Upload folder using huggingface_hub

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

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,132 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "float32",
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.57.1"
+}

global_step4252/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad578dad128dffdbe1ee56fbba70f0b9415e671e11ebc804c8539cf6f0d5841
+size 49753009707

global_step4252/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec77a787e3e9fe17ae03b3cdfc8ee71e06080293d3c20c7daf0ed64b22f1588
+size 49753009707

global_step4252/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d5bd2fa46d14c6eb2a0dc21520daf1a79b5949703221c8d044307327991216
+size 370830

global_step4252/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec8c4274cdc34e195af87d127f343bfe24ac04c728e93f4e6a40e39671bc1b4
+size 370830

latest

@@ -0,0 +1 @@
+global_step4252

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf12ff3a833c25c61199fb00d7f432529d082e9cd62a6a9cdf2c61ab47ce7f3
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808495368733bd478c205cd2f593c4089381d1f72e1ffa845df7c4e2a71bd357
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da0becd29098c8202778e46056ecf4ffdcbf206b917701154f1a4f7949f4d0d9
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbde0526018dc62f5d5bd452be2d044c3f6a6d972528f599700336cab7f176e8
+size 1691924384

model.safetensors.index.json

@@ -0,0 +1,737 @@
+{
+  "metadata": {
+    "total_parameters": 848896,
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d971eb6abf3febcd9b6caeba54b2cc7b45deea36ce1ee4e746826906a2d1542a
+size 14917

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d120f681115d349dfbbdb1fe1ea4073c32fa0f70434ec433cc5932c8cae722c1
+size 14917

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ce6a9494978cfd7a683fa5f6bba18e567e13dd0f16141f6bcc070664946a7c
+size 1465

