Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.3.19",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "pad_token_id": 128004,
+  "transformers_version": "4.52.2",
+  "use_cache": false
+}

global_step105/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d69210d6f4ab71976932ddb337bbd9691ef03115fd9a5ca4c2cb9265a43e8a
+size 32121053258

global_step105/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f75ccebffa8a29d748a9db46c30d6c8669244e8da037723408b1d4c20ebfbd
+size 32121053258

global_step105/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556addd31067581684e513025a6ab887241798a33747d6f0ca53ea741fe55260
+size 32121053258

global_step105/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42ddce0bafa86bc697581b6d78f090858947b3732b2c05f24917714a13fca1b
+size 147237

global_step105/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c91ef83fd5a907a84966be9ccf7073ff98afc5eb3053ed40d5dcb2808a625cf
+size 147237

global_step105/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b47f19b774d1628ce2dc89fc5e1d613a9b0a9f99242c0d4e155c70e035922d
+size 147237

latest

@@ -0,0 +1 @@
+global_step105

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d6841c744ba17b3500cd73ba2f33ac5c202a7d57d7137c517775e685ab309c
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed75cb193c10a3bafe44e9b3129217ef3ac30fdd291eb605dffe53a8776c8bd6
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc450529e1b5731d97aecf989074a679fc729e35649e7a0b2c5f4fa2ce23d07
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d6bedb2f944fc599af141ca624a4cf5e1e4e2aba595f53656132d452718480
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d701d97a5c34ac763d3fc30134b192556235d4dda0e7c18884522e97a65de9
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5a47b9c2b510c4f3d9643a4288a90ef1061f18c150b864436a68f3972a73cf
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac77f356bc1dcf08116044cec78bc0e7d8ef7a7e1f84049735b65918be37e830
+size 14960

