705882355, "percentage": 85.83, "elapsed_time": "0:33:35", "remaining_time": "0:05:32"}
+{"current_steps": 104, "total_steps": 120, "loss": 0.0988, "lr": 2.6591839919146963e-07, "epoch": 8.0, "percentage": 86.67, "elapsed_time": "0:33:52", "remaining_time": "0:05:12"}
+{"current_steps": 105, "total_steps": 120, "loss": 0.1326, "lr": 2.3423053240837518e-07, "epoch": 8.07843137254902, "percentage": 87.5, "elapsed_time": "0:34:12", "remaining_time": "0:04:53"}
+{"current_steps": 106, "total_steps": 120, "loss": 0.1382, "lr": 2.044597327993153e-07, "epoch": 8.156862745098039, "percentage": 88.33, "elapsed_time": "0:34:30", "remaining_time": "0:04:33"}
+{"current_steps": 107, "total_steps": 120, "loss": 0.1394, "lr": 1.7663118943294367e-07, "epoch": 8.235294117647058, "percentage": 89.17, "elapsed_time": "0:34:48", "remaining_time": "0:04:13"}
+{"current_steps": 108, "total_steps": 120, "loss": 0.1278, "lr": 1.507684480352292e-07, "epoch": 8.313725490196079, "percentage": 90.0, "elapsed_time": "0:35:06", "remaining_time": "0:03:54"}
+{"current_steps": 109, "total_steps": 120, "loss": 0.1391, "lr": 1.2689339106741529e-07, "epoch": 8.392156862745098, "percentage": 90.83, "elapsed_time": "0:35:28", "remaining_time": "0:03:34"}
+{"current_steps": 110, "total_steps": 120, "loss": 0.1311, "lr": 1.0502621921127776e-07, "epoch": 8.470588235294118, "percentage": 91.67, "elapsed_time": "0:35:48", "remaining_time": "0:03:15"}
+{"current_steps": 111, "total_steps": 120, "loss": 0.1296, "lr": 8.518543427732951e-08, "epoch": 8.549019607843137, "percentage": 92.5, "elapsed_time": "0:36:09", "remaining_time": "0:02:55"}
+{"current_steps": 112, "total_steps": 120, "loss": 0.1263, "lr": 6.738782355044048e-08, "epoch": 8.627450980392156, "percentage": 93.33, "elapsed_time": "0:36:28", "remaining_time": "0:02:36"}
+{"current_steps": 113, "total_steps": 120, "loss": 0.1381, "lr": 5.164844558612131e-08, "epoch": 8.705882352941176, "percentage": 94.17, "elapsed_time": "0:36:48", "remaining_time": "0:02:16"}
+{"current_steps": 114, "total_steps": 120, "loss": 0.1282, "lr": 3.798061746947995e-08, "epoch": 8.784313725490197, "percentage": 95.0, "elapsed_time": "0:37:06", "remaining_time": "0:01:57"}
+{"current_steps": 115, "total_steps": 120, "loss": 0.1331, "lr": 2.6395903547638825e-08, "epoch": 8.862745098039216, "percentage": 95.83, "elapsed_time": "0:37:23", "remaining_time": "0:01:37"}
+{"current_steps": 116, "total_steps": 120, "loss": 0.1264, "lr": 1.6904105645142443e-08, "epoch": 8.941176470588236, "percentage": 96.67, "elapsed_time": "0:37:44", "remaining_time": "0:01:18"}
+{"current_steps": 117, "total_steps": 120, "loss": 0.0991, "lr": 9.513254770636138e-09, "epoch": 9.0, "percentage": 97.5, "elapsed_time": "0:38:01", "remaining_time": "0:00:58"}
+{"current_steps": 118, "total_steps": 120, "loss": 0.1293, "lr": 4.229604321829561e-09, "epoch": 9.07843137254902, "percentage": 98.33, "elapsed_time": "0:38:22", "remaining_time": "0:00:39"}
+{"current_steps": 119, "total_steps": 120, "loss": 0.1269, "lr": 1.0576247944985018e-09, "epoch": 9.156862745098039, "percentage": 99.17, "elapsed_time": "0:38:41", "remaining_time": "0:00:19"}
+{"current_steps": 120, "total_steps": 120, "loss": 0.1341, "lr": 0.0, "epoch": 9.235294117647058, "percentage": 100.0, "elapsed_time": "0:39:00", "remaining_time": "0:00:00"}
+{"current_steps": 120, "total_steps": 120, "epoch": 9.235294117647058, "percentage": 100.0, "elapsed_time": "0:41:27", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,882 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.235294117647058,
+  "eval_steps": 500,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 5.935066953271119,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 1.1559,
+      "step": 1
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 5.931820940431562,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.1107,
+      "step": 2
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 6.143905320771078,
+      "learning_rate": 1.25e-06,
+      "loss": 1.1384,
+      "step": 3
