Upload local model

.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 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "eos_token_id": [
+    151643,
+    151645
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.56.0"
+}

global_step2000/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:f8dec47ce5c36f5861278d8fa3550255f7c1ed1704a7eab622a01a36d209c537
+size 11423430241

global_step2000/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:ebdf827cce49de1e2a3ec05036ef91a9f5a56c0848e9b29995cbf4f57b9e104e
+size 11423430241

global_step2000/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:e6e03f0f28ac5e946cff861ba30f8777e653b4d5d0de2c7c321e20e520c4426f
+size 11423430241

global_step2000/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:ae103fa2cfee763e8007e6b50bc5dbcc21f6c291b8cbc9db57c93d84b6466498
+size 11423430241

global_step2000/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:fba3a38d4779affff9c66d86fec0d9f6845725936dbd699f713080ff7871d84a
+size 11423430241

global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d467d08c484f4d5b055efaa002bcf0077db15f71431a261170e45bca8366253
+size 11423430241

global_step2000/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:e13b98a67f10cb4fca83f00790cd408d4603f53b137a163987b5174b6b504095
+size 11423430241

global_step2000/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:c8060479e37d774e4b14902346f13cf84ffde2fc7a04233d29d9d56fd01db12c
+size 11423430241

global_step2000/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa07e61ef77d6c1b883ab3dbd00a92945b9b92a6433694e43b3fa85050373712
+size 166752

global_step2000/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7bc581a25c738a0465d87a57902c556711d6cbcee4221b1b65dd9957e10eae
+size 166752

global_step2000/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877024cb6c31cb889dce0a3d6d7d6732e1440ef20d43d59ca6aff1ef7818c308
+size 166752

global_step2000/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed40849c7931a4ec6ad2f317ce7b0d6c01846470503aca95af7733bb6e8ba0bd
+size 166752

global_step2000/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a07b25e6c32f38f948ed53820b24f7ca64b3d13daeb59d21f95914d67c39cd
+size 166752

global_step2000/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e395099f2d78bd8e8c8a6230de23e058ba303ce351b6f5ab3b31e92f3b035a09
+size 166752

global_step2000/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49dcb786c4de28fe9bab7a3fbb4cc825a0953c407ee312b6db63de487343cca6
+size 166752

global_step2000/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9791b6dcda1d2edf3491c5c9900975dd97751706d5e69e2bb733ea4bbcda9c
+size 166752

latest

@@ -0,0 +1 @@
+global_step2000

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d70a4e0ae59658e283e853cb3ea75f8c3ffe2fe4b6d9ec8a43158f5868c4be
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf68d9f42aff78f09370b3ac81620e7fc190d0323c1b7c18673469b57ccd3a97
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b544123735c1bdfe447054f7c65a1f52d34d105c5b65ff46af78c0f0dc053e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6382df46852c0cb621bb6b240fba83f26fe9dfad4590f5bbc8e72ffad5dc770
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "total_size": 15231233024
+  },
+  "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-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-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-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-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-00003-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84750af6bd4c34478c638e5299fa86cb8f0f3128e5a353af7e4aa00b600124b4
+size 16325

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cdd6b07b9796a600d1534d8719a801f1c120c193fb1c3890b20b6a96e01cc20
+size 16325

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c53d380012c858e876248dadf803453a9406d4f96257f341becb2e4f6d219d
+size 16325

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670a4d80b20868ee65bf71ea7bb701ab312d8a25628994e76c577be2c1517e05
+size 16325

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0766173b35f69d24cd65464a91fcc6bace35fc846062f1b181518d3158c67e4c
+size 16325

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ceee0c36070f6d4ca84acb7bf39ca74ed45e32e5a3adc32a594388cb2a72e1
+size 16325

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9bd1d56de9f175f7980bbefcc1a996526855bdba4b646649dc6c453d2a40ee
+size 16325

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea930010081807404b2efc0b7ec27590a59fca05aca0ed1cbcfc03a693429f3f
+size 16325

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8090b0e048918471f5675a9599d07bf4b60aded9dda2eeaab9a0865546a6f8
+size 1465