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b13c9cab4d6d47492f390a1a4c760fb9d79c0b6a8b48019ed2338865b96133d
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2066 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1983 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7,
+  "eval_steps": 15,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_Per_token_kl_mean": 0.028602013221153848,
+      "eval_average_num_turns": 34.35897435897436,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completion_length": 2341.974421574519,
+      "eval_loss": 0.26710209250450134,
+      "eval_reward": 1.435897456911894,
+      "eval_reward_std": 2.163183496548579,
+      "eval_rewards/format_error_penalty": -0.06837606888550979,
+      "eval_rewards/task_completion_reward": 0.41025641904427457,
+      "eval_runtime": 2865.8873,
+      "eval_samples_per_second": 0.04,
+      "eval_steps_per_second": 0.005,
+      "step": 0
+    },
+    {
+      "Per_token_kl_mean": 0.030059814453125,
+      "Unclipped Grad Norm": 2.5555081367492676,
+      "average_num_turns": 30.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2132.5833740234375,
+      "complexity_score": 6.0,
+      "epoch": 0.006666666666666667,
+      "learning_rate": 0.0,
+      "loss": 0.0005,
+      "num_customer_asks": 2.0,
+      "reward": 1.722222238779068,
+      "reward_std": 1.5796964764595032,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.4722222313284874,
+      "step": 1
+    },
+    {
+      "Per_token_kl_mean": 0.030059814453125,
+      "Unclipped Grad Norm": 2.5553574562072754,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.013333333333333334,
+      "learning_rate": 3.3333333333333334e-08,
+      "loss": 0.0005,
+      "step": 2
+    },
+    {
+      "Per_token_kl_mean": 0.02203369140625,
+      "Unclipped Grad Norm": 2.6852898597717285,
+      "average_num_turns": 28.166666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1803.0000305175781,
+      "complexity_score": 6.0,
+      "epoch": 0.02,
+      "learning_rate": 6.666666666666667e-08,
+      "loss": 0.095,
+      "num_customer_asks": 2.0,
+      "reward": 3.055555582046509,
+      "reward_std": 1.5523057281970978,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.8055555671453476,
+      "step": 3
+    },
+    {
+      "Per_token_kl_mean": 0.022064208984375,
+      "Unclipped Grad Norm": 2.5881826877593994,
+      "clip_ratio/high_max": 0.002588869712781161,
+      "clip_ratio/high_mean": 0.0017693563713692129,
+      "clip_ratio/low_mean": 0.00048547789629083127,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0022548342822119594,
+      "epoch": 0.02666666666666667,
+      "learning_rate": 1e-07,
+      "loss": 0.0957,
+      "step": 4
+    },
+    {
+      "Per_token_kl_mean": 0.03814697265625,
+      "Unclipped Grad Norm": 2.3860931396484375,
+      "average_num_turns": 32.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2203.5833435058594,
+      "complexity_score": 6.0,
+      "epoch": 0.03333333333333333,
+      "learning_rate": 1.3333333333333334e-07,
+      "loss": -0.1129,
+      "num_customer_asks": 2.75,
+      "reward": 0.5555555336177349,
+      "reward_std": 1.7567797005176544,
+      "rewards/format_error_penalty": -0.1111111119389534,
+      "rewards/task_completion_reward": 0.2222222276031971,
+      "step": 5
+    },
+    {
+      "Per_token_kl_mean": 0.038330078125,
+      "Unclipped Grad Norm": 2.332904577255249,
+      "clip_ratio/high_max": 0.0035354613210074604,
+      "clip_ratio/high_mean": 0.002562987479905132,
+      "clip_ratio/low_mean": 0.0006413227893062867,
+      "clip_ratio/low_min": 0.0002706883242353797,
+      "clip_ratio/region_mean": 0.0032043102546595037,
+      "epoch": 0.04,
+      "learning_rate": 1.6666666666666665e-07,
+      "loss": -0.113,
+      "step": 6
+    },
+    {
+      "Per_token_kl_mean": 0.0321044921875,
+      "Unclipped Grad Norm": 7.160241603851318,
+      "average_num_turns": 32.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2051.166717529297,
+      "complexity_score": 6.0,
+      "epoch": 0.04666666666666667,
+      "learning_rate": 2e-07,
+      "loss": -0.2645,
+      "num_customer_asks": 3.0,
+      "reward": 1.750000037252903,
+      "reward_std": 1.7073046267032623,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.5000000074505806,
+      "step": 7
+    },
+    {
+      "Per_token_kl_mean": 0.0323486328125,
+      "Unclipped Grad Norm": 7.028786659240723,
+      "clip_ratio/high_max": 0.0038157374947331846,
+      "clip_ratio/high_mean": 0.0027122838655486703,
+      "clip_ratio/low_mean": 0.0004040636194986291,
+      "clip_ratio/low_min": 5.172770397621207e-05,
+      "clip_ratio/region_mean": 0.003116347477771342,
+      "epoch": 0.05333333333333334,
+      "learning_rate": 2.3333333333333333e-07,
+      "loss": -0.2645,
+      "step": 8
+    },
+    {
+      "Per_token_kl_mean": 0.0271148681640625,
+      "Unclipped Grad Norm": 6.270898342132568,
+      "average_num_turns": 30.166666666666668,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2023.0000610351562,
+      "complexity_score": 6.0,
+      "epoch": 0.06,
+      "learning_rate": 2.6666666666666667e-07,
+      "loss": -0.2929,
+      "num_customer_asks": 3.0,
+      "reward": 1.2500000149011612,
+      "reward_std": 2.177278846502304,
+      "rewards/format_error_penalty": -0.13888888992369175,
+      "rewards/task_completion_reward": 0.4166666716337204,
+      "step": 9
+    },
+    {
+      "Per_token_kl_mean": 0.02618408203125,
+      "Unclipped Grad Norm": 6.559571266174316,
+      "clip_ratio/high_max": 0.003160445368848741,
+      "clip_ratio/high_mean": 0.002441313030431047,
+      "clip_ratio/low_mean": 0.000625347585810232,
+      "clip_ratio/low_min": 0.00015612477727700025,
+      "clip_ratio/region_mean": 0.0030666604870930314,
+      "epoch": 0.06666666666666667,
+      "learning_rate": 3e-07,
+      "loss": -0.2931,
+      "step": 10
+    },
+    {
+      "Per_token_kl_mean": 0.0250396728515625,
+      "Unclipped Grad Norm": 2.1664702892303467,
