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 +1,135 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "image_token_id": null,
+    "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,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "float32",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "float32",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.55.0"
+}

global_step937/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872572a993aab88b8e2ecdc60d6ef665c0cad364968d2f21cfa0608366abbd05
+size 11423430497

global_step937/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b1956fa4c79690df4e64e3e9f5960d3f6f8e125314fe84cd2c2584f3a46c4d
+size 11423430497

global_step937/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a3995f2fbf20339153870295c7f7f37f60f9974d5535d4ef4fec78c09d18e2
+size 11423430497

global_step937/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2d412ece77474bd8177d797c8d41d4ee7ae86f2eb3588221a967934a8cac6e
+size 11423430497

global_step937/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401c2d17a34372c0051b393a620962b934a833b817586ad03e65a955b1ff45f8
+size 11423430497

global_step937/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ecb2fcd8b69f3e40204420c666baffffcfa6a6626cdda32b97ecaff24c9da3c
+size 11423430497

global_step937/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0d3da9cf81565eb386885bd74b443b9bc9ef43026a2452dc4272a2bf5bc663
+size 11423430497

global_step937/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a179c5adc0863faffec99b32d1ec23d851d804518dc60af50bb8357441ec051
+size 11423430497

global_step937/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40df9f4bcc85930d945fa0678ff88ae1a9c69d4a157b8ebe16f505f6f83d3cb5
+size 169627507

global_step937/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab59817f4453589263aa5e7a01959517629a6a861a4b16cea28ff354a4d4c56a
+size 169627507

global_step937/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ece99d0e4757353f0570d48534a2ed9a98eadfbd1ba55094374614177c8d2f9
+size 169627507

global_step937/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570ae7bd9ff29d075bcda4b86de24c596b339fa69f2f0d9485f6de5bf1d965b0
+size 169627507

global_step937/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9224fee2222ca76d62aa1f75cb78079f9200d5e9e5e8dcd08174cc2b1bb303a4
+size 169627507

global_step937/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2150a4e8bec55181049d5d6affeb0a2e6fe1c6b62cfea616ebc1d6cce0501290
+size 169627507

global_step937/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88cbc3fd1c76cce48ca91d6ddf26fa1cddb6f77cfeea7807aea6e4d442a72078
+size 169627507

global_step937/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417157661063ba254457db511ae24999b611f2e465f68c45b7f2fe362c29e035
+size 169627507

latest

@@ -0,0 +1 @@
+global_step937

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb9eaa6c375b0df0426e58437d792fd53fd06418dad292784dcc6bccb9c188d
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59657b4548cc7d16af3798f32fab6464d7022cc7e790098af37132543bfb7b1e
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42eed8a45b1c3a3bbaf4732b98ae267c528e7b321ae085dfd9068546e4f3943
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3356ac68d601e410d185e2b78d2ac12f2259aa7f6d7eb25b9027e3ec610f01
+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 +1,37 @@
+{
+  "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_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,
+  "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 sha256:478b41e9f26d338fd8f896e08cad1adab7c423b61f1b45754113bc78d256a3f9
+size 16389

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce29a8767a7d907dd24987aa2c3e654d4317f3042fbc13b5b72cadb46d43311a
+size 16389

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a48db011646b4e9a867bf12f4a233cad5dfbfe309686f8996c250196d3783a
+size 16389

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9562ee822472a4f01dcd6349ab3d1ef42a48915fe3b92e843a0c37db53c8421
+size 16389

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d2767d83c3bf27f12db022b0632e2c4f8c164274ba75e380cf18f9d5f21819
+size 16389

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76816358d4e5db8149d60d55234db658d67a13c0c1ce05d7404cf7125a676a5c
+size 16389

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1562e7520c977d178183d641f70abcf3f57da2489938756cfbebf9b6e6c1a9fd
+size 16389

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b6cabaed045c5398cd1b732f7ec48bd363f3b43cd24e0e70e641a42bd00c28
+size 16389