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>",
+  "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 +1,207 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1634 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06095330976472022,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00030476654882360114,
+      "grad_norm": 0.7457249747340627,
+      "learning_rate": 9.137055837563454e-08,
+      "loss": 0.6142,
+      "num_tokens": 2980145.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0006095330976472023,
+      "grad_norm": 0.5230562451977644,
+      "learning_rate": 1.9289340101522847e-07,
+      "loss": 0.6164,
+      "num_tokens": 5996839.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0009142996464708034,
+      "grad_norm": 0.49714383563689274,
+      "learning_rate": 2.9441624365482237e-07,
+      "loss": 0.6091,
+      "num_tokens": 8885936.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0012190661952944045,
+      "grad_norm": 0.49096988376057554,
+      "learning_rate": 3.959390862944162e-07,
+      "loss": 0.6178,
+      "num_tokens": 11902174.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0015238327441180056,
+      "grad_norm": 0.4330398526762992,
+      "learning_rate": 4.974619289340102e-07,
+      "loss": 0.6199,
+      "num_tokens": 14925906.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0018285992929416067,
+      "grad_norm": 0.41516586177368875,
+      "learning_rate": 5.989847715736042e-07,
+      "loss": 0.616,
+      "num_tokens": 17930059.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.002133365841765208,
+      "grad_norm": 0.43028637001925885,
+      "learning_rate": 7.005076142131981e-07,
+      "loss": 0.6131,
+      "num_tokens": 20906359.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.002438132390588809,
+      "grad_norm": 0.4332500284703439,
+      "learning_rate": 8.020304568527919e-07,
+      "loss": 0.6044,
+      "num_tokens": 23929250.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.00274289893941241,
+      "grad_norm": 0.3908329550293861,
+      "learning_rate": 9.035532994923858e-07,
+      "loss": 0.611,
+      "num_tokens": 26927837.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.0030476654882360113,
+      "grad_norm": 0.41749282992761355,
+      "learning_rate": 1.0050761421319798e-06,
+      "loss": 0.6032,
+      "num_tokens": 29987544.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.003352432037059612,
+      "grad_norm": 0.4169278523962904,
+      "learning_rate": 1.1065989847715738e-06,
+      "loss": 0.5916,
+      "num_tokens": 33038706.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.0036571985858832134,
+      "grad_norm": 0.4028416591982731,
+      "learning_rate": 1.2081218274111676e-06,
+      "loss": 0.6008,
+      "num_tokens": 36086832.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.003961965134706815,
+      "grad_norm": 0.474979518300003,
+      "learning_rate": 1.3096446700507614e-06,
+      "loss": 0.6145,
+      "num_tokens": 39092440.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.004266731683530416,
+      "grad_norm": 0.47119945262680424,
+      "learning_rate": 1.4111675126903554e-06,
+      "loss": 0.6128,
+      "num_tokens": 42041721.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.0045714982323540165,
+      "grad_norm": 0.4067936922360184,
+      "learning_rate": 1.5126903553299494e-06,
+      "loss": 0.6095,
+      "num_tokens": 45028968.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.004876264781177618,
+      "grad_norm": 0.4858340781478565,
+      "learning_rate": 1.6142131979695432e-06,
+      "loss": 0.6175,
+      "num_tokens": 47973669.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.005181031330001219,
+      "grad_norm": 0.4401239901711096,
+      "learning_rate": 1.7157360406091372e-06,
+      "loss": 0.5893,
+      "num_tokens": 50987779.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.00548579787882482,
+      "grad_norm": 0.4460687010247,
+      "learning_rate": 1.8172588832487312e-06,
+      "loss": 0.6026,
+      "num_tokens": 54041218.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.005790564427648422,
+      "grad_norm": 0.4501185094476908,
+      "learning_rate": 1.9187817258883252e-06,
+      "loss": 0.6008,
+      "num_tokens": 56982269.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0060953309764720225,
+      "grad_norm": 0.4909095450175495,
+      "learning_rate": 2.0203045685279192e-06,
+      "loss": 0.6089,
+      "num_tokens": 59938083.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.006400097525295623,
+      "grad_norm": 0.407422663157645,
+      "learning_rate": 2.121827411167513e-06,
+      "loss": 0.6116,
+      "num_tokens": 62969469.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.006704864074119224,
+      "grad_norm": 0.4483755982384412,
+      "learning_rate": 2.223350253807107e-06,
+      "loss": 0.5879,
+      "num_tokens": 65900724.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.007009630622942826,
+      "grad_norm": 0.4611576231522366,
+      "learning_rate": 2.324873096446701e-06,
+      "loss": 0.6119,
+      "num_tokens": 68899345.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.007314397171766427,
+      "grad_norm": 0.4493444382084047,
+      "learning_rate": 2.4263959390862944e-06,
+      "loss": 0.6006,
+      "num_tokens": 71888265.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.007619163720590028,
+      "grad_norm": 0.48989463829316715,
+      "learning_rate": 2.527918781725889e-06,
+      "loss": 0.5935,
+      "num_tokens": 74852357.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.00792393026941363,
+      "grad_norm": 0.44739062063292384,
+      "learning_rate": 2.6294416243654824e-06,
+      "loss": 0.6055,
+      "num_tokens": 77887469.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.00822869681823723,
+      "grad_norm": 0.48068140497642214,
+      "learning_rate": 2.730964467005076e-06,
+      "loss": 0.5901,
+      "num_tokens": 80914803.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.008533463367060831,
+      "grad_norm": 0.5233143764709678,
+      "learning_rate": 2.8324873096446704e-06,
+      "loss": 0.6069,
+      "num_tokens": 83909605.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.008838229915884432,
+      "grad_norm": 0.4774701979403596,
+      "learning_rate": 2.934010152284264e-06,
+      "loss": 0.5846,
