Initial upload

.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

added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|diff_marker|>": 151666,
+  "<|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,
+  "<|pointer_end|>": 151668,
+  "<|pointer_pad|>": 151669,
+  "<|pointer_start|>": 151667,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|recipient|>": 151665,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

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 +1,74 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGenerationWithPointer"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151666
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pointer_end_token_id": 151668,
+  "pointer_pad_token_id": 151669,
+  "pointer_start_token_id": 151667,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 2048,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151670,
+  "part_query_weighting": false,
+  "kl_query_weighting": false,
+  "query_topk": 1,
+  "layer_wise_query_weighting": false
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "attn_implementation": null,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151666
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.51.3"
+}

latest

@@ -0,0 +1 @@
+global_step2500

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da30c802fa686b5ff4a6534d0fc9211cddb6fb31404d5ec95bb9b1c614fd22fb
+size 4996661224

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f071fbd917d0ccfe8ee94036c69d17708c926918394fd1a42be8a140b69fbd1
+size 2511587184

model.safetensors.index.json

@@ -0,0 +1,831 @@
+{
+  "metadata": {
+    "total_size": 7508156416
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

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": 4014080,
+  "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
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863bd3e0e2503c41d348bea30e369e3ac69196ca3d0c876691a02a9d14e73e31
+size 1064

special_tokens_map.json

@@ -0,0 +1,47 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|recipient|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|diff_marker|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|pointer_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|pointer_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|pointer_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": "<|diff_marker|>",
+  "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:c8721840eaf5e00bdaca36c7e64e77ad97a413389028ffc659b542c8d5d763b8
+size 11422856