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3009 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4252,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023518344308560675,
+      "grad_norm": 116.89811794868847,
+      "learning_rate": 2.1126760563380282e-08,
+      "loss": 1.1517,
+      "step": 10
+    },
+    {
+      "epoch": 0.004703668861712135,
+      "grad_norm": 277.9710155529788,
+      "learning_rate": 4.460093896713615e-08,
+      "loss": 1.2647,
+      "step": 20
+    },
+    {
+      "epoch": 0.0070555032925682035,
+      "grad_norm": 136.25013023553325,
+      "learning_rate": 6.807511737089202e-08,
+      "loss": 1.1512,
+      "step": 30
+    },
+    {
+      "epoch": 0.00940733772342427,
+      "grad_norm": 113.12348827889794,
+      "learning_rate": 9.154929577464789e-08,
+      "loss": 1.0798,
+      "step": 40
+    },
+    {
+      "epoch": 0.011759172154280339,
+      "grad_norm": 116.51120422837609,
+      "learning_rate": 1.1502347417840374e-07,
+      "loss": 1.0682,
+      "step": 50
+    },
+    {
+      "epoch": 0.014111006585136407,
+      "grad_norm": 158.25517802003571,
+      "learning_rate": 1.384976525821596e-07,
+      "loss": 1.0344,
+      "step": 60
+    },
+    {
+      "epoch": 0.016462841015992474,
+      "grad_norm": 100.5101888275114,
+      "learning_rate": 1.619718309859155e-07,
+      "loss": 0.9328,
+      "step": 70
+    },
+    {
+      "epoch": 0.01881467544684854,
+      "grad_norm": 56.20830713816404,
+      "learning_rate": 1.8544600938967138e-07,
+      "loss": 0.8777,
+      "step": 80
+    },
+    {
+      "epoch": 0.02116650987770461,
+      "grad_norm": 240.15395280772944,
+      "learning_rate": 2.089201877934272e-07,
+      "loss": 0.9159,
+      "step": 90
+    },
+    {
+      "epoch": 0.023518344308560677,
+      "grad_norm": 203.37555869337805,
+      "learning_rate": 2.323943661971831e-07,
+      "loss": 0.8656,
+      "step": 100
+    },
+    {
+      "epoch": 0.025870178739416744,
+      "grad_norm": 118.0083364283108,
+      "learning_rate": 2.5586854460093895e-07,
+      "loss": 0.7863,
+      "step": 110
+    },
+    {
+      "epoch": 0.028222013170272814,
+      "grad_norm": 79.77067789322896,
+      "learning_rate": 2.7934272300469483e-07,
+      "loss": 0.8134,
+      "step": 120
+    },
+    {
+      "epoch": 0.03057384760112888,
+      "grad_norm": 267.7680667397846,
+      "learning_rate": 3.0281690140845066e-07,
+      "loss": 0.7945,
+      "step": 130
+    },
+    {
+      "epoch": 0.03292568203198495,
+      "grad_norm": 189.00926278298175,
+      "learning_rate": 3.2629107981220654e-07,
+      "loss": 0.8096,
+      "step": 140
+    },
+    {
+      "epoch": 0.03527751646284102,
+      "grad_norm": 57.70972405124874,
+      "learning_rate": 3.497652582159624e-07,
+      "loss": 0.7752,
+      "step": 150
+    },
+    {
+      "epoch": 0.03762935089369708,
+      "grad_norm": 69.99759640153404,
+      "learning_rate": 3.732394366197183e-07,
+      "loss": 0.7083,
+      "step": 160
+    },
+    {
+      "epoch": 0.03998118532455315,
+      "grad_norm": 8809.659775787271,
+      "learning_rate": 3.967136150234742e-07,
+      "loss": 0.748,
+      "step": 170
+    },
+    {
+      "epoch": 0.04233301975540922,
+      "grad_norm": 71.05386775505833,
+      "learning_rate": 4.2018779342723e-07,
+      "loss": 0.7624,
+      "step": 180
+    },
+    {
+      "epoch": 0.044684854186265284,
+      "grad_norm": 35.37716956890071,
+      "learning_rate": 4.436619718309859e-07,
+      "loss": 0.751,
+      "step": 190
+    },
+    {
+      "epoch": 0.047036688617121354,
+      "grad_norm": 80.85891409276856,
+      "learning_rate": 4.671361502347418e-07,
+      "loss": 0.7739,
+      "step": 200
+    },
+    {
+      "epoch": 0.049388523047977424,
+      "grad_norm": 45.92516752004636,
+      "learning_rate": 4.906103286384976e-07,
+      "loss": 0.7545,
+      "step": 210
+    },
+    {
+      "epoch": 0.05174035747883349,
+      "grad_norm": 68.60575847289506,
+      "learning_rate": 5.140845070422535e-07,
+      "loss": 0.726,
+      "step": 220
+    },
+    {
+      "epoch": 0.05409219190968956,
+      "grad_norm": 442.4046356251326,
+      "learning_rate": 5.375586854460093e-07,
+      "loss": 0.7692,
+      "step": 230
+    },
+    {
+      "epoch": 0.05644402634054563,
+      "grad_norm": 148.22276704875333,
+      "learning_rate": 5.610328638497653e-07,
+      "loss": 0.7193,
+      "step": 240
+    },
+    {
+      "epoch": 0.05879586077140169,
+      "grad_norm": 121.42536705157094,
+      "learning_rate": 5.845070422535211e-07,
+      "loss": 0.7235,
+      "step": 250
+    },
+    {
+      "epoch": 0.06114769520225776,
+      "grad_norm": 57.2265048995909,
+      "learning_rate": 6.079812206572769e-07,
+      "loss": 0.749,
+      "step": 260
+    },
+    {
+      "epoch": 0.06349952963311382,
+      "grad_norm": 142.6135442328223,
+      "learning_rate": 6.314553990610329e-07,
+      "loss": 0.677,
+      "step": 270
+    },
+    {
+      "epoch": 0.0658513640639699,
+      "grad_norm": 66.8189535712452,
+      "learning_rate": 6.549295774647887e-07,
+      "loss": 0.7162,
+      "step": 280
+    },
+    {
+      "epoch": 0.06820319849482596,
+      "grad_norm": 47.59798393227095,
+      "learning_rate": 6.784037558685446e-07,
+      "loss": 0.7246,
+      "step": 290
+    },
+    {
+      "epoch": 0.07055503292568203,
+      "grad_norm": 201.28699484373632,
+      "learning_rate": 7.018779342723005e-07,
+      "loss": 0.6994,
+      "step": 300
+    },
+    {
+      "epoch": 0.0729068673565381,
+      "grad_norm": 236.38896159577624,
+      "learning_rate": 7.253521126760564e-07,
+      "loss": 0.6451,
+      "step": 310
+    },
+    {
+      "epoch": 0.07525870178739416,
+      "grad_norm": 162.15190996547886,
+      "learning_rate": 7.488262910798122e-07,
+      "loss": 0.6597,
+      "step": 320
+    },
+    {
+      "epoch": 0.07761053621825023,
+      "grad_norm": 56.18228731138108,
+      "learning_rate": 7.72300469483568e-07,
+      "loss": 0.6914,
+      "step": 330
+    },
+    {
+      "epoch": 0.0799623706491063,
+      "grad_norm": 324.865693829362,
+      "learning_rate": 7.95774647887324e-07,
+      "loss": 0.6758,
+      "step": 340
+    },
+    {
+      "epoch": 0.08231420507996237,
+      "grad_norm": 137.83272350854858,
+      "learning_rate": 8.192488262910797e-07,
+      "loss": 0.6552,
+      "step": 350
+    },
+    {
+      "epoch": 0.08466603951081844,
+      "grad_norm": 51.74661746915652,
+      "learning_rate": 8.427230046948356e-07,
+      "loss": 0.6257,
+      "step": 360
+    },
+    {
+      "epoch": 0.08701787394167451,
+      "grad_norm": 94.85986008371302,
+      "learning_rate": 8.661971830985915e-07,
+      "loss": 0.6168,
+      "step": 370
+    },
+    {
+      "epoch": 0.08936970837253057,
+      "grad_norm": 83.03153262845805,
+      "learning_rate": 8.896713615023473e-07,
+      "loss": 0.6406,
+      "step": 380
+    },
+    {
+      "epoch": 0.09172154280338664,
+      "grad_norm": 295.36784847538064,
+      "learning_rate": 9.131455399061032e-07,
+      "loss": 0.6493,
+      "step": 390
+    },
+    {
+      "epoch": 0.09407337723424271,
+      "grad_norm": 87.86096387558246,
+      "learning_rate": 9.366197183098591e-07,
+      "loss": 0.6093,
+      "step": 400
+    },
+    {
+      "epoch": 0.09642521166509878,
+      "grad_norm": 55.21521035928988,
+      "learning_rate": 9.60093896713615e-07,
+      "loss": 0.681,
+      "step": 410
+    },
+    {
+      "epoch": 0.09877704609595485,
+      "grad_norm": 149.75943970393467,
+      "learning_rate": 9.83568075117371e-07,
+      "loss": 0.6635,
+      "step": 420
+    },
+    {
+      "epoch": 0.10112888052681092,
+      "grad_norm": 96.72986417277598,
+      "learning_rate": 9.999984829771844e-07,
+      "loss": 0.6782,
+      "step": 430
+    },
+    {
+      "epoch": 0.10348071495766697,
+      "grad_norm": 42.184520996896104,
+      "learning_rate": 9.999715139387692e-07,
+      "loss": 0.6748,
+      "step": 440
+    },
+    {
+      "epoch": 0.10583254938852305,
+      "grad_norm": 93.47313883617879,
+      "learning_rate": 9.99910835375207e-07,
+      "loss": 0.6883,
+      "step": 450
+    },
+    {
+      "epoch": 0.10818438381937912,
+      "grad_norm": 51.181550134553135,
+      "learning_rate": 9.99816451377622e-07,
+      "loss": 0.6567,
+      "step": 460
+    },
+    {
+      "epoch": 0.11053621825023519,
+      "grad_norm": 88.52012869382804,
+      "learning_rate": 9.996883683096559e-07,
+      "loss": 0.6579,
+      "step": 470
+    },
+    {
+      "epoch": 0.11288805268109126,
+      "grad_norm": 56.48549654574926,
+      "learning_rate": 9.995265948070397e-07,
+      "loss": 0.6076,
+      "step": 480
+    },
+    {
+      "epoch": 0.11523988711194733,
+      "grad_norm": 50.9131497233012,
+      "learning_rate": 9.99331141777011e-07,
+      "loss": 0.5999,
+      "step": 490
+    },
+    {
+      "epoch": 0.11759172154280338,
+      "grad_norm": 70.73723550031531,
+      "learning_rate": 9.991020223975778e-07,
+      "loss": 0.63,
+      "step": 500
+    },
+    {
+      "epoch": 0.11994355597365945,
+      "grad_norm": 88.64709002603719,
+      "learning_rate": 9.988392521166315e-07,
+      "loss": 0.6039,
+      "step": 510
+    },
+    {
+      "epoch": 0.12229539040451552,
+      "grad_norm": 75.39690510928469,
+      "learning_rate": 9.98542848650904e-07,
+      "loss": 0.586,
+      "step": 520
+    },
+    {
+      "epoch": 0.12464722483537159,
+      "grad_norm": 113.20042490187971,
+      "learning_rate": 9.98212831984774e-07,
+      "loss": 0.5865,
+      "step": 530
+    },
+    {
+      "epoch": 0.12699905926622765,
+      "grad_norm": 94.68667178533609,
+      "learning_rate": 9.978492243689197e-07,
+      "loss": 0.6069,
+      "step": 540
+    },
+    {
+      "epoch": 0.12935089369708372,
+      "grad_norm": 34.52540469666706,
+      "learning_rate": 9.974520503188178e-07,
+      "loss": 0.6206,
+      "step": 550
+    },
+    {
+      "epoch": 0.1317027281279398,
+      "grad_norm": 117.14521192427702,
+      "learning_rate": 9.970213366130908e-07,
+      "loss": 0.6274,
+      "step": 560
+    },
+    {
+      "epoch": 0.13405456255879586,
+      "grad_norm": 53.776543081710706,
+      "learning_rate": 9.965571122917027e-07,
+      "loss": 0.6426,
+      "step": 570
+    },
+    {
+      "epoch": 0.13640639698965193,
+      "grad_norm": 124.09156480152814,
+      "learning_rate": 9.960594086539992e-07,
+      "loss": 0.6068,
+      "step": 580
+    },
+    {
+      "epoch": 0.138758231420508,
+      "grad_norm": 58.91257394960272,
+      "learning_rate": 9.95528259256599e-07,
+      "loss": 0.6136,
+      "step": 590
+    },
+    {
+      "epoch": 0.14111006585136407,
+      "grad_norm": 44.14364925959302,
+      "learning_rate": 9.949636999111302e-07,
+      "loss": 0.6182,
+      "step": 600
+    },
+    {
+      "epoch": 0.14346190028222014,
+      "grad_norm": 102.41392308653452,