+      "num_tokens": 86917981.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.009142996464708033,
+      "grad_norm": 0.5130960008034174,
+      "learning_rate": 3.035532994923858e-06,
+      "loss": 0.6034,
+      "num_tokens": 89890382.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.009447763013531636,
+      "grad_norm": 0.5410605184236367,
+      "learning_rate": 3.137055837563452e-06,
+      "loss": 0.6011,
+      "num_tokens": 92882407.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.009752529562355236,
+      "grad_norm": 0.4744253443258629,
+      "learning_rate": 3.238578680203046e-06,
+      "loss": 0.596,
+      "num_tokens": 95952332.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.010057296111178837,
+      "grad_norm": 0.4771199402059675,
+      "learning_rate": 3.3401015228426396e-06,
+      "loss": 0.5961,
+      "num_tokens": 98980436.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.010362062660002438,
+      "grad_norm": 0.4637328128768241,
+      "learning_rate": 3.441624365482234e-06,
+      "loss": 0.5941,
+      "num_tokens": 102004099.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.010666829208826039,
+      "grad_norm": 0.5192952235899345,
+      "learning_rate": 3.5431472081218276e-06,
+      "loss": 0.5816,
+      "num_tokens": 105032718.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.01097159575764964,
+      "grad_norm": 0.5301506204288337,
+      "learning_rate": 3.644670050761422e-06,
+      "loss": 0.6062,
+      "num_tokens": 108023271.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.01127636230647324,
+      "grad_norm": 0.5199604764649894,
+      "learning_rate": 3.7461928934010156e-06,
+      "loss": 0.6046,
+      "num_tokens": 111041751.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.011581128855296843,
+      "grad_norm": 0.5159668884756926,
+      "learning_rate": 3.847715736040609e-06,
+      "loss": 0.595,
+      "num_tokens": 113998068.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.011885895404120444,
+      "grad_norm": 0.541343488588413,
+      "learning_rate": 3.949238578680203e-06,
+      "loss": 0.5909,
+      "num_tokens": 117011555.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.012190661952944045,
+      "grad_norm": 0.5507329622876062,
+      "learning_rate": 4.050761421319797e-06,
+      "loss": 0.6116,
+      "num_tokens": 119971082.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.012495428501767646,
+      "grad_norm": 0.5387900338289145,
+      "learning_rate": 4.152284263959391e-06,
+      "loss": 0.5972,
+      "num_tokens": 122935836.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.012800195050591247,
+      "grad_norm": 0.5211259283987176,
+      "learning_rate": 4.253807106598985e-06,
+      "loss": 0.5972,
+      "num_tokens": 125930244.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.013104961599414848,
+      "grad_norm": 0.5193796245645712,
+      "learning_rate": 4.355329949238579e-06,
+      "loss": 0.62,
+      "num_tokens": 128941908.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.013409728148238449,
+      "grad_norm": 0.5529483243359413,
+      "learning_rate": 4.456852791878173e-06,
+      "loss": 0.6036,
+      "num_tokens": 131937447.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.013714494697062051,
+      "grad_norm": 0.6030580723464019,
+      "learning_rate": 4.558375634517767e-06,
+      "loss": 0.597,
+      "num_tokens": 134893931.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.014019261245885652,
+      "grad_norm": 0.5638437321715631,
+      "learning_rate": 4.6598984771573604e-06,
+      "loss": 0.6115,
+      "num_tokens": 137827084.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.014324027794709253,
+      "grad_norm": 0.5089162615052084,
+      "learning_rate": 4.7614213197969544e-06,
+      "loss": 0.6033,
+      "num_tokens": 140842870.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.014628794343532854,
+      "grad_norm": 0.5368683405687481,
+      "learning_rate": 4.8629441624365485e-06,
+      "loss": 0.6017,
+      "num_tokens": 143843882.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.014933560892356455,
+      "grad_norm": 0.560866440724884,
+      "learning_rate": 4.9644670050761425e-06,
+      "loss": 0.6025,
+      "num_tokens": 146811617.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.015238327441180055,
+      "grad_norm": 0.5651422936330702,
+      "learning_rate": 5.0659898477157365e-06,
+      "loss": 0.5936,
+      "num_tokens": 149829605.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.015543093990003658,
+      "grad_norm": 0.47211095143464976,
+      "learning_rate": 5.1675126903553305e-06,
+      "loss": 0.6002,
+      "num_tokens": 152879090.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.01584786053882726,
+      "grad_norm": 0.5419676421463695,
+      "learning_rate": 5.269035532994924e-06,
+      "loss": 0.6068,
+      "num_tokens": 155844929.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.016152627087650858,
+      "grad_norm": 0.6246209039471872,
+      "learning_rate": 5.3705583756345185e-06,
+      "loss": 0.5964,
+      "num_tokens": 158860844.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.01645739363647446,
+      "grad_norm": 0.549771097832386,
+      "learning_rate": 5.4720812182741125e-06,
+      "loss": 0.5955,
+      "num_tokens": 161834390.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.016762160185298063,
+      "grad_norm": 0.5238364197670614,
+      "learning_rate": 5.5736040609137065e-06,
+      "loss": 0.6105,
+      "num_tokens": 164903408.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.017066926734121662,
+      "grad_norm": 0.5431655224279603,
+      "learning_rate": 5.6751269035533e-06,
+      "loss": 0.5808,
+      "num_tokens": 167945658.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.017371693282945265,
+      "grad_norm": 0.5257430900462962,
+      "learning_rate": 5.776649746192894e-06,
+      "loss": 0.5987,
+      "num_tokens": 170984358.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.017676459831768864,
+      "grad_norm": 0.6003046913840301,
+      "learning_rate": 5.878172588832488e-06,
+      "loss": 0.6033,
+      "num_tokens": 173989761.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.017981226380592467,
+      "grad_norm": 0.5672973145643517,
+      "learning_rate": 5.979695431472081e-06,
+      "loss": 0.6102,