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35277d637a1704fbdf5c960b22475478a524394a3809ddf0f6c2eb198b7cd21c
+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 +1,1429 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 938,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010666666666666666,
+      "grad_norm": 46.42798146527443,
+      "learning_rate": 9.574468085106382e-08,
+      "logits/chosen": 2.382258415222168,
+      "logits/rejected": 2.7442336082458496,
+      "logps/chosen": -138.31182861328125,
+      "logps/rejected": -147.63272094726562,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4281249940395355,
+      "rewards/chosen": -0.0015843239380046725,
+      "rewards/margins": 3.248453140258789e-06,
+      "rewards/rejected": -0.0015875725075602531,
+      "step": 10
+    },
+    {
+      "epoch": 0.021333333333333333,
+      "grad_norm": 48.61255110254263,
+      "learning_rate": 2.0212765957446807e-07,
+      "logits/chosen": 2.313032627105713,
+      "logits/rejected": 2.844193458557129,
+      "logps/chosen": -138.99807739257812,
+      "logps/rejected": -135.5998992919922,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.008929151110351086,
+      "rewards/margins": 0.0014812585432082415,
+      "rewards/rejected": -0.010410408489406109,
+      "step": 20
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 41.089142727664616,
+      "learning_rate": 3.085106382978723e-07,
+      "logits/chosen": 2.291680097579956,
+      "logits/rejected": 2.7390356063842773,
+      "logps/chosen": -126.77516174316406,
+      "logps/rejected": -131.89663696289062,
+      "loss": 0.6804,
+      "rewards/accuracies": 0.6312499642372131,
+      "rewards/chosen": -0.013881472870707512,
+      "rewards/margins": 0.028002463281154633,
+      "rewards/rejected": -0.041883938014507294,
+      "step": 30
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 45.92788214228633,
+      "learning_rate": 4.148936170212766e-07,
+      "logits/chosen": 2.523430585861206,
+      "logits/rejected": 2.84600567817688,
+      "logps/chosen": -134.11170959472656,
+      "logps/rejected": -140.52801513671875,
+      "loss": 0.6492,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.009366204962134361,
+      "rewards/margins": 0.1010168194770813,
+      "rewards/rejected": -0.11038301885128021,
+      "step": 40
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 39.55493674378011,
+      "learning_rate": 5.212765957446809e-07,
+      "logits/chosen": 2.463056802749634,
+      "logits/rejected": 3.003122329711914,
+      "logps/chosen": -134.13511657714844,
+      "logps/rejected": -153.1929473876953,
+      "loss": 0.6023,
+      "rewards/accuracies": 0.7468750476837158,
+      "rewards/chosen": -0.04466788098216057,
+      "rewards/margins": 0.24204480648040771,
+      "rewards/rejected": -0.2867127060890198,
+      "step": 50
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 30.3497904000491,
+      "learning_rate": 6.276595744680851e-07,
+      "logits/chosen": 2.2184526920318604,
+      "logits/rejected": 2.7464191913604736,
+      "logps/chosen": -125.64830017089844,
+      "logps/rejected": -129.73838806152344,
+      "loss": 0.5494,
+      "rewards/accuracies": 0.7531250715255737,
+      "rewards/chosen": 0.06083741411566734,
+      "rewards/margins": 0.429790735244751,
+      "rewards/rejected": -0.3689533472061157,
+      "step": 60
+    },
+    {
+      "epoch": 0.07466666666666667,
+      "grad_norm": 38.90457231803085,
+      "learning_rate": 7.340425531914893e-07,
+      "logits/chosen": 2.197575569152832,
+      "logits/rejected": 2.578211784362793,
+      "logps/chosen": -135.662353515625,
+      "logps/rejected": -136.03961181640625,
+      "loss": 0.5285,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": 0.29434823989868164,
+      "rewards/margins": 0.5787851810455322,
+      "rewards/rejected": -0.28443700075149536,
+      "step": 70
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 43.610746377169825,
+      "learning_rate": 8.404255319148936e-07,
+      "logits/chosen": 2.2334251403808594,
+      "logits/rejected": 2.8087658882141113,
+      "logps/chosen": -132.78274536132812,
+      "logps/rejected": -142.40440368652344,
+      "loss": 0.4869,
+      "rewards/accuracies": 0.7718750834465027,
+      "rewards/chosen": 0.16994354128837585,
+      "rewards/margins": 0.8923333287239075,
+      "rewards/rejected": -0.722389817237854,
+      "step": 80
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 26.982449978848148,
+      "learning_rate": 9.468085106382978e-07,
+      "logits/chosen": 2.2855160236358643,
+      "logits/rejected": 2.6503257751464844,
+      "logps/chosen": -136.7552947998047,
+      "logps/rejected": -148.2338104248047,
+      "loss": 0.4819,
+      "rewards/accuracies": 0.778124988079071,
+      "rewards/chosen": -0.1698712259531021,
+      "rewards/margins": 1.1215158700942993,
+      "rewards/rejected": -1.2913870811462402,
+      "step": 90
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 29.896207171331433,
+      "learning_rate": 9.999134070902206e-07,
+      "logits/chosen": 2.382267951965332,
+      "logits/rejected": 2.517061948776245,
+      "logps/chosen": -126.52420806884766,
+      "logps/rejected": -158.33543395996094,
+      "loss": 0.4183,
+      "rewards/accuracies": 0.778124988079071,
+      "rewards/chosen": -0.3784619867801666,
+      "rewards/margins": 1.4470703601837158,
+      "rewards/rejected": -1.82553231716156,
+      "step": 100
+    },
+    {
+      "epoch": 0.11733333333333333,
+      "grad_norm": 22.595589720258207,
+      "learning_rate": 9.99220843761565e-07,
+      "logits/chosen": 2.2189204692840576,
+      "logits/rejected": 2.7971031665802,
+      "logps/chosen": -145.4073486328125,
+      "logps/rejected": -148.38609313964844,
+      "loss": 0.3777,
+      "rewards/accuracies": 0.8343750238418579,
+      "rewards/chosen": -0.6497014760971069,
+      "rewards/margins": 1.5745065212249756,
+      "rewards/rejected": -2.224207878112793,
+      "step": 110
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 30.721800605452906,
+      "learning_rate": 9.97836676558346e-07,
+      "logits/chosen": 2.174267292022705,
+      "logits/rejected": 2.853877544403076,
+      "logps/chosen": -142.8085479736328,
+      "logps/rejected": -149.57443237304688,
+      "loss": 0.4048,
+      "rewards/accuracies": 0.796875,
+      "rewards/chosen": -0.5126703381538391,
+      "rewards/margins": 1.7328587770462036,
+      "rewards/rejected": -2.2455291748046875,
+      "step": 120
+    },
+    {
+      "epoch": 0.13866666666666666,
+      "grad_norm": 34.136357440276,
+      "learning_rate": 9.957628230595525e-07,
+      "logits/chosen": 2.1472320556640625,
+      "logits/rejected": 2.640443801879883,
+      "logps/chosen": -141.8199005126953,
+      "logps/rejected": -155.64419555664062,
+      "loss": 0.4673,
+      "rewards/accuracies": 0.746874988079071,
+      "rewards/chosen": -0.25329455733299255,
+      "rewards/margins": 1.7003322839736938,
+      "rewards/rejected": -1.9536267518997192,