+      "learning_rate": 9.94365768681816e-07,
+      "loss": 0.5759,
+      "step": 610
+    },
+    {
+      "epoch": 0.1458137347130762,
+      "grad_norm": 105.69613721621276,
+      "learning_rate": 9.937345058829093e-07,
+      "loss": 0.5786,
+      "step": 620
+    },
+    {
+      "epoch": 0.14816556914393228,
+      "grad_norm": 38.98828708919228,
+      "learning_rate": 9.930699540759728e-07,
+      "loss": 0.6084,
+      "step": 630
+    },
+    {
+      "epoch": 0.15051740357478832,
+      "grad_norm": 354.4940196727006,
+      "learning_rate": 9.923721580670113e-07,
+      "loss": 0.5689,
+      "step": 640
+    },
+    {
+      "epoch": 0.1528692380056444,
+      "grad_norm": 153.95231269118221,
+      "learning_rate": 9.916411649034491e-07,
+      "loss": 0.5657,
+      "step": 650
+    },
+    {
+      "epoch": 0.15522107243650046,
+      "grad_norm": 928.564170107045,
+      "learning_rate": 9.908770238709592e-07,
+      "loss": 0.6084,
+      "step": 660
+    },
+    {
+      "epoch": 0.15757290686735653,
+      "grad_norm": 92.12341812343223,
+      "learning_rate": 9.900797864901394e-07,
+      "loss": 0.5847,
+      "step": 670
+    },
+    {
+      "epoch": 0.1599247412982126,
+      "grad_norm": 50.21703372463601,
+      "learning_rate": 9.892495065130394e-07,
+      "loss": 0.6206,
+      "step": 680
+    },
+    {
+      "epoch": 0.16227657572906867,
+      "grad_norm": 38.305107297666325,
+      "learning_rate": 9.883862399195357e-07,
+      "loss": 0.6206,
+      "step": 690
+    },
+    {
+      "epoch": 0.16462841015992474,
+      "grad_norm": 105.72112815211388,
+      "learning_rate": 9.874900449135582e-07,
+      "loss": 0.5821,
+      "step": 700
+    },
+    {
+      "epoch": 0.1669802445907808,
+      "grad_norm": 162.13055243234115,
+      "learning_rate": 9.865609819191659e-07,
+      "loss": 0.5742,
+      "step": 710
+    },
+    {
+      "epoch": 0.16933207902163688,
+      "grad_norm": 58.70026610582205,
+      "learning_rate": 9.855991135764718e-07,
+      "loss": 0.547,
+      "step": 720
+    },
+    {
+      "epoch": 0.17168391345249295,
+      "grad_norm": 100.43914638169913,
+      "learning_rate": 9.846045047374215e-07,
+      "loss": 0.5794,
+      "step": 730
+    },
+    {
+      "epoch": 0.17403574788334902,
+      "grad_norm": 139.51085792167504,
+      "learning_rate": 9.83577222461418e-07,
+      "loss": 0.5835,
+      "step": 740
+    },
+    {
+      "epoch": 0.1763875823142051,
+      "grad_norm": 91.55902670992894,
+      "learning_rate": 9.825173360108034e-07,
+      "loss": 0.568,
+      "step": 750
+    },
+    {
+      "epoch": 0.17873941674506114,
+      "grad_norm": 49.09585389161329,
+      "learning_rate": 9.814249168461868e-07,
+      "loss": 0.5416,
+      "step": 760
+    },
+    {
+      "epoch": 0.1810912511759172,
+      "grad_norm": 39.30524914731049,
+      "learning_rate": 9.80300038621627e-07,
+      "loss": 0.5974,
+      "step": 770
+    },
+    {
+      "epoch": 0.18344308560677328,
+      "grad_norm": 437.03477978317704,
+      "learning_rate": 9.79142777179666e-07,
+      "loss": 0.614,
+      "step": 780
+    },
+    {
+      "epoch": 0.18579492003762935,
+      "grad_norm": 113.50973293517667,
+      "learning_rate": 9.779532105462173e-07,
+      "loss": 0.5798,
+      "step": 790
+    },
+    {
+      "epoch": 0.18814675446848542,
+      "grad_norm": 310.99758984616733,
+      "learning_rate": 9.767314189253023e-07,
+      "loss": 0.5609,
+      "step": 800
+    },
+    {
+      "epoch": 0.1904985888993415,
+      "grad_norm": 78.52431684901823,
+      "learning_rate": 9.754774846936455e-07,
+      "loss": 0.582,
+      "step": 810
+    },
+    {
+      "epoch": 0.19285042333019756,
+      "grad_norm": 34.79880147456029,
+      "learning_rate": 9.74191492395118e-07,
+      "loss": 0.5538,
+      "step": 820
+    },
+    {
+      "epoch": 0.19520225776105363,
+      "grad_norm": 48.17636180244228,
+      "learning_rate": 9.728735287350395e-07,
+      "loss": 0.5686,
+      "step": 830
+    },
+    {
+      "epoch": 0.1975540921919097,
+      "grad_norm": 222.11427267611163,
+      "learning_rate": 9.715236825743306e-07,
+      "loss": 0.5695,
+      "step": 840
+    },
+    {
+      "epoch": 0.19990592662276577,
+      "grad_norm": 163.48188564313824,
+      "learning_rate": 9.701420449235224e-07,
+      "loss": 0.5993,
+      "step": 850
+    },
+    {
+      "epoch": 0.20225776105362184,
+      "grad_norm": 180.8729345274767,
+      "learning_rate": 9.687287089366208e-07,
+      "loss": 0.5765,
+      "step": 860
+    },
+    {
+      "epoch": 0.20460959548447788,
+      "grad_norm": 64.88971976462376,
+      "learning_rate": 9.672837699048247e-07,
+      "loss": 0.6076,
+      "step": 870
+    },
+    {
+      "epoch": 0.20696142991533395,
+      "grad_norm": 45.66335791522097,
+      "learning_rate": 9.65807325250101e-07,
+      "loss": 0.5102,
+      "step": 880
+    },
+    {
+      "epoch": 0.20931326434619002,
+      "grad_norm": 69.3940533519506,
+      "learning_rate": 9.642994745186186e-07,
+      "loss": 0.596,
+      "step": 890
+    },
+    {
+      "epoch": 0.2116650987770461,
+      "grad_norm": 90.66599474951411,
+      "learning_rate": 9.627603193740329e-07,
+      "loss": 0.5539,
+      "step": 900
+    },
+    {
+      "epoch": 0.21401693320790216,
+      "grad_norm": 203.88445976449455,
+      "learning_rate": 9.611899635906345e-07,
+      "loss": 0.5494,
+      "step": 910
+    },
+    {
+      "epoch": 0.21636876763875823,
+      "grad_norm": 35.55143547858949,
+      "learning_rate": 9.595885130463512e-07,
+      "loss": 0.5821,
+      "step": 920
+    },
+    {
+      "epoch": 0.2187206020696143,
+      "grad_norm": 135.08153342145144,
+      "learning_rate": 9.579560757156092e-07,
+      "loss": 0.5466,
+      "step": 930
+    },
+    {
+      "epoch": 0.22107243650047037,
+      "grad_norm": 89.381610871162,
+      "learning_rate": 9.562927616620534e-07,
+      "loss": 0.532,
+      "step": 940
+    },
+    {
+      "epoch": 0.22342427093132644,
+      "grad_norm": 178.58317872348456,
+      "learning_rate": 9.545986830311271e-07,
+      "loss": 0.6014,
+      "step": 950
+    },
+    {
+      "epoch": 0.2257761053621825,
+      "grad_norm": 84.70137793347699,
+      "learning_rate": 9.528739540425097e-07,
+      "loss": 0.5751,
+      "step": 960
+    },
+    {
+      "epoch": 0.22812793979303858,
+      "grad_norm": 26.339901114155346,
+      "learning_rate": 9.511186909824171e-07,
+      "loss": 0.5783,
+      "step": 970
+    },
+    {
+      "epoch": 0.23047977422389465,
+      "grad_norm": 67.79506982367464,
+      "learning_rate": 9.493330121957599e-07,
+      "loss": 0.563,
+      "step": 980
+    },
+    {
+      "epoch": 0.2328316086547507,
+      "grad_norm": 119.24074854076687,
+      "learning_rate": 9.475170380781654e-07,
+      "loss": 0.5572,
+      "step": 990
+    },
+    {
+      "epoch": 0.23518344308560676,
+      "grad_norm": 146.1667351412439,
+      "learning_rate": 9.456708910678595e-07,
+      "loss": 0.5367,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23753527751646283,
+      "grad_norm": 88.88690460802079,
+      "learning_rate": 9.437946956374117e-07,
+      "loss": 0.5375,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2398871119473189,
+      "grad_norm": 81.31694958580168,
+      "learning_rate": 9.41888578285343e-07,
+      "loss": 0.5458,
+      "step": 1020
+    },
+    {
+      "epoch": 0.24223894637817497,
+      "grad_norm": 45.5082728792024,
+      "learning_rate": 9.399526675275968e-07,
+      "loss": 0.5648,
+      "step": 1030
+    },
+    {
+      "epoch": 0.24459078080903104,
+      "grad_norm": 54.62994929806069,
+      "learning_rate": 9.379870938888743e-07,
+      "loss": 0.5464,
+      "step": 1040
+    },
+    {
+      "epoch": 0.24694261523988711,
+      "grad_norm": 95.25990550468921,
+      "learning_rate": 9.359919898938336e-07,
+      "loss": 0.5276,
+      "step": 1050
+    },
+    {
+      "epoch": 0.24929444967074318,
+      "grad_norm": 56.86836827412844,
+      "learning_rate": 9.33967490058155e-07,
+      "loss": 0.5037,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2516462841015992,
+      "grad_norm": 263.1519863594519,
+      "learning_rate": 9.319137308794712e-07,
+      "loss": 0.5763,
+      "step": 1070
+    },
+    {
+      "epoch": 0.2539981185324553,
+      "grad_norm": 48.975787835710975,
+      "learning_rate": 9.298308508281645e-07,
+      "loss": 0.5204,
+      "step": 1080
+    },
+    {
+      "epoch": 0.25634995296331137,
+      "grad_norm": 618.5840505320624,
+      "learning_rate": 9.277189903380308e-07,
+      "loss": 0.5375,
+      "step": 1090
+    },
+    {
+      "epoch": 0.25870178739416744,
+      "grad_norm": 113.884112676073,
+      "learning_rate": 9.255782917968107e-07,
+      "loss": 0.568,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2610536218250235,
+      "grad_norm": 385.97433675604555,
+      "learning_rate": 9.234088995365898e-07,
+      "loss": 0.5479,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2634054562558796,
+      "grad_norm": 235.00439426458524,
+      "learning_rate": 9.212109598240669e-07,
+      "loss": 0.5667,
+      "step": 1120
+    },
+    {
+      "epoch": 0.26575729068673565,
+      "grad_norm": 526.3091500577647,
+      "learning_rate": 9.189846208506931e-07,
+      "loss": 0.519,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2681091251175917,
+      "grad_norm": 150.0750656097666,
+      "learning_rate": 9.167300327226794e-07,
+      "loss": 0.4965,
+      "step": 1140
+    },
+    {
+      "epoch": 0.2704609595484478,
+      "grad_norm": 30.016558195777204,
+      "learning_rate": 9.144473474508765e-07,
+      "loss": 0.4756,
+      "step": 1150
+    },
+    {
+      "epoch": 0.27281279397930386,
+      "grad_norm": 60.193732037518764,
+      "learning_rate": 9.12136718940526e-07,
+      "loss": 0.5377,
+      "step": 1160
+    },
+    {
+      "epoch": 0.27516462841015993,
+      "grad_norm": 219.87409938307607,
+      "learning_rate": 9.097983029808831e-07,
+      "loss": 0.5231,
+      "step": 1170
+    },
+    {
+      "epoch": 0.277516462841016,
+      "grad_norm": 691.5188548277733,
+      "learning_rate": 9.074322572347135e-07,
+      "loss": 0.5553,
+      "step": 1180
+    },
+    {
+      "epoch": 0.27986829727187207,
+      "grad_norm": 58.14856175427267,
+      "learning_rate": 9.050387412276628e-07,
+      "loss": 0.5261,
+      "step": 1190
+    },
+    {
+      "epoch": 0.28222013170272814,
+      "grad_norm": 72.18580518142099,
+      "learning_rate": 9.026179163375012e-07,
+      "loss": 0.5083,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2845719661335842,
+      "grad_norm": 48.319128442643155,
+      "learning_rate": 9.001699457832425e-07,
+      "loss": 0.5661,
+      "step": 1210
+    },
+    {
+      "epoch": 0.2869238005644403,
+      "grad_norm": 85.74869777359726,
+      "learning_rate": 8.976949946141399e-07,