+      "num_tokens": 176968810.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.018285992929416066,
+      "grad_norm": 0.5503549692186483,
+      "learning_rate": 6.081218274111676e-06,
+      "loss": 0.6077,
+      "num_tokens": 179971815.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.01859075947823967,
+      "grad_norm": 0.529283833183057,
+      "learning_rate": 6.18274111675127e-06,
+      "loss": 0.5999,
+      "num_tokens": 183003541.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.01889552602706327,
+      "grad_norm": 0.6080338349548227,
+      "learning_rate": 6.284263959390864e-06,
+      "loss": 0.6049,
+      "num_tokens": 185970071.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.01920029257588687,
+      "grad_norm": 0.5457834941063321,
+      "learning_rate": 6.385786802030457e-06,
+      "loss": 0.6061,
+      "num_tokens": 188977852.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.019505059124710473,
+      "grad_norm": 0.5811218073065819,
+      "learning_rate": 6.487309644670051e-06,
+      "loss": 0.5996,
+      "num_tokens": 191894102.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.019809825673534072,
+      "grad_norm": 0.5874876696821952,
+      "learning_rate": 6.588832487309646e-06,
+      "loss": 0.5917,
+      "num_tokens": 194930427.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.020114592222357675,
+      "grad_norm": 0.643812726542813,
+      "learning_rate": 6.69035532994924e-06,
+      "loss": 0.5991,
+      "num_tokens": 197878331.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.020419358771181274,
+      "grad_norm": 0.5164219399748118,
+      "learning_rate": 6.791878172588833e-06,
+      "loss": 0.6038,
+      "num_tokens": 200865810.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.020724125320004876,
+      "grad_norm": 0.520689078647113,
+      "learning_rate": 6.893401015228427e-06,
+      "loss": 0.5979,
+      "num_tokens": 203817250.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.02102889186882848,
+      "grad_norm": 0.5039371962942628,
+      "learning_rate": 6.994923857868021e-06,
+      "loss": 0.5975,
+      "num_tokens": 206811537.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.021333658417652078,
+      "grad_norm": 0.5544674068606494,
+      "learning_rate": 7.096446700507614e-06,
+      "loss": 0.6025,
+      "num_tokens": 209795067.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.02163842496647568,
+      "grad_norm": 0.5784724273304568,
+      "learning_rate": 7.197969543147209e-06,
+      "loss": 0.6007,
+      "num_tokens": 212800409.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.02194319151529928,
+      "grad_norm": 0.5019397033545099,
+      "learning_rate": 7.299492385786803e-06,
+      "loss": 0.5891,
+      "num_tokens": 215812500.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.022247958064122882,
+      "grad_norm": 0.5145496859403778,
+      "learning_rate": 7.401015228426397e-06,
+      "loss": 0.5978,
+      "num_tokens": 218829927.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.02255272461294648,
+      "grad_norm": 0.5948272370253752,
+      "learning_rate": 7.50253807106599e-06,
+      "loss": 0.5981,
+      "num_tokens": 221910127.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.022857491161770084,
+      "grad_norm": 0.6324523630669571,
+      "learning_rate": 7.604060913705584e-06,
+      "loss": 0.5977,
+      "num_tokens": 224950377.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.023162257710593687,
+      "grad_norm": 0.5522771359702385,
+      "learning_rate": 7.705583756345178e-06,
+      "loss": 0.5968,
+      "num_tokens": 227912016.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.023467024259417286,
+      "grad_norm": 0.5678284942531937,
+      "learning_rate": 7.807106598984773e-06,
+      "loss": 0.6069,
+      "num_tokens": 230845440.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.02377179080824089,
+      "grad_norm": 0.5086079282374418,
+      "learning_rate": 7.908629441624366e-06,
+      "loss": 0.5958,
+      "num_tokens": 233888653.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.024076557357064488,
+      "grad_norm": 0.6113040771193711,
+      "learning_rate": 8.01015228426396e-06,
+      "loss": 0.592,
+      "num_tokens": 236913104.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.02438132390588809,
+      "grad_norm": 0.5112624603004914,
+      "learning_rate": 8.111675126903554e-06,
+      "loss": 0.5965,
+      "num_tokens": 239863099.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.02468609045471169,
+      "grad_norm": 0.5386776285755579,
+      "learning_rate": 8.213197969543147e-06,
+      "loss": 0.6047,
+      "num_tokens": 242936678.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.024990857003535292,
+      "grad_norm": 0.6449184905774187,
+      "learning_rate": 8.314720812182742e-06,
+      "loss": 0.6078,
+      "num_tokens": 245924372.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.025295623552358894,
+      "grad_norm": 0.5877934183571296,
+      "learning_rate": 8.416243654822335e-06,
+      "loss": 0.6138,
+      "num_tokens": 248814799.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.025600390101182494,
+      "grad_norm": 0.5726975217126076,
+      "learning_rate": 8.51776649746193e-06,
+      "loss": 0.6003,
+      "num_tokens": 251864383.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.025905156650006096,
+      "grad_norm": 0.5884163738699382,
+      "learning_rate": 8.619289340101523e-06,
+      "loss": 0.5989,
+      "num_tokens": 254912320.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.026209923198829695,
+      "grad_norm": 0.5868691029072695,
+      "learning_rate": 8.720812182741118e-06,
+      "loss": 0.6153,
+      "num_tokens": 257948800.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.026514689747653298,
+      "grad_norm": 0.7286662139359907,
+      "learning_rate": 8.822335025380711e-06,
+      "loss": 0.5946,
+      "num_tokens": 260981575.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.026819456296476897,
+      "grad_norm": 0.5782176364766526,
+      "learning_rate": 8.923857868020306e-06,
+      "loss": 0.605,
+      "num_tokens": 263946166.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.0271242228453005,
+      "grad_norm": 0.6566796557977583,
+      "learning_rate": 9.0253807106599e-06,
+      "loss": 0.5947,
+      "num_tokens": 266932084.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.027428989394124102,