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 6.065274861977263,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.1421,
+      "step": 4
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 5.8625107951536535,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 1.1439,
+      "step": 5
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 5.067374092992189,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0618,
+      "step": 6
+    },
+    {
+      "epoch": 0.5490196078431373,
+      "grad_norm": 4.755801552471063,
+      "learning_rate": 2.916666666666667e-06,
+      "loss": 1.0401,
+      "step": 7
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 3.3129565953149323,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9898,
+      "step": 8
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 3.3912326629630547,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.011,
+      "step": 9
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 3.2048784731280806,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.9935,
+      "step": 10
+    },
+    {
+      "epoch": 0.8627450980392157,
+      "grad_norm": 3.752806588180809,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 0.9037,
+      "step": 11
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 3.7034973959501185,
+      "learning_rate": 5e-06,
+      "loss": 0.9095,
+      "step": 12
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.7034973959501185,
+      "learning_rate": 4.998942375205502e-06,
+      "loss": 0.6715,
+      "step": 13
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 3.3436999577667104,
+      "learning_rate": 4.995770395678171e-06,
+      "loss": 0.8186,
+      "step": 14
+    },
+    {
+      "epoch": 1.156862745098039,
+      "grad_norm": 2.662791286273683,
+      "learning_rate": 4.990486745229364e-06,
+      "loss": 0.7876,
+      "step": 15
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 3.1462660546154915,
+      "learning_rate": 4.983095894354858e-06,
+      "loss": 0.7498,
+      "step": 16
+    },
+    {
+      "epoch": 1.3137254901960784,
+      "grad_norm": 2.806483473961631,
+      "learning_rate": 4.973604096452361e-06,
+      "loss": 0.7377,
+      "step": 17
+    },
+    {
+      "epoch": 1.392156862745098,
+      "grad_norm": 2.4168449532239933,
+      "learning_rate": 4.962019382530521e-06,
+      "loss": 0.6722,
+      "step": 18
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 2.1659663165693823,
+      "learning_rate": 4.948351554413879e-06,
+      "loss": 0.6785,
+      "step": 19
+    },
+    {
+      "epoch": 1.5490196078431373,
+      "grad_norm": 1.9715057945884606,
+      "learning_rate": 4.93261217644956e-06,
+      "loss": 0.6873,
+      "step": 20
+    },
+    {
+      "epoch": 1.6274509803921569,
+      "grad_norm": 2.03020256390926,
+      "learning_rate": 4.914814565722671e-06,
+      "loss": 0.659,
+      "step": 21
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 1.9753159977423889,
+      "learning_rate": 4.894973780788722e-06,
+      "loss": 0.6438,
+      "step": 22
+    },
+    {
+      "epoch": 1.784313725490196,
+      "grad_norm": 1.7231552446064127,
+      "learning_rate": 4.873106608932585e-06,
+      "loss": 0.6467,
+      "step": 23
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 1.7271946867600179,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 0.6004,
+      "step": 24
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 1.908074354983798,
+      "learning_rate": 4.823368810567056e-06,
+      "loss": 0.6608,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.8986968468078707,
+      "learning_rate": 4.7955402672006855e-06,
+      "loss": 0.4767,
+      "step": 26
+    },
+    {
+      "epoch": 2.0784313725490198,
+      "grad_norm": 1.7821876091389497,
+      "learning_rate": 4.765769467591626e-06,
+      "loss": 0.5677,
+      "step": 27
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 1.5729961003705275,
+      "learning_rate": 4.734081600808531e-06,
+      "loss": 0.5875,
+      "step": 28
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 1.6161908564695435,