+      "step": 130
+    },
+    {
+      "epoch": 0.14933333333333335,
+      "grad_norm": 42.43483647388403,
+      "learning_rate": 9.9300215631252e-07,
+      "logits/chosen": 2.1069414615631104,
+      "logits/rejected": 2.291423797607422,
+      "logps/chosen": -125.19463348388672,
+      "logps/rejected": -158.3802032470703,
+      "loss": 0.3758,
+      "rewards/accuracies": 0.8437499403953552,
+      "rewards/chosen": 0.07672759145498276,
+      "rewards/margins": 2.0006155967712402,
+      "rewards/rejected": -1.9238877296447754,
+      "step": 140
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 36.02384513576028,
+      "learning_rate": 9.895585008527075e-07,
+      "logits/chosen": 2.3169870376586914,
+      "logits/rejected": 2.500821590423584,
+      "logps/chosen": -138.5598907470703,
+      "logps/rejected": -168.0284881591797,
+      "loss": 0.4251,
+      "rewards/accuracies": 0.8218750953674316,
+      "rewards/chosen": -0.4848916530609131,
+      "rewards/margins": 2.033202886581421,
+      "rewards/rejected": -2.518094301223755,
+      "step": 150
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 15.042416822714568,
+      "learning_rate": 9.854366274053124e-07,
+      "logits/chosen": 2.0532939434051514,
+      "logits/rejected": 2.4741499423980713,
+      "logps/chosen": -135.32594299316406,
+      "logps/rejected": -155.9827880859375,
+      "loss": 0.3675,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -0.19416652619838715,
+      "rewards/margins": 2.0035641193389893,
+      "rewards/rejected": -2.197730541229248,
+      "step": 160
+    },
+    {
+      "epoch": 0.18133333333333335,
+      "grad_norm": 29.38433081829733,
+      "learning_rate": 9.806422462760687e-07,
+      "logits/chosen": 2.0831096172332764,
+      "logits/rejected": 2.4652578830718994,
+      "logps/chosen": -139.71656799316406,
+      "logps/rejected": -160.39244079589844,
+      "loss": 0.4298,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -0.6061689853668213,
+      "rewards/margins": 2.0064656734466553,
+      "rewards/rejected": -2.6126346588134766,
+      "step": 170
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 30.944868310764818,
+      "learning_rate": 9.7518199944038e-07,
+      "logits/chosen": 2.0607786178588867,
+      "logits/rejected": 2.363945245742798,
+      "logps/chosen": -136.1494598388672,
+      "logps/rejected": -157.36947631835938,
+      "loss": 0.4231,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.39128583669662476,
+      "rewards/margins": 1.969771385192871,
+      "rewards/rejected": -2.3610572814941406,
+      "step": 180
+    },
+    {
+      "epoch": 0.20266666666666666,
+      "grad_norm": 42.05053142859476,
+      "learning_rate": 9.690634513417486e-07,
+      "logits/chosen": 2.169426918029785,
+      "logits/rejected": 2.328373670578003,
+      "logps/chosen": -135.956298828125,
+      "logps/rejected": -170.6649169921875,
+      "loss": 0.3561,
+      "rewards/accuracies": 0.859375,
+      "rewards/chosen": -0.7195563912391663,
+      "rewards/margins": 2.492656946182251,
+      "rewards/rejected": -3.2122128009796143,
+      "step": 190
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 35.520349085403645,
+      "learning_rate": 9.622950784122471e-07,
+      "logits/chosen": 2.020885944366455,
+      "logits/rejected": 2.4902377128601074,
+      "logps/chosen": -139.86936950683594,
+      "logps/rejected": -165.3739013671875,
+      "loss": 0.3948,
+      "rewards/accuracies": 0.8093750476837158,
+      "rewards/chosen": -0.8580716252326965,
+      "rewards/margins": 2.244415283203125,
+      "rewards/rejected": -3.1024868488311768,
+      "step": 200
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 30.914393418212303,
+      "learning_rate": 9.54886257329555e-07,
+      "logits/chosen": 2.032724380493164,
+      "logits/rejected": 2.399937152862549,
+      "logps/chosen": -131.96702575683594,
+      "logps/rejected": -155.24063110351562,
+      "loss": 0.4144,
+      "rewards/accuracies": 0.8125000596046448,
+      "rewards/chosen": -0.2814589738845825,
+      "rewards/margins": 2.195185422897339,
+      "rewards/rejected": -2.476644515991211,
+      "step": 210
+    },
+    {
+      "epoch": 0.23466666666666666,
+      "grad_norm": 33.70657801293605,
+      "learning_rate": 9.468472520268205e-07,
+      "logits/chosen": 2.0024030208587646,
+      "logits/rejected": 2.4853296279907227,
+      "logps/chosen": -137.35540771484375,
+      "logps/rejected": -155.17100524902344,
+      "loss": 0.38,
+      "rewards/accuracies": 0.8218749761581421,
+      "rewards/chosen": -0.004300939850509167,
+      "rewards/margins": 2.1314268112182617,
+      "rewards/rejected": -2.135727643966675,
+      "step": 220
+    },
+    {
+      "epoch": 0.24533333333333332,
+      "grad_norm": 37.495577601362356,
+      "learning_rate": 9.381891994733519e-07,
+      "logits/chosen": 2.243539810180664,
+      "logits/rejected": 2.352928400039673,
+      "logps/chosen": -129.24896240234375,
+      "logps/rejected": -169.98135375976562,
+      "loss": 0.3679,
+      "rewards/accuracies": 0.8218750357627869,
+      "rewards/chosen": -0.28722256422042847,
+      "rewards/margins": 2.4391627311706543,
+      "rewards/rejected": -2.7263851165771484,
+      "step": 230
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 25.343951064869156,
+      "learning_rate": 9.289240942458321e-07,
+      "logits/chosen": 2.0728087425231934,
+      "logits/rejected": 2.4773340225219727,
+      "logps/chosen": -135.0269775390625,
+      "logps/rejected": -168.2124481201172,
+      "loss": 0.3123,
+      "rewards/accuracies": 0.846875011920929,
+      "rewards/chosen": -0.4651724398136139,
+      "rewards/margins": 2.803205966949463,
+      "rewards/rejected": -3.268378734588623,
+      "step": 240
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 29.0620379587301,
+      "learning_rate": 9.190647719114326e-07,
+      "logits/chosen": 1.8383233547210693,
+      "logits/rejected": 2.2059688568115234,
+      "logps/chosen": -136.12245178222656,
+      "logps/rejected": -174.0221405029297,
+      "loss": 0.4021,
+      "rewards/accuracies": 0.8250000476837158,
+      "rewards/chosen": -0.4718845784664154,
+      "rewards/margins": 2.437692642211914,
+      "rewards/rejected": -2.9095773696899414,
+      "step": 250
+    },
+    {
+      "epoch": 0.2773333333333333,
+      "grad_norm": 32.206451154260584,
+      "learning_rate": 9.086248912458483e-07,
+      "logits/chosen": 1.901822805404663,
+      "logits/rejected": 2.3750545978546143,
+      "logps/chosen": -137.2100830078125,
+      "logps/rejected": -160.05950927734375,
+      "loss": 0.3368,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.45527350902557373,
+      "rewards/margins": 2.3181633949279785,
+      "rewards/rejected": -2.7734367847442627,
+      "step": 260
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 22.28437598082458,
+      "learning_rate": 8.976189153108852e-07,
+      "logits/chosen": 1.8406670093536377,
+      "logits/rejected": 2.231459617614746,