tokenizer_config.json

@@ -0,0 +1,242 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|recipient|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|diff_marker|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|pointer_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|pointer_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|pointer_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|recipient|>",
+    "<|diff_marker|>",
+    "<|pointer_start|>",
+    "<|pointer_end|>",
+    "<|pointer_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": "<|diff_marker|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 24576,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6279829188646069,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0025119316754584277,
+      "grad_norm": 239.86626690426797,
+      "learning_rate": 3.75e-07,
+      "loss": 14.0514,
+      "step": 10
+    },
+    {
+      "epoch": 0.005023863350916855,
+      "grad_norm": 241.65713375934203,
+      "learning_rate": 7.916666666666667e-07,
+      "loss": 13.4641,
+      "step": 20
+    },
+    {
+      "epoch": 0.007535795026375283,
+      "grad_norm": 173.45543000884305,
+      "learning_rate": 1.2083333333333333e-06,
+      "loss": 11.1434,
+      "step": 30
+    },
+    {
+      "epoch": 0.01004772670183371,
+      "grad_norm": 146.2934339088987,
+      "learning_rate": 1.6250000000000001e-06,
+      "loss": 8.4913,
+      "step": 40
+    },
+    {
+      "epoch": 0.012559658377292138,
+      "grad_norm": 398.82757406036774,
+      "learning_rate": 2.041666666666667e-06,
+      "loss": 6.7104,
+      "step": 50
+    },
+    {
+      "epoch": 0.015071590052750565,
+      "grad_norm": 120.60920314822488,
+      "learning_rate": 2.4583333333333332e-06,
+      "loss": 5.7821,
+      "step": 60
+    },
+    {
+      "epoch": 0.017583521728208994,
+      "grad_norm": 90.0978520948313,
+      "learning_rate": 2.875e-06,
+      "loss": 5.272,
+      "step": 70
+    },
+    {
+      "epoch": 0.02009545340366742,
+      "grad_norm": 61.367400551825064,
+      "learning_rate": 3.2916666666666668e-06,
+      "loss": 4.9503,
+      "step": 80
+    },
+    {
+      "epoch": 0.02260738507912585,
+      "grad_norm": 59.29031096773261,
+      "learning_rate": 3.708333333333334e-06,
+      "loss": 4.7641,
+      "step": 90
+    },
+    {
+      "epoch": 0.025119316754584276,
+      "grad_norm": 89.49483058191011,
+      "learning_rate": 4.125e-06,
+      "loss": 4.6544,
+      "step": 100
+    },
+    {
+      "epoch": 0.027631248430042703,
+      "grad_norm": 56.71283853366937,
+      "learning_rate": 4.541666666666667e-06,
+      "loss": 4.6721,
+      "step": 110
+    },
+    {
+      "epoch": 0.03014318010550113,
+      "grad_norm": 86.45361872418661,
+      "learning_rate": 4.958333333333334e-06,
+      "loss": 4.5809,
+      "step": 120
+    },
+    {
+      "epoch": 0.032655111780959555,
+      "grad_norm": 45.58440716196556,
+      "learning_rate": 4.999932966293553e-06,
+      "loss": 4.4436,
+      "step": 130
+    },
+    {
+      "epoch": 0.03516704345641799,
+      "grad_norm": 58.442106591817584,
+      "learning_rate": 4.999701249454364e-06,
+      "loss": 4.3183,
+      "step": 140
+    },
+    {
+      "epoch": 0.037678975131876416,
+      "grad_norm": 217.45706394827462,
+      "learning_rate": 4.999304037243215e-06,
+      "loss": 4.0309,
+      "step": 150
+    },
+    {
+      "epoch": 0.04019090680733484,
+      "grad_norm": 190.98402036268755,
+      "learning_rate": 4.998741355957963e-06,
+      "loss": 3.978,
+      "step": 160
+    },
+    {
+      "epoch": 0.04270283848279327,
+      "grad_norm": 47.98571572612224,
+      "learning_rate": 4.998013242851519e-06,
+      "loss": 3.7108,
+      "step": 170
+    },
+    {
+      "epoch": 0.0452147701582517,
+      "grad_norm": 48.772737633211705,
+      "learning_rate": 4.997119746129383e-06,
+      "loss": 3.4587,
+      "step": 180
+    },
+    {
+      "epoch": 0.047726701833710125,
+      "grad_norm": 60.9476907692281,
+      "learning_rate": 4.996060924946452e-06,
+      "loss": 3.1639,
+      "step": 190
+    },
+    {
+      "epoch": 0.05023863350916855,
+      "grad_norm": 41.74169393637858,
+      "learning_rate": 4.994836849403107e-06,
+      "loss": 2.9012,
+      "step": 200
+    },
+    {
+      "epoch": 0.05275056518462698,
+      "grad_norm": 40.83252344589926,
+      "learning_rate": 4.9934476005405665e-06,
+      "loss": 2.6201,
+      "step": 210
+    },
+    {
+      "epoch": 0.05526249686008541,
+      "grad_norm": 37.63985646203945,
+      "learning_rate": 4.991893270335526e-06,
+      "loss": 2.3558,
+      "step": 220
+    },
+    {
+      "epoch": 0.057774428535543834,
+      "grad_norm": 119.09847504178867,
+      "learning_rate": 4.990173961694062e-06,
+      "loss": 2.1942,
+      "step": 230
+    },
+    {
+      "epoch": 0.06028636021100226,
+      "grad_norm": 54.69969747642922,
+      "learning_rate": 4.988289788444829e-06,
+      "loss": 1.9617,
+      "step": 240
+    },
+    {
+      "epoch": 0.06279829188646069,
+      "grad_norm": 29.75999921966923,
+      "learning_rate": 4.986240875331513e-06,
+      "loss": 1.7483,
+      "step": 250
+    },
+    {
+      "epoch": 0.06531022356191911,
+      "grad_norm": 32.41681828008889,
+      "learning_rate": 4.984027358004582e-06,
+      "loss": 1.6636,
+      "step": 260
+    },
+    {
+      "epoch": 0.06782215523737754,
+      "grad_norm": 36.40268660590211,
+      "learning_rate": 4.981649383012295e-06,
+      "loss": 1.4163,
+      "step": 270
+    },
+    {
+      "epoch": 0.07033408691283598,
+      "grad_norm": 25.472902003029926,
+      "learning_rate": 4.979107107791009e-06,
+      "loss": 1.4181,
+      "step": 280
+    },
+    {
+      "epoch": 0.0728460185882944,
+      "grad_norm": 83.17909181810148,
+      "learning_rate": 4.976400700654752e-06,
+      "loss": 1.48,
+      "step": 290
+    },
+    {
+      "epoch": 0.07535795026375283,
+      "grad_norm": 34.58350421170401,
+      "learning_rate": 4.9735303407840775e-06,
+      "loss": 1.3707,
+      "step": 300
+    },
+    {
+      "epoch": 0.07786988193921125,
+      "grad_norm": 33.83287957678044,
+      "learning_rate": 4.970496218214205e-06,
+      "loss": 1.2926,
+      "step": 310
+    },
+    {
+      "epoch": 0.08038181361466969,
+      "grad_norm": 18.116080898978627,
+      "learning_rate": 4.9672985338224355e-06,
+      "loss": 1.1966,
+      "step": 320
+    },
+    {
+      "epoch": 0.0828937452901281,
+      "grad_norm": 14.920052462705657,
+      "learning_rate": 4.963937499314857e-06,
+      "loss": 1.2477,