+      "learning_rate": 4.700503477950278e-06,
+      "loss": 0.5528,
+      "step": 29
+    },
+    {
+      "epoch": 2.313725490196078,
+      "grad_norm": 1.453253235686431,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 0.5471,
+      "step": 30
+    },
+    {
+      "epoch": 2.392156862745098,
+      "grad_norm": 1.5747903710062445,
+      "learning_rate": 4.627791681092499e-06,
+      "loss": 0.5058,
+      "step": 31
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 1.4435044859613202,
+      "learning_rate": 4.588719528532342e-06,
+      "loss": 0.5226,
+      "step": 32
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 1.39605748394361,
+      "learning_rate": 4.54788011072248e-06,
+      "loss": 0.5071,
+      "step": 33
+    },
+    {
+      "epoch": 2.627450980392157,
+      "grad_norm": 1.5254258052298646,
+      "learning_rate": 4.50530798188761e-06,
+      "loss": 0.4998,
+      "step": 34
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 1.4261873477979348,
+      "learning_rate": 4.46103916229894e-06,
+      "loss": 0.5009,
+      "step": 35
+    },
+    {
+      "epoch": 2.784313725490196,
+      "grad_norm": 1.4137129832097197,
+      "learning_rate": 4.415111107797445e-06,
+      "loss": 0.479,
+      "step": 36
+    },
+    {
+      "epoch": 2.8627450980392157,
+      "grad_norm": 1.520647591268587,
+      "learning_rate": 4.367562678102491e-06,
+      "loss": 0.5122,
+      "step": 37
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 1.437130314805203,
+      "learning_rate": 4.318434103932622e-06,
+      "loss": 0.4938,
+      "step": 38
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.381198514753958,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.3629,
+      "step": 39
+    },
+    {
+      "epoch": 3.0784313725490198,
+      "grad_norm": 1.4414609712821322,
+      "learning_rate": 4.215604094671835e-06,
+      "loss": 0.4262,
+      "step": 40
+    },
+    {
+      "epoch": 3.156862745098039,
+      "grad_norm": 1.3346547206899726,
+      "learning_rate": 4.161989664034844e-06,
+      "loss": 0.4259,
+      "step": 41
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 1.2955870784243064,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 0.4009,
+      "step": 42
+    },
+    {
+      "epoch": 3.313725490196078,
+      "grad_norm": 1.381727916852796,
+      "learning_rate": 4.0505887281706505e-06,
+      "loss": 0.4082,
+      "step": 43
+    },
+    {
+      "epoch": 3.392156862745098,
+      "grad_norm": 1.2215807897629705,
+      "learning_rate": 3.992896479256966e-06,
+      "loss": 0.4012,
+      "step": 44
+    },
+    {
+      "epoch": 3.4705882352941178,
+      "grad_norm": 1.341754935028127,
+      "learning_rate": 3.933941090877615e-06,
+      "loss": 0.4003,
+      "step": 45
+    },
+    {
+      "epoch": 3.549019607843137,
+      "grad_norm": 1.3219873249674265,
+      "learning_rate": 3.8737724451770155e-06,
+      "loss": 0.3906,
+      "step": 46
+    },
+    {
+      "epoch": 3.627450980392157,
+      "grad_norm": 1.2735261344863207,
+      "learning_rate": 3.8124414508364005e-06,
+      "loss": 0.3956,
+      "step": 47
+    },
+    {
+      "epoch": 3.7058823529411766,
+      "grad_norm": 1.408667555717726,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.3841,
+      "step": 48
+    },
+    {
+      "epoch": 3.784313725490196,
+      "grad_norm": 1.3920186495457132,
+      "learning_rate": 3.6865009243691015e-06,
+      "loss": 0.3998,
+      "step": 49
+    },
+    {
+      "epoch": 3.8627450980392157,
+      "grad_norm": 1.3668192562682828,
+      "learning_rate": 3.621997950501156e-06,
+      "loss": 0.3947,
+      "step": 50
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 1.3220345352979812,
+      "learning_rate": 3.556545654351749e-06,
+      "loss": 0.3898,
+      "step": 51
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.273119605790472,
+      "learning_rate": 3.4901994150978926e-06,
+      "loss": 0.2635,
+      "step": 52
+    },
+    {
+      "epoch": 4.078431372549019,