+      "logps/chosen": -136.8876495361328,
+      "logps/rejected": -162.5147247314453,
+      "loss": 0.3545,
+      "rewards/accuracies": 0.8468750715255737,
+      "rewards/chosen": -0.5715955495834351,
+      "rewards/margins": 2.6194005012512207,
+      "rewards/rejected": -3.1909961700439453,
+      "step": 270
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 26.163035485727516,
+      "learning_rate": 8.860620914178187e-07,
+      "logits/chosen": 1.7282989025115967,
+      "logits/rejected": 2.090369462966919,
+      "logps/chosen": -133.57354736328125,
+      "logps/rejected": -169.84217834472656,
+      "loss": 0.3629,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.4477410912513733,
+      "rewards/margins": 2.430133581161499,
+      "rewards/rejected": -2.8778748512268066,
+      "step": 280
+    },
+    {
+      "epoch": 0.30933333333333335,
+      "grad_norm": 27.544558000777418,
+      "learning_rate": 8.739704300042778e-07,
+      "logits/chosen": 1.6349306106567383,
+      "logits/rejected": 2.2942090034484863,
+      "logps/chosen": -137.38523864746094,
+      "logps/rejected": -158.7125244140625,
+      "loss": 0.3788,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.5446420907974243,
+      "rewards/margins": 2.5425944328308105,
+      "rewards/rejected": -3.0872364044189453,
+      "step": 290
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 28.15835022856019,
+      "learning_rate": 8.613606824539197e-07,
+      "logits/chosen": 1.611955165863037,
+      "logits/rejected": 2.1477112770080566,
+      "logps/chosen": -137.20155334472656,
+      "logps/rejected": -163.80764770507812,
+      "loss": 0.3507,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.41365841031074524,
+      "rewards/margins": 2.4483883380889893,
+      "rewards/rejected": -2.8620471954345703,
+      "step": 300
+    },
+    {
+      "epoch": 0.33066666666666666,
+      "grad_norm": 26.9394473330418,
+      "learning_rate": 8.482503178896226e-07,
+      "logits/chosen": 1.5950888395309448,
+      "logits/rejected": 1.8947237730026245,
+      "logps/chosen": -138.35462951660156,
+      "logps/rejected": -167.69569396972656,
+      "loss": 0.3696,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -0.8275109529495239,
+      "rewards/margins": 2.685105323791504,
+      "rewards/rejected": -3.5126163959503174,
+      "step": 310
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 23.332637225870037,
+      "learning_rate": 8.346574989723469e-07,
+      "logits/chosen": 1.7531938552856445,
+      "logits/rejected": 2.2487497329711914,
+      "logps/chosen": -143.16526794433594,
+      "logps/rejected": -166.20895385742188,
+      "loss": 0.3582,
+      "rewards/accuracies": 0.8437500596046448,
+      "rewards/chosen": -0.5256407260894775,
+      "rewards/margins": 2.5411202907562256,
+      "rewards/rejected": -3.0667612552642822,
+      "step": 320
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 21.87942904244536,
+      "learning_rate": 8.206010567391916e-07,
+      "logits/chosen": 1.593059778213501,
+      "logits/rejected": 2.1650094985961914,
+      "logps/chosen": -131.16326904296875,
+      "logps/rejected": -158.94223022460938,
+      "loss": 0.3461,
+      "rewards/accuracies": 0.8468750715255737,
+      "rewards/chosen": -0.4646984934806824,
+      "rewards/margins": 2.3126156330108643,
+      "rewards/rejected": -2.7773139476776123,
+      "step": 330
+    },
+    {
+      "epoch": 0.3626666666666667,
+      "grad_norm": 31.101098463657916,
+      "learning_rate": 8.061004645155048e-07,
+      "logits/chosen": 1.5677554607391357,
+      "logits/rejected": 1.9733402729034424,
+      "logps/chosen": -146.71609497070312,
+      "logps/rejected": -171.69955444335938,
+      "loss": 0.3235,
+      "rewards/accuracies": 0.8656250238418579,
+      "rewards/chosen": -0.48211732506752014,
+      "rewards/margins": 2.4466898441314697,
+      "rewards/rejected": -2.928807020187378,
+      "step": 340
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 30.645699097464068,
+      "learning_rate": 7.911758109371889e-07,
+      "logits/chosen": 1.6403833627700806,
+      "logits/rejected": 1.8808367252349854,
+      "logps/chosen": -140.71217346191406,
+      "logps/rejected": -175.47921752929688,
+      "loss": 0.3459,
+      "rewards/accuracies": 0.8437500596046448,
+      "rewards/chosen": -0.7281967401504517,
+      "rewards/margins": 2.3733932971954346,
+      "rewards/rejected": -3.1015896797180176,
+      "step": 350
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 24.51134274765049,
+      "learning_rate": 7.758477721205765e-07,
+      "logits/chosen": 1.7783101797103882,
+      "logits/rejected": 2.1137070655822754,
+      "logps/chosen": -137.43540954589844,
+      "logps/rejected": -163.09820556640625,
+      "loss": 0.3483,
+      "rewards/accuracies": 0.8375000357627869,
+      "rewards/chosen": -0.7030624747276306,
+      "rewards/margins": 2.4687132835388184,
+      "rewards/rejected": -3.1717755794525146,
+      "step": 360
+    },
+    {
+      "epoch": 0.39466666666666667,
+      "grad_norm": 18.074083008686905,
+      "learning_rate": 7.601375830184295e-07,
+      "logits/chosen": 1.5980160236358643,
+      "logits/rejected": 1.8996552228927612,
+      "logps/chosen": -140.5148162841797,
+      "logps/rejected": -171.46630859375,
+      "loss": 0.313,
+      "rewards/accuracies": 0.8875000476837158,
+      "rewards/chosen": -0.7159416675567627,
+      "rewards/margins": 2.979588508605957,
+      "rewards/rejected": -3.695530414581299,
+      "step": 370
+    },
+    {
+      "epoch": 0.4053333333333333,
+      "grad_norm": 29.247823050349254,
+      "learning_rate": 7.440670080017454e-07,
+      "logits/chosen": 1.5842480659484863,
+      "logits/rejected": 2.019357919692993,
+      "logps/chosen": -132.16673278808594,
+      "logps/rejected": -162.817138671875,
+      "loss": 0.3415,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.69346022605896,
+      "rewards/margins": 2.366546392440796,
+      "rewards/rejected": -3.060007095336914,
+      "step": 380
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 31.9631460774584,
+      "learning_rate": 7.276583107081242e-07,
+      "logits/chosen": 1.6213833093643188,
+      "logits/rejected": 2.0778937339782715,
+      "logps/chosen": -141.9418487548828,
+      "logps/rejected": -174.61468505859375,
+      "loss": 0.3329,
+      "rewards/accuracies": 0.8624999523162842,
+      "rewards/chosen": -1.060402750968933,
+      "rewards/margins": 2.9680538177490234,
+      "rewards/rejected": -4.028456211090088,
+      "step": 390
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 26.16381075907044,
+      "learning_rate": 7.109342231984698e-07,
+      "logits/chosen": 1.3554099798202515,
+      "logits/rejected": 2.0283570289611816,
+      "logps/chosen": -138.100341796875,
+      "logps/rejected": -159.7268829345703,
+      "loss": 0.3786,
+      "rewards/accuracies": 0.8343749642372131,
+      "rewards/chosen": -1.067877173423767,
+      "rewards/margins": 2.4551329612731934,