+      "step": 330
+    },
+    {
+      "epoch": 0.08540567696558654,
+      "grad_norm": 35.38568073442068,
+      "learning_rate": 4.960413337212321e-06,
+      "loss": 1.1804,
+      "step": 340
+    },
+    {
+      "epoch": 0.08791760864104496,
+      "grad_norm": 21.461935419382467,
+      "learning_rate": 4.956726280835718e-06,
+      "loss": 1.0769,
+      "step": 350
+    },
+    {
+      "epoch": 0.0904295403165034,
+      "grad_norm": 13.281431782416353,
+      "learning_rate": 4.952876574290525e-06,
+      "loss": 1.1561,
+      "step": 360
+    },
+    {
+      "epoch": 0.09294147199196182,
+      "grad_norm": 19.82726524818117,
+      "learning_rate": 4.948864472450646e-06,
+      "loss": 1.0875,
+      "step": 370
+    },
+    {
+      "epoch": 0.09545340366742025,
+      "grad_norm": 24.291862600707194,
+      "learning_rate": 4.9446902409415386e-06,
+      "loss": 0.9654,
+      "step": 380
+    },
+    {
+      "epoch": 0.09796533534287867,
+      "grad_norm": 14.96805767144798,
+      "learning_rate": 4.940354156122624e-06,
+      "loss": 1.1098,
+      "step": 390
+    },
+    {
+      "epoch": 0.1004772670183371,
+      "grad_norm": 95.52602922310824,
+      "learning_rate": 4.935856505068999e-06,
+      "loss": 1.1063,
+      "step": 400
+    },
+    {
+      "epoch": 0.10298919869379553,
+      "grad_norm": 22.186939442062904,
+      "learning_rate": 4.931197585552418e-06,
+      "loss": 1.1467,
+      "step": 410
+    },
+    {
+      "epoch": 0.10550113036925396,
+      "grad_norm": 18.397731165160682,
+      "learning_rate": 4.92637770602159e-06,
+      "loss": 0.9853,
+      "step": 420
+    },
+    {
+      "epoch": 0.10801306204471238,
+      "grad_norm": 21.500466390648395,
+      "learning_rate": 4.92139718558175e-06,
+      "loss": 1.0165,
+      "step": 430
+    },
+    {
+      "epoch": 0.11052499372017081,
+      "grad_norm": 56.657630075172975,
+      "learning_rate": 4.916256353973535e-06,
+      "loss": 1.1114,
+      "step": 440
+    },
+    {
+      "epoch": 0.11303692539562923,
+      "grad_norm": 15.653730448263433,
+      "learning_rate": 4.910955551551153e-06,
+      "loss": 0.9635,
+      "step": 450
+    },
+    {
+      "epoch": 0.11554885707108767,
+      "grad_norm": 24.17906938244907,
+      "learning_rate": 4.90549512925985e-06,
+      "loss": 0.9795,
+      "step": 460
+    },
+    {
+      "epoch": 0.11806078874654609,
+      "grad_norm": 14.124410705790005,
+      "learning_rate": 4.899875448612672e-06,
+      "loss": 1.06,
+      "step": 470
+    },
+    {
+      "epoch": 0.12057272042200452,
+      "grad_norm": 29.243194398526683,
+      "learning_rate": 4.894096881666538e-06,
+      "loss": 1.0627,
+      "step": 480
+    },
+    {
+      "epoch": 0.12308465209746294,
+      "grad_norm": 29.825510941940802,
+      "learning_rate": 4.8881598109976e-06,
+      "loss": 1.0064,
+      "step": 490
+    },
+    {
+      "epoch": 0.12559658377292138,
+      "grad_norm": 22.230058918228227,
+      "learning_rate": 4.882064629675917e-06,
+      "loss": 1.0108,
+      "step": 500
+    },
+    {
+      "epoch": 0.1281085154483798,
+      "grad_norm": 14.598952675757223,
+      "learning_rate": 4.875811741239431e-06,
+      "loss": 1.0237,
+      "step": 510
+    },
+    {
+      "epoch": 0.13062044712383822,
+      "grad_norm": 20.636959354053275,
+      "learning_rate": 4.869401559667253e-06,
+      "loss": 1.0505,
+      "step": 520
+    },
+    {
+      "epoch": 0.13313237879929665,
+      "grad_norm": 15.807398300710538,
+      "learning_rate": 4.862834509352251e-06,
+      "loss": 0.9586,
+      "step": 530
+    },
+    {
+      "epoch": 0.1356443104747551,
+      "grad_norm": 16.74866266140211,
+      "learning_rate": 4.8561110250729546e-06,
+      "loss": 1.0777,
+      "step": 540
+    },
+    {
+      "epoch": 0.13815624215021352,
+      "grad_norm": 15.937206376325129,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 0.9419,
+      "step": 550
+    },
+    {
+      "epoch": 0.14066817382567195,
+      "grad_norm": 24.91540373905989,
+      "learning_rate": 4.842196545490512e-06,
+      "loss": 0.8815,
+      "step": 560
+    },
+    {
+      "epoch": 0.14318010550113036,
+      "grad_norm": 110.81817108541208,
+      "learning_rate": 4.8350064714102415e-06,
+      "loss": 0.9471,
+      "step": 570
+    },
+    {
+      "epoch": 0.1456920371765888,
+      "grad_norm": 12.67485379375325,
+      "learning_rate": 4.827661805750438e-06,
+      "loss": 0.8974,
+      "step": 580
+    },
+    {
+      "epoch": 0.14820396885204723,
+      "grad_norm": 12.572269748750621,
+      "learning_rate": 4.82016303477248e-06,
+      "loss": 1.0504,
+      "step": 590
+    },
+    {
+      "epoch": 0.15071590052750566,
+      "grad_norm": 77.42629443684905,
+      "learning_rate": 4.812510654940453e-06,
+      "loss": 0.9303,
+      "step": 600
+    },
+    {
+      "epoch": 0.15322783220296407,
+      "grad_norm": 24.16222859058385,
+      "learning_rate": 4.804705172888277e-06,
+      "loss": 0.8517,
+      "step": 610
+    },
+    {
+      "epoch": 0.1557397638784225,
+      "grad_norm": 29.389692353618713,
+      "learning_rate": 4.796747105386169e-06,
+      "loss": 0.9901,
+      "step": 620
+    },
+    {
+      "epoch": 0.15825169555388094,
+      "grad_norm": 25.36478869014837,
+      "learning_rate": 4.788636979306428e-06,
+      "loss": 0.9971,
+      "step": 630
+    },
+    {
+      "epoch": 0.16076362722933937,
+      "grad_norm": 27.923949328894885,
+      "learning_rate": 4.78037533158855e-06,
+      "loss": 0.9602,
+      "step": 640
+    },
+    {
+      "epoch": 0.16327555890479778,
+      "grad_norm": 21.01129716893739,
+      "learning_rate": 4.771962709203684e-06,
+      "loss": 0.8699,
+      "step": 650
+    },
+    {
+      "epoch": 0.1657874905802562,
+      "grad_norm": 48.56522034229219,
+      "learning_rate": 4.763399669118414e-06,
+      "loss": 1.032,
+      "step": 660
+    },
+    {
+      "epoch": 0.16829942225571465,
+      "grad_norm": 22.751382541347517,
+      "learning_rate": 4.754686778257891e-06,
+      "loss": 1.0234,
+      "step": 670
+    },
+    {
+      "epoch": 0.17081135393117308,
+      "grad_norm": 60.316201164816675,
+      "learning_rate": 4.745824613468293e-06,
+      "loss": 0.9245,
+      "step": 680
+    },
+    {
+      "epoch": 0.1733232856066315,
+      "grad_norm": 11.91074816824941,
+      "learning_rate": 4.736813761478638e-06,
+      "loss": 0.8775,
+      "step": 690
+    },
+    {
+      "epoch": 0.17583521728208992,
+      "grad_norm": 26.5579528835264,
+      "learning_rate": 4.727654818861937e-06,