+      "loss": 0.5502,
+      "step": 1220
+    },
+    {
+      "epoch": 0.28927563499529635,
+      "grad_norm": 27.470838511127315,
+      "learning_rate": 8.951932296985576e-07,
+      "loss": 0.5194,
+      "step": 1230
+    },
+    {
+      "epoch": 0.2916274694261524,
+      "grad_norm": 103.72100326338919,
+      "learning_rate": 8.926648197127202e-07,
+      "loss": 0.5538,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2939793038570085,
+      "grad_norm": 37.395281219640474,
+      "learning_rate": 8.901099351293397e-07,
+      "loss": 0.5585,
+      "step": 1250
+    },
+    {
+      "epoch": 0.29633113828786456,
+      "grad_norm": 76.92500519691636,
+      "learning_rate": 8.875287482061225e-07,
+      "loss": 0.5556,
+      "step": 1260
+    },
+    {
+      "epoch": 0.29868297271872063,
+      "grad_norm": 115.83402029314064,
+      "learning_rate": 8.849214329741542e-07,
+      "loss": 0.5347,
+      "step": 1270
+    },
+    {
+      "epoch": 0.30103480714957664,
+      "grad_norm": 26.861221309569398,
+      "learning_rate": 8.822881652261671e-07,
+      "loss": 0.5434,
+      "step": 1280
+    },
+    {
+      "epoch": 0.3033866415804327,
+      "grad_norm": 47.06480089234017,
+      "learning_rate": 8.796291225046866e-07,
+      "loss": 0.515,
+      "step": 1290
+    },
+    {
+      "epoch": 0.3057384760112888,
+      "grad_norm": 242.58390403927206,
+      "learning_rate": 8.76944484090062e-07,
+      "loss": 0.5204,
+      "step": 1300
+    },
+    {
+      "epoch": 0.30809031044214485,
+      "grad_norm": 69.9924587472249,
+      "learning_rate": 8.742344309883776e-07,
+      "loss": 0.5266,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3104421448730009,
+      "grad_norm": 174.79009098016476,
+      "learning_rate": 8.7149914591925e-07,
+      "loss": 0.5269,
+      "step": 1320
+    },
+    {
+      "epoch": 0.312793979303857,
+      "grad_norm": 51.84251807068747,
+      "learning_rate": 8.687388133035074e-07,
+      "loss": 0.513,
+      "step": 1330
+    },
+    {
+      "epoch": 0.31514581373471307,
+      "grad_norm": 101.12451895232418,
+      "learning_rate": 8.659536192507564e-07,
+      "loss": 0.5578,
+      "step": 1340
+    },
+    {
+      "epoch": 0.31749764816556914,
+      "grad_norm": 91.89776616663202,
+      "learning_rate": 8.631437515468336e-07,
+      "loss": 0.509,
+      "step": 1350
+    },
+    {
+      "epoch": 0.3198494825964252,
+      "grad_norm": 363.4004724877564,
+      "learning_rate": 8.603093996411444e-07,
+      "loss": 0.5398,
+      "step": 1360
+    },
+    {
+      "epoch": 0.3222013170272813,
+      "grad_norm": 66.77614323450521,
+      "learning_rate": 8.574507546338895e-07,
+      "loss": 0.4921,
+      "step": 1370
+    },
+    {
+      "epoch": 0.32455315145813735,
+      "grad_norm": 49.08933240076176,
+      "learning_rate": 8.545680092631815e-07,
+      "loss": 0.5313,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3269049858889934,
+      "grad_norm": 49.554772352006694,
+      "learning_rate": 8.516613578920488e-07,
+      "loss": 0.447,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3292568203198495,
+      "grad_norm": 43.55060672795549,
+      "learning_rate": 8.487309964953311e-07,
+      "loss": 0.5278,
+      "step": 1400
+    },
+    {
+      "epoch": 0.33160865475070556,
+      "grad_norm": 53.0380482362615,
+      "learning_rate": 8.457771226464674e-07,
+      "loss": 0.505,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3339604891815616,
+      "grad_norm": 79.64660023563455,
+      "learning_rate": 8.427999355041735e-07,
+      "loss": 0.5226,
+      "step": 1420
+    },
+    {
+      "epoch": 0.3363123236124177,
+      "grad_norm": 55.95587949885615,
+      "learning_rate": 8.397996357990153e-07,
+      "loss": 0.5258,
+      "step": 1430
+    },
+    {
+      "epoch": 0.33866415804327377,
+      "grad_norm": 411.2146929812851,
+      "learning_rate": 8.367764258198744e-07,
+      "loss": 0.5709,
+      "step": 1440
+    },
+    {
+      "epoch": 0.34101599247412984,
+      "grad_norm": 43.734123642110056,
+      "learning_rate": 8.337305094003091e-07,
+      "loss": 0.5129,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3433678269049859,
+      "grad_norm": 227.72574989130484,
+      "learning_rate": 8.306620919048115e-07,
+      "loss": 0.5365,
+      "step": 1460
+    },
+    {
+      "epoch": 0.345719661335842,
+      "grad_norm": 230.09797130940922,
+      "learning_rate": 8.275713802149622e-07,
+      "loss": 0.4906,
+      "step": 1470
+    },
+    {
+      "epoch": 0.34807149576669805,
+      "grad_norm": 54.19875482542778,
+      "learning_rate": 8.244585827154795e-07,
+      "loss": 0.499,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3504233301975541,
+      "grad_norm": 55.791984177409674,
+      "learning_rate": 8.213239092801718e-07,
+      "loss": 0.5155,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3527751646284102,
+      "grad_norm": 38.61566415419522,
+      "learning_rate": 8.181675712577864e-07,
+      "loss": 0.4924,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3551269990592662,
+      "grad_norm": 59.61394018369017,
+      "learning_rate": 8.149897814577589e-07,
+      "loss": 0.4948,
+      "step": 1510
+    },
+    {
+      "epoch": 0.35747883349012227,
+      "grad_norm": 52.530770820466806,
+      "learning_rate": 8.117907541358664e-07,
+      "loss": 0.4625,
+      "step": 1520
+    },
+    {
+      "epoch": 0.35983066792097834,
+      "grad_norm": 53.03111212968418,
+      "learning_rate": 8.08570704979781e-07,
+      "loss": 0.4853,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3621825023518344,
+      "grad_norm": 65.37886086917705,
+      "learning_rate": 8.053298510945279e-07,
+      "loss": 0.499,
+      "step": 1540
+    },
+    {
+      "epoch": 0.3645343367826905,
+      "grad_norm": 274.0211083038785,
+      "learning_rate": 8.020684109878465e-07,
+      "loss": 0.5308,
+      "step": 1550
+    },
+    {
+      "epoch": 0.36688617121354655,
+      "grad_norm": 207.52089838136985,
+      "learning_rate": 7.987866045554598e-07,
+      "loss": 0.5111,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3692380056444026,
+      "grad_norm": 201.91551525915267,
+      "learning_rate": 7.954846530662467e-07,
+      "loss": 0.5095,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3715898400752587,
+      "grad_norm": 66.61996761679119,
+      "learning_rate": 7.921627791473242e-07,
+      "loss": 0.4668,
+      "step": 1580
+    },
+    {
+      "epoch": 0.37394167450611476,
+      "grad_norm": 29.688431988926887,
+      "learning_rate": 7.888212067690372e-07,
+      "loss": 0.5093,
+      "step": 1590
+    },
+    {
+      "epoch": 0.37629350893697083,
+      "grad_norm": 96.58502652217979,
+      "learning_rate": 7.854601612298577e-07,
+      "loss": 0.5492,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3786453433678269,
+      "grad_norm": 160.08236167143332,
+      "learning_rate": 7.820798691411945e-07,
+      "loss": 0.5056,
+      "step": 1610
+    },
+    {
+      "epoch": 0.380997177798683,
+      "grad_norm": 94.89520708968821,
+      "learning_rate": 7.786805584121143e-07,
+      "loss": 0.5017,
+      "step": 1620
+    },
+    {
+      "epoch": 0.38334901222953904,
+      "grad_norm": 111.60483541208626,
+      "learning_rate": 7.75262458233976e-07,
+      "loss": 0.4888,
+      "step": 1630
+    },
+    {
+      "epoch": 0.3857008466603951,
+      "grad_norm": 52.130149242500984,
+      "learning_rate": 7.718257990649766e-07,
+      "loss": 0.5116,
+      "step": 1640
+    },
+    {
+      "epoch": 0.3880526810912512,
+      "grad_norm": 132.947730554617,
+      "learning_rate": 7.683708126146146e-07,
+      "loss": 0.4888,
+      "step": 1650
+    },
+    {
+      "epoch": 0.39040451552210725,
+      "grad_norm": 119.19032436133351,
+      "learning_rate": 7.648977318280667e-07,
+      "loss": 0.5562,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3927563499529633,
+      "grad_norm": 79.62177704099146,
+      "learning_rate": 7.614067908704822e-07,
+      "loss": 0.4979,
+      "step": 1670
+    },
+    {
+      "epoch": 0.3951081843838194,
+      "grad_norm": 276.43996320587473,
+      "learning_rate": 7.578982251111941e-07,
+      "loss": 0.5253,
+      "step": 1680
+    },
+    {
+      "epoch": 0.39746001881467546,
+      "grad_norm": 33.12487289775825,
+      "learning_rate": 7.543722711078515e-07,
+      "loss": 0.4725,
+      "step": 1690
+    },
+    {
+      "epoch": 0.39981185324553153,
+      "grad_norm": 196.6122063462283,
+      "learning_rate": 7.508291665904684e-07,
+      "loss": 0.4929,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4021636876763876,
+      "grad_norm": 65.99306854525632,
+      "learning_rate": 7.472691504453963e-07,
+      "loss": 0.5353,
+      "step": 1710
+    },
+    {
+      "epoch": 0.4045155221072437,
+      "grad_norm": 419.0366078449193,
+      "learning_rate": 7.436924626992177e-07,
+      "loss": 0.5149,
+      "step": 1720
+    },
+    {
+      "epoch": 0.40686735653809974,
+      "grad_norm": 63.6596547753076,
+      "learning_rate": 7.400993445025623e-07,
+      "loss": 0.5043,
+      "step": 1730
+    },
+    {
+      "epoch": 0.40921919096895576,
+      "grad_norm": 94.23732036703356,
+      "learning_rate": 7.364900381138488e-07,
+      "loss": 0.5123,
+      "step": 1740
+    },
+    {
+      "epoch": 0.41157102539981183,
+      "grad_norm": 125.17343539075726,
+      "learning_rate": 7.3286478688295e-07,
+      "loss": 0.5495,
+      "step": 1750
+    },
+    {
+      "epoch": 0.4139228598306679,
+      "grad_norm": 490.21785388787504,
+      "learning_rate": 7.292238352347865e-07,
+      "loss": 0.5369,
+      "step": 1760
+    },
+    {
+      "epoch": 0.41627469426152397,
+      "grad_norm": 35.884085037680386,
+      "learning_rate": 7.255674286528462e-07,
+      "loss": 0.5539,
+      "step": 1770
+    },
+    {
+      "epoch": 0.41862652869238004,
+      "grad_norm": 106.9642458702286,
+      "learning_rate": 7.218958136626336e-07,
+      "loss": 0.441,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4209783631232361,
+      "grad_norm": 71.82566114451349,
+      "learning_rate": 7.182092378150479e-07,
+      "loss": 0.5205,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4233301975540922,
+      "grad_norm": 779.4365683391414,
+      "learning_rate": 7.145079496696924e-07,
+      "loss": 0.4959,
+      "step": 1800
+    },
+    {
+      "epoch": 0.42568203198494825,
+      "grad_norm": 44.667117126603884,
+      "learning_rate": 7.107921987781162e-07,
+      "loss": 0.4753,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4280338664158043,
+      "grad_norm": 110.85747495169443,
+      "learning_rate": 7.070622356669887e-07,
+      "loss": 0.4958,
+      "step": 1820
+    },
+    {
+      "epoch": 0.4303857008466604,
+      "grad_norm": 113.10527215049324,
+      "learning_rate": 7.03318311821208e-07,
+      "loss": 0.454,
+      "step": 1830