+      "rewards/rejected": -3.52301025390625,
+      "step": 400
+    },
+    {
+      "epoch": 0.43733333333333335,
+      "grad_norm": 11.140411163657106,
+      "learning_rate": 6.939179144647515e-07,
+      "logits/chosen": 1.385094165802002,
+      "logits/rejected": 1.9930095672607422,
+      "logps/chosen": -129.92941284179688,
+      "logps/rejected": -155.423095703125,
+      "loss": 0.2945,
+      "rewards/accuracies": 0.878125011920929,
+      "rewards/chosen": -0.29770562052726746,
+      "rewards/margins": 2.735492706298828,
+      "rewards/rejected": -3.033198118209839,
+      "step": 410
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 28.56957418913061,
+      "learning_rate": 6.766329583324581e-07,
+      "logits/chosen": 1.437608003616333,
+      "logits/rejected": 1.9395537376403809,
+      "logps/chosen": -131.2879638671875,
+      "logps/rejected": -159.0998992919922,
+      "loss": 0.3127,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.49805647134780884,
+      "rewards/margins": 2.613166570663452,
+      "rewards/rejected": -3.111222743988037,
+      "step": 420
+    },
+    {
+      "epoch": 0.45866666666666667,
+      "grad_norm": 33.23437534680263,
+      "learning_rate": 6.591033008022067e-07,
+      "logits/chosen": 1.3858729600906372,
+      "logits/rejected": 1.6989398002624512,
+      "logps/chosen": -134.23770141601562,
+      "logps/rejected": -176.20919799804688,
+      "loss": 0.3096,
+      "rewards/accuracies": 0.871874988079071,
+      "rewards/chosen": -0.535869836807251,
+      "rewards/margins": 3.0371181964874268,
+      "rewards/rejected": -3.572988510131836,
+      "step": 430
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 28.346897945132458,
+      "learning_rate": 6.413532268757537e-07,
+      "logits/chosen": 1.4444637298583984,
+      "logits/rejected": 1.6581867933273315,
+      "logps/chosen": -138.23431396484375,
+      "logps/rejected": -168.9981689453125,
+      "loss": 0.4194,
+      "rewards/accuracies": 0.796875,
+      "rewards/chosen": -0.7419812083244324,
+      "rewards/margins": 2.335297107696533,
+      "rewards/rejected": -3.0772783756256104,
+      "step": 440
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 29.164626019209308,
+      "learning_rate": 6.234073269123653e-07,
+      "logits/chosen": 1.393236756324768,
+      "logits/rejected": 1.7022786140441895,
+      "logps/chosen": -142.96592712402344,
+      "logps/rejected": -173.4695587158203,
+      "loss": 0.3408,
+      "rewards/accuracies": 0.8375000357627869,
+      "rewards/chosen": -1.0506477355957031,
+      "rewards/margins": 2.8269805908203125,
+      "rewards/rejected": -3.8776283264160156,
+      "step": 450
+    },
+    {
+      "epoch": 0.49066666666666664,
+      "grad_norm": 27.21924736505641,
+      "learning_rate": 6.052904625621555e-07,
+      "logits/chosen": 1.4608548879623413,
+      "logits/rejected": 1.7432273626327515,
+      "logps/chosen": -138.21566772460938,
+      "logps/rejected": -167.56101989746094,
+      "loss": 0.3906,
+      "rewards/accuracies": 0.8343750238418579,
+      "rewards/chosen": -0.971255362033844,
+      "rewards/margins": 2.769684314727783,
+      "rewards/rejected": -3.7409396171569824,
+      "step": 460
+    },
+    {
+      "epoch": 0.5013333333333333,
+      "grad_norm": 23.667407037284928,
+      "learning_rate": 5.870277323235871e-07,
+      "logits/chosen": 1.3296135663986206,
+      "logits/rejected": 1.8589414358139038,
+      "logps/chosen": -145.2051239013672,
+      "logps/rejected": -172.4295196533203,
+      "loss": 0.3328,
+      "rewards/accuracies": 0.8593749403953552,
+      "rewards/chosen": -0.9092783331871033,
+      "rewards/margins": 2.5038325786590576,
+      "rewards/rejected": -3.4131109714508057,
+      "step": 470
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 32.4308081410924,
+      "learning_rate": 5.686444367728494e-07,
+      "logits/chosen": 1.3602862358093262,
+      "logits/rejected": 1.752657413482666,
+      "logps/chosen": -137.1173858642578,
+      "logps/rejected": -167.48741149902344,
+      "loss": 0.3152,
+      "rewards/accuracies": 0.8812499642372131,
+      "rewards/chosen": -0.6123771071434021,
+      "rewards/margins": 2.6645078659057617,
+      "rewards/rejected": -3.2768850326538086,
+      "step": 480
+    },
+    {
+      "epoch": 0.5226666666666666,
+      "grad_norm": 22.650259255481703,
+      "learning_rate": 5.50166043513287e-07,
+      "logits/chosen": 1.3106579780578613,
+      "logits/rejected": 1.7208105325698853,
+      "logps/chosen": -132.9499969482422,
+      "logps/rejected": -168.179443359375,
+      "loss": 0.3225,
+      "rewards/accuracies": 0.8250000476837158,
+      "rewards/chosen": -0.5453524589538574,
+      "rewards/margins": 2.830275058746338,
+      "rewards/rejected": -3.3756275177001953,
+      "step": 490
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 34.87144459717604,
+      "learning_rate": 5.316181518934318e-07,
+      "logits/chosen": 1.4427666664123535,
+      "logits/rejected": 1.6337779760360718,
+      "logps/chosen": -131.83047485351562,
+      "logps/rejected": -163.92172241210938,
+      "loss": 0.3208,
+      "rewards/accuracies": 0.8531249761581421,
+      "rewards/chosen": -0.47837477922439575,
+      "rewards/margins": 2.7933568954467773,
+      "rewards/rejected": -3.2717316150665283,
+      "step": 500
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 31.52951767510459,
+      "learning_rate": 5.130264575425224e-07,
+      "logits/chosen": 1.4013196229934692,
+      "logits/rejected": 1.6610275506973267,
+      "logps/chosen": -132.53924560546875,
+      "logps/rejected": -167.6267547607422,
+      "loss": 0.272,
+      "rewards/accuracies": 0.8593749403953552,
+      "rewards/chosen": -0.5326389074325562,
+      "rewards/margins": 2.8615810871124268,
+      "rewards/rejected": -3.3942196369171143,
+      "step": 510
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 29.37500979396824,
+      "learning_rate": 4.944167167726367e-07,
+      "logits/chosen": 1.4267271757125854,
+      "logits/rejected": 1.6526139974594116,
+      "logps/chosen": -133.26963806152344,
+      "logps/rejected": -173.13449096679688,
+      "loss": 0.3273,
+      "rewards/accuracies": 0.8375000357627869,
+      "rewards/chosen": -0.6281304955482483,
+      "rewards/margins": 3.023805856704712,
+      "rewards/rejected": -3.6519365310668945,
+      "step": 520
+    },
+    {
+      "epoch": 0.5653333333333334,
+      "grad_norm": 45.4295336560468,
+      "learning_rate": 4.758147108967584e-07,
+      "logits/chosen": 1.5470153093338013,
+      "logits/rejected": 1.7743972539901733,
+      "logps/chosen": -150.69190979003906,
+      "logps/rejected": -186.68701171875,
+      "loss": 0.3734,
+      "rewards/accuracies": 0.8281250596046448,
+      "rewards/chosen": -1.2518389225006104,
+      "rewards/margins": 2.885488271713257,
+      "rewards/rejected": -4.137327194213867,
+      "step": 530
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 21.855665145983874,