+      "loss": 0.9152,
+      "step": 700
+    },
+    {
+      "epoch": 0.17834714895754836,
+      "grad_norm": 15.380228011033301,
+      "learning_rate": 4.718348391995698e-06,
+      "loss": 0.9011,
+      "step": 710
+    },
+    {
+      "epoch": 0.1808590806330068,
+      "grad_norm": 12.487600026078852,
+      "learning_rate": 4.7088950970217825e-06,
+      "loss": 0.8569,
+      "step": 720
+    },
+    {
+      "epoch": 0.1833710123084652,
+      "grad_norm": 35.41259056682878,
+      "learning_rate": 4.699295559805606e-06,
+      "loss": 0.967,
+      "step": 730
+    },
+    {
+      "epoch": 0.18588294398392363,
+      "grad_norm": 13.677677058059642,
+      "learning_rate": 4.68955041589471e-06,
+      "loss": 0.797,
+      "step": 740
+    },
+    {
+      "epoch": 0.18839487565938207,
+      "grad_norm": 18.440514541051645,
+      "learning_rate": 4.679660310476682e-06,
+      "loss": 0.927,
+      "step": 750
+    },
+    {
+      "epoch": 0.1909068073348405,
+      "grad_norm": 23.014405812725435,
+      "learning_rate": 4.669625898336439e-06,
+      "loss": 0.9384,
+      "step": 760
+    },
+    {
+      "epoch": 0.1934187390102989,
+      "grad_norm": 11.20886261879898,
+      "learning_rate": 4.659447843812876e-06,
+      "loss": 0.9643,
+      "step": 770
+    },
+    {
+      "epoch": 0.19593067068575734,
+      "grad_norm": 80.39449597646359,
+      "learning_rate": 4.649126820754887e-06,
+      "loss": 0.8381,
+      "step": 780
+    },
+    {
+      "epoch": 0.19844260236121578,
+      "grad_norm": 29.00291875030787,
+      "learning_rate": 4.638663512476748e-06,
+      "loss": 0.8494,
+      "step": 790
+    },
+    {
+      "epoch": 0.2009545340366742,
+      "grad_norm": 38.02886951298836,
+      "learning_rate": 4.628058611712879e-06,
+      "loss": 0.9796,
+      "step": 800
+    },
+    {
+      "epoch": 0.20346646571213264,
+      "grad_norm": 18.192543794768483,
+      "learning_rate": 4.617312820571981e-06,
+      "loss": 0.9138,
+      "step": 810
+    },
+    {
+      "epoch": 0.20597839738759105,
+      "grad_norm": 23.82338721037481,
+      "learning_rate": 4.606426850490551e-06,
+      "loss": 0.9102,
+      "step": 820
+    },
+    {
+      "epoch": 0.20849032906304948,
+      "grad_norm": 10.709097786905685,
+      "learning_rate": 4.595401422185783e-06,
+      "loss": 0.8003,
+      "step": 830
+    },
+    {
+      "epoch": 0.21100226073850792,
+      "grad_norm": 13.764481906980386,
+      "learning_rate": 4.584237265607847e-06,
+      "loss": 0.8165,
+      "step": 840
+    },
+    {
+      "epoch": 0.21351419241396635,
+      "grad_norm": 16.585153588850403,
+      "learning_rate": 4.5729351198915715e-06,
+      "loss": 0.9796,
+      "step": 850
+    },
+    {
+      "epoch": 0.21602612408942476,
+      "grad_norm": 20.43649156380754,
+      "learning_rate": 4.561495733307496e-06,
+      "loss": 0.9035,
+      "step": 860
+    },
+    {
+      "epoch": 0.2185380557648832,
+      "grad_norm": 33.63536514401432,
+      "learning_rate": 4.549919863212341e-06,
+      "loss": 0.8352,
+      "step": 870
+    },
+    {
+      "epoch": 0.22104998744034163,
+      "grad_norm": 14.506793953608973,
+      "learning_rate": 4.538208275998861e-06,
+      "loss": 0.8947,
+      "step": 880
+    },
+    {
+      "epoch": 0.22356191911580006,
+      "grad_norm": 11.578331400954918,
+      "learning_rate": 4.526361747045108e-06,
+      "loss": 0.9039,
+      "step": 890
+    },
+    {
+      "epoch": 0.22607385079125847,
+      "grad_norm": 18.384322305782966,
+      "learning_rate": 4.514381060663092e-06,
+      "loss": 0.8723,
+      "step": 900
+    },
+    {
+      "epoch": 0.2285857824667169,
+      "grad_norm": 13.552448363311854,
+      "learning_rate": 4.50226701004686e-06,
+      "loss": 0.8576,
+      "step": 910
+    },
+    {
+      "epoch": 0.23109771414217534,
+      "grad_norm": 30.371496853106105,
+      "learning_rate": 4.49002039721998e-06,
+      "loss": 0.8734,
+      "step": 920
+    },
+    {
+      "epoch": 0.23360964581763377,
+      "grad_norm": 12.90853135307357,
+      "learning_rate": 4.477642032982439e-06,
+      "loss": 0.8967,
+      "step": 930
+    },
+    {
+      "epoch": 0.23612157749309218,
+      "grad_norm": 17.349733063466882,
+      "learning_rate": 4.4651327368569695e-06,
+      "loss": 0.8721,
+      "step": 940
+    },
+    {
+      "epoch": 0.2386335091685506,
+      "grad_norm": 10.22639212014615,
+      "learning_rate": 4.452493337034785e-06,
+      "loss": 0.8251,
+      "step": 950
+    },
+    {
+      "epoch": 0.24114544084400905,
+      "grad_norm": 14.036845792480072,
+      "learning_rate": 4.439724670320755e-06,
+      "loss": 0.82,
+      "step": 960
+    },
+    {
+      "epoch": 0.24365737251946748,
+      "grad_norm": 30.558423682821672,
+      "learning_rate": 4.426827582077999e-06,
+      "loss": 0.9052,
+      "step": 970
+    },
+    {
+      "epoch": 0.2461693041949259,
+      "grad_norm": 10.87817158904601,
+      "learning_rate": 4.413802926171921e-06,
+      "loss": 0.9395,
+      "step": 980
+    },
+    {
+      "epoch": 0.24868123587038432,
+      "grad_norm": 11.860625532466202,
+      "learning_rate": 4.400651564913676e-06,
+      "loss": 0.8354,
+      "step": 990
+    },
+    {
+      "epoch": 0.25119316754584275,
+      "grad_norm": 26.804303100656824,
+      "learning_rate": 4.387374369003083e-06,
+      "loss": 1.0365,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2537050992213012,
+      "grad_norm": 13.980929588055153,
+      "learning_rate": 4.373972217470976e-06,
+      "loss": 0.8842,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2562170308967596,
+      "grad_norm": 64.87903614595136,
+      "learning_rate": 4.36044599762101e-06,
+      "loss": 0.9892,
+      "step": 1020
+    },
+    {
+      "epoch": 0.25872896257221806,
+      "grad_norm": 15.680619895690414,
+      "learning_rate": 4.346796604970913e-06,
+      "loss": 0.8724,
+      "step": 1030
+    },
+    {
+      "epoch": 0.26124089424767644,
+      "grad_norm": 11.448264006151128,
+      "learning_rate": 4.333024943193198e-06,
+      "loss": 0.7712,
+      "step": 1040
+    },
+    {
+      "epoch": 0.26375282592313487,
+      "grad_norm": 17.29885656134933,
+      "learning_rate": 4.31913192405534e-06,
+      "loss": 0.8548,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2662647575985933,
+      "grad_norm": 20.225278932621606,
+      "learning_rate": 4.305118467359402e-06,
+      "loss": 0.7605,
+      "step": 1060
+    },
+    {
+      "epoch": 0.26877668927405174,
+      "grad_norm": 17.040194261706198,
+      "learning_rate": 4.290985500881143e-06,
