Add files using upload-large-folder tool

.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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 +1,78 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "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",
+    "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": 32768,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "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": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

latest

@@ -0,0 +1 @@
+global_step2400

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c944e8034d0dcfbdc72bb9117803cee4f717be1231d50d70e75936ffffc75a44
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6846b569f171e39518b2c398e83f3d36021adcbbd6bc7f386ce93d4919b11f1
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0529c6a3e1d13dfd7f87941f196ac7339f54153465253cd170b7d369d04cd76c
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7072e498f5e61bb836c7f3886f5b6445dea9cc5bc73bb2f6f21b19a9739dc469
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22bea1e0dfb91219ce2fd7ca1392beda00e9ef02b90b7f4eb87d15acc9766677
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ba5d34e78641188503fa5966750a226ba7c40fa3625dcf326bdc13ffaa4471
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,587 @@
+{
+  "metadata": {
+    "total_parameters": 840704,
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60bec299619e780b470cf39b5ba4e1f2237b59b626ea783a379d0304bba0202
+size 15472

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7311e0bb74019a1aca1d8f21cc008554ed3ea7d08ba2c86512295e3c7fb36a6
+size 15472

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db642e50c79f6a61db3bab83bfa9db7c612ae50e5cd7274bfaf8c1340e8dab89
+size 15472

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb7311689c33b20d6e64a4178a32c8a4b61ce3b8023d17b7564602498de6638
+size 15472

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329ad2413b3f770d04352616d125658cd26df70349b5bf49c759840421aec07a
+size 15472

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b283fa9933451127a0485a71ed346bf29c0cf7e04c4f380b6b8c0562d4895ada
+size 15472

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9587fdee48cd937e1e6ebe2e293940f1c57d7f4903b453c182457f32e9b2990
+size 1064

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1714 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8882769472856018,
+  "eval_steps": 500,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007867820613690008,
+      "grad_norm": 1.2563396792767205,
+      "learning_rate": 3.529411764705883e-07,
+      "loss": 0.526,
+      "step": 10
+    },
+    {
+      "epoch": 0.015735641227380016,
+      "grad_norm": 1.3135030094493094,
+      "learning_rate": 7.450980392156863e-07,
+      "loss": 0.5306,
+      "step": 20
+    },
+    {
+      "epoch": 0.023603461841070025,
+      "grad_norm": 0.9198901527878915,
+      "learning_rate": 1.1372549019607845e-06,
+      "loss": 0.5362,
+      "step": 30
+    },
+    {
+      "epoch": 0.03147128245476003,
+      "grad_norm": 1.051735166336249,
+      "learning_rate": 1.5294117647058826e-06,
+      "loss": 0.4387,
+      "step": 40
+    },
+    {
+      "epoch": 0.03933910306845004,
+      "grad_norm": 0.7809357908026243,
+      "learning_rate": 1.921568627450981e-06,
+      "loss": 0.3786,
+      "step": 50
+    },
+    {
+      "epoch": 0.04720692368214005,
+      "grad_norm": 0.563392747701715,
+      "learning_rate": 2.3137254901960787e-06,
+      "loss": 0.3296,
+      "step": 60
+    },
+    {
+      "epoch": 0.05507474429583006,
+      "grad_norm": 1.1346022293188862,
+      "learning_rate": 2.7058823529411766e-06,
+      "loss": 0.2929,
+      "step": 70
+    },
+    {
+      "epoch": 0.06294256490952006,
+      "grad_norm": 0.8241470994379115,
+      "learning_rate": 3.098039215686275e-06,
+      "loss": 0.297,
+      "step": 80
+    },
+    {
+      "epoch": 0.07081038552321008,
+      "grad_norm": 0.7238934422089937,
+      "learning_rate": 3.4901960784313727e-06,
+      "loss": 0.2786,
+      "step": 90
+    },
+    {
+      "epoch": 0.07867820613690008,
+      "grad_norm": 0.7728354013131394,
+      "learning_rate": 3.882352941176471e-06,
+      "loss": 0.2713,
+      "step": 100
+    },
+    {
+      "epoch": 0.08654602675059009,
+      "grad_norm": 0.5639400638066838,
+      "learning_rate": 4.274509803921569e-06,
+      "loss": 0.2643,
+      "step": 110
+    },
+    {
+      "epoch": 0.0944138473642801,
+      "grad_norm": 0.5573827064400829,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.2453,
+      "step": 120
+    },
+    {
+      "epoch": 0.1022816679779701,
+      "grad_norm": 0.5141191658970772,
+      "learning_rate": 5.058823529411765e-06,
+      "loss": 0.2213,
+      "step": 130
+    },
+    {
+      "epoch": 0.11014948859166011,
+      "grad_norm": 0.9826766755342299,
+      "learning_rate": 5.450980392156863e-06,
+      "loss": 0.2496,
+      "step": 140
+    },
+    {
+      "epoch": 0.11801730920535011,
+      "grad_norm": 1.1449821117002568,
+      "learning_rate": 5.843137254901961e-06,
+      "loss": 0.256,
+      "step": 150
+    },
+    {
+      "epoch": 0.12588512981904013,
+      "grad_norm": 0.6097199410429881,
+      "learning_rate": 6.2352941176470595e-06,
+      "loss": 0.2153,
+      "step": 160
+    },
+    {
+      "epoch": 0.13375295043273014,
+      "grad_norm": 0.7226694157983251,
+      "learning_rate": 6.627450980392157e-06,
+      "loss": 0.2417,
+      "step": 170
+    },
+    {
+      "epoch": 0.14162077104642015,
+      "grad_norm": 0.8191125193248624,
+      "learning_rate": 7.019607843137255e-06,
+      "loss": 0.2446,
+      "step": 180
+    },
+    {
+      "epoch": 0.14948859166011014,