+      "learning_rate": 4.572462105122077e-07,
+      "logits/chosen": 1.3561698198318481,
+      "logits/rejected": 1.7270151376724243,
+      "logps/chosen": -139.5657501220703,
+      "logps/rejected": -175.99508666992188,
+      "loss": 0.2833,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": -1.112634301185608,
+      "rewards/margins": 3.2117066383361816,
+      "rewards/rejected": -4.3243408203125,
+      "step": 540
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 24.367461053001698,
+      "learning_rate": 4.3873693979891696e-07,
+      "logits/chosen": 1.4616541862487793,
+      "logits/rejected": 1.7883496284484863,
+      "logps/chosen": -140.05160522460938,
+      "logps/rejected": -181.77622985839844,
+      "loss": 0.2513,
+      "rewards/accuracies": 0.9062500596046448,
+      "rewards/chosen": -0.8183116912841797,
+      "rewards/margins": 3.3123300075531006,
+      "rewards/rejected": -4.130641937255859,
+      "step": 550
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 23.757622976541885,
+      "learning_rate": 4.203125408820105e-07,
+      "logits/chosen": 1.4851560592651367,
+      "logits/rejected": 1.794302225112915,
+      "logps/chosen": -134.1141357421875,
+      "logps/rejected": -170.49234008789062,
+      "loss": 0.3149,
+      "rewards/accuracies": 0.8843750357627869,
+      "rewards/chosen": -0.9360587000846863,
+      "rewards/margins": 2.853070020675659,
+      "rewards/rejected": -3.7891287803649902,
+      "step": 560
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 21.213296976158986,
+      "learning_rate": 4.019985383080632e-07,
+      "logits/chosen": 1.237152338027954,
+      "logits/rejected": 1.7590258121490479,
+      "logps/chosen": -138.93270874023438,
+      "logps/rejected": -160.0484619140625,
+      "loss": 0.3722,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.7550384998321533,
+      "rewards/margins": 2.6985340118408203,
+      "rewards/rejected": -3.4535727500915527,
+      "step": 570
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": 26.294885755983195,
+      "learning_rate": 3.8382030368424454e-07,
+      "logits/chosen": 1.3558965921401978,
+      "logits/rejected": 1.6953362226486206,
+      "logps/chosen": -137.65817260742188,
+      "logps/rejected": -170.1033477783203,
+      "loss": 0.3269,
+      "rewards/accuracies": 0.8531249761581421,
+      "rewards/chosen": -0.6933549046516418,
+      "rewards/margins": 2.7456483840942383,
+      "rewards/rejected": -3.4390032291412354,
+      "step": 580
+    },
+    {
+      "epoch": 0.6293333333333333,
+      "grad_norm": 33.07924807089865,
+      "learning_rate": 3.6580302052934297e-07,
+      "logits/chosen": 1.2663443088531494,
+      "logits/rejected": 1.5939358472824097,
+      "logps/chosen": -132.91456604003906,
+      "logps/rejected": -162.4006805419922,
+      "loss": 0.331,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.6310861706733704,
+      "rewards/margins": 2.8310067653656006,
+      "rewards/rejected": -3.4620931148529053,
+      "step": 590
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 20.115198065979413,
+      "learning_rate": 3.479716493853611e-07,
+      "logits/chosen": 1.18405020236969,
+      "logits/rejected": 1.536871075630188,
+      "logps/chosen": -131.33584594726562,
+      "logps/rejected": -168.03636169433594,
+      "loss": 0.2805,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": -0.6372289061546326,
+      "rewards/margins": 3.1736860275268555,
+      "rewards/rejected": -3.810914993286133,
+      "step": 600
+    },
+    {
+      "epoch": 0.6506666666666666,
+      "grad_norm": 19.273605121929624,
+      "learning_rate": 3.303508932380132e-07,
+      "logits/chosen": 1.2737094163894653,
+      "logits/rejected": 1.6445541381835938,
+      "logps/chosen": -136.96719360351562,
+      "logps/rejected": -174.71083068847656,
+      "loss": 0.3445,
+      "rewards/accuracies": 0.8562500476837158,
+      "rewards/chosen": -0.6345027685165405,
+      "rewards/margins": 2.950732946395874,
+      "rewards/rejected": -3.585235834121704,
+      "step": 610
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": 30.667064690871456,
+      "learning_rate": 3.129651632940362e-07,
+      "logits/chosen": 1.292923927307129,
+      "logits/rejected": 1.5391473770141602,
+      "logps/chosen": -141.96238708496094,
+      "logps/rejected": -173.04873657226562,
+      "loss": 0.2906,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.597599983215332,
+      "rewards/margins": 3.03706955909729,
+      "rewards/rejected": -3.634669303894043,
+      "step": 620
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 25.676210849380702,
+      "learning_rate": 2.958385451627181e-07,
+      "logits/chosen": 1.231809139251709,
+      "logits/rejected": 1.600536823272705,
+      "logps/chosen": -139.60745239257812,
+      "logps/rejected": -178.7290496826172,
+      "loss": 0.2972,
+      "rewards/accuracies": 0.871874988079071,
+      "rewards/chosen": -0.7131984829902649,
+      "rewards/margins": 3.2930028438568115,
+      "rewards/rejected": -4.006201267242432,
+      "step": 630
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 30.707834181954617,
+      "learning_rate": 2.7899476548850043e-07,
+      "logits/chosen": 1.299914836883545,
+      "logits/rejected": 1.624165415763855,
+      "logps/chosen": -139.61639404296875,
+      "logps/rejected": -172.74610900878906,
+      "loss": 0.3445,
+      "rewards/accuracies": 0.8500000834465027,
+      "rewards/chosen": -0.7801929116249084,
+      "rewards/margins": 2.922720432281494,
+      "rewards/rejected": -3.702913284301758,
+      "step": 640
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 26.04525358558716,
+      "learning_rate": 2.6245715908087804e-07,
+      "logits/chosen": 1.3557870388031006,
+      "logits/rejected": 1.6440367698669434,
+      "logps/chosen": -138.72109985351562,
+      "logps/rejected": -166.85986328125,
+      "loss": 0.3891,
+      "rewards/accuracies": 0.8375000357627869,
+      "rewards/chosen": -0.8479130864143372,
+      "rewards/margins": 2.6863441467285156,
+      "rewards/rejected": -3.534257173538208,
+      "step": 650
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 38.60539175189378,
+      "learning_rate": 2.462486365871338e-07,
+      "logits/chosen": 1.117995262145996,
+      "logits/rejected": 1.5660450458526611,
+      "logps/chosen": -139.3802490234375,
+      "logps/rejected": -170.3036346435547,
+      "loss": 0.3707,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.7362462878227234,
+      "rewards/margins": 2.719696521759033,
+      "rewards/rejected": -3.4559431076049805,
+      "step": 660
+    },
+    {
+      "epoch": 0.7146666666666667,
+      "grad_norm": 29.88817411661078,
+      "learning_rate": 2.3039165275269214e-07,
+      "logits/chosen": 1.2235151529312134,
+      "logits/rejected": 1.5882010459899902,
+      "logps/chosen": -133.53123474121094,
+      "logps/rejected": -165.77561950683594,
+      "loss": 0.3481,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.7423657178878784,