+    },
+    {
+      "epoch": 0.43273753527751646,
+      "grad_norm": 17.84232109387917,
+      "learning_rate": 6.995606796669454e-07,
+      "loss": 0.5019,
+      "step": 1840
+    },
+    {
+      "epoch": 0.43508936970837253,
+      "grad_norm": 110.74344931358036,
+      "learning_rate": 6.957895925546262e-07,
+      "loss": 0.4719,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4374412041392286,
+      "grad_norm": 41.489250407979306,
+      "learning_rate": 6.920053047418475e-07,
+      "loss": 0.5075,
+      "step": 1860
+    },
+    {
+      "epoch": 0.43979303857008467,
+      "grad_norm": 30.1685856705556,
+      "learning_rate": 6.88208071376236e-07,
+      "loss": 0.4843,
+      "step": 1870
+    },
+    {
+      "epoch": 0.44214487300094074,
+      "grad_norm": 145.26880468994483,
+      "learning_rate": 6.843981484782452e-07,
+      "loss": 0.4794,
+      "step": 1880
+    },
+    {
+      "epoch": 0.4444967074317968,
+      "grad_norm": 108.30784248543398,
+      "learning_rate": 6.80575792923893e-07,
+      "loss": 0.4918,
+      "step": 1890
+    },
+    {
+      "epoch": 0.4468485418626529,
+      "grad_norm": 272.0716196572391,
+      "learning_rate": 6.767412624274434e-07,
+      "loss": 0.4926,
+      "step": 1900
+    },
+    {
+      "epoch": 0.44920037629350895,
+      "grad_norm": 53.98848770173013,
+      "learning_rate": 6.728948155240303e-07,
+      "loss": 0.5,
+      "step": 1910
+    },
+    {
+      "epoch": 0.451552210724365,
+      "grad_norm": 90.77607158800988,
+      "learning_rate": 6.690367115522257e-07,
+      "loss": 0.4901,
+      "step": 1920
+    },
+    {
+      "epoch": 0.4539040451552211,
+      "grad_norm": 42.55048877269962,
+      "learning_rate": 6.651672106365554e-07,
+      "loss": 0.5189,
+      "step": 1930
+    },
+    {
+      "epoch": 0.45625587958607716,
+      "grad_norm": 44.97567866783233,
+      "learning_rate": 6.612865736699598e-07,
+      "loss": 0.5033,
+      "step": 1940
+    },
+    {
+      "epoch": 0.45860771401693323,
+      "grad_norm": 67.49282430103631,
+      "learning_rate": 6.573950622962039e-07,
+      "loss": 0.5276,
+      "step": 1950
+    },
+    {
+      "epoch": 0.4609595484477893,
+      "grad_norm": 59.17058897377058,
+      "learning_rate": 6.534929388922374e-07,
+      "loss": 0.4735,
+      "step": 1960
+    },
+    {
+      "epoch": 0.4633113828786453,
+      "grad_norm": 111.86181053840893,
+      "learning_rate": 6.495804665505029e-07,
+      "loss": 0.4788,
+      "step": 1970
+    },
+    {
+      "epoch": 0.4656632173095014,
+      "grad_norm": 189.94498833584603,
+      "learning_rate": 6.456579090611987e-07,
+      "loss": 0.5144,
+      "step": 1980
+    },
+    {
+      "epoch": 0.46801505174035746,
+      "grad_norm": 122.35102212459157,
+      "learning_rate": 6.417255308944928e-07,
+      "loss": 0.5283,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4703668861712135,
+      "grad_norm": 186.0617213529026,
+      "learning_rate": 6.37783597182692e-07,
+      "loss": 0.4672,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4727187206020696,
+      "grad_norm": 115.36410352920348,
+      "learning_rate": 6.338323737023651e-07,
+      "loss": 0.4965,
+      "step": 2010
+    },
+    {
+      "epoch": 0.47507055503292567,
+      "grad_norm": 85.9333267678821,
+      "learning_rate": 6.298721268564243e-07,
+      "loss": 0.4895,
+      "step": 2020
+    },
+    {
+      "epoch": 0.47742238946378174,
+      "grad_norm": 211.95325107965013,
+      "learning_rate": 6.259031236561632e-07,
+      "loss": 0.5538,
+      "step": 2030
+    },
+    {
+      "epoch": 0.4797742238946378,
+      "grad_norm": 91.27430764319159,
+      "learning_rate": 6.219256317032537e-07,
+      "loss": 0.4437,
+      "step": 2040
+    },
+    {
+      "epoch": 0.4821260583254939,
+      "grad_norm": 298.2235290567097,
+      "learning_rate": 6.179399191717046e-07,
+      "loss": 0.4904,
+      "step": 2050
+    },
+    {
+      "epoch": 0.48447789275634995,
+      "grad_norm": 36.409310791398326,
+      "learning_rate": 6.139462547897793e-07,
+      "loss": 0.5011,
+      "step": 2060
+    },
+    {
+      "epoch": 0.486829727187206,
+      "grad_norm": 61.35140792241313,
+      "learning_rate": 6.099449078218781e-07,
+      "loss": 0.4999,
+      "step": 2070
+    },
+    {
+      "epoch": 0.4891815616180621,
+      "grad_norm": 192.0635061382374,
+      "learning_rate": 6.059361480503839e-07,
+      "loss": 0.4978,
+      "step": 2080
+    },
+    {
+      "epoch": 0.49153339604891816,
+      "grad_norm": 1602.6959579230695,
+      "learning_rate": 6.019202457574717e-07,
+      "loss": 0.5296,
+      "step": 2090
+    },
+    {
+      "epoch": 0.49388523047977423,
+      "grad_norm": 46.88396962107588,
+      "learning_rate": 5.97897471706886e-07,
+      "loss": 0.4666,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4962370649106303,
+      "grad_norm": 42.5404300683936,
+      "learning_rate": 5.938680971256855e-07,
+      "loss": 0.4917,
+      "step": 2110
+    },
+    {
+      "epoch": 0.49858889934148637,
+      "grad_norm": 168.45591180658585,
+      "learning_rate": 5.898323936859554e-07,
+      "loss": 0.4982,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5009407337723424,
+      "grad_norm": 98.29895214863133,
+      "learning_rate": 5.857906334864908e-07,
+      "loss": 0.4613,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5032925682031985,
+      "grad_norm": 84.14383238818485,
+      "learning_rate": 5.817430890344514e-07,
+      "loss": 0.4573,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5056444026340545,
+      "grad_norm": 63.91190561893289,
+      "learning_rate": 5.776900332269874e-07,
+      "loss": 0.4658,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5079962370649106,
+      "grad_norm": 105.97500836643457,
+      "learning_rate": 5.73631739332841e-07,
+      "loss": 0.4943,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5103480714957667,
+      "grad_norm": 84.24147849783279,
+      "learning_rate": 5.695684809739212e-07,
+      "loss": 0.4429,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5126999059266227,
+      "grad_norm": 189.39210679587683,
+      "learning_rate": 5.655005321068556e-07,
+      "loss": 0.4739,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5150517403574788,
+      "grad_norm": 154.99555922544172,
+      "learning_rate": 5.614281670045191e-07,
+      "loss": 0.4914,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5174035747883349,
+      "grad_norm": 54.60327223607897,
+      "learning_rate": 5.573516602375427e-07,
+      "loss": 0.4801,
+      "step": 2200
+    },
+    {
+      "epoch": 0.519755409219191,
+      "grad_norm": 83.19875850848948,
+      "learning_rate": 5.532712866557994e-07,
+      "loss": 0.5323,
+      "step": 2210
+    },
+    {
+      "epoch": 0.522107243650047,
+      "grad_norm": 42.60436730500025,
+      "learning_rate": 5.491873213698749e-07,
+      "loss": 0.4573,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5244590780809031,
+      "grad_norm": 65.42258392696083,
+      "learning_rate": 5.451000397325176e-07,
+      "loss": 0.4814,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5268109125117592,
+      "grad_norm": 115.80636504665334,
+      "learning_rate": 5.410097173200738e-07,
+      "loss": 0.4587,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5291627469426152,
+      "grad_norm": 69.60117550551328,
+      "learning_rate": 5.36916629913908e-07,
+      "loss": 0.5132,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5315145813734713,
+      "grad_norm": 66.375344126355,
+      "learning_rate": 5.32821053481808e-07,
+      "loss": 0.4671,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5338664158043274,
+      "grad_norm": 35.28013711011858,
+      "learning_rate": 5.287232641593799e-07,
+      "loss": 0.4786,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5362182502351834,
+      "grad_norm": 786.6344541862824,
+      "learning_rate": 5.24623538231428e-07,
+      "loss": 0.446,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5385700846660395,
+      "grad_norm": 123.10978108283794,
+      "learning_rate": 5.205221521133293e-07,
+      "loss": 0.4589,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5409219190968956,
+      "grad_norm": 219.42520028684848,
+      "learning_rate": 5.164193823323949e-07,
+      "loss": 0.5345,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5432737535277516,
+      "grad_norm": 42.749936673742305,
+      "learning_rate": 5.123155055092266e-07,
+      "loss": 0.5589,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5456255879586077,
+      "grad_norm": 132.15751551013375,
+      "learning_rate": 5.082107983390663e-07,
+      "loss": 0.4669,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5479774223894638,
+      "grad_norm": 102.8246996509365,
+      "learning_rate": 5.041055375731404e-07,
+      "loss": 0.4539,
+      "step": 2330
+    },
+    {
+      "epoch": 0.5503292568203199,
+      "grad_norm": 38.44411987577502,
+      "learning_rate": 5e-07,
+      "loss": 0.5467,
+      "step": 2340
+    },
+    {
+      "epoch": 0.5526810912511759,
+      "grad_norm": 74.77277783685864,
+      "learning_rate": 4.958944624268596e-07,
+      "loss": 0.5021,
+      "step": 2350
+    },
+    {
+      "epoch": 0.555032925682032,
+      "grad_norm": 38.676119419707206,
+      "learning_rate": 4.917892016609336e-07,
+      "loss": 0.4276,
+      "step": 2360
+    },
+    {
+      "epoch": 0.5573847601128881,
+      "grad_norm": 108.70553186871935,
+      "learning_rate": 4.876844944907734e-07,
+      "loss": 0.4719,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5597365945437441,
+      "grad_norm": 295.3911082440077,
+      "learning_rate": 4.835806176676051e-07,
+      "loss": 0.4445,
+      "step": 2380
+    },
+    {
+      "epoch": 0.5620884289746002,
+      "grad_norm": 49.65291441301108,
+      "learning_rate": 4.794778478866707e-07,
+      "loss": 0.4846,
+      "step": 2390
+    },
+    {
+      "epoch": 0.5644402634054563,
+      "grad_norm": 60.72248586512295,
+      "learning_rate": 4.753764617685719e-07,
+      "loss": 0.4897,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5667920978363123,
+      "grad_norm": 64.47512708646681,
+      "learning_rate": 4.7127673584062015e-07,
+      "loss": 0.4741,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5691439322671684,
+      "grad_norm": 47.47422172419129,
+      "learning_rate": 4.671789465181919e-07,
+      "loss": 0.4669,
+      "step": 2420
+    },
+    {
+      "epoch": 0.5714957666980245,
+      "grad_norm": 23.291621066236825,
+      "learning_rate": 4.6308337008609215e-07,
+      "loss": 0.4387,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5738476011288806,
+      "grad_norm": 38.681058186421566,
+      "learning_rate": 4.5899028267992613e-07,
+      "loss": 0.478,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5761994355597366,