+      "grad_norm": 0.6415116110823444,
+      "learning_rate": 7.4117647058823535e-06,
+      "loss": 0.2304,
+      "step": 190
+    },
+    {
+      "epoch": 0.15735641227380015,
+      "grad_norm": 0.810010219902764,
+      "learning_rate": 7.803921568627452e-06,
+      "loss": 0.2393,
+      "step": 200
+    },
+    {
+      "epoch": 0.16522423288749016,
+      "grad_norm": 0.7501347675730082,
+      "learning_rate": 8.19607843137255e-06,
+      "loss": 0.2542,
+      "step": 210
+    },
+    {
+      "epoch": 0.17309205350118018,
+      "grad_norm": 0.6434902631537739,
+      "learning_rate": 8.588235294117647e-06,
+      "loss": 0.2223,
+      "step": 220
+    },
+    {
+      "epoch": 0.1809598741148702,
+      "grad_norm": 0.5862939512221611,
+      "learning_rate": 8.980392156862746e-06,
+      "loss": 0.224,
+      "step": 230
+    },
+    {
+      "epoch": 0.1888276947285602,
+      "grad_norm": 0.6791678726203656,
+      "learning_rate": 9.372549019607843e-06,
+      "loss": 0.2275,
+      "step": 240
+    },
+    {
+      "epoch": 0.1966955153422502,
+      "grad_norm": 0.7398256157477153,
+      "learning_rate": 9.764705882352942e-06,
+      "loss": 0.2258,
+      "step": 250
+    },
+    {
+      "epoch": 0.2045633359559402,
+      "grad_norm": 0.6256137829806282,
+      "learning_rate": 9.999924520969215e-06,
+      "loss": 0.2233,
+      "step": 260
+    },
+    {
+      "epoch": 0.21243115656963021,
+      "grad_norm": 1.2073294469775442,
+      "learning_rate": 9.999075408043623e-06,
+      "loss": 0.2378,
+      "step": 270
+    },
+    {
+      "epoch": 0.22029897718332023,
+      "grad_norm": 0.7222238878673806,
+      "learning_rate": 9.997282994161499e-06,
+      "loss": 0.2201,
+      "step": 280
+    },
+    {
+      "epoch": 0.22816679779701024,
+      "grad_norm": 0.672068169462996,
+      "learning_rate": 9.994547617542525e-06,
+      "loss": 0.2187,
+      "step": 290
+    },
+    {
+      "epoch": 0.23603461841070023,
+      "grad_norm": 0.706362832607499,
+      "learning_rate": 9.990869794338829e-06,
+      "loss": 0.2235,
+      "step": 300
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.46445443905814426,
+      "learning_rate": 9.986250218537568e-06,
+      "loss": 0.2036,
+      "step": 310
+    },
+    {
+      "epoch": 0.25177025963808025,
+      "grad_norm": 0.527545707844664,
+      "learning_rate": 9.980689761829989e-06,
+      "loss": 0.2157,
+      "step": 320
+    },
+    {
+      "epoch": 0.25963808025177026,
+      "grad_norm": 0.8781830284482457,
+      "learning_rate": 9.97418947344694e-06,
+      "loss": 0.2217,
+      "step": 330
+    },
+    {
+      "epoch": 0.2675059008654603,
+      "grad_norm": 0.5973386834944165,
+      "learning_rate": 9.966750579960886e-06,
+      "loss": 0.2022,
+      "step": 340
+    },
+    {
+      "epoch": 0.2753737214791503,
+      "grad_norm": 0.8092038324125969,
+      "learning_rate": 9.958374485054466e-06,
+      "loss": 0.2325,
+      "step": 350
+    },
+    {
+      "epoch": 0.2832415420928403,
+      "grad_norm": 0.6124530337562732,
+      "learning_rate": 9.94906276925561e-06,
+      "loss": 0.2107,
+      "step": 360
+    },
+    {
+      "epoch": 0.2911093627065303,
+      "grad_norm": 0.4264047566808134,
+      "learning_rate": 9.93881718963932e-06,
+      "loss": 0.2216,
+      "step": 370
+    },
+    {
+      "epoch": 0.2989771833202203,
+      "grad_norm": 0.8212521750702654,
+      "learning_rate": 9.92763967949611e-06,
+      "loss": 0.226,
+      "step": 380
+    },
+    {
+      "epoch": 0.3068450039339103,
+      "grad_norm": 0.7892646236417317,
+      "learning_rate": 9.915532347967195e-06,
+      "loss": 0.2229,
+      "step": 390
+    },
+    {
+      "epoch": 0.3147128245476003,
+      "grad_norm": 0.7301451419876369,
+      "learning_rate": 9.902497479646529e-06,
+      "loss": 0.2297,
+      "step": 400
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.647813328790849,
+      "learning_rate": 9.888537534149685e-06,
+      "loss": 0.2359,
+      "step": 410
+    },
+    {
+      "epoch": 0.3304484657749803,
+      "grad_norm": 0.5862447269062615,
+      "learning_rate": 9.87365514564976e-06,
+      "loss": 0.2172,
+      "step": 420
+    },
+    {
+      "epoch": 0.33831628638867034,
+      "grad_norm": 0.5715079744148545,
+      "learning_rate": 9.85785312238031e-06,
+      "loss": 0.2015,
+      "step": 430
+    },
+    {
+      "epoch": 0.34618410700236035,
+      "grad_norm": 0.5454549512450757,
+      "learning_rate": 9.841134446105451e-06,
+      "loss": 0.2174,
+      "step": 440
+    },
+    {
+      "epoch": 0.35405192761605037,
+      "grad_norm": 0.6967493701407584,
+      "learning_rate": 9.823502271557215e-06,
+      "loss": 0.2144,
+      "step": 450
+    },
+    {
+      "epoch": 0.3619197482297404,
+      "grad_norm": 0.570431175732896,
+      "learning_rate": 9.804959925840267e-06,
+      "loss": 0.2249,
+      "step": 460
+    },
+    {
+      "epoch": 0.3697875688434304,
+      "grad_norm": 0.536491130690211,
+      "learning_rate": 9.785510907804102e-06,
+      "loss": 0.2164,
+      "step": 470
+    },
+    {
+      "epoch": 0.3776553894571204,
+      "grad_norm": 0.5175232634662781,
+      "learning_rate": 9.76515888738282e-06,
+      "loss": 0.1972,
+      "step": 480
+    },
+    {
+      "epoch": 0.38552321007081036,
+      "grad_norm": 1.0367228684704208,
+      "learning_rate": 9.743907704902632e-06,
+      "loss": 0.2181,
+      "step": 490
+    },
+    {
+      "epoch": 0.3933910306845004,
+      "grad_norm": 0.814039380294453,
+      "learning_rate": 9.721761370357215e-06,
+      "loss": 0.2151,
+      "step": 500
+    },
+    {
+      "epoch": 0.4012588512981904,