+      "loss": 0.7947,
+      "step": 1070
+    },
+    {
+      "epoch": 0.2712886209495102,
+      "grad_norm": 27.511228295337173,
+      "learning_rate": 4.276733960308599e-06,
+      "loss": 0.8198,
+      "step": 1080
+    },
+    {
+      "epoch": 0.2738005526249686,
+      "grad_norm": 21.703931190646244,
+      "learning_rate": 4.262364789180123e-06,
+      "loss": 0.8903,
+      "step": 1090
+    },
+    {
+      "epoch": 0.27631248430042704,
+      "grad_norm": 13.748758938168764,
+      "learning_rate": 4.247878938821929e-06,
+      "loss": 0.7911,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2788244159758855,
+      "grad_norm": 15.62240442461118,
+      "learning_rate": 4.2332773682851e-06,
+      "loss": 0.8658,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2813363476513439,
+      "grad_norm": 26.11975126253329,
+      "learning_rate": 4.218561044282099e-06,
+      "loss": 0.8139,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2838482793268023,
+      "grad_norm": 20.533664867643136,
+      "learning_rate": 4.20373094112276e-06,
+      "loss": 0.8064,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2863602110022607,
+      "grad_norm": 20.520058509961064,
+      "learning_rate": 4.18878804064979e-06,
+      "loss": 0.7653,
+      "step": 1140
+    },
+    {
+      "epoch": 0.28887214267771916,
+      "grad_norm": 46.83279939211064,
+      "learning_rate": 4.173733332173759e-06,
+      "loss": 0.8728,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2913840743531776,
+      "grad_norm": 8.759453123826004,
+      "learning_rate": 4.158567812407609e-06,
+      "loss": 0.8234,
+      "step": 1160
+    },
+    {
+      "epoch": 0.293896006028636,
+      "grad_norm": 10.180380124180049,
+      "learning_rate": 4.1432924854006554e-06,
+      "loss": 0.814,
+      "step": 1170
+    },
+    {
+      "epoch": 0.29640793770409446,
+      "grad_norm": 13.135943397270523,
+      "learning_rate": 4.127908362472121e-06,
+      "loss": 0.8766,
+      "step": 1180
+    },
+    {
+      "epoch": 0.2989198693795529,
+      "grad_norm": 12.454769736602296,
+      "learning_rate": 4.112416462144181e-06,
+      "loss": 0.8088,
+      "step": 1190
+    },
+    {
+      "epoch": 0.30143180105501133,
+      "grad_norm": 11.723203566108994,
+      "learning_rate": 4.096817810074521e-06,
+      "loss": 0.7919,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3039437327304697,
+      "grad_norm": 82.86393754853735,
+      "learning_rate": 4.081113438988443e-06,
+      "loss": 0.8764,
+      "step": 1210
+    },
+    {
+      "epoch": 0.30645566440592814,
+      "grad_norm": 21.389805182156973,
+      "learning_rate": 4.065304388610491e-06,
+      "loss": 0.8616,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3089675960813866,
+      "grad_norm": 15.115349552996772,
+      "learning_rate": 4.049391705595605e-06,
+      "loss": 0.8603,
+      "step": 1230
+    },
+    {
+      "epoch": 0.311479527756845,
+      "grad_norm": 29.440743998600162,
+      "learning_rate": 4.033376443459842e-06,
+      "loss": 0.7943,
+      "step": 1240
+    },
+    {
+      "epoch": 0.31399145943230344,
+      "grad_norm": 12.995722305307849,
+      "learning_rate": 4.017259662510613e-06,
+      "loss": 0.8954,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3165033911077619,
+      "grad_norm": 16.98906364726587,
+      "learning_rate": 4.00104242977649e-06,
+      "loss": 0.7972,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3190153227832203,
+      "grad_norm": 17.6927776404821,
+      "learning_rate": 3.9847258189365664e-06,
+      "loss": 0.8581,
+      "step": 1270
+    },
+    {
+      "epoch": 0.32152725445867875,
+      "grad_norm": 9.28077592066664,
+      "learning_rate": 3.968310910249364e-06,
+      "loss": 0.8417,
+      "step": 1280
+    },
+    {
+      "epoch": 0.3240391861341371,
+      "grad_norm": 26.108357627107726,
+      "learning_rate": 3.951798790481318e-06,
+      "loss": 0.8331,
+      "step": 1290
+    },
+    {
+      "epoch": 0.32655111780959556,
+      "grad_norm": 22.27977095042067,
+      "learning_rate": 3.9351905528348285e-06,
+      "loss": 0.809,
+      "step": 1300
+    },
+    {
+      "epoch": 0.329063049485054,
+      "grad_norm": 26.195187018877128,
+      "learning_rate": 3.918487296875881e-06,
+      "loss": 0.8115,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3315749811605124,
+      "grad_norm": 8.981062790137392,
+      "learning_rate": 3.901690128461248e-06,
+      "loss": 0.8126,
+      "step": 1320
+    },
+    {
+      "epoch": 0.33408691283597086,
+      "grad_norm": 12.190142909378212,
+      "learning_rate": 3.8848001596652765e-06,
+      "loss": 0.847,
+      "step": 1330
+    },
+    {
+      "epoch": 0.3365988445114293,
+      "grad_norm": 14.289070322541887,
+      "learning_rate": 3.867818508706261e-06,
+      "loss": 0.9118,
+      "step": 1340
+    },
+    {
+      "epoch": 0.33911077618688773,
+      "grad_norm": 20.52257104242371,
+      "learning_rate": 3.850746299872412e-06,
+      "loss": 0.8079,
+      "step": 1350
+    },
+    {
+      "epoch": 0.34162270786234616,
+      "grad_norm": 9.860716436817095,
+      "learning_rate": 3.833584663447418e-06,
+      "loss": 0.7781,
+      "step": 1360
+    },
+    {
+      "epoch": 0.3441346395378046,
+      "grad_norm": 22.728194106614687,
+      "learning_rate": 3.816334735635618e-06,
+      "loss": 0.7898,
+      "step": 1370
+    },
+    {
+      "epoch": 0.346646571213263,
+      "grad_norm": 11.06707256166425,
+      "learning_rate": 3.7989976584867743e-06,
+      "loss": 0.8269,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3491585028887214,
+      "grad_norm": 16.528387975809682,
+      "learning_rate": 3.7815745798204646e-06,
+      "loss": 0.7337,
+      "step": 1390
+    },
+    {
+      "epoch": 0.35167043456417985,
+      "grad_norm": 17.419842160012934,
+      "learning_rate": 3.7640666531500868e-06,
+      "loss": 0.8245,
+      "step": 1400
+    },
+    {
+      "epoch": 0.3541823662396383,
+      "grad_norm": 11.662746289809721,
+      "learning_rate": 3.7464750376064934e-06,
+      "loss": 0.7479,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3566942979150967,
+      "grad_norm": 10.055941346241807,
+      "learning_rate": 3.7288008978612457e-06,
+      "loss": 0.752,
+      "step": 1420
+    },
+    {
+      "epoch": 0.35920622959055515,
+      "grad_norm": 9.970709148074596,
+      "learning_rate": 3.711045404049507e-06,
+      "loss": 0.7915,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3617181612660136,
+      "grad_norm": 13.613528995924305,