+      "grad_norm": 1.5507480548662818,
+      "learning_rate": 3.4230153682817112e-06,
+      "loss": 0.3232,
+      "step": 53
+    },
+    {
+      "epoch": 4.1568627450980395,
+      "grad_norm": 1.2464576840916806,
+      "learning_rate": 3.3550503583141726e-06,
+      "loss": 0.2997,
+      "step": 54
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 1.2140787104099877,
+      "learning_rate": 3.2863618903790346e-06,
+      "loss": 0.3061,
+      "step": 55
+    },
+    {
+      "epoch": 4.313725490196078,
+      "grad_norm": 1.2569518947420275,
+      "learning_rate": 3.217008081777726e-06,
+      "loss": 0.2995,
+      "step": 56
+    },
+    {
+      "epoch": 4.392156862745098,
+      "grad_norm": 1.2248006221848717,
+      "learning_rate": 3.147047612756302e-06,
+      "loss": 0.2973,
+      "step": 57
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 1.2928146585389553,
+      "learning_rate": 3.0765396768561005e-06,
+      "loss": 0.2987,
+      "step": 58
+    },
+    {
+      "epoch": 4.549019607843137,
+      "grad_norm": 1.3574488686929125,
+      "learning_rate": 3.0055439308300954e-06,
+      "loss": 0.3132,
+      "step": 59
+    },
+    {
+      "epoch": 4.627450980392156,
+      "grad_norm": 1.2894955154605787,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 0.2929,
+      "step": 60
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 1.2326192638645608,
+      "learning_rate": 2.862329648268117e-06,
+      "loss": 0.2794,
+      "step": 61
+    },
+    {
+      "epoch": 4.784313725490196,
+      "grad_norm": 1.3599625008219607,
+      "learning_rate": 2.7902322853130758e-06,
+      "loss": 0.2911,
+      "step": 62
+    },
+    {
+      "epoch": 4.862745098039216,
+      "grad_norm": 1.2507485894142631,
+      "learning_rate": 2.717889356869146e-06,
+      "loss": 0.2945,
+      "step": 63
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 1.3120759092640928,
+      "learning_rate": 2.6453620722761897e-06,
+      "loss": 0.3093,
+      "step": 64
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3120759092640928,
+      "learning_rate": 2.572711796857779e-06,
+      "loss": 0.2038,
+      "step": 65
+    },
+    {
+      "epoch": 5.078431372549019,
+      "grad_norm": 1.2133928459250458,
+      "learning_rate": 2.5e-06,
+      "loss": 0.2457,
+      "step": 66
+    },
+    {
+      "epoch": 5.1568627450980395,
+      "grad_norm": 1.1164096271756436,
+      "learning_rate": 2.4272882031422216e-06,
+      "loss": 0.2378,
+      "step": 67
+    },
+    {
+      "epoch": 5.235294117647059,
+      "grad_norm": 1.1865964714246466,
+      "learning_rate": 2.3546379277238107e-06,
+      "loss": 0.2365,
+      "step": 68
+    },
+    {
+      "epoch": 5.313725490196078,
+      "grad_norm": 1.1133005502471431,
+      "learning_rate": 2.2821106431308546e-06,
+      "loss": 0.2273,
+      "step": 69
+    },
+    {
+      "epoch": 5.392156862745098,
+      "grad_norm": 1.0726780522048756,
+      "learning_rate": 2.2097677146869242e-06,
+      "loss": 0.2251,
+      "step": 70
+    },
+    {
+      "epoch": 5.470588235294118,
+      "grad_norm": 1.1507923857528541,
+      "learning_rate": 2.1376703517318835e-06,
+      "loss": 0.2199,
+      "step": 71
+    },
+    {
+      "epoch": 5.549019607843137,
+      "grad_norm": 1.1965895392459576,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 0.2275,
+      "step": 72
+    },
+    {
+      "epoch": 5.627450980392156,
+      "grad_norm": 1.2081935303041835,
+      "learning_rate": 1.994456069169906e-06,
+      "loss": 0.2219,
+      "step": 73
+    },
+    {
+      "epoch": 5.705882352941177,
+      "grad_norm": 1.2037511840449118,
+      "learning_rate": 1.9234603231439e-06,
+      "loss": 0.2204,
+      "step": 74
+    },
+    {
+      "epoch": 5.784313725490196,
+      "grad_norm": 1.1530325179032028,
+      "learning_rate": 1.852952387243698e-06,
+      "loss": 0.22,
+      "step": 75
+    },
+    {
+      "epoch": 5.862745098039216,
+      "grad_norm": 1.1780261182347391,
+      "learning_rate": 1.7829919182222752e-06,
+      "loss": 0.2199,