+      "grad_norm": 0.5964252911962427,
+      "learning_rate": 9.126903553299493e-06,
+      "loss": 0.597,
+      "num_tokens": 269940123.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.0277337559429477,
+      "grad_norm": 0.6610602117570733,
+      "learning_rate": 9.228426395939087e-06,
+      "loss": 0.5997,
+      "num_tokens": 272996550.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.028038522491771304,
+      "grad_norm": 0.5481291317994652,
+      "learning_rate": 9.32994923857868e-06,
+      "loss": 0.6079,
+      "num_tokens": 276005284.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.028343289040594903,
+      "grad_norm": 0.5935276827938708,
+      "learning_rate": 9.431472081218275e-06,
+      "loss": 0.594,
+      "num_tokens": 278961666.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.028648055589418506,
+      "grad_norm": 0.5973378747127883,
+      "learning_rate": 9.532994923857869e-06,
+      "loss": 0.6044,
+      "num_tokens": 281935833.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.028952822138242105,
+      "grad_norm": 0.5912756041045825,
+      "learning_rate": 9.634517766497463e-06,
+      "loss": 0.5926,
+      "num_tokens": 284883466.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.029257588687065707,
+      "grad_norm": 0.5810487871964766,
+      "learning_rate": 9.736040609137057e-06,
+      "loss": 0.6037,
+      "num_tokens": 287922376.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.02956235523588931,
+      "grad_norm": 0.7608788298202219,
+      "learning_rate": 9.83756345177665e-06,
+      "loss": 0.617,
+      "num_tokens": 290949742.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.02986712178471291,
+      "grad_norm": 0.6348669161902478,
+      "learning_rate": 9.939086294416245e-06,
+      "loss": 0.6015,
+      "num_tokens": 293974513.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.030171888333536512,
+      "grad_norm": 0.5580420361871727,
+      "learning_rate": 9.999999649239378e-06,
+      "loss": 0.5986,
+      "num_tokens": 297055223.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.03047665488236011,
+      "grad_norm": 0.5886314947114983,
+      "learning_rate": 9.999995703183002e-06,
+      "loss": 0.6089,
+      "num_tokens": 300092531.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.030781421431183714,
+      "grad_norm": 0.5718023626398742,
+      "learning_rate": 9.99998737262333e-06,
+      "loss": 0.5981,
+      "num_tokens": 303195919.0,
+      "step": 1010
+    },
+    {
+      "epoch": 0.031086187980007316,
+      "grad_norm": 0.6206116128972652,
+      "learning_rate": 9.999974657568477e-06,
+      "loss": 0.5928,
+      "num_tokens": 306247864.0,
+      "step": 1020
+    },
+    {
+      "epoch": 0.031390954528830915,
+      "grad_norm": 0.5172240579813588,
+      "learning_rate": 9.999957558030833e-06,
+      "loss": 0.6059,
+      "num_tokens": 309235571.0,
+      "step": 1030
+    },
+    {
+      "epoch": 0.03169572107765452,
+      "grad_norm": 0.5098188832148954,
+      "learning_rate": 9.999936074027058e-06,
+      "loss": 0.6184,
+      "num_tokens": 312233701.0,
+      "step": 1040
+    },
+    {
+      "epoch": 0.03200048762647812,
+      "grad_norm": 0.6712184280872747,
+      "learning_rate": 9.999910205578088e-06,
+      "loss": 0.6182,
+      "num_tokens": 315180794.0,
+      "step": 1050
+    },
+    {
+      "epoch": 0.032305254175301716,
+      "grad_norm": 0.5381662063088128,
+      "learning_rate": 9.99987995270912e-06,
+      "loss": 0.6157,
+      "num_tokens": 318145236.0,
+      "step": 1060
+    },
+    {
+      "epoch": 0.03261002072412532,
+      "grad_norm": 0.6327671055732239,
+      "learning_rate": 9.999845315449637e-06,
+      "loss": 0.5918,
+      "num_tokens": 321201600.0,
+      "step": 1070
+    },
+    {
+      "epoch": 0.03291478727294892,
+      "grad_norm": 0.6518354594585019,
+      "learning_rate": 9.999806293833387e-06,
+      "loss": 0.6081,
+      "num_tokens": 324242875.0,
+      "step": 1080
+    },
+    {
+      "epoch": 0.033219553821772524,
+      "grad_norm": 0.5539270879326635,
+      "learning_rate": 9.999762887898387e-06,
+      "loss": 0.6004,
+      "num_tokens": 327299868.0,
+      "step": 1090
+    },
+    {
+      "epoch": 0.033524320370596127,
+      "grad_norm": 0.5411600759723616,
+      "learning_rate": 9.999715097686932e-06,
+      "loss": 0.612,
+      "num_tokens": 330350525.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.03382908691941972,
+      "grad_norm": 0.5585636408454607,
+      "learning_rate": 9.999662923245582e-06,
+      "loss": 0.5932,
+      "num_tokens": 333397170.0,
+      "step": 1110
+    },
+    {
+      "epoch": 0.034133853468243325,
+      "grad_norm": 0.60791649981183,
+      "learning_rate": 9.999606364625174e-06,
+      "loss": 0.6001,
+      "num_tokens": 336273179.0,
+      "step": 1120
+    },
+    {
+      "epoch": 0.03443862001706693,
+      "grad_norm": 0.6351784309943206,
+      "learning_rate": 9.999545421880819e-06,
+      "loss": 0.6043,
+      "num_tokens": 339257454.0,
+      "step": 1130
+    },
+    {
+      "epoch": 0.03474338656589053,
+      "grad_norm": 0.5653344825112488,
+      "learning_rate": 9.999480095071888e-06,
+      "loss": 0.5955,
+      "num_tokens": 342345138.0,
+      "step": 1140
+    },
+    {
+      "epoch": 0.035048153114714126,
+      "grad_norm": 0.6610539460568494,
+      "learning_rate": 9.999410384262038e-06,
+      "loss": 0.6003,
+      "num_tokens": 345336558.0,
+      "step": 1150
+    },
+    {
+      "epoch": 0.03535291966353773,
+      "grad_norm": 0.6040031590644234,
+      "learning_rate": 9.999336289519188e-06,
+      "loss": 0.6077,
+      "num_tokens": 348348169.0,
+      "step": 1160
+    },
+    {
+      "epoch": 0.03565768621236133,
+      "grad_norm": 0.5684955670142974,
+      "learning_rate": 9.99925781091553e-06,
+      "loss": 0.6057,
+      "num_tokens": 351414195.0,
+      "step": 1170
+    },
+    {
+      "epoch": 0.03596245276118493,
+      "grad_norm": 0.6156749822501932,
+      "learning_rate": 9.99917494852753e-06,
+      "loss": 0.5824,
+      "num_tokens": 354539074.0,
+      "step": 1180
+    },
+    {
+      "epoch": 0.036267219310008536,
+      "grad_norm": 0.6099142423052227,
+      "learning_rate": 9.999087702435924e-06,
+      "loss": 0.6063,
+      "num_tokens": 357558942.0,
+      "step": 1190
+    },
+    {