+      "grad_norm": 49.47985557527302,
+      "learning_rate": 4.548999602674824e-07,
+      "loss": 0.4768,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5785512699905927,
+      "grad_norm": 61.860260636343476,
+      "learning_rate": 4.5081267863012504e-07,
+      "loss": 0.4633,
+      "step": 2460
+    },
+    {
+      "epoch": 0.5809031044214488,
+      "grad_norm": 71.87446520905469,
+      "learning_rate": 4.4672871334420054e-07,
+      "loss": 0.4902,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5832549388523048,
+      "grad_norm": 59.913860308252595,
+      "learning_rate": 4.4264833976245736e-07,
+      "loss": 0.4773,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5856067732831609,
+      "grad_norm": 66.42267107533596,
+      "learning_rate": 4.3857183299548084e-07,
+      "loss": 0.4871,
+      "step": 2490
+    },
+    {
+      "epoch": 0.587958607714017,
+      "grad_norm": 31.108180028188862,
+      "learning_rate": 4.344994678931445e-07,
+      "loss": 0.4645,
+      "step": 2500
+    },
+    {
+      "epoch": 0.590310442144873,
+      "grad_norm": 28.34707994823098,
+      "learning_rate": 4.304315190260787e-07,
+      "loss": 0.4702,
+      "step": 2510
+    },
+    {
+      "epoch": 0.5926622765757291,
+      "grad_norm": 171.3392721123324,
+      "learning_rate": 4.2636826066715895e-07,
+      "loss": 0.4394,
+      "step": 2520
+    },
+    {
+      "epoch": 0.5950141110065852,
+      "grad_norm": 52.496086063752934,
+      "learning_rate": 4.2230996677301265e-07,
+      "loss": 0.468,
+      "step": 2530
+    },
+    {
+      "epoch": 0.5973659454374413,
+      "grad_norm": 152.40165257833203,
+      "learning_rate": 4.182569109655488e-07,
+      "loss": 0.4449,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5997177798682972,
+      "grad_norm": 49.22527606031466,
+      "learning_rate": 4.142093665135092e-07,
+      "loss": 0.4621,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6020696142991533,
+      "grad_norm": 204.6300032968629,
+      "learning_rate": 4.101676063140447e-07,
+      "loss": 0.4697,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6044214487300094,
+      "grad_norm": 49.04313064544541,
+      "learning_rate": 4.0613190287431457e-07,
+      "loss": 0.4672,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6067732831608654,
+      "grad_norm": 75.74845619142411,
+      "learning_rate": 4.0210252829311384e-07,
+      "loss": 0.4547,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6091251175917215,
+      "grad_norm": 41.52522300616638,
+      "learning_rate": 3.980797542425284e-07,
+      "loss": 0.4841,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6114769520225776,
+      "grad_norm": 24.660847040050093,
+      "learning_rate": 3.9406385194961617e-07,
+      "loss": 0.505,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6138287864534336,
+      "grad_norm": 32.07608549927192,
+      "learning_rate": 3.9005509217812195e-07,
+      "loss": 0.4588,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6161806208842897,
+      "grad_norm": 39.70294250231196,
+      "learning_rate": 3.8605374521022074e-07,
+      "loss": 0.4559,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6185324553151458,
+      "grad_norm": 77.97272809649765,
+      "learning_rate": 3.8206008082829546e-07,
+      "loss": 0.4406,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6208842897460018,
+      "grad_norm": 45.67613106527001,
+      "learning_rate": 3.7807436829674625e-07,
+      "loss": 0.4385,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6232361241768579,
+      "grad_norm": 76.59247815028435,
+      "learning_rate": 3.740968763438369e-07,
+      "loss": 0.4869,
+      "step": 2650
+    },
+    {
+      "epoch": 0.625587958607714,
+      "grad_norm": 39.68012913221431,
+      "learning_rate": 3.7012787314357564e-07,
+      "loss": 0.4721,
+      "step": 2660
+    },
+    {
+      "epoch": 0.6279397930385701,
+      "grad_norm": 141.25589970566216,
+      "learning_rate": 3.6616762629763485e-07,
+      "loss": 0.5125,
+      "step": 2670
+    },
+    {
+      "epoch": 0.6302916274694261,
+      "grad_norm": 23.55149435862232,
+      "learning_rate": 3.6221640281730807e-07,
+      "loss": 0.4115,
+      "step": 2680
+    },
+    {
+      "epoch": 0.6326434619002822,
+      "grad_norm": 143.42525243309444,
+      "learning_rate": 3.5827446910550706e-07,
+      "loss": 0.4668,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6349952963311383,
+      "grad_norm": 77.81781401332093,
+      "learning_rate": 3.543420909388013e-07,
+      "loss": 0.4647,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6373471307619943,
+      "grad_norm": 368.31014969438706,
+      "learning_rate": 3.5041953344949713e-07,
+      "loss": 0.5143,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6396989651928504,
+      "grad_norm": 191.99282418445105,
+      "learning_rate": 3.4650706110776263e-07,
+      "loss": 0.4714,
+      "step": 2720
+    },
+    {
+      "epoch": 0.6420507996237065,
+      "grad_norm": 172.6805749126617,
+      "learning_rate": 3.4260493770379594e-07,
+      "loss": 0.4876,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6444026340545626,
+      "grad_norm": 61.17327984316229,
+      "learning_rate": 3.387134263300403e-07,
+      "loss": 0.4178,
+      "step": 2740
+    },
+    {
+      "epoch": 0.6467544684854186,
+      "grad_norm": 114.17761831777952,
+      "learning_rate": 3.3483278936344473e-07,
+      "loss": 0.4889,
+      "step": 2750
+    },
+    {
+      "epoch": 0.6491063029162747,
+      "grad_norm": 29.259182763118652,
+      "learning_rate": 3.3096328844777445e-07,
+      "loss": 0.4508,
+      "step": 2760
+    },
+    {
+      "epoch": 0.6514581373471308,
+      "grad_norm": 119.4854028220211,
+      "learning_rate": 3.2710518447596975e-07,
+      "loss": 0.4392,
+      "step": 2770
+    },
+    {
+      "epoch": 0.6538099717779868,
+      "grad_norm": 25.936405577527868,
+      "learning_rate": 3.232587375725566e-07,
+      "loss": 0.4725,
+      "step": 2780
+    },
+    {
+      "epoch": 0.6561618062088429,
+      "grad_norm": 67.32516092680038,
+      "learning_rate": 3.1942420707610713e-07,
+      "loss": 0.4363,
+      "step": 2790
+    },
+    {
+      "epoch": 0.658513640639699,
+      "grad_norm": 49.096928986568244,
+      "learning_rate": 3.156018515217549e-07,
+      "loss": 0.4891,
+      "step": 2800
+    },
+    {
+      "epoch": 0.660865475070555,
+      "grad_norm": 48.270407025181726,
+      "learning_rate": 3.11791928623764e-07,
+      "loss": 0.4846,
+      "step": 2810
+    },
+    {
+      "epoch": 0.6632173095014111,
+      "grad_norm": 33.146338229003334,
+      "learning_rate": 3.079946952581526e-07,
+      "loss": 0.4372,
+      "step": 2820
+    },
+    {
+      "epoch": 0.6655691439322672,
+      "grad_norm": 65.86339846284933,
+      "learning_rate": 3.042104074453739e-07,
+      "loss": 0.4938,
+      "step": 2830
+    },
+    {
+      "epoch": 0.6679209783631233,
+      "grad_norm": 81.43044910317796,
+      "learning_rate": 3.0043932033305455e-07,
+      "loss": 0.5127,
+      "step": 2840
+    },
+    {
+      "epoch": 0.6702728127939793,
+      "grad_norm": 28.25621020100993,
+      "learning_rate": 2.9668168817879205e-07,
+      "loss": 0.5283,
+      "step": 2850
+    },
+    {
+      "epoch": 0.6726246472248354,
+      "grad_norm": 70.5644459258473,
+      "learning_rate": 2.9293776433301144e-07,
+      "loss": 0.4676,
+      "step": 2860
+    },
+    {
+      "epoch": 0.6749764816556915,
+      "grad_norm": 833.1173554079337,
+      "learning_rate": 2.8920780122188393e-07,
+      "loss": 0.4238,
+      "step": 2870
+    },
+    {
+      "epoch": 0.6773283160865475,
+      "grad_norm": 50.15505341992137,
+      "learning_rate": 2.854920503303076e-07,
+      "loss": 0.4317,
+      "step": 2880
+    },
+    {
+      "epoch": 0.6796801505174036,
+      "grad_norm": 53.62160731503517,
+      "learning_rate": 2.8179076218495213e-07,
+      "loss": 0.5074,
+      "step": 2890
+    },
+    {
+      "epoch": 0.6820319849482597,
+      "grad_norm": 82.67486758357786,
+      "learning_rate": 2.7810418633736637e-07,
+      "loss": 0.451,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6843838193791157,
+      "grad_norm": 70.65167543458996,
+      "learning_rate": 2.744325713471536e-07,
+      "loss": 0.4832,
+      "step": 2910
+    },
+    {
+      "epoch": 0.6867356538099718,
+      "grad_norm": 70.82701033248681,
+      "learning_rate": 2.707761647652135e-07,
+      "loss": 0.4679,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6890874882408279,
+      "grad_norm": 119.20686302974886,
+      "learning_rate": 2.6713521311705e-07,
+      "loss": 0.4545,
+      "step": 2930
+    },
+    {
+      "epoch": 0.691439322671684,
+      "grad_norm": 46.64006057310895,
+      "learning_rate": 2.635099618861513e-07,
+      "loss": 0.5192,
+      "step": 2940
+    },
+    {
+      "epoch": 0.69379115710254,
+      "grad_norm": 62.9139122700984,
+      "learning_rate": 2.5990065549743766e-07,
+      "loss": 0.4554,
+      "step": 2950
+    },
+    {
+      "epoch": 0.6961429915333961,
+      "grad_norm": 134.31949058487535,
+      "learning_rate": 2.5630753730078236e-07,
+      "loss": 0.5069,
+      "step": 2960
+    },
+    {
+      "epoch": 0.6984948259642522,
+      "grad_norm": 91.61539909081964,
+      "learning_rate": 2.527308495546038e-07,
+      "loss": 0.4289,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7008466603951082,
+      "grad_norm": 104.86257682935386,
+      "learning_rate": 2.4917083340953175e-07,
+      "loss": 0.433,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7031984948259643,
+      "grad_norm": 21.474222567958595,
+      "learning_rate": 2.456277288921485e-07,
+      "loss": 0.4365,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7055503292568204,
+      "grad_norm": 324.3124016674876,
+      "learning_rate": 2.4210177488880587e-07,
+      "loss": 0.4179,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7079021636876763,
+      "grad_norm": 39.24490171045256,
+      "learning_rate": 2.3859320912951797e-07,
+      "loss": 0.4258,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7102539981185324,
+      "grad_norm": 26.55750023296075,
+      "learning_rate": 2.3510226817193319e-07,
+      "loss": 0.4575,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7126058325493885,
+      "grad_norm": 76.18210272558196,
+      "learning_rate": 2.3162918738538539e-07,
+      "loss": 0.4474,
+      "step": 3030
+    },
+    {
+      "epoch": 0.7149576669802445,
+      "grad_norm": 163.82835782749893,
+      "learning_rate": 2.281742009350235e-07,
+      "loss": 0.5178,
+      "step": 3040
+    },
+    {
+      "epoch": 0.7173095014111006,
+      "grad_norm": 71.20621946298115,
+      "learning_rate": 2.247375417660241e-07,
+      "loss": 0.4542,
+      "step": 3050
+    },
+    {
+      "epoch": 0.7196613358419567,
+      "grad_norm": 29.44780246695801,