+      "step": 76
+    },
+    {
+      "epoch": 5.9411764705882355,
+      "grad_norm": 1.1895169708488194,
+      "learning_rate": 1.7136381096209665e-06,
+      "loss": 0.2037,
+      "step": 77
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.0854093120483197,
+      "learning_rate": 1.6449496416858285e-06,
+      "loss": 0.1583,
+      "step": 78
+    },
+    {
+      "epoch": 6.078431372549019,
+      "grad_norm": 1.0801354684612592,
+      "learning_rate": 1.5769846317182894e-06,
+      "loss": 0.1934,
+      "step": 79
+    },
+    {
+      "epoch": 6.1568627450980395,
+      "grad_norm": 1.0439246440370717,
+      "learning_rate": 1.509800584902108e-06,
+      "loss": 0.1705,
+      "step": 80
+    },
+    {
+      "epoch": 6.235294117647059,
+      "grad_norm": 1.0284457474816655,
+      "learning_rate": 1.443454345648252e-06,
+      "loss": 0.1723,
+      "step": 81
+    },
+    {
+      "epoch": 6.313725490196078,
+      "grad_norm": 0.9926653408766625,
+      "learning_rate": 1.3780020494988447e-06,
+      "loss": 0.1792,
+      "step": 82
+    },
+    {
+      "epoch": 6.392156862745098,
+      "grad_norm": 1.0138502371712474,
+      "learning_rate": 1.313499075630899e-06,
+      "loss": 0.1679,
+      "step": 83
+    },
+    {
+      "epoch": 6.470588235294118,
+      "grad_norm": 1.0083965688320564,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.169,
+      "step": 84
+    },
+    {
+      "epoch": 6.549019607843137,
+      "grad_norm": 1.0514389443911982,
+      "learning_rate": 1.1875585491636e-06,
+      "loss": 0.1807,
+      "step": 85
+    },
+    {
+      "epoch": 6.627450980392156,
+      "grad_norm": 1.0545495890932062,
+      "learning_rate": 1.1262275548229852e-06,
+      "loss": 0.1735,
+      "step": 86
+    },
+    {
+      "epoch": 6.705882352941177,
+      "grad_norm": 1.1020211072090924,
+      "learning_rate": 1.0660589091223854e-06,
+      "loss": 0.1728,
+      "step": 87
+    },
+    {
+      "epoch": 6.784313725490196,
+      "grad_norm": 1.0983738677411488,
+      "learning_rate": 1.0071035207430352e-06,
+      "loss": 0.171,
+      "step": 88
+    },
+    {
+      "epoch": 6.862745098039216,
+      "grad_norm": 1.0848006154577043,
+      "learning_rate": 9.494112718293503e-07,
+      "loss": 0.1761,
+      "step": 89
+    },
+    {
+      "epoch": 6.9411764705882355,
+      "grad_norm": 1.0504620709430657,
+      "learning_rate": 8.930309757836517e-07,
+      "loss": 0.1689,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.0335128775784548,
+      "learning_rate": 8.380103359651554e-07,
+      "loss": 0.1193,
+      "step": 91
+    },
+    {
+      "epoch": 7.078431372549019,
+      "grad_norm": 0.9668349947212325,
+      "learning_rate": 7.843959053281663e-07,
+      "loss": 0.1531,
+      "step": 92
+    },
+    {
+      "epoch": 7.1568627450980395,
+      "grad_norm": 0.9049193018844318,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.1449,
+      "step": 93
+    },
+    {
+      "epoch": 7.235294117647059,
+      "grad_norm": 0.8855250299857752,
+      "learning_rate": 6.815658960673782e-07,
+      "loss": 0.1398,
+      "step": 94
+    },
+    {
+      "epoch": 7.313725490196078,
+      "grad_norm": 0.9608687848192914,
+      "learning_rate": 6.324373218975105e-07,
+      "loss": 0.1487,
+      "step": 95
+    },
+    {
+      "epoch": 7.392156862745098,
+      "grad_norm": 0.9692880229899594,
+      "learning_rate": 5.848888922025553e-07,
+      "loss": 0.1403,
+      "step": 96
+    },
+    {
+      "epoch": 7.470588235294118,
+      "grad_norm": 0.9035708627250062,
+      "learning_rate": 5.389608377010608e-07,
+      "loss": 0.1449,
+      "step": 97
+    },
+    {
+      "epoch": 7.549019607843137,
+      "grad_norm": 0.8748928881891229,
+      "learning_rate": 4.946920181123904e-07,
+      "loss": 0.1451,
+      "step": 98
+    },
+    {
+      "epoch": 7.627450980392156,
+      "grad_norm": 0.8912371091414796,
+      "learning_rate": 4.5211988927752026e-07,
+      "loss": 0.134,
+      "step": 99
+    },
+    {
+      "epoch": 7.705882352941177,