+      "epoch": 0.03657198585883213,
+      "grad_norm": 0.665879466142715,
+      "learning_rate": 9.998996072725716e-06,
+      "loss": 0.6012,
+      "num_tokens": 360650474.0,
+      "step": 1200
+    },
+    {
+      "epoch": 0.036876752407655734,
+      "grad_norm": 0.60485897990858,
+      "learning_rate": 9.998900059486189e-06,
+      "loss": 0.6032,
+      "num_tokens": 363700986.0,
+      "step": 1210
+    },
+    {
+      "epoch": 0.03718151895647934,
+      "grad_norm": 0.7598824750362458,
+      "learning_rate": 9.998799662810888e-06,
+      "loss": 0.61,
+      "num_tokens": 366705230.0,
+      "step": 1220
+    },
+    {
+      "epoch": 0.03748628550530294,
+      "grad_norm": 0.5876567393111121,
+      "learning_rate": 9.998694882797634e-06,
+      "loss": 0.6124,
+      "num_tokens": 369694176.0,
+      "step": 1230
+    },
+    {
+      "epoch": 0.03779105205412654,
+      "grad_norm": 0.7072433052411577,
+      "learning_rate": 9.998585719548519e-06,
+      "loss": 0.6037,
+      "num_tokens": 372694789.0,
+      "step": 1240
+    },
+    {
+      "epoch": 0.03809581860295014,
+      "grad_norm": 0.6166270390022508,
+      "learning_rate": 9.998472173169904e-06,
+      "loss": 0.5974,
+      "num_tokens": 375709531.0,
+      "step": 1250
+    },
+    {
+      "epoch": 0.03840058515177374,
+      "grad_norm": 0.6299556744164037,
+      "learning_rate": 9.99835424377242e-06,
+      "loss": 0.6084,
+      "num_tokens": 378721461.0,
+      "step": 1260
+    },
+    {
+      "epoch": 0.03870535170059734,
+      "grad_norm": 0.6019823193375798,
+      "learning_rate": 9.998231931470972e-06,
+      "loss": 0.6064,
+      "num_tokens": 381814974.0,
+      "step": 1270
+    },
+    {
+      "epoch": 0.039010118249420946,
+      "grad_norm": 0.5740532096312945,
+      "learning_rate": 9.998105236384729e-06,
+      "loss": 0.6041,
+      "num_tokens": 384900077.0,
+      "step": 1280
+    },
+    {
+      "epoch": 0.03931488479824454,
+      "grad_norm": 0.6790343891386362,
+      "learning_rate": 9.99797415863714e-06,
+      "loss": 0.6013,
+      "num_tokens": 387879610.0,
+      "step": 1290
+    },
+    {
+      "epoch": 0.039619651347068144,
+      "grad_norm": 0.7077423025471166,
+      "learning_rate": 9.997838698355914e-06,
+      "loss": 0.6076,
+      "num_tokens": 390864425.0,
+      "step": 1300
+    },
+    {
+      "epoch": 0.039924417895891746,
+      "grad_norm": 0.6024679257495524,
+      "learning_rate": 9.997698855673038e-06,
+      "loss": 0.6014,
+      "num_tokens": 393808852.0,
+      "step": 1310
+    },
+    {
+      "epoch": 0.04022918444471535,
+      "grad_norm": 0.6810529775806461,
+      "learning_rate": 9.997554630724764e-06,
+      "loss": 0.6154,
+      "num_tokens": 396845763.0,
+      "step": 1320
+    },
+    {
+      "epoch": 0.04053395099353895,
+      "grad_norm": 0.5431520105621443,
+      "learning_rate": 9.997406023651616e-06,
+      "loss": 0.603,
+      "num_tokens": 399849414.0,
+      "step": 1330
+    },
+    {
+      "epoch": 0.04083871754236255,
+      "grad_norm": 0.6739822771280697,
+      "learning_rate": 9.997253034598387e-06,
+      "loss": 0.5996,
+      "num_tokens": 402855291.0,
+      "step": 1340
+    },
+    {
+      "epoch": 0.04114348409118615,
+      "grad_norm": 0.5806695994649888,
+      "learning_rate": 9.997095663714137e-06,
+      "loss": 0.6001,
+      "num_tokens": 405820396.0,
+      "step": 1350
+    },
+    {
+      "epoch": 0.04144825064000975,
+      "grad_norm": 0.6946026869742606,
+      "learning_rate": 9.996933911152202e-06,
+      "loss": 0.6109,
+      "num_tokens": 408837615.0,
+      "step": 1360
+    },
+    {
+      "epoch": 0.041753017188833355,
+      "grad_norm": 0.659471975792841,
+      "learning_rate": 9.996767777070181e-06,
+      "loss": 0.6059,
+      "num_tokens": 411854462.0,
+      "step": 1370
+    },
+    {
+      "epoch": 0.04205778373765696,
+      "grad_norm": 0.6261217460987484,
+      "learning_rate": 9.996597261629946e-06,
+      "loss": 0.5943,
+      "num_tokens": 414836975.0,
+      "step": 1380
+    },
+    {
+      "epoch": 0.04236255028648055,
+      "grad_norm": 0.581519216568936,
+      "learning_rate": 9.996422364997634e-06,
+      "loss": 0.617,
+      "num_tokens": 417838818.0,
+      "step": 1390
+    },
+    {
+      "epoch": 0.042667316835304156,
+      "grad_norm": 0.5929977486471997,
+      "learning_rate": 9.996243087343653e-06,
+      "loss": 0.5893,
+      "num_tokens": 420796359.0,
+      "step": 1400
+    },
+    {
+      "epoch": 0.04297208338412776,
+      "grad_norm": 0.6012824149251887,
+      "learning_rate": 9.996059428842681e-06,
+      "loss": 0.6016,
+      "num_tokens": 423785552.0,
+      "step": 1410
+    },
+    {
+      "epoch": 0.04327684993295136,
+      "grad_norm": 0.5813336121248558,
+      "learning_rate": 9.995871389673661e-06,
+      "loss": 0.6002,
+      "num_tokens": 426814600.0,
+      "step": 1420
+    },
+    {
+      "epoch": 0.043581616481774964,
+      "grad_norm": 0.5465897814086882,
+      "learning_rate": 9.99567897001981e-06,
+      "loss": 0.6125,
+      "num_tokens": 429802508.0,
+      "step": 1430
+    },
+    {
+      "epoch": 0.04388638303059856,
+      "grad_norm": 0.5984329688655077,
+      "learning_rate": 9.995482170068605e-06,
+      "loss": 0.6079,
+      "num_tokens": 432764345.0,
+      "step": 1440
+    },
+    {
+      "epoch": 0.04419114957942216,
+      "grad_norm": 0.610168092795878,
+      "learning_rate": 9.995280990011796e-06,
+      "loss": 0.6062,
+      "num_tokens": 435741101.0,
+      "step": 1450
+    },
+    {
+      "epoch": 0.044495916128245765,
+      "grad_norm": 0.5709650873056764,
+      "learning_rate": 9.995075430045402e-06,
+      "loss": 0.6013,
+      "num_tokens": 438789688.0,
+      "step": 1460
+    },
+    {
+      "epoch": 0.04480068267706937,
+      "grad_norm": 0.5172547307532018,
+      "learning_rate": 9.994865490369703e-06,
+      "loss": 0.5993,
+      "num_tokens": 441759109.0,
+      "step": 1470
+    },
+    {
+      "epoch": 0.04510544922589296,
+      "grad_norm": 0.5222110494511161,
+      "learning_rate": 9.994651171189255e-06,
+      "loss": 0.6013,
+      "num_tokens": 444767322.0,
+      "step": 1480
+    },
+    {
+      "epoch": 0.045410215774716566,
+      "grad_norm": 0.6120571227841243,
+      "learning_rate": 9.994432472712875e-06,
+      "loss": 0.608,
+      "num_tokens": 447776227.0,
+      "step": 1490
+    },