+      "grad_norm": 1.0247867428118445,
+      "learning_rate": 9.698724062651036e-06,
+      "loss": 0.2194,
+      "step": 510
+    },
+    {
+      "epoch": 0.4091266719118804,
+      "grad_norm": 0.4772814370759674,
+      "learning_rate": 9.67480012881082e-06,
+      "loss": 0.2018,
+      "step": 520
+    },
+    {
+      "epoch": 0.4169944925255704,
+      "grad_norm": 0.6334991193585142,
+      "learning_rate": 9.649994083165282e-06,
+      "loss": 0.2186,
+      "step": 530
+    },
+    {
+      "epoch": 0.42486231313926043,
+      "grad_norm": 0.5929466045597842,
+      "learning_rate": 9.624310606493306e-06,
+      "loss": 0.2007,
+      "step": 540
+    },
+    {
+      "epoch": 0.43273013375295044,
+      "grad_norm": 0.682618389982754,
+      "learning_rate": 9.597754545140687e-06,
+      "loss": 0.2102,
+      "step": 550
+    },
+    {
+      "epoch": 0.44059795436664045,
+      "grad_norm": 0.5505458532295032,
+      "learning_rate": 9.570330910105673e-06,
+      "loss": 0.2253,
+      "step": 560
+    },
+    {
+      "epoch": 0.44846577498033047,
+      "grad_norm": 0.5573586177808739,
+      "learning_rate": 9.542044876093385e-06,
+      "loss": 0.2068,
+      "step": 570
+    },
+    {
+      "epoch": 0.4563335955940205,
+      "grad_norm": 0.48471218796883714,
+      "learning_rate": 9.51290178053941e-06,
+      "loss": 0.1981,
+      "step": 580
+    },
+    {
+      "epoch": 0.46420141620771044,
+      "grad_norm": 1.1960176181958666,
+      "learning_rate": 9.48290712260262e-06,
+      "loss": 0.1989,
+      "step": 590
+    },
+    {
+      "epoch": 0.47206923682140045,
+      "grad_norm": 0.6042229333585943,
+      "learning_rate": 9.452066562127533e-06,
+      "loss": 0.2118,
+      "step": 600
+    },
+    {
+      "epoch": 0.47993705743509046,
+      "grad_norm": 0.6678108159264212,
+      "learning_rate": 9.420385918576309e-06,
+      "loss": 0.2183,
+      "step": 610
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.6124767060478632,
+      "learning_rate": 9.387871169930665e-06,
+      "loss": 0.215,
+      "step": 620
+    },
+    {
+      "epoch": 0.4956726986624705,
+      "grad_norm": 0.7714561316034021,
+      "learning_rate": 9.354528451563842e-06,
+      "loss": 0.2149,
+      "step": 630
+    },
+    {
+      "epoch": 0.5035405192761605,
+      "grad_norm": 1.0245509624483824,
+      "learning_rate": 9.3203640550829e-06,
+      "loss": 0.2163,
+      "step": 640
+    },
+    {
+      "epoch": 0.5114083398898505,
+      "grad_norm": 0.7403203582429149,
+      "learning_rate": 9.285384427141518e-06,
+      "loss": 0.1966,
+      "step": 650
+    },
+    {
+      "epoch": 0.5192761605035405,
+      "grad_norm": 0.603347726106838,
+      "learning_rate": 9.249596168223546e-06,
+      "loss": 0.2223,
+      "step": 660
+    },
+    {
+      "epoch": 0.5271439811172305,
+      "grad_norm": 0.9915859514934033,
+      "learning_rate": 9.21300603139753e-06,
+      "loss": 0.2162,
+      "step": 670
+    },
+    {
+      "epoch": 0.5350118017309206,
+      "grad_norm": 0.5558916281664622,
+      "learning_rate": 9.175620921042426e-06,
+      "loss": 0.2259,
+      "step": 680
+    },
+    {
+      "epoch": 0.5428796223446105,
+      "grad_norm": 0.6626877700846282,
+      "learning_rate": 9.137447891544788e-06,
+      "loss": 0.2168,
+      "step": 690
+    },
+    {
+      "epoch": 0.5507474429583006,
+      "grad_norm": 0.5674818356283944,
+      "learning_rate": 9.09849414596765e-06,
+      "loss": 0.2059,
+      "step": 700
+    },
+    {
+      "epoch": 0.5586152635719905,
+      "grad_norm": 0.7077012697683026,
+      "learning_rate": 9.05876703469132e-06,
+      "loss": 0.1989,
+      "step": 710
+    },
+    {
+      "epoch": 0.5664830841856806,
+      "grad_norm": 0.42222310303001537,
+      "learning_rate": 9.01827405402642e-06,
+      "loss": 0.2041,
+      "step": 720
+    },
+    {
+      "epoch": 0.5743509047993706,
+      "grad_norm": 0.5573404932415545,
+      "learning_rate": 8.977022844799354e-06,
+      "loss": 0.2111,
+      "step": 730
+    },
+    {
+      "epoch": 0.5822187254130606,
+      "grad_norm": 0.6307914163115699,
+      "learning_rate": 8.93502119091054e-06,
+      "loss": 0.2146,
+      "step": 740
+    },
+    {
+      "epoch": 0.5900865460267506,
+      "grad_norm": 0.8272678907322577,
+      "learning_rate": 8.8922770178656e-06,
+      "loss": 0.1971,
+      "step": 750
+    },
+    {
+      "epoch": 0.5979543666404405,
+      "grad_norm": 0.7039582605212021,
+      "learning_rate": 8.848798391279882e-06,
+      "loss": 0.21,
+      "step": 760
+    },
+    {
+      "epoch": 0.6058221872541306,
+      "grad_norm": 0.492399569766261,
+      "learning_rate": 8.804593515356505e-06,
+      "loss": 0.2059,
+      "step": 770
+    },
+    {
+      "epoch": 0.6136900078678206,
+      "grad_norm": 0.5684983190033265,
+      "learning_rate": 8.759670731338263e-06,
+      "loss": 0.2067,
+      "step": 780
+    },
+    {
+      "epoch": 0.6215578284815106,
+      "grad_norm": 0.7118145133517305,
+      "learning_rate": 8.714038515933688e-06,
+      "loss": 0.1902,
+      "step": 790
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "grad_norm": 0.7788292282243499,
+      "learning_rate": 8.667705479717515e-06,
+      "loss": 0.2114,
+      "step": 800
+    },
+    {
+      "epoch": 0.6372934697088907,
+      "grad_norm": 0.43707246869115934,
+      "learning_rate": 8.62068036550593e-06,
+      "loss": 0.2007,
+      "step": 810
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.4630271644053931,
+      "learning_rate": 8.572972046706834e-06,
+      "loss": 0.2068,
+      "step": 820
+    },
+    {
+      "epoch": 0.6530291109362707,
+      "grad_norm": 0.5602138747940821,