+      "rewards/margins": 2.9302687644958496,
+      "rewards/rejected": -3.6726343631744385,
+      "step": 670
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 26.689941208436807,
+      "learning_rate": 2.1490817531306775e-07,
+      "logits/chosen": 1.199167013168335,
+      "logits/rejected": 1.4307794570922852,
+      "logps/chosen": -138.82012939453125,
+      "logps/rejected": -172.9408416748047,
+      "loss": 0.3102,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": -0.6661445498466492,
+      "rewards/margins": 3.147897958755493,
+      "rewards/rejected": -3.814042329788208,
+      "step": 680
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 26.51411323153538,
+      "learning_rate": 1.9981965456049598e-07,
+      "logits/chosen": 1.2847270965576172,
+      "logits/rejected": 1.527156949043274,
+      "logps/chosen": -144.3943634033203,
+      "logps/rejected": -172.289306640625,
+      "loss": 0.3899,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -0.9222854971885681,
+      "rewards/margins": 2.454240322113037,
+      "rewards/rejected": -3.376525640487671,
+      "step": 690
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 28.227088451077186,
+      "learning_rate": 1.8514699362741738e-07,
+      "logits/chosen": 1.2821115255355835,
+      "logits/rejected": 1.5955793857574463,
+      "logps/chosen": -143.79371643066406,
+      "logps/rejected": -168.42379760742188,
+      "loss": 0.2676,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": -0.8676904439926147,
+      "rewards/margins": 3.0038087368011475,
+      "rewards/rejected": -3.8714990615844727,
+      "step": 700
+    },
+    {
+      "epoch": 0.7573333333333333,
+      "grad_norm": 33.39329635319409,
+      "learning_rate": 1.7091051952797402e-07,
+      "logits/chosen": 1.2979816198349,
+      "logits/rejected": 1.5841856002807617,
+      "logps/chosen": -140.95835876464844,
+      "logps/rejected": -180.0380401611328,
+      "loss": 0.2788,
+      "rewards/accuracies": 0.878125011920929,
+      "rewards/chosen": -0.6436134576797485,
+      "rewards/margins": 3.160693645477295,
+      "rewards/rejected": -3.804307222366333,
+      "step": 710
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 29.663583912080895,
+      "learning_rate": 1.571299549976456e-07,
+      "logits/chosen": 1.376884937286377,
+      "logits/rejected": 1.7266371250152588,
+      "logps/chosen": -134.19406127929688,
+      "logps/rejected": -173.26148986816406,
+      "loss": 0.3333,
+      "rewards/accuracies": 0.846875011920929,
+      "rewards/chosen": -0.7068169116973877,
+      "rewards/margins": 2.9150471687316895,
+      "rewards/rejected": -3.6218643188476562,
+      "step": 720
+    },
+    {
+      "epoch": 0.7786666666666666,
+      "grad_norm": 23.891419469257354,
+      "learning_rate": 1.4382439117002936e-07,
+      "logits/chosen": 1.2695218324661255,
+      "logits/rejected": 1.564518928527832,
+      "logps/chosen": -136.83729553222656,
+      "logps/rejected": -178.53765869140625,
+      "loss": 0.3344,
+      "rewards/accuracies": 0.8281250596046448,
+      "rewards/chosen": -0.796572744846344,
+      "rewards/margins": 2.8927884101867676,
+      "rewards/rejected": -3.689361095428467,
+      "step": 730
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": 23.85877560834035,
+      "learning_rate": 1.310122611286223e-07,
+      "logits/chosen": 1.2756718397140503,
+      "logits/rejected": 1.7924617528915405,
+      "logps/chosen": -140.0908203125,
+      "logps/rejected": -170.6318817138672,
+      "loss": 0.3521,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -0.7002599239349365,
+      "rewards/margins": 3.0346288681030273,
+      "rewards/rejected": -3.734888792037964,
+      "step": 740
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 31.266912743625518,
+      "learning_rate": 1.187113143702429e-07,
+      "logits/chosen": 1.1684255599975586,
+      "logits/rejected": 1.6504334211349487,
+      "logps/chosen": -138.86920166015625,
+      "logps/rejected": -172.11294555664062,
+      "loss": 0.3586,
+      "rewards/accuracies": 0.8625000715255737,
+      "rewards/chosen": -0.6606683135032654,
+      "rewards/margins": 2.9746954441070557,
+      "rewards/rejected": -3.6353635787963867,
+      "step": 750
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 27.45969382970204,
+      "learning_rate": 1.0693859221547113e-07,
+      "logits/chosen": 1.2002224922180176,
+      "logits/rejected": 1.4490042924880981,
+      "logps/chosen": -135.4897918701172,
+      "logps/rejected": -168.1680908203125,
+      "loss": 0.3814,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -0.8046519160270691,
+      "rewards/margins": 2.8222813606262207,
+      "rewards/rejected": -3.6269333362579346,
+      "step": 760
+    },
+    {
+      "epoch": 0.8213333333333334,
+      "grad_norm": 27.34194048181446,
+      "learning_rate": 9.571040420017323e-08,
+      "logits/chosen": 1.2844430208206177,
+      "logits/rejected": 1.5368437767028809,
+      "logps/chosen": -137.79006958007812,
+      "logps/rejected": -180.3217010498047,
+      "loss": 0.2863,
+      "rewards/accuracies": 0.8718750476837158,
+      "rewards/chosen": -0.5950286388397217,
+      "rewards/margins": 3.1103334426879883,
+      "rewards/rejected": -3.705361843109131,
+      "step": 770
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 22.71500177829076,
+      "learning_rate": 8.504230548081498e-08,
+      "logits/chosen": 1.1534736156463623,
+      "logits/rejected": 1.5489188432693481,
+      "logps/chosen": -135.84356689453125,
+      "logps/rejected": -163.74789428710938,
+      "loss": 0.3245,
+      "rewards/accuracies": 0.8406250476837158,
+      "rewards/chosen": -0.6919512152671814,
+      "rewards/margins": 2.70729398727417,
+      "rewards/rejected": -3.399244785308838,
+      "step": 780
+    },
+    {
+      "epoch": 0.8426666666666667,
+      "grad_norm": 33.585488423583136,
+      "learning_rate": 7.494907528486799e-08,
+      "logits/chosen": 1.1899046897888184,
+      "logits/rejected": 1.558382272720337,
+      "logps/chosen": -144.0318603515625,
+      "logps/rejected": -173.2529754638672,
+      "loss": 0.2885,
+      "rewards/accuracies": 0.8687500357627869,
+      "rewards/chosen": -0.45610812306404114,
+      "rewards/margins": 2.986624240875244,
+      "rewards/rejected": -3.442732572555542,
+      "step": 790
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 23.51906755223801,
+      "learning_rate": 6.54446964361619e-08,
+      "logits/chosen": 1.3951364755630493,
+      "logits/rejected": 1.5346930027008057,
+      "logps/chosen": -135.73672485351562,
+      "logps/rejected": -177.74282836914062,
+      "loss": 0.3352,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.6097190380096436,
+      "rewards/margins": 2.9158732891082764,
+      "rewards/rejected": -3.52559232711792,
+      "step": 800
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 18.099767999889643,
+      "learning_rate": 5.6542335983547515e-08,
+      "logits/chosen": 1.0958290100097656,