+    {
+      "epoch": 0.04571498232354017,
+      "grad_norm": 0.6956715541420607,
+      "learning_rate": 9.994209395153648e-06,
+      "loss": 0.5909,
+      "num_tokens": 450799563.0,
+      "step": 1500
+    },
+    {
+      "epoch": 0.04601974887236377,
+      "grad_norm": 0.5613221067988521,
+      "learning_rate": 9.993981938728927e-06,
+      "loss": 0.6131,
+      "num_tokens": 453829588.0,
+      "step": 1510
+    },
+    {
+      "epoch": 0.04632451542118737,
+      "grad_norm": 0.5858287013485725,
+      "learning_rate": 9.99375010366033e-06,
+      "loss": 0.6003,
+      "num_tokens": 456869534.0,
+      "step": 1520
+    },
+    {
+      "epoch": 0.04662928197001097,
+      "grad_norm": 0.6229656396539505,
+      "learning_rate": 9.993513890173744e-06,
+      "loss": 0.6026,
+      "num_tokens": 459859723.0,
+      "step": 1530
+    },
+    {
+      "epoch": 0.04693404851883457,
+      "grad_norm": 0.5841220954567161,
+      "learning_rate": 9.993273298499316e-06,
+      "loss": 0.6023,
+      "num_tokens": 462867699.0,
+      "step": 1540
+    },
+    {
+      "epoch": 0.047238815067658174,
+      "grad_norm": 0.6425202001571686,
+      "learning_rate": 9.993028328871467e-06,
+      "loss": 0.6044,
+      "num_tokens": 465823281.0,
+      "step": 1550
+    },
+    {
+      "epoch": 0.04754358161648178,
+      "grad_norm": 0.6228764781021571,
+      "learning_rate": 9.992778981528877e-06,
+      "loss": 0.6196,
+      "num_tokens": 468743583.0,
+      "step": 1560
+    },
+    {
+      "epoch": 0.04784834816530538,
+      "grad_norm": 0.6205726565240487,
+      "learning_rate": 9.992525256714497e-06,
+      "loss": 0.6074,
+      "num_tokens": 471737961.0,
+      "step": 1570
+    },
+    {
+      "epoch": 0.048153114714128975,
+      "grad_norm": 0.5869602201717057,
+      "learning_rate": 9.992267154675535e-06,
+      "loss": 0.6099,
+      "num_tokens": 474795805.0,
+      "step": 1580
+    },
+    {
+      "epoch": 0.04845788126295258,
+      "grad_norm": 0.6445995250488186,
+      "learning_rate": 9.992004675663475e-06,
+      "loss": 0.6112,
+      "num_tokens": 477809117.0,
+      "step": 1590
+    },
+    {
+      "epoch": 0.04876264781177618,
+      "grad_norm": 0.6103612168796501,
+      "learning_rate": 9.991737819934055e-06,
+      "loss": 0.5964,
+      "num_tokens": 480802930.0,
+      "step": 1600
+    },
+    {
+      "epoch": 0.04906741436059978,
+      "grad_norm": 0.6333844320175454,
+      "learning_rate": 9.991466587747281e-06,
+      "loss": 0.5979,
+      "num_tokens": 483854212.0,
+      "step": 1610
+    },
+    {
+      "epoch": 0.04937218090942338,
+      "grad_norm": 0.6720644558500382,
+      "learning_rate": 9.991190979367427e-06,
+      "loss": 0.6028,
+      "num_tokens": 486911723.0,
+      "step": 1620
+    },
+    {
+      "epoch": 0.04967694745824698,
+      "grad_norm": 0.6257467769927044,
+      "learning_rate": 9.990910995063027e-06,
+      "loss": 0.6001,
+      "num_tokens": 489973388.0,
+      "step": 1630
+    },
+    {
+      "epoch": 0.049981714007070584,
+      "grad_norm": 0.6076395236262263,
+      "learning_rate": 9.99062663510688e-06,
+      "loss": 0.6127,
+      "num_tokens": 492950960.0,
+      "step": 1640
+    },
+    {
+      "epoch": 0.050286480555894186,
+      "grad_norm": 0.5886754916747438,
+      "learning_rate": 9.990337899776045e-06,
+      "loss": 0.6092,
+      "num_tokens": 496022992.0,
+      "step": 1650
+    },
+    {
+      "epoch": 0.05059124710471779,
+      "grad_norm": 0.5960181526222773,
+      "learning_rate": 9.99004478935185e-06,
+      "loss": 0.6128,
+      "num_tokens": 499023533.0,
+      "step": 1660
+    },
+    {
+      "epoch": 0.050896013653541385,
+      "grad_norm": 0.5953397756091234,
+      "learning_rate": 9.989747304119884e-06,
+      "loss": 0.5999,
+      "num_tokens": 501998703.0,
+      "step": 1670
+    },
+    {
+      "epoch": 0.05120078020236499,
+      "grad_norm": 0.584895120211458,
+      "learning_rate": 9.989445444369994e-06,
+      "loss": 0.6055,
+      "num_tokens": 504912306.0,
+      "step": 1680
+    },
+    {
+      "epoch": 0.05150554675118859,
+      "grad_norm": 0.6377962999203446,
+      "learning_rate": 9.989139210396293e-06,
+      "loss": 0.6058,
+      "num_tokens": 507940287.0,
+      "step": 1690
+    },
+    {
+      "epoch": 0.05181031330001219,
+      "grad_norm": 0.5216876947745497,
+      "learning_rate": 9.988828602497158e-06,
+      "loss": 0.6187,
+      "num_tokens": 510967111.0,
+      "step": 1700
+    },
+    {
+      "epoch": 0.052115079848835795,
+      "grad_norm": 0.5976651645934364,
+      "learning_rate": 9.98851362097522e-06,
+      "loss": 0.5964,
+      "num_tokens": 513983124.0,
+      "step": 1710
+    },
+    {
+      "epoch": 0.05241984639765939,
+      "grad_norm": 0.6763718773959415,
+      "learning_rate": 9.988194266137383e-06,
+      "loss": 0.6018,
+      "num_tokens": 516951871.0,
+      "step": 1720
+    },
+    {
+      "epoch": 0.05272461294648299,
+      "grad_norm": 0.5908803974280435,
+      "learning_rate": 9.987870538294802e-06,
+      "loss": 0.5964,
+      "num_tokens": 519990414.0,
+      "step": 1730
+    },
+    {
+      "epoch": 0.053029379495306596,
+      "grad_norm": 0.6265785359754944,
+      "learning_rate": 9.987542437762896e-06,
+      "loss": 0.6059,
+      "num_tokens": 522974513.0,
+      "step": 1740
+    },
+    {
+      "epoch": 0.0533341460441302,
+      "grad_norm": 0.606965411131078,
+      "learning_rate": 9.987209964861345e-06,
+      "loss": 0.6001,
+      "num_tokens": 526039695.0,
+      "step": 1750
+    },
+    {
+      "epoch": 0.053638912592953794,
+      "grad_norm": 0.658199574501422,
+      "learning_rate": 9.98687311991409e-06,
+      "loss": 0.6128,
+      "num_tokens": 528979930.0,
+      "step": 1760
+    },
+    {
+      "epoch": 0.0539436791417774,
+      "grad_norm": 0.6042645727517373,
+      "learning_rate": 9.986531903249331e-06,
+      "loss": 0.608,
+      "num_tokens": 532010385.0,
+      "step": 1770
+    },
+    {
+      "epoch": 0.054248445690601,
+      "grad_norm": 0.5483189537275404,
+      "learning_rate": 9.986186315199528e-06,
+      "loss": 0.5959,
+      "num_tokens": 535016806.0,
+      "step": 1780
+    },
+    {
+      "epoch": 0.0545532122394246,
+      "grad_norm": 0.6248724261843619,
+      "learning_rate": 9.985836356101398e-06,
+      "loss": 0.5961,
+      "num_tokens": 537949771.0,
+      "step": 1790