+      "learning_rate": 8.524589525645475e-06,
+      "loss": 0.1987,
+      "step": 830
+    },
+    {
+      "epoch": 0.6608969315499607,
+      "grad_norm": 0.6170216493044052,
+      "learning_rate": 8.47554193186575e-06,
+      "loss": 0.2033,
+      "step": 840
+    },
+    {
+      "epoch": 0.6687647521636507,
+      "grad_norm": 0.8315831243219495,
+      "learning_rate": 8.425838520407514e-06,
+      "loss": 0.2158,
+      "step": 850
+    },
+    {
+      "epoch": 0.6766325727773407,
+      "grad_norm": 0.5579036969239893,
+      "learning_rate": 8.37548867006019e-06,
+      "loss": 0.2061,
+      "step": 860
+    },
+    {
+      "epoch": 0.6845003933910306,
+      "grad_norm": 0.590186415349968,
+      "learning_rate": 8.324501881593046e-06,
+      "loss": 0.2174,
+      "step": 870
+    },
+    {
+      "epoch": 0.6923682140047207,
+      "grad_norm": 0.5644166501889786,
+      "learning_rate": 8.272887775962439e-06,
+      "loss": 0.2077,
+      "step": 880
+    },
+    {
+      "epoch": 0.7002360346184107,
+      "grad_norm": 0.5849246059339895,
+      "learning_rate": 8.220656092496391e-06,
+      "loss": 0.1996,
+      "step": 890
+    },
+    {
+      "epoch": 0.7081038552321007,
+      "grad_norm": 0.6543260172108398,
+      "learning_rate": 8.16781668705683e-06,
+      "loss": 0.2192,
+      "step": 900
+    },
+    {
+      "epoch": 0.7159716758457907,
+      "grad_norm": 0.7580405775602811,
+      "learning_rate": 8.114379530179828e-06,
+      "loss": 0.2158,
+      "step": 910
+    },
+    {
+      "epoch": 0.7238394964594808,
+      "grad_norm": 0.540519415520931,
+      "learning_rate": 8.060354705194218e-06,
+      "loss": 0.2004,
+      "step": 920
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.6322971950927899,
+      "learning_rate": 8.005752406318916e-06,
+      "loss": 0.2073,
+      "step": 930
+    },
+    {
+      "epoch": 0.7395751376868608,
+      "grad_norm": 0.6943117033299396,
+      "learning_rate": 7.950582936739322e-06,
+      "loss": 0.2098,
+      "step": 940
+    },
+    {
+      "epoch": 0.7474429583005507,
+      "grad_norm": 0.950871224262797,
+      "learning_rate": 7.894856706663158e-06,
+      "loss": 0.1958,
+      "step": 950
+    },
+    {
+      "epoch": 0.7553107789142408,
+      "grad_norm": 0.5619870214568407,
+      "learning_rate": 7.83858423135612e-06,
+      "loss": 0.2074,
+      "step": 960
+    },
+    {
+      "epoch": 0.7631785995279308,
+      "grad_norm": 0.5520555392202162,
+      "learning_rate": 7.781776129157693e-06,
+      "loss": 0.1941,
+      "step": 970
+    },
+    {
+      "epoch": 0.7710464201416207,
+      "grad_norm": 0.39005505221270387,
+      "learning_rate": 7.724443119477513e-06,
+      "loss": 0.2094,
+      "step": 980
+    },
+    {
+      "epoch": 0.7789142407553108,
+      "grad_norm": 0.6056166619335882,
+      "learning_rate": 7.666596020772695e-06,
+      "loss": 0.1945,
+      "step": 990
+    },
+    {
+      "epoch": 0.7867820613690008,
+      "grad_norm": 0.6955016619315612,
+      "learning_rate": 7.608245748506413e-06,
+      "loss": 0.1961,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7946498819826908,
+      "grad_norm": 0.4179143665308098,
+      "learning_rate": 7.5494033130882224e-06,
+      "loss": 0.195,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8025177025963808,
+      "grad_norm": 0.4416211173138847,
+      "learning_rate": 7.4900798177964494e-06,
+      "loss": 0.2181,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8103855232100708,
+      "grad_norm": 0.8590528047221729,
+      "learning_rate": 7.430286456683049e-06,
+      "loss": 0.1812,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8182533438237608,
+      "grad_norm": 0.5289996376858749,
+      "learning_rate": 7.370034512461347e-06,
+      "loss": 0.2006,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8261211644374509,
+      "grad_norm": 0.7036314475795769,
+      "learning_rate": 7.309335354377051e-06,
+      "loss": 0.1862,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8339889850511408,
+      "grad_norm": 0.5219578550655386,
+      "learning_rate": 7.248200436062928e-06,
+      "loss": 0.1938,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8418568056648308,
+      "grad_norm": 0.4994038905679838,
+      "learning_rate": 7.186641293377551e-06,
+      "loss": 0.1977,
+      "step": 1070
+    },
+    {
+      "epoch": 0.8497246262785209,
+      "grad_norm": 0.54839453001551,
+      "learning_rate": 7.124669542228553e-06,
+      "loss": 0.1833,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8575924468922108,
+      "grad_norm": 0.47763800570583487,
+      "learning_rate": 7.062296876380751e-06,
+      "loss": 0.182,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8654602675059009,
+      "grad_norm": 0.7511024504079028,
+      "learning_rate": 6.999535065249599e-06,
+      "loss": 0.1966,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8733280881195908,
+      "grad_norm": 0.4864261759839409,
+      "learning_rate": 6.936395951680353e-06,
+      "loss": 0.1971,
+      "step": 1110
+    },
+    {
+      "epoch": 0.8811959087332809,
+      "grad_norm": 0.6010785000589546,
+      "learning_rate": 6.872891449713383e-06,
+      "loss": 0.2013,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8890637293469709,
+      "grad_norm": 0.626673072527654,
+      "learning_rate": 6.809033542336049e-06,
+      "loss": 0.2169,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8969315499606609,
+      "grad_norm": 0.554417524671533,
+      "learning_rate": 6.744834279221586e-06,
+      "loss": 0.2094,
+      "step": 1140
+    },
+    {
+      "epoch": 0.9047993705743509,
+      "grad_norm": 0.5808479841315488,