+      "learning_rate": 2.2131944158788545e-07,
+      "loss": 0.4696,
+      "step": 3060
+    },
+    {
+      "epoch": 0.7220131702728128,
+      "grad_norm": 28.85017992785853,
+      "learning_rate": 2.1792013085880539e-07,
+      "loss": 0.4262,
+      "step": 3070
+    },
+    {
+      "epoch": 0.7243650047036688,
+      "grad_norm": 161.1358114916103,
+      "learning_rate": 2.1453983877014224e-07,
+      "loss": 0.4506,
+      "step": 3080
+    },
+    {
+      "epoch": 0.7267168391345249,
+      "grad_norm": 48.21294290482945,
+      "learning_rate": 2.1117879323096283e-07,
+      "loss": 0.4762,
+      "step": 3090
+    },
+    {
+      "epoch": 0.729068673565381,
+      "grad_norm": 92.39652488615809,
+      "learning_rate": 2.0783722085267592e-07,
+      "loss": 0.4569,
+      "step": 3100
+    },
+    {
+      "epoch": 0.731420507996237,
+      "grad_norm": 72.21113504991627,
+      "learning_rate": 2.0451534693375344e-07,
+      "loss": 0.4738,
+      "step": 3110
+    },
+    {
+      "epoch": 0.7337723424270931,
+      "grad_norm": 92.26016205643168,
+      "learning_rate": 2.0121339544454035e-07,
+      "loss": 0.4435,
+      "step": 3120
+    },
+    {
+      "epoch": 0.7361241768579492,
+      "grad_norm": 68.48228287299885,
+      "learning_rate": 1.9793158901215346e-07,
+      "loss": 0.4313,
+      "step": 3130
+    },
+    {
+      "epoch": 0.7384760112888052,
+      "grad_norm": 164.80360664767645,
+      "learning_rate": 1.9467014890547223e-07,
+      "loss": 0.4148,
+      "step": 3140
+    },
+    {
+      "epoch": 0.7408278457196613,
+      "grad_norm": 66.07514802799065,
+      "learning_rate": 1.9142929502021904e-07,
+      "loss": 0.4557,
+      "step": 3150
+    },
+    {
+      "epoch": 0.7431796801505174,
+      "grad_norm": 54.18230405158542,
+      "learning_rate": 1.8820924586413373e-07,
+      "loss": 0.4389,
+      "step": 3160
+    },
+    {
+      "epoch": 0.7455315145813735,
+      "grad_norm": 54.933584541808706,
+      "learning_rate": 1.8501021854224115e-07,
+      "loss": 0.4405,
+      "step": 3170
+    },
+    {
+      "epoch": 0.7478833490122295,
+      "grad_norm": 73.88687819153088,
+      "learning_rate": 1.8183242874221365e-07,
+      "loss": 0.444,
+      "step": 3180
+    },
+    {
+      "epoch": 0.7502351834430856,
+      "grad_norm": 155.9296620837369,
+      "learning_rate": 1.786760907198281e-07,
+      "loss": 0.4456,
+      "step": 3190
+    },
+    {
+      "epoch": 0.7525870178739417,
+      "grad_norm": 98.13292721707111,
+      "learning_rate": 1.7554141728452038e-07,
+      "loss": 0.4804,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7549388523047977,
+      "grad_norm": 20.87180402977683,
+      "learning_rate": 1.7242861978503782e-07,
+      "loss": 0.3997,
+      "step": 3210
+    },
+    {
+      "epoch": 0.7572906867356538,
+      "grad_norm": 139.8758062253345,
+      "learning_rate": 1.6933790809518839e-07,
+      "loss": 0.4336,
+      "step": 3220
+    },
+    {
+      "epoch": 0.7596425211665099,
+      "grad_norm": 67.67816700607545,
+      "learning_rate": 1.6626949059969098e-07,
+      "loss": 0.4371,
+      "step": 3230
+    },
+    {
+      "epoch": 0.761994355597366,
+      "grad_norm": 31.044524767135282,
+      "learning_rate": 1.632235741801255e-07,
+      "loss": 0.4678,
+      "step": 3240
+    },
+    {
+      "epoch": 0.764346190028222,
+      "grad_norm": 31.59032271901563,
+      "learning_rate": 1.6020036420098455e-07,
+      "loss": 0.4474,
+      "step": 3250
+    },
+    {
+      "epoch": 0.7666980244590781,
+      "grad_norm": 56.09519646865281,
+      "learning_rate": 1.5720006449582635e-07,
+      "loss": 0.4464,
+      "step": 3260
+    },
+    {
+      "epoch": 0.7690498588899342,
+      "grad_norm": 60.68844089135062,
+      "learning_rate": 1.5422287735353257e-07,
+      "loss": 0.4525,
+      "step": 3270
+    },
+    {
+      "epoch": 0.7714016933207902,
+      "grad_norm": 44.61096552113006,
+      "learning_rate": 1.5126900350466886e-07,
+      "loss": 0.4514,
+      "step": 3280
+    },
+    {
+      "epoch": 0.7737535277516463,
+      "grad_norm": 79.00286386953672,
+      "learning_rate": 1.4833864210795132e-07,
+      "loss": 0.4546,
+      "step": 3290
+    },
+    {
+      "epoch": 0.7761053621825024,
+      "grad_norm": 96.77266999382469,
+      "learning_rate": 1.4543199073681855e-07,
+      "loss": 0.4188,
+      "step": 3300
+    },
+    {
+      "epoch": 0.7784571966133584,
+      "grad_norm": 62.93527984098046,
+      "learning_rate": 1.4254924536611046e-07,
+      "loss": 0.4931,
+      "step": 3310
+    },
+    {
+      "epoch": 0.7808090310442145,
+      "grad_norm": 78.89136393447265,
+      "learning_rate": 1.396906003588557e-07,
+      "loss": 0.478,
+      "step": 3320
+    },
+    {
+      "epoch": 0.7831608654750706,
+      "grad_norm": 123.25424347020814,
+      "learning_rate": 1.368562484531664e-07,
+      "loss": 0.4439,
+      "step": 3330
+    },
+    {
+      "epoch": 0.7855126999059266,
+      "grad_norm": 72.17648953992217,
+      "learning_rate": 1.3404638074924356e-07,
+      "loss": 0.4661,
+      "step": 3340
+    },
+    {
+      "epoch": 0.7878645343367827,
+      "grad_norm": 29.181609218156055,
+      "learning_rate": 1.3126118669649255e-07,
+      "loss": 0.4775,
+      "step": 3350
+    },
+    {
+      "epoch": 0.7902163687676388,
+      "grad_norm": 26.80987859871448,
+      "learning_rate": 1.2850085408075e-07,
+      "loss": 0.432,
+      "step": 3360
+    },
+    {
+      "epoch": 0.7925682031984949,
+      "grad_norm": 42.77599635619014,
+      "learning_rate": 1.2576556901162234e-07,
+      "loss": 0.4705,
+      "step": 3370
+    },
+    {
+      "epoch": 0.7949200376293509,
+      "grad_norm": 45.81217647451442,
+      "learning_rate": 1.2305551590993806e-07,
+      "loss": 0.47,
+      "step": 3380
+    },
+    {
+      "epoch": 0.797271872060207,
+      "grad_norm": 101.96913312576068,
+      "learning_rate": 1.2037087749531328e-07,
+      "loss": 0.4229,
+      "step": 3390
+    },
+    {
+      "epoch": 0.7996237064910631,
+      "grad_norm": 215.88495935464798,
+      "learning_rate": 1.177118347738329e-07,
+      "loss": 0.4447,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8019755409219191,
+      "grad_norm": 72.55346736718074,
+      "learning_rate": 1.1507856702584573e-07,
+      "loss": 0.4563,
+      "step": 3410
+    },
+    {
+      "epoch": 0.8043273753527752,
+      "grad_norm": 267.60170600595404,
+      "learning_rate": 1.1247125179387734e-07,
+      "loss": 0.4835,
+      "step": 3420
+    },
+    {
+      "epoch": 0.8066792097836313,
+      "grad_norm": 38.91519432313084,
+      "learning_rate": 1.098900648706601e-07,
+      "loss": 0.445,
+      "step": 3430
+    },
+    {
+      "epoch": 0.8090310442144873,
+      "grad_norm": 107.08048276724904,
+      "learning_rate": 1.0733518028727973e-07,
+      "loss": 0.437,
+      "step": 3440
+    },
+    {
+      "epoch": 0.8113828786453434,
+      "grad_norm": 39.41515052926627,
+      "learning_rate": 1.048067703014423e-07,
+      "loss": 0.4016,
+      "step": 3450
+    },
+    {
+      "epoch": 0.8137347130761995,
+      "grad_norm": 64.66608261177336,
+      "learning_rate": 1.0230500538586012e-07,
+      "loss": 0.4537,
+      "step": 3460
+    },
+    {
+      "epoch": 0.8160865475070554,
+      "grad_norm": 61.054737141139334,
+      "learning_rate": 9.983005421675761e-08,
+      "loss": 0.4124,
+      "step": 3470
+    },
+    {
+      "epoch": 0.8184383819379115,
+      "grad_norm": 59.104871236625186,
+      "learning_rate": 9.738208366249895e-08,
+      "loss": 0.447,
+      "step": 3480
+    },
+    {
+      "epoch": 0.8207902163687676,
+      "grad_norm": 110.57928796201509,
+      "learning_rate": 9.496125877233736e-08,
+      "loss": 0.461,
+      "step": 3490
+    },
+    {
+      "epoch": 0.8231420507996237,
+      "grad_norm": 234.52785886205078,
+      "learning_rate": 9.256774276528655e-08,
+      "loss": 0.4856,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8254938852304797,
+      "grad_norm": 63.124590798290406,
+      "learning_rate": 9.020169701911695e-08,
+      "loss": 0.4501,
+      "step": 3510
+    },
+    {
+      "epoch": 0.8278457196613358,
+      "grad_norm": 146.5239433816864,
+      "learning_rate": 8.786328105947405e-08,
+      "loss": 0.4902,
+      "step": 3520
+    },
+    {
+      "epoch": 0.8301975540921919,
+      "grad_norm": 34.913788680016566,
+      "learning_rate": 8.555265254912337e-08,
+      "loss": 0.4275,
+      "step": 3530
+    },
+    {
+      "epoch": 0.8325493885230479,
+      "grad_norm": 79.65521261255103,
+      "learning_rate": 8.326996727732055e-08,
+      "loss": 0.4531,
+      "step": 3540
+    },
+    {
+      "epoch": 0.834901222953904,
+      "grad_norm": 47.72263945629518,
+      "learning_rate": 8.101537914930684e-08,
+      "loss": 0.4062,
+      "step": 3550
+    },
+    {
+      "epoch": 0.8372530573847601,
+      "grad_norm": 94.48797265907596,
+      "learning_rate": 7.878904017593302e-08,
+      "loss": 0.4462,
+      "step": 3560
+    },
+    {
+      "epoch": 0.8396048918156162,
+      "grad_norm": 89.24680993944979,
+      "learning_rate": 7.659110046341016e-08,
+      "loss": 0.4334,
+      "step": 3570
+    },
+    {
+      "epoch": 0.8419567262464722,
+      "grad_norm": 31.758114332081302,
+      "learning_rate": 7.442170820318922e-08,
+      "loss": 0.423,
+      "step": 3580
+    },
+    {
+      "epoch": 0.8443085606773283,
+      "grad_norm": 108.36139891290028,
+      "learning_rate": 7.228100966196916e-08,
+      "loss": 0.46,
+      "step": 3590
+    },
+    {
+      "epoch": 0.8466603951081844,
+      "grad_norm": 45.42121511612232,
+      "learning_rate": 7.016914917183541e-08,
+      "loss": 0.4393,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8490122295390404,
+      "grad_norm": 38.06302239041297,
+      "learning_rate": 6.808626912052878e-08,
+      "loss": 0.4123,
+      "step": 3610
+    },
+    {
+      "epoch": 0.8513640639698965,
+      "grad_norm": 144.0496907397513,
+      "learning_rate": 6.603250994184506e-08,
+      "loss": 0.4226,
+      "step": 3620
+    },
+    {
+      "epoch": 0.8537158984007526,
+      "grad_norm": 57.78752403702503,
+      "learning_rate": 6.40080101061664e-08,
+      "loss": 0.4378,
+      "step": 3630
+    },
+    {
+      "epoch": 0.8560677328316086,
+      "grad_norm": 37.60367979124333,
+      "learning_rate": 6.201290611112564e-08,
+      "loss": 0.4561,
+      "step": 3640
+    },
+    {
+      "epoch": 0.8584195672624647,
+      "grad_norm": 53.18398073653025,
+      "learning_rate": 6.004733247240317e-08,
+      "loss": 0.4678,
+      "step": 3650
+    },
+    {
+      "epoch": 0.8607714016933208,
+      "grad_norm": 133.8658799415832,
+      "learning_rate": 5.8111421714657105e-08,
+      "loss": 0.4677,
+      "step": 3660
+    },
+    {
+      "epoch": 0.8631232361241769,
+      "grad_norm": 53.25914607379931,
+      "learning_rate": 5.620530436258841e-08,