+    },
+    {
+      "epoch": 0.054857978788248205,
+      "grad_norm": 0.6267355747936748,
+      "learning_rate": 9.985482026295916e-06,
+      "loss": 0.593,
+      "num_tokens": 541001861.0,
+      "step": 1800
+    },
+    {
+      "epoch": 0.0551627453370718,
+      "grad_norm": 0.658428373202468,
+      "learning_rate": 9.985123326128322e-06,
+      "loss": 0.6037,
+      "num_tokens": 543989524.0,
+      "step": 1810
+    },
+    {
+      "epoch": 0.0554675118858954,
+      "grad_norm": 0.5832078235901029,
+      "learning_rate": 9.984760255948109e-06,
+      "loss": 0.6021,
+      "num_tokens": 546968879.0,
+      "step": 1820
+    },
+    {
+      "epoch": 0.055772278434719005,
+      "grad_norm": 0.6389770992791528,
+      "learning_rate": 9.98439281610903e-06,
+      "loss": 0.6109,
+      "num_tokens": 549917192.0,
+      "step": 1830
+    },
+    {
+      "epoch": 0.05607704498354261,
+      "grad_norm": 0.5907814850641283,
+      "learning_rate": 9.984021006969093e-06,
+      "loss": 0.6009,
+      "num_tokens": 552985209.0,
+      "step": 1840
+    },
+    {
+      "epoch": 0.05638181153236621,
+      "grad_norm": 0.6302612593484054,
+      "learning_rate": 9.983644828890563e-06,
+      "loss": 0.5989,
+      "num_tokens": 555998654.0,
+      "step": 1850
+    },
+    {
+      "epoch": 0.056686578081189806,
+      "grad_norm": 0.5404399265212917,
+      "learning_rate": 9.983264282239967e-06,
+      "loss": 0.6118,
+      "num_tokens": 558972706.0,
+      "step": 1860
+    },
+    {
+      "epoch": 0.05699134463001341,
+      "grad_norm": 0.6668943312807988,
+      "learning_rate": 9.982879367388083e-06,
+      "loss": 0.61,
+      "num_tokens": 561941114.0,
+      "step": 1870
+    },
+    {
+      "epoch": 0.05729611117883701,
+      "grad_norm": 0.6465293149801645,
+      "learning_rate": 9.982490084709946e-06,
+      "loss": 0.5947,
+      "num_tokens": 564917589.0,
+      "step": 1880
+    },
+    {
+      "epoch": 0.057600877727660614,
+      "grad_norm": 0.6746757663556419,
+      "learning_rate": 9.982096434584851e-06,
+      "loss": 0.6181,
+      "num_tokens": 567836529.0,
+      "step": 1890
+    },
+    {
+      "epoch": 0.05790564427648421,
+      "grad_norm": 0.5706015932809062,
+      "learning_rate": 9.981698417396341e-06,
+      "loss": 0.5953,
+      "num_tokens": 570916570.0,
+      "step": 1900
+    },
+    {
+      "epoch": 0.05821041082530781,
+      "grad_norm": 0.6048135316190368,
+      "learning_rate": 9.981296033532221e-06,
+      "loss": 0.6054,
+      "num_tokens": 573986324.0,
+      "step": 1910
+    },
+    {
+      "epoch": 0.058515177374131415,
+      "grad_norm": 0.5692749712433784,
+      "learning_rate": 9.980889283384547e-06,
+      "loss": 0.6058,
+      "num_tokens": 576974706.0,
+      "step": 1920
+    },
+    {
+      "epoch": 0.05881994392295502,
+      "grad_norm": 0.604338117924098,
+      "learning_rate": 9.980478167349631e-06,
+      "loss": 0.6199,
+      "num_tokens": 580018172.0,
+      "step": 1930
+    },
+    {
+      "epoch": 0.05912471047177862,
+      "grad_norm": 0.6830120859009248,
+      "learning_rate": 9.980062685828036e-06,
+      "loss": 0.6057,
+      "num_tokens": 583000914.0,
+      "step": 1940
+    },
+    {
+      "epoch": 0.059429477020602216,
+      "grad_norm": 0.6600306750958782,
+      "learning_rate": 9.979642839224579e-06,
+      "loss": 0.6062,
+      "num_tokens": 585955930.0,
+      "step": 1950
+    },
+    {
+      "epoch": 0.05973424356942582,
+      "grad_norm": 0.7728378701939743,
+      "learning_rate": 9.979218627948333e-06,
+      "loss": 0.6125,
+      "num_tokens": 588924595.0,
+      "step": 1960
+    },
+    {
+      "epoch": 0.06003901011824942,
+      "grad_norm": 0.6981817636130082,
+      "learning_rate": 9.978790052412624e-06,
+      "loss": 0.6021,
+      "num_tokens": 591944037.0,
+      "step": 1970
+    },
+    {
+      "epoch": 0.060343776667073024,
+      "grad_norm": 0.6602287311975624,
+      "learning_rate": 9.978357113035025e-06,
+      "loss": 0.6212,
+      "num_tokens": 594948638.0,
+      "step": 1980
+    },
+    {
+      "epoch": 0.060648543215896626,
+      "grad_norm": 0.5880700660748177,
+      "learning_rate": 9.977919810237367e-06,
+      "loss": 0.5991,
+      "num_tokens": 597995285.0,
+      "step": 1990
+    },
+    {
+      "epoch": 0.06095330976472022,
+      "grad_norm": 0.4944145943397841,
+      "learning_rate": 9.977478144445725e-06,
+      "loss": 0.5982,
+      "num_tokens": 601009341.0,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 32812,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2174801484358615e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a3c59545a23db9c385146f1715d0778ee8a1d40421439adb1b2cc46a3150d5
+size 7505

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/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 . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+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)
+
+        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 files:
+        state_dict = torch.load(f, map_location=device)
+        # 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}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) 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")
+
+
+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 = fp32_flat_groups[0].numel() * 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
+    for name, shape in param_shapes.items():
+
+        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}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        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 get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=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
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    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.
+
+    """
+    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")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, 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_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``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
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+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_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    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_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)