+      "learning_rate": 6.680305774455369e-06,
+      "loss": 0.1822,
+      "step": 1150
+    },
+    {
+      "epoch": 0.912667191188041,
+      "grad_norm": 0.6340314095846309,
+      "learning_rate": 6.615460204249057e-06,
+      "loss": 0.21,
+      "step": 1160
+    },
+    {
+      "epoch": 0.9205350118017309,
+      "grad_norm": 0.5590484986953396,
+      "learning_rate": 6.550309804642999e-06,
+      "loss": 0.1784,
+      "step": 1170
+    },
+    {
+      "epoch": 0.9284028324154209,
+      "grad_norm": 0.6207380978933481,
+      "learning_rate": 6.484866869197357e-06,
+      "loss": 0.2088,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9362706530291109,
+      "grad_norm": 0.5355087089093686,
+      "learning_rate": 6.4191437466723605e-06,
+      "loss": 0.2036,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9441384736428009,
+      "grad_norm": 0.717634760697657,
+      "learning_rate": 6.353152838698173e-06,
+      "loss": 0.2022,
+      "step": 1200
+    },
+    {
+      "epoch": 0.952006294256491,
+      "grad_norm": 0.3879032447703543,
+      "learning_rate": 6.286906597434746e-06,
+      "loss": 0.1924,
+      "step": 1210
+    },
+    {
+      "epoch": 0.9598741148701809,
+      "grad_norm": 0.435414668856126,
+      "learning_rate": 6.220417523222173e-06,
+      "loss": 0.1905,
+      "step": 1220
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.4522163677196112,
+      "learning_rate": 6.153698162221934e-06,
+      "loss": 0.187,
+      "step": 1230
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.6665942005501231,
+      "learning_rate": 6.086761104049488e-06,
+      "loss": 0.1907,
+      "step": 1240
+    },
+    {
+      "epoch": 0.983477576711251,
+      "grad_norm": 0.787016566749408,
+      "learning_rate": 6.019618979398683e-06,
+      "loss": 0.1925,
+      "step": 1250
+    },
+    {
+      "epoch": 0.991345397324941,
+      "grad_norm": 0.42251883753591335,
+      "learning_rate": 5.952284457658403e-06,
+      "loss": 0.173,
+      "step": 1260
+    },
+    {
+      "epoch": 0.999213217938631,
+      "grad_norm": 0.5110746269375878,
+      "learning_rate": 5.884770244521921e-06,
+      "loss": 0.2003,
+      "step": 1270
+    },
+    {
+      "epoch": 1.007081038552321,
+      "grad_norm": 0.48207535192082634,
+      "learning_rate": 5.817089079589386e-06,
+      "loss": 0.1424,
+      "step": 1280
+    },
+    {
+      "epoch": 1.014948859166011,
+      "grad_norm": 0.5730807347527337,
+      "learning_rate": 5.749253733963935e-06,
+      "loss": 0.1407,
+      "step": 1290
+    },
+    {
+      "epoch": 1.022816679779701,
+      "grad_norm": 0.4876484181063124,
+      "learning_rate": 5.6812770078418434e-06,
+      "loss": 0.1331,
+      "step": 1300
+    },
+    {
+      "epoch": 1.030684500393391,
+      "grad_norm": 0.5370215556633184,
+      "learning_rate": 5.613171728097188e-06,
+      "loss": 0.128,
+      "step": 1310
+    },
+    {
+      "epoch": 1.038552321007081,
+      "grad_norm": 0.7133393324735307,
+      "learning_rate": 5.544950745861491e-06,
+      "loss": 0.1254,
+      "step": 1320
+    },
+    {
+      "epoch": 1.046420141620771,
+      "grad_norm": 0.42504978332627247,
+      "learning_rate": 5.476626934098753e-06,
+      "loss": 0.1389,
+      "step": 1330
+    },
+    {
+      "epoch": 1.054287962234461,
+      "grad_norm": 0.4928830442725478,
+      "learning_rate": 5.408213185176411e-06,
+      "loss": 0.139,
+      "step": 1340
+    },
+    {
+      "epoch": 1.0621557828481512,
+      "grad_norm": 0.5093343700952453,
+      "learning_rate": 5.339722408432599e-06,
+      "loss": 0.1351,
+      "step": 1350
+    },
+    {
+      "epoch": 1.070023603461841,
+      "grad_norm": 0.6049398277176702,
+      "learning_rate": 5.271167527740223e-06,
+      "loss": 0.1461,
+      "step": 1360
+    },
+    {
+      "epoch": 1.077891424075531,
+      "grad_norm": 0.5239605881859222,
+      "learning_rate": 5.202561479068286e-06,
+      "loss": 0.1339,
+      "step": 1370
+    },
+    {
+      "epoch": 1.085759244689221,
+      "grad_norm": 0.6312769880979752,
+      "learning_rate": 5.1339172080409395e-06,
+      "loss": 0.1361,
+      "step": 1380
+    },
+    {
+      "epoch": 1.0936270653029112,
+      "grad_norm": 0.3895827766594216,
+      "learning_rate": 5.0652476674947075e-06,
+      "loss": 0.1424,
+      "step": 1390
+    },
+    {
+      "epoch": 1.1014948859166012,
+      "grad_norm": 1.235155913903572,
+      "learning_rate": 4.996565815034343e-06,
+      "loss": 0.1344,
+      "step": 1400
+    },
+    {
+      "epoch": 1.1093627065302911,
+      "grad_norm": 0.6987084756734921,
+      "learning_rate": 4.927884610587799e-06,
+      "loss": 0.1416,
+      "step": 1410
+    },
+    {
+      "epoch": 1.117230527143981,
+      "grad_norm": 0.5553589292587866,
+      "learning_rate": 4.859217013960756e-06,
+      "loss": 0.121,
+      "step": 1420
+    },
+    {
+      "epoch": 1.125098347757671,
+      "grad_norm": 0.5395922903657083,
+      "learning_rate": 4.790575982391159e-06,
+      "loss": 0.1248,
+      "step": 1430
+    },
+    {
+      "epoch": 1.1329661683713612,
+      "grad_norm": 0.4524173447369168,
+      "learning_rate": 4.721974468104262e-06,
+      "loss": 0.1343,
+      "step": 1440
+    },
+    {
+      "epoch": 1.1408339889850512,
+      "grad_norm": 0.5473952888473318,
+      "learning_rate": 4.653425415868598e-06,
+      "loss": 0.1416,
+      "step": 1450
+    },
+    {
+      "epoch": 1.1487018095987411,
+      "grad_norm": 0.4738838437624414,
+      "learning_rate": 4.5849417605533715e-06,
+      "loss": 0.1488,
+      "step": 1460
+    },
+    {
+      "epoch": 1.156569630212431,
+      "grad_norm": 0.5179993948561279,