+      "loss": 0.5194,
+      "step": 3670
+    },
+    {
+      "epoch": 0.8654750705550329,
+      "grad_norm": 70.42760542084339,
+      "learning_rate": 5.4329108932140546e-08,
+      "loss": 0.427,
+      "step": 3680
+    },
+    {
+      "epoch": 0.867826904985889,
+      "grad_norm": 64.38658865994383,
+      "learning_rate": 5.2482961921834604e-08,
+      "loss": 0.4482,
+      "step": 3690
+    },
+    {
+      "epoch": 0.8701787394167451,
+      "grad_norm": 42.99630254744219,
+      "learning_rate": 5.066698780424006e-08,
+      "loss": 0.4426,
+      "step": 3700
+    },
+    {
+      "epoch": 0.8725305738476011,
+      "grad_norm": 51.11741118831597,
+      "learning_rate": 4.888130901758292e-08,
+      "loss": 0.434,
+      "step": 3710
+    },
+    {
+      "epoch": 0.8748824082784572,
+      "grad_norm": 53.96851327406331,
+      "learning_rate": 4.71260459574902e-08,
+      "loss": 0.3842,
+      "step": 3720
+    },
+    {
+      "epoch": 0.8772342427093133,
+      "grad_norm": 56.59443774149579,
+      "learning_rate": 4.5401316968873004e-08,
+      "loss": 0.4481,
+      "step": 3730
+    },
+    {
+      "epoch": 0.8795860771401693,
+      "grad_norm": 83.85863914669255,
+      "learning_rate": 4.370723833794665e-08,
+      "loss": 0.4266,
+      "step": 3740
+    },
+    {
+      "epoch": 0.8819379115710254,
+      "grad_norm": 39.06100931375012,
+      "learning_rate": 4.2043924284390854e-08,
+      "loss": 0.4238,
+      "step": 3750
+    },
+    {
+      "epoch": 0.8842897460018815,
+      "grad_norm": 107.61806818011783,
+      "learning_rate": 4.041148695364882e-08,
+      "loss": 0.4485,
+      "step": 3760
+    },
+    {
+      "epoch": 0.8866415804327376,
+      "grad_norm": 33.85213758711094,
+      "learning_rate": 3.881003640936548e-08,
+      "loss": 0.446,
+      "step": 3770
+    },
+    {
+      "epoch": 0.8889934148635936,
+      "grad_norm": 61.187373812156466,
+      "learning_rate": 3.723968062596711e-08,
+      "loss": 0.4344,
+      "step": 3780
+    },
+    {
+      "epoch": 0.8913452492944497,
+      "grad_norm": 736.9312025906532,
+      "learning_rate": 3.570052548138147e-08,
+      "loss": 0.4541,
+      "step": 3790
+    },
+    {
+      "epoch": 0.8936970837253058,
+      "grad_norm": 119.33344609512177,
+      "learning_rate": 3.4192674749898785e-08,
+      "loss": 0.4908,
+      "step": 3800
+    },
+    {
+      "epoch": 0.8960489181561618,
+      "grad_norm": 25.5797619702394,
+      "learning_rate": 3.2716230095175435e-08,
+      "loss": 0.4004,
+      "step": 3810
+    },
+    {
+      "epoch": 0.8984007525870179,
+      "grad_norm": 49.359917397601,
+      "learning_rate": 3.127129106337917e-08,
+      "loss": 0.4518,
+      "step": 3820
+    },
+    {
+      "epoch": 0.900752587017874,
+      "grad_norm": 25.07989197247865,
+      "learning_rate": 2.985795507647754e-08,
+      "loss": 0.4131,
+      "step": 3830
+    },
+    {
+      "epoch": 0.90310442144873,
+      "grad_norm": 64.61035042248321,
+      "learning_rate": 2.8476317425669527e-08,
+      "loss": 0.447,
+      "step": 3840
+    },
+    {
+      "epoch": 0.9054562558795861,
+      "grad_norm": 93.42176266818919,
+      "learning_rate": 2.7126471264960593e-08,
+      "loss": 0.4329,
+      "step": 3850
+    },
+    {
+      "epoch": 0.9078080903104422,
+      "grad_norm": 89.24070781803138,
+      "learning_rate": 2.580850760488196e-08,
+      "loss": 0.4753,
+      "step": 3860
+    },
+    {
+      "epoch": 0.9101599247412983,
+      "grad_norm": 26.373133567746557,
+      "learning_rate": 2.4522515306354517e-08,
+      "loss": 0.4606,
+      "step": 3870
+    },
+    {
+      "epoch": 0.9125117591721543,
+      "grad_norm": 473.7854777781819,
+      "learning_rate": 2.3268581074697536e-08,
+      "loss": 0.5009,
+      "step": 3880
+    },
+    {
+      "epoch": 0.9148635936030104,
+      "grad_norm": 32.436085698187235,
+      "learning_rate": 2.204678945378269e-08,
+      "loss": 0.4162,
+      "step": 3890
+    },
+    {
+      "epoch": 0.9172154280338665,
+      "grad_norm": 170.05001192780844,
+      "learning_rate": 2.0857222820333808e-08,
+      "loss": 0.4458,
+      "step": 3900
+    },
+    {
+      "epoch": 0.9195672624647225,
+      "grad_norm": 48.18623345953366,
+      "learning_rate": 1.9699961378373097e-08,
+      "loss": 0.4123,
+      "step": 3910
+    },
+    {
+      "epoch": 0.9219190968955786,
+      "grad_norm": 1358.9466832068094,
+      "learning_rate": 1.8575083153813175e-08,
+      "loss": 0.4355,
+      "step": 3920
+    },
+    {
+      "epoch": 0.9242709313264346,
+      "grad_norm": 113.07515347161218,
+      "learning_rate": 1.7482663989196456e-08,
+      "loss": 0.4339,
+      "step": 3930
+    },
+    {
+      "epoch": 0.9266227657572906,
+      "grad_norm": 70.74972682616625,
+      "learning_rate": 1.64227775385819e-08,
+      "loss": 0.4448,
+      "step": 3940
+    },
+    {
+      "epoch": 0.9289746001881467,
+      "grad_norm": 42.63045190997477,
+      "learning_rate": 1.539549526257866e-08,
+      "loss": 0.446,
+      "step": 3950
+    },
+    {
+      "epoch": 0.9313264346190028,
+      "grad_norm": 297.25978639344856,
+      "learning_rate": 1.4400886423528103e-08,
+      "loss": 0.422,
+      "step": 3960
+    },
+    {
+      "epoch": 0.9336782690498588,
+      "grad_norm": 67.23940820577212,
+      "learning_rate": 1.3439018080834142e-08,
+      "loss": 0.4835,
+      "step": 3970
+    },
+    {
+      "epoch": 0.9360301034807149,
+      "grad_norm": 77.9763692203697,
+      "learning_rate": 1.2509955086441758e-08,
+      "loss": 0.4637,
+      "step": 3980
+    },
+    {
+      "epoch": 0.938381937911571,
+      "grad_norm": 118.62750518663206,
+      "learning_rate": 1.1613760080464385e-08,
+      "loss": 0.44,
+      "step": 3990
+    },
+    {
+      "epoch": 0.940733772342427,
+      "grad_norm": 34.90355156969723,
+      "learning_rate": 1.0750493486960666e-08,
+      "loss": 0.4278,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9430856067732831,
+      "grad_norm": 25.802830924781176,
+      "learning_rate": 9.920213509860498e-09,
+      "loss": 0.4353,
+      "step": 4010
+    },
+    {
+      "epoch": 0.9454374412041392,
+      "grad_norm": 44.67589158879238,
+      "learning_rate": 9.122976129040782e-09,
+      "loss": 0.4026,
+      "step": 4020
+    },
+    {
+      "epoch": 0.9477892756349953,
+      "grad_norm": 31.063785760081664,
+      "learning_rate": 8.358835096550886e-09,
+      "loss": 0.4056,
+      "step": 4030
+    },
+    {
+      "epoch": 0.9501411100658513,
+      "grad_norm": 29.538919263142972,
+      "learning_rate": 7.627841932988765e-09,
+      "loss": 0.392,
+      "step": 4040
+    },
+    {
+      "epoch": 0.9524929444967074,
+      "grad_norm": 48.153765650560715,
+      "learning_rate": 6.9300459240271835e-09,
+      "loss": 0.434,
+      "step": 4050
+    },
+    {
+      "epoch": 0.9548447789275635,
+      "grad_norm": 97.9376546668311,
+      "learning_rate": 6.265494117090764e-09,
+      "loss": 0.4637,
+      "step": 4060
+    },
+    {
+      "epoch": 0.9571966133584195,
+      "grad_norm": 46.369837122592855,
+      "learning_rate": 5.634231318183913e-09,
+      "loss": 0.4483,
+      "step": 4070
+    },
+    {
+      "epoch": 0.9595484477892756,
+      "grad_norm": 34.112979889172955,
+      "learning_rate": 5.036300088869794e-09,
+      "loss": 0.3958,
+      "step": 4080
+    },
+    {
+      "epoch": 0.9619002822201317,
+      "grad_norm": 67.68046313703896,
+      "learning_rate": 4.471740743400843e-09,
+      "loss": 0.3998,
+      "step": 4090
+    },
+    {
+      "epoch": 0.9642521166509878,
+      "grad_norm": 64.94301439710068,
+      "learning_rate": 3.94059134600061e-09,
+      "loss": 0.5025,
+      "step": 4100
+    },
+    {
+      "epoch": 0.9666039510818438,
+      "grad_norm": 72.14615132171306,
+      "learning_rate": 3.4428877082972597e-09,
+      "loss": 0.4421,
+      "step": 4110
+    },
+    {
+      "epoch": 0.9689557855126999,
+      "grad_norm": 24.113378758695696,
+      "learning_rate": 2.9786633869091083e-09,
+      "loss": 0.4162,
+      "step": 4120
+    },
+    {
+      "epoch": 0.971307619943556,
+      "grad_norm": 241.97699208841857,
+      "learning_rate": 2.5479496811823264e-09,
+      "loss": 0.4298,
+      "step": 4130
+    },
+    {
+      "epoch": 0.973659454374412,
+      "grad_norm": 133.43074381257875,
+      "learning_rate": 2.1507756310802926e-09,
+      "loss": 0.4428,
+      "step": 4140
+    },
+    {
+      "epoch": 0.9760112888052681,
+      "grad_norm": 26.108621458874143,
+      "learning_rate": 1.7871680152258816e-09,
+      "loss": 0.478,
+      "step": 4150
+    },
+    {
+      "epoch": 0.9783631232361242,
+      "grad_norm": 48.05086153194788,
+      "learning_rate": 1.4571513490960197e-09,
+      "loss": 0.4364,
+      "step": 4160
+    },
+    {
+      "epoch": 0.9807149576669802,
+      "grad_norm": 135.6321121517264,
+      "learning_rate": 1.1607478833685624e-09,
+      "loss": 0.4654,
+      "step": 4170
+    },
+    {
+      "epoch": 0.9830667920978363,
+      "grad_norm": 43.352481280379564,
+      "learning_rate": 8.97977602422162e-10,
+      "loss": 0.4522,
+      "step": 4180
+    },
+    {
+      "epoch": 0.9854186265286924,
+      "grad_norm": 400.18828509454596,
+      "learning_rate": 6.688582229890106e-10,
+      "loss": 0.4308,
+      "step": 4190
+    },
+    {
+      "epoch": 0.9877704609595485,
+      "grad_norm": 118.9697384571146,
+      "learning_rate": 4.734051929601857e-10,
+      "loss": 0.4335,
+      "step": 4200
+    },
+    {
+      "epoch": 0.9901222953904045,
+      "grad_norm": 620.0407392361634,
+      "learning_rate": 3.116316903440941e-10,
+      "loss": 0.4353,
+      "step": 4210
+    },
+    {
+      "epoch": 0.9924741298212606,
+      "grad_norm": 93.82732661926246,
+      "learning_rate": 1.8354862237812685e-10,
+      "loss": 0.4672,
+      "step": 4220
+    },
+    {
+      "epoch": 0.9948259642521167,
+      "grad_norm": 39.8947952442234,
+      "learning_rate": 8.916462479297005e-11,
+      "loss": 0.4519,
+      "step": 4230
+    },
+    {
+      "epoch": 0.9971777986829727,
+      "grad_norm": 220.48761793592806,
+      "learning_rate": 2.8486061230736934e-11,
+      "loss": 0.4331,
+      "step": 4240
+    },
+    {
+      "epoch": 0.9995296331138288,
+      "grad_norm": 32.77645356865427,
+      "learning_rate": 1.5170228155891861e-12,
+      "loss": 0.4223,
+      "step": 4250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 4000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.149639304655667e+17,
+  "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 sha256:0a757353c01c2f283f2572e92f8623e708ef52bc6122d5574667b2788b47a5a5
+size 8273

video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_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 list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_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)