+      "learning_rate": 3.693209731692573e-06,
+      "loss": 0.8025,
+      "step": 1440
+    },
+    {
+      "epoch": 0.364230092941472,
+      "grad_norm": 12.956565795874571,
+      "learning_rate": 3.675295061620047e-06,
+      "loss": 0.864,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3667420246169304,
+      "grad_norm": 11.532047927745776,
+      "learning_rate": 3.6573025798916566e-06,
+      "loss": 0.8479,
+      "step": 1460
+    },
+    {
+      "epoch": 0.36925395629238883,
+      "grad_norm": 7.676884255386899,
+      "learning_rate": 3.6392334777187354e-06,
+      "loss": 0.7574,
+      "step": 1470
+    },
+    {
+      "epoch": 0.37176588796784726,
+      "grad_norm": 14.55513552978451,
+      "learning_rate": 3.621088951385353e-06,
+      "loss": 0.8758,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3742778196433057,
+      "grad_norm": 9.00576341192229,
+      "learning_rate": 3.6028702021691164e-06,
+      "loss": 0.8539,
+      "step": 1490
+    },
+    {
+      "epoch": 0.37678975131876413,
+      "grad_norm": 16.629700582969903,
+      "learning_rate": 3.5845784362616375e-06,
+      "loss": 0.8677,
+      "step": 1500
+    },
+    {
+      "epoch": 0.37930168299422257,
+      "grad_norm": 15.58729229875228,
+      "learning_rate": 3.566214864688674e-06,
+      "loss": 0.8108,
+      "step": 1510
+    },
+    {
+      "epoch": 0.381813614669681,
+      "grad_norm": 8.109973150767999,
+      "learning_rate": 3.5477807032299565e-06,
+      "loss": 0.7806,
+      "step": 1520
+    },
+    {
+      "epoch": 0.38432554634513943,
+      "grad_norm": 358.6548735693993,
+      "learning_rate": 3.5292771723386916e-06,
+      "loss": 0.7545,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3868374780205978,
+      "grad_norm": 15.689015148432157,
+      "learning_rate": 3.5107054970607624e-06,
+      "loss": 0.7804,
+      "step": 1540
+    },
+    {
+      "epoch": 0.38934940969605625,
+      "grad_norm": 17.369780867530082,
+      "learning_rate": 3.4920669069536265e-06,
+      "loss": 0.8063,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3918613413715147,
+      "grad_norm": 13.55904293487558,
+      "learning_rate": 3.4733626360049065e-06,
+      "loss": 0.8116,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3943732730469731,
+      "grad_norm": 17.985632267568405,
+      "learning_rate": 3.4545939225506935e-06,
+      "loss": 0.8476,
+      "step": 1570
+    },
+    {
+      "epoch": 0.39688520472243155,
+      "grad_norm": 9.223471964630404,
+      "learning_rate": 3.4357620091935656e-06,
+      "loss": 0.8083,
+      "step": 1580
+    },
+    {
+      "epoch": 0.39939713639789,
+      "grad_norm": 13.127573945038847,
+      "learning_rate": 3.416868142720316e-06,
+      "loss": 0.7692,
+      "step": 1590
+    },
+    {
+      "epoch": 0.4019090680733484,
+      "grad_norm": 19.166047696842995,
+      "learning_rate": 3.39791357401941e-06,
+      "loss": 0.7629,
+      "step": 1600
+    },
+    {
+      "epoch": 0.40442099974880685,
+      "grad_norm": 19.073085938227123,
+      "learning_rate": 3.3788995579981694e-06,
+      "loss": 0.766,
+      "step": 1610
+    },
+    {
+      "epoch": 0.4069329314242653,
+      "grad_norm": 9.814868220725515,
+      "learning_rate": 3.359827353499685e-06,
+      "loss": 0.7389,
+      "step": 1620
+    },
+    {
+      "epoch": 0.40944486309972367,
+      "grad_norm": 14.28370461119568,
+      "learning_rate": 3.340698223219484e-06,
+      "loss": 0.7524,
+      "step": 1630
+    },
+    {
+      "epoch": 0.4119567947751821,
+      "grad_norm": 16.466934303359782,
+      "learning_rate": 3.321513433621919e-06,
+      "loss": 0.6399,
+      "step": 1640
+    },
+    {
+      "epoch": 0.41446872645064053,
+      "grad_norm": 12.585855025691094,
+      "learning_rate": 3.3022742548563293e-06,
+      "loss": 0.8027,
+      "step": 1650
+    },
+    {
+      "epoch": 0.41698065812609897,
+      "grad_norm": 15.17112518560438,
+      "learning_rate": 3.282981960672948e-06,
+      "loss": 0.7372,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4194925898015574,
+      "grad_norm": 10.1925592126811,
+      "learning_rate": 3.2636378283385684e-06,
+      "loss": 0.6634,
+      "step": 1670
+    },
+    {
+      "epoch": 0.42200452147701584,
+      "grad_norm": 8.90929028765655,
+      "learning_rate": 3.2442431385519853e-06,
+      "loss": 0.7982,
+      "step": 1680
+    },
+    {
+      "epoch": 0.42451645315247427,
+      "grad_norm": 9.557908478822391,
+      "learning_rate": 3.2247991753592018e-06,
+      "loss": 0.7691,
+      "step": 1690
+    },
+    {
+      "epoch": 0.4270283848279327,
+      "grad_norm": 9.664514055810029,
+      "learning_rate": 3.2053072260684206e-06,
+      "loss": 0.6568,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4295403165033911,
+      "grad_norm": 19.011017141741334,
+      "learning_rate": 3.1857685811648143e-06,
+      "loss": 0.7778,
+      "step": 1710
+    },
+    {
+      "epoch": 0.4320522481788495,
+      "grad_norm": 22.150881397515466,
+      "learning_rate": 3.1661845342250874e-06,
+      "loss": 0.7075,
+      "step": 1720
+    },
+    {
+      "epoch": 0.43456417985430795,
+      "grad_norm": 10.679435211952306,
+      "learning_rate": 3.1465563818318356e-06,
+      "loss": 0.7504,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4370761115297664,
+      "grad_norm": 14.675829901709204,
+      "learning_rate": 3.1268854234877023e-06,
+      "loss": 0.785,
+      "step": 1740
+    },
+    {
+      "epoch": 0.4395880432052248,
+      "grad_norm": 14.060363356585295,
+      "learning_rate": 3.107172961529343e-06,
+      "loss": 0.6944,
+      "step": 1750
+    },
+    {
+      "epoch": 0.44209997488068326,
+      "grad_norm": 19.971130673134304,
+      "learning_rate": 3.0874203010412057e-06,
+      "loss": 0.8689,
+      "step": 1760
+    },
+    {
+      "epoch": 0.4446119065561417,
+      "grad_norm": 12.429787369780517,
+      "learning_rate": 3.067628749769125e-06,
+      "loss": 0.7491,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4471238382316001,
+      "grad_norm": 19.264474676183987,
+      "learning_rate": 3.047799618033739e-06,
+      "loss": 0.7187,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4496357699070585,
+      "grad_norm": 15.711992128592648,
+      "learning_rate": 3.027934218643742e-06,
+      "loss": 0.8347,
+      "step": 1790
+    },
+    {
+      "epoch": 0.45214770158251694,
+      "grad_norm": 14.747778190305047,
+      "learning_rate": 3.008033866808967e-06,
+      "loss": 0.7629,
+      "step": 1800
+    },
+    {