+      "learning_rate": 4.516536424687709e-06,
+      "loss": 0.1255,
+      "step": 1470
+    },
+    {
+      "epoch": 1.1644374508261213,
+      "grad_norm": 0.7628254212853918,
+      "learning_rate": 4.4482223160222415e-06,
+      "loss": 0.1256,
+      "step": 1480
+    },
+    {
+      "epoch": 1.1723052714398112,
+      "grad_norm": 0.5381860186708352,
+      "learning_rate": 4.380012325093479e-06,
+      "loss": 0.1254,
+      "step": 1490
+    },
+    {
+      "epoch": 1.1801730920535012,
+      "grad_norm": 1.2696006427866238,
+      "learning_rate": 4.31191932279142e-06,
+      "loss": 0.1357,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1880409126671911,
+      "grad_norm": 0.5568884541915783,
+      "learning_rate": 4.243956157930887e-06,
+      "loss": 0.1198,
+      "step": 1510
+    },
+    {
+      "epoch": 1.195908733280881,
+      "grad_norm": 0.5476579574748749,
+      "learning_rate": 4.176135654827021e-06,
+      "loss": 0.1391,
+      "step": 1520
+    },
+    {
+      "epoch": 1.2037765538945713,
+      "grad_norm": 0.589463430203363,
+      "learning_rate": 4.1084706108753785e-06,
+      "loss": 0.1433,
+      "step": 1530
+    },
+    {
+      "epoch": 1.2116443745082612,
+      "grad_norm": 0.5687455802317931,
+      "learning_rate": 4.040973794137153e-06,
+      "loss": 0.128,
+      "step": 1540
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 0.5820447935879994,
+      "learning_rate": 3.973657940929878e-06,
+      "loss": 0.1356,
+      "step": 1550
+    },
+    {
+      "epoch": 1.2273800157356411,
+      "grad_norm": 0.534904199825102,
+      "learning_rate": 3.9065357534241655e-06,
+      "loss": 0.132,
+      "step": 1560
+    },
+    {
+      "epoch": 1.2352478363493313,
+      "grad_norm": 0.5620782809979786,
+      "learning_rate": 3.839619897246856e-06,
+      "loss": 0.122,
+      "step": 1570
+    },
+    {
+      "epoch": 1.2431156569630213,
+      "grad_norm": 0.5731520084920008,
+      "learning_rate": 3.772922999091086e-06,
+      "loss": 0.1359,
+      "step": 1580
+    },
+    {
+      "epoch": 1.2509834775767112,
+      "grad_norm": 0.5230577564560227,
+      "learning_rate": 3.706457644333686e-06,
+      "loss": 0.1205,
+      "step": 1590
+    },
+    {
+      "epoch": 1.2588512981904012,
+      "grad_norm": 0.5453427125049689,
+      "learning_rate": 3.6402363746603934e-06,
+      "loss": 0.1351,
+      "step": 1600
+    },
+    {
+      "epoch": 1.2667191188040912,
+      "grad_norm": 0.5242247079964139,
+      "learning_rate": 3.574271685699283e-06,
+      "loss": 0.1307,
+      "step": 1610
+    },
+    {
+      "epoch": 1.2745869394177813,
+      "grad_norm": 0.47402338207853245,
+      "learning_rate": 3.5085760246629117e-06,
+      "loss": 0.1343,
+      "step": 1620
+    },
+    {
+      "epoch": 1.2824547600314713,
+      "grad_norm": 0.47926470260952986,
+      "learning_rate": 3.443161787999589e-06,
+      "loss": 0.1273,
+      "step": 1630
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.49390437437594975,
+      "learning_rate": 3.3780413190542306e-06,
+      "loss": 0.1294,
+      "step": 1640
+    },
+    {
+      "epoch": 1.2981904012588514,
+      "grad_norm": 0.6880284576105457,
+      "learning_rate": 3.313226905739225e-06,
+      "loss": 0.1296,
+      "step": 1650
+    },
+    {
+      "epoch": 1.3060582218725414,
+      "grad_norm": 0.5136975391112322,
+      "learning_rate": 3.2487307782157727e-06,
+      "loss": 0.1307,
+      "step": 1660
+    },
+    {
+      "epoch": 1.3139260424862313,
+      "grad_norm": 0.4920134908767139,
+      "learning_rate": 3.184565106586105e-06,
+      "loss": 0.1283,
+      "step": 1670
+    },
+    {
+      "epoch": 1.3217938630999213,
+      "grad_norm": 0.4852479788866672,
+      "learning_rate": 3.120741998597051e-06,
+      "loss": 0.1249,
+      "step": 1680
+    },
+    {
+      "epoch": 1.3296616837136113,
+      "grad_norm": 0.42812157679700585,
+      "learning_rate": 3.057273497355367e-06,
+      "loss": 0.1393,
+      "step": 1690
+    },
+    {
+      "epoch": 1.3375295043273012,
+      "grad_norm": 0.6645288869530637,
+      "learning_rate": 2.994171579055257e-06,
+      "loss": 0.1291,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3453973249409914,
+      "grad_norm": 0.6138248428532651,
+      "learning_rate": 2.9314481507185253e-06,
+      "loss": 0.1345,
+      "step": 1710
+    },
+    {
+      "epoch": 1.3532651455546814,
+      "grad_norm": 0.5050171462426947,
+      "learning_rate": 2.8691150479477856e-06,
+      "loss": 0.13,
+      "step": 1720
+    },
+    {
+      "epoch": 1.3611329661683713,
+      "grad_norm": 0.4864737735070035,
+      "learning_rate": 2.8071840326931297e-06,
+      "loss": 0.1322,
+      "step": 1730
+    },
+    {
+      "epoch": 1.3690007867820615,
+      "grad_norm": 0.5339153715325883,
+      "learning_rate": 2.745666791032713e-06,
+      "loss": 0.1251,
+      "step": 1740
+    },
+    {
+      "epoch": 1.3768686073957515,
+      "grad_norm": 0.6301667510785364,
+      "learning_rate": 2.6845749309676526e-06,
+      "loss": 0.1338,
+      "step": 1750
+    },
+    {
+      "epoch": 1.3847364280094414,
+      "grad_norm": 0.6265388703656523,
+      "learning_rate": 2.623919980231643e-06,
+      "loss": 0.1241,
+      "step": 1760
+    },
+    {
+      "epoch": 1.3926042486231314,
+      "grad_norm": 0.6604085665334744,
+      "learning_rate": 2.563713384115737e-06,
+      "loss": 0.1227,
+      "step": 1770
+    },
+    {
+      "epoch": 1.4004720692368213,
+      "grad_norm": 0.7446116599770134,
+      "learning_rate": 2.50396650330868e-06,
+      "loss": 0.1234,
+      "step": 1780
+    },
+    {
+      "epoch": 1.4083398898505113,