+      "grad_norm": 0.9454342145405766,
+      "learning_rate": 4.1128047146765936e-07,
+      "loss": 0.1497,
+      "step": 100
+    },
+    {
+      "epoch": 7.784313725490196,
+      "grad_norm": 0.9466608405460601,
+      "learning_rate": 3.722083189075007e-07,
+      "loss": 0.1523,
+      "step": 101
+    },
+    {
+      "epoch": 7.862745098039216,
+      "grad_norm": 0.9716836299571869,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 0.1406,
+      "step": 102
+    },
+    {
+      "epoch": 7.9411764705882355,
+      "grad_norm": 0.9517618408879835,
+      "learning_rate": 2.9949652204972257e-07,
+      "loss": 0.1414,
+      "step": 103
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.8961669761492526,
+      "learning_rate": 2.6591839919146963e-07,
+      "loss": 0.0988,
+      "step": 104
+    },
+    {
+      "epoch": 8.07843137254902,
+      "grad_norm": 0.8800809597012162,
+      "learning_rate": 2.3423053240837518e-07,
+      "loss": 0.1326,
+      "step": 105
+    },
+    {
+      "epoch": 8.156862745098039,
+      "grad_norm": 0.8678268581817502,
+      "learning_rate": 2.044597327993153e-07,
+      "loss": 0.1382,
+      "step": 106
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 0.8749341283858125,
+      "learning_rate": 1.7663118943294367e-07,
+      "loss": 0.1394,
+      "step": 107
+    },
+    {
+      "epoch": 8.313725490196079,
+      "grad_norm": 0.8593112391578863,
+      "learning_rate": 1.507684480352292e-07,
+      "loss": 0.1278,
+      "step": 108
+    },
+    {
+      "epoch": 8.392156862745098,
+      "grad_norm": 0.9129847126820709,
+      "learning_rate": 1.2689339106741529e-07,
+      "loss": 0.1391,
+      "step": 109
+    },
+    {
+      "epoch": 8.470588235294118,
+      "grad_norm": 0.8656126791419273,
+      "learning_rate": 1.0502621921127776e-07,
+      "loss": 0.1311,
+      "step": 110
+    },
+    {
+      "epoch": 8.549019607843137,
+      "grad_norm": 0.8593751089585534,
+      "learning_rate": 8.518543427732951e-08,
+      "loss": 0.1296,
+      "step": 111
+    },
+    {
+      "epoch": 8.627450980392156,
+      "grad_norm": 0.8879560191886899,
+      "learning_rate": 6.738782355044048e-08,
+      "loss": 0.1263,
+      "step": 112
+    },
+    {
+      "epoch": 8.705882352941176,
+      "grad_norm": 0.9206743688905853,
+      "learning_rate": 5.164844558612131e-08,
+      "loss": 0.1381,
+      "step": 113
+    },
+    {
+      "epoch": 8.784313725490197,
+      "grad_norm": 0.8795400657114122,
+      "learning_rate": 3.798061746947995e-08,
+      "loss": 0.1282,
+      "step": 114
+    },
+    {
+      "epoch": 8.862745098039216,
+      "grad_norm": 0.8568365367984947,
+      "learning_rate": 2.6395903547638825e-08,
+      "loss": 0.1331,
+      "step": 115
+    },
+    {
+      "epoch": 8.941176470588236,
+      "grad_norm": 0.847262314471311,
+      "learning_rate": 1.6904105645142443e-08,
+      "loss": 0.1264,
+      "step": 116
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.847262314471311,
+      "learning_rate": 9.513254770636138e-09,
+      "loss": 0.0991,
+      "step": 117
+    },
+    {
+      "epoch": 9.07843137254902,
+      "grad_norm": 0.8727190548675097,
+      "learning_rate": 4.229604321829561e-09,
+      "loss": 0.1293,
+      "step": 118
+    },
+    {
+      "epoch": 9.156862745098039,
+      "grad_norm": 0.816661788373,
+      "learning_rate": 1.0576247944985018e-09,
+      "loss": 0.1269,
+      "step": 119
+    },
+    {
+      "epoch": 9.235294117647058,
+      "grad_norm": 0.885147564294731,
+      "learning_rate": 0.0,
+      "loss": 0.1341,
+      "step": 120
+    },
+    {
+      "epoch": 9.235294117647058,
+      "step": 120,
+      "total_flos": 27074593947648.0,
+      "train_loss": 0.388430199213326,
+      "train_runtime": 2487.6221,
+      "train_samples_per_second": 1.624,
+      "train_steps_per_second": 0.048
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 27074593947648.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988992eb42dabc20482f60c79a00b82b969bae9d92487c57c629f39c008e4750
+size 7672