+      "epoch": 0.45465963325797537,
+      "grad_norm": 142.02157763927625,
+      "learning_rate": 2.9880998800533095e-06,
+      "loss": 0.7364,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4571715649334338,
+      "grad_norm": 9.208553308254146,
+      "learning_rate": 2.968133578127501e-06,
+      "loss": 0.732,
+      "step": 1820
+    },
+    {
+      "epoch": 0.45968349660889224,
+      "grad_norm": 18.199275383195122,
+      "learning_rate": 2.9481362829217335e-06,
+      "loss": 0.7407,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4621954282843507,
+      "grad_norm": 54.93632766069859,
+      "learning_rate": 2.9281093183781406e-06,
+      "loss": 0.7108,
+      "step": 1840
+    },
+    {
+      "epoch": 0.4647073599598091,
+      "grad_norm": 12.509038784283435,
+      "learning_rate": 2.9080540104031487e-06,
+      "loss": 0.7655,
+      "step": 1850
+    },
+    {
+      "epoch": 0.46721929163526754,
+      "grad_norm": 155.54741969346532,
+      "learning_rate": 2.887971686779688e-06,
+      "loss": 0.776,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4697312233107259,
+      "grad_norm": 56.47645825280525,
+      "learning_rate": 2.8678636770792907e-06,
+      "loss": 0.7276,
+      "step": 1870
+    },
+    {
+      "epoch": 0.47224315498618435,
+      "grad_norm": 6.543567900761877,
+      "learning_rate": 2.847731312574061e-06,
+      "loss": 0.7735,
+      "step": 1880
+    },
+    {
+      "epoch": 0.4747550866616428,
+      "grad_norm": 23.264756777925705,
+      "learning_rate": 2.8275759261485407e-06,
+      "loss": 0.7229,
+      "step": 1890
+    },
+    {
+      "epoch": 0.4772670183371012,
+      "grad_norm": 44.93214806726316,
+      "learning_rate": 2.80739885221146e-06,
+      "loss": 0.6674,
+      "step": 1900
+    },
+    {
+      "epoch": 0.47977895001255966,
+      "grad_norm": 25.84745154307416,
+      "learning_rate": 2.7872014266073972e-06,
+      "loss": 0.7193,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4822908816880181,
+      "grad_norm": 7.344615993536025,
+      "learning_rate": 2.7669849865283303e-06,
+      "loss": 0.7117,
+      "step": 1920
+    },
+    {
+      "epoch": 0.4848028133634765,
+      "grad_norm": 9.51062651511805,
+      "learning_rate": 2.746750870425114e-06,
+      "loss": 0.6812,
+      "step": 1930
+    },
+    {
+      "epoch": 0.48731474503893496,
+      "grad_norm": 28.929115729401307,
+      "learning_rate": 2.7265004179188607e-06,
+      "loss": 0.7467,
+      "step": 1940
+    },
+    {
+      "epoch": 0.4898266767143934,
+      "grad_norm": 41.88957977789014,
+      "learning_rate": 2.7062349697122536e-06,
+      "loss": 0.7923,
+      "step": 1950
+    },
+    {
+      "epoch": 0.4923386083898518,
+      "grad_norm": 47.80850971743806,
+      "learning_rate": 2.68595586750078e-06,
+      "loss": 0.7642,
+      "step": 1960
+    },
+    {
+      "epoch": 0.4948505400653102,
+      "grad_norm": 16.86335348359801,
+      "learning_rate": 2.665664453883907e-06,
+      "loss": 0.7609,
+      "step": 1970
+    },
+    {
+      "epoch": 0.49736247174076864,
+      "grad_norm": 68.10748645404419,
+      "learning_rate": 2.6453620722761897e-06,
+      "loss": 0.7434,
+      "step": 1980
+    },
+    {
+      "epoch": 0.4998744034162271,
+      "grad_norm": 16.352566165282152,
+      "learning_rate": 2.6250500668183325e-06,
+      "loss": 0.7735,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5023863350916855,
+      "grad_norm": 22.634772722575875,
+      "learning_rate": 2.6047297822881962e-06,
+      "loss": 0.7574,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5048982667671439,
+      "grad_norm": 18.64929243189173,
+      "learning_rate": 2.5844025640117655e-06,
+      "loss": 0.6732,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5074101984426024,
+      "grad_norm": 103.03687825558029,
+      "learning_rate": 2.564069757774082e-06,
+      "loss": 0.7944,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5099221301180608,
+      "grad_norm": 21.400257542565846,
+      "learning_rate": 2.5437327097301435e-06,
+      "loss": 0.765,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5124340617935192,
+      "grad_norm": 18.698921151360036,
+      "learning_rate": 2.5233927663157833e-06,
+      "loss": 0.6306,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5149459934689776,
+      "grad_norm": 21.046075973315375,
+      "learning_rate": 2.503051274158522e-06,
+      "loss": 0.68,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5174579251444361,
+      "grad_norm": 14.45304409664666,
+      "learning_rate": 2.4827095799884198e-06,
+      "loss": 0.6982,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5199698568198945,
+      "grad_norm": 17.001820758958978,
+      "learning_rate": 2.462369030548909e-06,
+      "loss": 0.8556,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5224817884953529,
+      "grad_norm": 17.39879838977829,
+      "learning_rate": 2.4420309725076364e-06,
+      "loss": 0.6847,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5249937201708114,
+      "grad_norm": 14.168679428393196,
+      "learning_rate": 2.4216967523673e-06,
+      "loss": 0.7197,
+      "step": 2090
+    },
+    {
+      "epoch": 0.5275056518462697,
+      "grad_norm": 84.65981735799092,
+      "learning_rate": 2.401367716376507e-06,
+      "loss": 0.7331,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5300175835217282,
+      "grad_norm": 16.371864478269647,
+      "learning_rate": 2.3810452104406444e-06,
+      "loss": 0.7602,
+      "step": 2110
+    },
+    {
+      "epoch": 0.5325295151971866,
+      "grad_norm": 32.40261645428156,
+      "learning_rate": 2.3607305800327663e-06,
+      "loss": 0.8223,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5350414468726451,
+      "grad_norm": 13.739845889729931,
+      "learning_rate": 2.3404251701045223e-06,
+      "loss": 0.7079,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5375533785481035,
+      "grad_norm": 18.92459341552145,
+      "learning_rate": 2.3201303249971068e-06,
+      "loss": 0.7048,
+      "step": 2140
+    },
+    {
+      "epoch": 0.540065310223562,
+      "grad_norm": 16.87005308083678,
+      "learning_rate": 2.2998473883522644e-06,
+      "loss": 0.7165,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5425772418990203,
+      "grad_norm": 18.306555104449767,
+      "learning_rate": 2.2795777030233212e-06,
+      "loss": 0.7554,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5450891735744787,
+      "grad_norm": 14.227807590995358,
+      "learning_rate": 2.2593226109862896e-06,