+      "logits/rejected": 1.7642685174942017,
+      "logps/chosen": -137.59483337402344,
+      "logps/rejected": -159.05628967285156,
+      "loss": 0.3021,
+      "rewards/accuracies": 0.8468749523162842,
+      "rewards/chosen": -0.548262357711792,
+      "rewards/margins": 2.8460323810577393,
+      "rewards/rejected": -3.3942949771881104,
+      "step": 810
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 22.736224970421958,
+      "learning_rate": 4.8254326959706714e-08,
+      "logits/chosen": 1.1229872703552246,
+      "logits/rejected": 1.6853474378585815,
+      "logps/chosen": -139.9053497314453,
+      "logps/rejected": -174.4130401611328,
+      "loss": 0.3367,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.6694452166557312,
+      "rewards/margins": 2.701251268386841,
+      "rewards/rejected": -3.370696544647217,
+      "step": 820
+    },
+    {
+      "epoch": 0.8853333333333333,
+      "grad_norm": 28.380431064935998,
+      "learning_rate": 4.059215129538246e-08,
+      "logits/chosen": 1.2847788333892822,
+      "logits/rejected": 1.3838608264923096,
+      "logps/chosen": -139.0540313720703,
+      "logps/rejected": -172.7044677734375,
+      "loss": 0.3149,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -0.6882542371749878,
+      "rewards/margins": 2.8262672424316406,
+      "rewards/rejected": -3.514521360397339,
+      "step": 830
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 24.47450186333891,
+      "learning_rate": 3.3566423912694045e-08,
+      "logits/chosen": 1.3405706882476807,
+      "logits/rejected": 1.4811562299728394,
+      "logps/chosen": -142.65008544921875,
+      "logps/rejected": -186.91891479492188,
+      "loss": 0.3103,
+      "rewards/accuracies": 0.8750000596046448,
+      "rewards/chosen": -0.6546552181243896,
+      "rewards/margins": 3.121577024459839,
+      "rewards/rejected": -3.7762320041656494,
+      "step": 840
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 26.10582659575781,
+      "learning_rate": 2.7186878019580194e-08,
+      "logits/chosen": 1.2894738912582397,
+      "logits/rejected": 1.5952208042144775,
+      "logps/chosen": -134.9425048828125,
+      "logps/rejected": -180.87374877929688,
+      "loss": 0.2955,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.5013420581817627,
+      "rewards/margins": 2.893864154815674,
+      "rewards/rejected": -3.3952059745788574,
+      "step": 850
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 16.69269334633985,
+      "learning_rate": 2.1462351625736673e-08,
+      "logits/chosen": 1.1675758361816406,
+      "logits/rejected": 1.6442891359329224,
+      "logps/chosen": -130.08786010742188,
+      "logps/rejected": -170.487548828125,
+      "loss": 0.2872,
+      "rewards/accuracies": 0.871874988079071,
+      "rewards/chosen": -0.6101741790771484,
+      "rewards/margins": 3.180131196975708,
+      "rewards/rejected": -3.7903053760528564,
+      "step": 860
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 27.109723201805032,
+      "learning_rate": 1.6400775298734015e-08,
+      "logits/chosen": 1.1326353549957275,
+      "logits/rejected": 1.4924323558807373,
+      "logps/chosen": -130.98184204101562,
+      "logps/rejected": -169.8687286376953,
+      "loss": 0.2554,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": -0.5216690301895142,
+      "rewards/margins": 3.1709208488464355,
+      "rewards/rejected": -3.6925899982452393,
+      "step": 870
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 14.828413315706442,
+      "learning_rate": 1.200916117727374e-08,
+      "logits/chosen": 0.9768412113189697,
+      "logits/rejected": 1.5602909326553345,
+      "logps/chosen": -140.74815368652344,
+      "logps/rejected": -172.26649475097656,
+      "loss": 0.2573,
+      "rewards/accuracies": 0.9000000357627869,
+      "rewards/chosen": -0.5175585746765137,
+      "rewards/margins": 3.088252544403076,
+      "rewards/rejected": -3.605811595916748,
+      "step": 880
+    },
+    {
+      "epoch": 0.9493333333333334,
+      "grad_norm": 26.86192866644961,
+      "learning_rate": 8.293593256805842e-09,
+      "logits/chosen": 1.1421420574188232,
+      "logits/rejected": 1.6538828611373901,
+      "logps/chosen": -141.6370086669922,
+      "logps/rejected": -169.20147705078125,
+      "loss": 0.3091,
+      "rewards/accuracies": 0.8593750596046448,
+      "rewards/chosen": -0.536719799041748,
+      "rewards/margins": 3.0636281967163086,
+      "rewards/rejected": -3.6003482341766357,
+      "step": 890
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 19.615598554875728,
+      "learning_rate": 5.2592189609648726e-09,
+      "logits/chosen": 1.0914634466171265,
+      "logits/rejected": 1.4714587926864624,
+      "logps/chosen": -131.58399963378906,
+      "logps/rejected": -164.37319946289062,
+      "loss": 0.3104,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.6866143345832825,
+      "rewards/margins": 2.836606025695801,
+      "rewards/rejected": -3.5232203006744385,
+      "step": 900
+    },
+    {
+      "epoch": 0.9706666666666667,
+      "grad_norm": 16.989834579672234,
+      "learning_rate": 2.910242010500996e-09,
+      "logits/chosen": 1.3143634796142578,
+      "logits/rejected": 1.5896141529083252,
+      "logps/chosen": -136.51361083984375,
+      "logps/rejected": -165.6531524658203,
+      "loss": 0.3146,
+      "rewards/accuracies": 0.8343749642372131,
+      "rewards/chosen": -0.6686439514160156,
+      "rewards/margins": 2.7611334323883057,
+      "rewards/rejected": -3.4297773838043213,
+      "step": 910
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 27.194483822978505,
+      "learning_rate": 1.249916599585954e-09,
+      "logits/chosen": 1.2227872610092163,
+      "logits/rejected": 1.5990573167800903,
+      "logps/chosen": -140.06248474121094,
+      "logps/rejected": -176.98333740234375,
+      "loss": 0.2738,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.6044124960899353,
+      "rewards/margins": 3.01471209526062,
+      "rewards/rejected": -3.619124412536621,
+      "step": 920
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 18.707222551914008,
+      "learning_rate": 2.8054288756129696e-10,
+      "logits/chosen": 1.316845417022705,
+      "logits/rejected": 1.5853126049041748,
+      "logps/chosen": -131.83575439453125,
+      "logps/rejected": -169.5233917236328,
+      "loss": 0.3086,
+      "rewards/accuracies": 0.8687500357627869,
+      "rewards/chosen": -0.5091441869735718,
+      "rewards/margins": 2.9370408058166504,
+      "rewards/rejected": -3.4461851119995117,
+      "step": 930
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 938,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 111524967546880.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0e758b07493d4ad7dfbfa864847bd388c1eebb974a6656aa3ab444c0baa82f
+size 8017

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_pad": null,
+  "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,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_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)