+      "grad_norm": 0.6003062951586554,
+      "learning_rate": 2.444690611753193e-06,
+      "loss": 0.1448,
+      "step": 1790
+    },
+    {
+      "epoch": 1.4162077104642015,
+      "grad_norm": 0.4959886630416798,
+      "learning_rate": 2.385896894518641e-06,
+      "loss": 0.136,
+      "step": 1800
+    },
+    {
+      "epoch": 1.4240755310778914,
+      "grad_norm": 0.5044330734030243,
+      "learning_rate": 2.3275964456904658e-06,
+      "loss": 0.1368,
+      "step": 1810
+    },
+    {
+      "epoch": 1.4319433516915814,
+      "grad_norm": 0.7222224778255394,
+      "learning_rate": 2.2698002662767843e-06,
+      "loss": 0.1434,
+      "step": 1820
+    },
+    {
+      "epoch": 1.4398111723052716,
+      "grad_norm": 0.6013748156108749,
+      "learning_rate": 2.212519262132555e-06,
+      "loss": 0.1385,
+      "step": 1830
+    },
+    {
+      "epoch": 1.4476789929189615,
+      "grad_norm": 0.5000632051134212,
+      "learning_rate": 2.155764241901698e-06,
+      "loss": 0.1307,
+      "step": 1840
+    },
+    {
+      "epoch": 1.4555468135326515,
+      "grad_norm": 0.5127376026766847,
+      "learning_rate": 2.0995459149775487e-06,
+      "loss": 0.1424,
+      "step": 1850
+    },
+    {
+      "epoch": 1.4634146341463414,
+      "grad_norm": 0.5122048137575661,
+      "learning_rate": 2.0438748894820578e-06,
+      "loss": 0.1154,
+      "step": 1860
+    },
+    {
+      "epoch": 1.4712824547600314,
+      "grad_norm": 0.49655880881793685,
+      "learning_rate": 1.9887616702640837e-06,
+      "loss": 0.1251,
+      "step": 1870
+    },
+    {
+      "epoch": 1.4791502753737213,
+      "grad_norm": 0.45728825106545223,
+      "learning_rate": 1.934216656917185e-06,
+      "loss": 0.1319,
+      "step": 1880
+    },
+    {
+      "epoch": 1.4870180959874115,
+      "grad_norm": 0.5641684786032549,
+      "learning_rate": 1.880250141817262e-06,
+      "loss": 0.1257,
+      "step": 1890
+    },
+    {
+      "epoch": 1.4948859166011015,
+      "grad_norm": 0.49948564715651084,
+      "learning_rate": 1.826872308180445e-06,
+      "loss": 0.1388,
+      "step": 1900
+    },
+    {
+      "epoch": 1.5027537372147917,
+      "grad_norm": 0.5491747248853652,
+      "learning_rate": 1.774093228141559e-06,
+      "loss": 0.146,
+      "step": 1910
+    },
+    {
+      "epoch": 1.5106215578284816,
+      "grad_norm": 0.6609941142645911,
+      "learning_rate": 1.7219228608535753e-06,
+      "loss": 0.1273,
+      "step": 1920
+    },
+    {
+      "epoch": 1.5184893784421716,
+      "grad_norm": 0.5765270392656745,
+      "learning_rate": 1.670371050608356e-06,
+      "loss": 0.1196,
+      "step": 1930
+    },
+    {
+      "epoch": 1.5263571990558615,
+      "grad_norm": 0.49574709764019,
+      "learning_rate": 1.6194475249790904e-06,
+      "loss": 0.1397,
+      "step": 1940
+    },
+    {
+      "epoch": 1.5342250196695515,
+      "grad_norm": 0.50574398649201,
+      "learning_rate": 1.5691618929847497e-06,
+      "loss": 0.1254,
+      "step": 1950
+    },
+    {
+      "epoch": 1.5420928402832415,
+      "grad_norm": 0.5055264862875227,
+      "learning_rate": 1.519523643276915e-06,
+      "loss": 0.1203,
+      "step": 1960
+    },
+    {
+      "epoch": 1.5499606608969314,
+      "grad_norm": 0.6078285140713774,
+      "learning_rate": 1.4705421423493072e-06,
+      "loss": 0.1337,
+      "step": 1970
+    },
+    {
+      "epoch": 1.5578284815106216,
+      "grad_norm": 0.42265373164633213,
+      "learning_rate": 1.4222266327703832e-06,
+      "loss": 0.1255,
+      "step": 1980
+    },
+    {
+      "epoch": 1.5656963021243115,
+      "grad_norm": 0.4440614240765907,
+      "learning_rate": 1.3745862314393038e-06,
+      "loss": 0.1357,
+      "step": 1990
+    },
+    {
+      "epoch": 1.5735641227380017,
+      "grad_norm": 0.5207511516766303,
+      "learning_rate": 1.3276299278656268e-06,
+      "loss": 0.137,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5814319433516917,
+      "grad_norm": 0.60293701790219,
+      "learning_rate": 1.2813665824730203e-06,
+      "loss": 0.1342,
+      "step": 2010
+    },
+    {
+      "epoch": 1.5892997639653816,
+      "grad_norm": 0.6714679025435634,
+      "learning_rate": 1.2358049249273545e-06,
+      "loss": 0.1293,
+      "step": 2020
+    },
+    {
+      "epoch": 1.5971675845790716,
+      "grad_norm": 0.5174425886824507,
+      "learning_rate": 1.1909535524894489e-06,
+      "loss": 0.121,
+      "step": 2030
+    },
+    {
+      "epoch": 1.6050354051927616,
+      "grad_norm": 0.525806798449929,
+      "learning_rate": 1.146820928392815e-06,
+      "loss": 0.1327,
+      "step": 2040
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.4810141729264956,
+      "learning_rate": 1.103415380246687e-06,
+      "loss": 0.1281,
+      "step": 2050
+    },
+    {
+      "epoch": 1.6207710464201415,
+      "grad_norm": 0.6189531578831641,
+      "learning_rate": 1.0607450984646388e-06,
+      "loss": 0.1383,
+      "step": 2060
+    },
+    {
+      "epoch": 1.6286388670338316,
+      "grad_norm": 0.5468090384247127,
+      "learning_rate": 1.0188181347190956e-06,
+      "loss": 0.121,
+      "step": 2070
+    },
+    {
+      "epoch": 1.6365066876475216,
+      "grad_norm": 0.57669664344985,
+      "learning_rate": 9.77642400422028e-07,
+      "loss": 0.1156,
+      "step": 2080
+    },
+    {
+      "epoch": 1.6443745082612118,
+      "grad_norm": 0.5282425493362835,
+      "learning_rate": 9.372256652320949e-07,
+      "loss": 0.1355,
+      "step": 2090
+    },
+    {
+      "epoch": 1.6522423288749017,
+      "grad_norm": 0.463685296666126,
+      "learning_rate": 8.975755555885607e-07,
+      "loss": 0.1481,
+      "step": 2100