+      "loss": 0.7514,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5476011052499372,
+      "grad_norm": 14.475257084233705,
+      "learning_rate": 2.239083453251019e-06,
+      "loss": 0.6911,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5501130369253956,
+      "grad_norm": 64.27770237736819,
+      "learning_rate": 2.2188615697724063e-06,
+      "loss": 0.7111,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5526249686008541,
+      "grad_norm": 14.823545470496894,
+      "learning_rate": 2.1986582993616926e-06,
+      "loss": 0.725,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5551369002763125,
+      "grad_norm": 29.236578558465343,
+      "learning_rate": 2.1784749795978193e-06,
+      "loss": 0.8391,
+      "step": 2210
+    },
+    {
+      "epoch": 0.557648831951771,
+      "grad_norm": 18.47114122523338,
+      "learning_rate": 2.1583129467388744e-06,
+      "loss": 0.7775,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5601607636272293,
+      "grad_norm": 13.359354179078316,
+      "learning_rate": 2.1381735356336225e-06,
+      "loss": 0.6873,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5626726953026878,
+      "grad_norm": 10.429843248526154,
+      "learning_rate": 2.1180580796331327e-06,
+      "loss": 0.7348,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5651846269781462,
+      "grad_norm": 23.94413986455692,
+      "learning_rate": 2.0979679105025014e-06,
+      "loss": 0.7535,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5676965586536046,
+      "grad_norm": 30.160894670824923,
+      "learning_rate": 2.077904358332678e-06,
+      "loss": 0.718,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5702084903290631,
+      "grad_norm": 42.43264507340181,
+      "learning_rate": 2.057868751452412e-06,
+      "loss": 0.7673,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5727204220045214,
+      "grad_norm": 17.470151949777193,
+      "learning_rate": 2.037862416340301e-06,
+      "loss": 0.6433,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5752323536799799,
+      "grad_norm": 28.93786786763041,
+      "learning_rate": 2.017886677536978e-06,
+      "loss": 0.7478,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5777442853554383,
+      "grad_norm": 15.653037877763948,
+      "learning_rate": 1.9979428575574115e-06,
+      "loss": 0.6457,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5802562170308968,
+      "grad_norm": 23.646097903363735,
+      "learning_rate": 1.978032276803354e-06,
+      "loss": 0.6778,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5827681487063552,
+      "grad_norm": 16.166528067183386,
+      "learning_rate": 1.958156253475916e-06,
+      "loss": 0.6919,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5852800803818136,
+      "grad_norm": 266.2133506781252,
+      "learning_rate": 1.9383161034883e-06,
+      "loss": 0.6417,
+      "step": 2330
+    },
+    {
+      "epoch": 0.587792012057272,
+      "grad_norm": 21.22097274883877,
+      "learning_rate": 1.9185131403786756e-06,
+      "loss": 0.6776,
+      "step": 2340
+    },
+    {
+      "epoch": 0.5903039437327304,
+      "grad_norm": 26.540378072909732,
+      "learning_rate": 1.8987486752232122e-06,
+      "loss": 0.6354,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5928158754081889,
+      "grad_norm": 16.861677195668356,
+      "learning_rate": 1.8790240165492882e-06,
+      "loss": 0.6343,
+      "step": 2360
+    },
+    {
+      "epoch": 0.5953278070836473,
+      "grad_norm": 10.924517829655493,
+      "learning_rate": 1.8593404702488439e-06,
+      "loss": 0.6621,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5978397387591058,
+      "grad_norm": 20.003687067129864,
+      "learning_rate": 1.8396993394919372e-06,
+      "loss": 0.8224,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6003516704345642,
+      "grad_norm": 60.097614071661454,
+      "learning_rate": 1.8201019246404562e-06,
+      "loss": 0.8186,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6028636021100227,
+      "grad_norm": 46.56417436666313,
+      "learning_rate": 1.8005495231620335e-06,
+      "loss": 0.7522,
+      "step": 2400
+    },
+    {
+      "epoch": 0.605375533785481,
+      "grad_norm": 21.096851786334234,
+      "learning_rate": 1.7810434295441434e-06,
+      "loss": 0.6803,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6078874654609394,
+      "grad_norm": 30.555482100955743,
+      "learning_rate": 1.7615849352083975e-06,
+      "loss": 0.6528,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6103993971363979,
+      "grad_norm": 26.107182660767418,
+      "learning_rate": 1.742175328425048e-06,
+      "loss": 0.7008,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6129113288118563,
+      "grad_norm": 16.07682961665447,
+      "learning_rate": 1.7228158942276942e-06,
+      "loss": 0.7293,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6154232604873148,
+      "grad_norm": 43.740400069003144,
+      "learning_rate": 1.7035079143282068e-06,
+      "loss": 0.7184,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6179351921627732,
+      "grad_norm": 17.348869862460315,
+      "learning_rate": 1.6842526670318688e-06,
+      "loss": 0.6825,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6204471238382316,
+      "grad_norm": 14.75027879094655,
+      "learning_rate": 1.6650514271527468e-06,
+      "loss": 0.7589,
+      "step": 2470
+    },
+    {
+      "epoch": 0.62295905551369,
+      "grad_norm": 53.0580743554731,
+      "learning_rate": 1.6459054659292883e-06,
+      "loss": 0.5771,
+      "step": 2480
+    },
+    {
+      "epoch": 0.6254709871891485,
+      "grad_norm": 22.044102377537943,
+      "learning_rate": 1.6268160509401587e-06,
+      "loss": 0.7446,
+      "step": 2490
+    },
+    {
+      "epoch": 0.6279829188646069,
+      "grad_norm": 18.305070744935684,
+      "learning_rate": 1.6077844460203207e-06,
+      "loss": 0.6455,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3981,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3812193975926784.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d2a0d769c28e6441e0071503590420a9232b917059a99cc343356913ed0ce06
+size 7992

zero_to_fp32.py

@@ -0,0 +1,758 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:
+            shared_tensor = state_dict[converted_tensors[tensor_id]]
+            state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                state_dict[name] = tensor.contiguous()
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in shard_state_dict:
+            del state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)