+    },
+    {
+      "epoch": 1.6601101494885917,
+      "grad_norm": 1.1693488862216819,
+      "learning_rate": 8.586995532722136e-07,
+      "loss": 0.1393,
+      "step": 2110
+    },
+    {
+      "epoch": 1.6679779701022817,
+      "grad_norm": 0.57198102250437,
+      "learning_rate": 8.206049939935962e-07,
+      "loss": 0.127,
+      "step": 2120
+    },
+    {
+      "epoch": 1.6758457907159716,
+      "grad_norm": 0.4863551065009116,
+      "learning_rate": 7.832990660087891e-07,
+      "loss": 0.1239,
+      "step": 2130
+    },
+    {
+      "epoch": 1.6837136113296616,
+      "grad_norm": 0.5400777045676572,
+      "learning_rate": 7.467888087630277e-07,
+      "loss": 0.1172,
+      "step": 2140
+    },
+    {
+      "epoch": 1.6915814319433515,
+      "grad_norm": 0.6424129555562107,
+      "learning_rate": 7.110811115623873e-07,
+      "loss": 0.131,
+      "step": 2150
+    },
+    {
+      "epoch": 1.6994492525570417,
+      "grad_norm": 0.4808650149119365,
+      "learning_rate": 6.761827122738074e-07,
+      "loss": 0.1359,
+      "step": 2160
+    },
+    {
+      "epoch": 1.7073170731707317,
+      "grad_norm": 0.4767218770068453,
+      "learning_rate": 6.421001960536927e-07,
+      "loss": 0.1263,
+      "step": 2170
+    },
+    {
+      "epoch": 1.7151848937844218,
+      "grad_norm": 0.5073097981490484,
+      "learning_rate": 6.088399941053186e-07,
+      "loss": 0.1236,
+      "step": 2180
+    },
+    {
+      "epoch": 1.7230527143981118,
+      "grad_norm": 0.41921496361071725,
+      "learning_rate": 5.76408382465305e-07,
+      "loss": 0.1391,
+      "step": 2190
+    },
+    {
+      "epoch": 1.7309205350118018,
+      "grad_norm": 0.5174538297932276,
+      "learning_rate": 5.448114808193488e-07,
+      "loss": 0.1307,
+      "step": 2200
+    },
+    {
+      "epoch": 1.7387883556254917,
+      "grad_norm": 0.7727110967410461,
+      "learning_rate": 5.140552513474772e-07,
+      "loss": 0.1297,
+      "step": 2210
+    },
+    {
+      "epoch": 1.7466561762391817,
+      "grad_norm": 0.49643212374608686,
+      "learning_rate": 4.84145497599009e-07,
+      "loss": 0.1256,
+      "step": 2220
+    },
+    {
+      "epoch": 1.7545239968528716,
+      "grad_norm": 0.47383198940465104,
+      "learning_rate": 4.550878633974537e-07,
+      "loss": 0.1275,
+      "step": 2230
+    },
+    {
+      "epoch": 1.7623918174665618,
+      "grad_norm": 0.5357331210533799,
+      "learning_rate": 4.2688783177555316e-07,
+      "loss": 0.131,
+      "step": 2240
+    },
+    {
+      "epoch": 1.7702596380802518,
+      "grad_norm": 0.49541291081541705,
+      "learning_rate": 3.995507239406582e-07,
+      "loss": 0.1279,
+      "step": 2250
+    },
+    {
+      "epoch": 1.7781274586939417,
+      "grad_norm": 0.44191596384810716,
+      "learning_rate": 3.730816982706398e-07,
+      "loss": 0.1156,
+      "step": 2260
+    },
+    {
+      "epoch": 1.785995279307632,
+      "grad_norm": 0.5889442162320265,
+      "learning_rate": 3.4748574934053534e-07,
+      "loss": 0.1278,
+      "step": 2270
+    },
+    {
+      "epoch": 1.7938630999213219,
+      "grad_norm": 0.4412787511352524,
+      "learning_rate": 3.227677069800894e-07,
+      "loss": 0.122,
+      "step": 2280
+    },
+    {
+      "epoch": 1.8017309205350118,
+      "grad_norm": 0.6259317203816922,
+      "learning_rate": 2.9893223536239526e-07,
+      "loss": 0.1939,
+      "step": 2290
+    },
+    {
+      "epoch": 1.8095987411487018,
+      "grad_norm": 0.4611419202854108,
+      "learning_rate": 2.759838321237818e-07,
+      "loss": 0.1317,
+      "step": 2300
+    },
+    {
+      "epoch": 1.8174665617623917,
+      "grad_norm": 0.5602814162914154,
+      "learning_rate": 2.5392682751513963e-07,
+      "loss": 0.1278,
+      "step": 2310
+    },
+    {
+      "epoch": 1.8253343823760817,
+      "grad_norm": 0.6428622599939015,
+      "learning_rate": 2.3276538358481592e-07,
+      "loss": 0.1241,
+      "step": 2320
+    },
+    {
+      "epoch": 1.8332022029897719,
+      "grad_norm": 0.46686214544110266,
+      "learning_rate": 2.1250349339326072e-07,
+      "loss": 0.1248,
+      "step": 2330
+    },
+    {
+      "epoch": 1.8410700236034618,
+      "grad_norm": 0.642826928906882,
+      "learning_rate": 1.9314498025955642e-07,
+      "loss": 0.137,
+      "step": 2340
+    },
+    {
+      "epoch": 1.8489378442171518,
+      "grad_norm": 0.5833202536130688,
+      "learning_rate": 1.7469349703997497e-07,
+      "loss": 0.1275,
+      "step": 2350
+    },
+    {
+      "epoch": 1.856805664830842,
+      "grad_norm": 0.4974607077572211,
+      "learning_rate": 1.5715252543870073e-07,
+      "loss": 0.1165,
+      "step": 2360
+    },
+    {
+      "epoch": 1.864673485444532,
+      "grad_norm": 0.5614261821280646,
+      "learning_rate": 1.4052537535085341e-07,
+      "loss": 0.1251,
+      "step": 2370
+    },
+    {
+      "epoch": 1.8725413060582219,
+      "grad_norm": 0.5680238467512716,
+      "learning_rate": 1.2481518423792306e-07,
+      "loss": 0.1344,
+      "step": 2380
+    },
+    {
+      "epoch": 1.8804091266719118,
+      "grad_norm": 0.4038817938451329,
+      "learning_rate": 1.100249165357492e-07,
+      "loss": 0.1374,
+      "step": 2390
+    },
+    {
+      "epoch": 1.8882769472856018,
+      "grad_norm": 0.7584255656822545,
+      "learning_rate": 9.615736309514567e-08,
+      "loss": 0.1257,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2542,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1353006276673536.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f569ab85fffce1ee68c1fdd97fd83d7b0f1f21a272dc56caaca1c3d628f8652
+size 8056

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)