+      "average_num_turns": 37.833333333333336,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2626.2500915527344,
+      "complexity_score": 6.0,
+      "epoch": 0.07333333333333333,
+      "learning_rate": 3.333333333333333e-07,
+      "loss": 0.0553,
+      "num_customer_asks": 3.0,
+      "reward": 1.55555559694767,
+      "reward_std": 1.440958559513092,
+      "rewards/format_error_penalty": 0.0,
+      "rewards/task_completion_reward": 0.3888888992369175,
+      "step": 11
+    },
+    {
+      "Per_token_kl_mean": 0.025238037109375,
+      "Unclipped Grad Norm": 2.2072267532348633,
+      "clip_ratio/high_max": 0.0019618187216110528,
+      "clip_ratio/high_mean": 0.0012091500830138102,
+      "clip_ratio/low_mean": 0.0008225331694120541,
+      "clip_ratio/low_min": 0.000321938656270504,
+      "clip_ratio/region_mean": 0.002031683281529695,
+      "epoch": 0.08,
+      "learning_rate": 3.666666666666666e-07,
+      "loss": 0.0557,
+      "step": 12
+    },
+    {
+      "Per_token_kl_mean": 0.0301513671875,
+      "Unclipped Grad Norm": 2.987588882446289,
+      "average_num_turns": 29.666666666666668,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1992.4166870117188,
+      "complexity_score": 6.0,
+      "epoch": 0.08666666666666667,
+      "learning_rate": 4e-07,
+      "loss": -0.0646,
+      "num_customer_asks": 3.0,
+      "reward": 1.4722222164273262,
+      "reward_std": 0.9841874539852142,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.38888888992369175,
+      "step": 13
+    },
+    {
+      "Per_token_kl_mean": 0.0303955078125,
+      "Unclipped Grad Norm": 2.9625842571258545,
+      "clip_ratio/high_max": 0.0011975533270742744,
+      "clip_ratio/high_mean": 0.0007141664100345224,
+      "clip_ratio/low_mean": 0.0008382906962651759,
+      "clip_ratio/low_min": 0.0006468697683885694,
+      "clip_ratio/region_mean": 0.0015524571645073593,
+      "epoch": 0.09333333333333334,
+      "learning_rate": 4.3333333333333335e-07,
+      "loss": -0.0652,
+      "step": 14
+    },
+    {
+      "Per_token_kl_mean": 0.034576416015625,
+      "Unclipped Grad Norm": 2.2712526321411133,
+      "average_num_turns": 28.333333333333332,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1760.9166870117188,
+      "complexity_score": 6.0,
+      "epoch": 0.1,
+      "learning_rate": 4.6666666666666666e-07,
+      "loss": 0.0936,
+      "num_customer_asks": 3.0,
+      "reward": 2.111111134290695,
+      "reward_std": 1.0270463228225708,
+      "rewards/format_error_penalty": 0.0,
+      "rewards/task_completion_reward": 0.5277777835726738,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "eval_Per_token_kl_mean": 0.025357759915865384,
+      "eval_average_num_turns": 34.35897435897436,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completion_length": 2353.794940655048,
+      "eval_loss": 0.24709098041057587,
+      "eval_reward": 1.52991456251878,
+      "eval_reward_std": 2.1771165499320397,
+      "eval_rewards/format_error_penalty": -0.05982906027482106,
+      "eval_rewards/task_completion_reward": 0.4273504397043815,
+      "eval_runtime": 2733.9302,
+      "eval_samples_per_second": 0.042,
+      "eval_steps_per_second": 0.005,
+      "step": 15
+    },
+    {
+      "Per_token_kl_mean": 0.033294677734375,
+      "Unclipped Grad Norm": 2.322817087173462,
+      "clip_ratio/high_max": 0.0018439284758642316,
+      "clip_ratio/high_mean": 0.0013078018673695624,
+      "clip_ratio/low_mean": 0.0004917525366181508,
+      "clip_ratio/low_min": 0.00031898114684736356,
+      "clip_ratio/region_mean": 0.001799554389435798,
+      "epoch": 0.10666666666666667,
+      "learning_rate": 5e-07,
+      "loss": 0.0935,
+      "step": 16
+    },
+    {
+      "Per_token_kl_mean": 0.0430755615234375,
+      "Unclipped Grad Norm": 2.7783238887786865,
+      "average_num_turns": 29.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1972.75,
+      "complexity_score": 6.0,
+      "epoch": 0.11333333333333333,
+      "learning_rate": 5.333333333333333e-07,
+      "loss": -0.0118,
+      "num_customer_asks": 3.0,
+      "reward": 2.3611111491918564,
+      "reward_std": 1.602652668952942,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.6111111156642437,
+      "step": 17
+    },
+    {
+      "Per_token_kl_mean": 0.044036865234375,
+      "Unclipped Grad Norm": 2.7810113430023193,
+      "clip_ratio/high_max": 0.0028563252999447286,
+      "clip_ratio/high_mean": 0.0016192300245165825,
+      "clip_ratio/low_mean": 0.0007866146333981305,
+      "clip_ratio/low_min": 0.0002636234785313718,
+      "clip_ratio/region_mean": 0.0024058446288108826,
+      "epoch": 0.12,
+      "learning_rate": 5.666666666666666e-07,
+      "loss": -0.0121,
+      "step": 18
+    },
+    {
+      "Per_token_kl_mean": 0.025054931640625,
+      "Unclipped Grad Norm": 3.528660535812378,
+      "average_num_turns": 31.333333333333332,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2019.3333435058594,
+      "complexity_score": 6.0,
+      "epoch": 0.12666666666666668,
+      "learning_rate": 6e-07,
+      "loss": -0.0314,
+      "num_customer_asks": 3.0,
+      "reward": 1.805555559694767,
+      "reward_std": 1.4841874539852142,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.47222222574055195,
+      "step": 19
+    },
+    {
+      "Per_token_kl_mean": 0.0247650146484375,
+      "Unclipped Grad Norm": 3.4883873462677,
+      "clip_ratio/high_max": 0.0018595074361655861,
+      "clip_ratio/high_mean": 0.0010996465716743842,
+      "clip_ratio/low_mean": 0.0010979147627949715,
+      "clip_ratio/low_min": 0.0005871060129720718,
+      "clip_ratio/region_mean": 0.0021975613199174404,
+      "epoch": 0.13333333333333333,
+      "learning_rate": 6.333333333333332e-07,
+      "loss": -0.032,
+      "step": 20
+    },
+    {
+      "Per_token_kl_mean": 0.02117919921875,
+      "Unclipped Grad Norm": 2.8084309101104736,
+      "average_num_turns": 34.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1941.9166870117188,
+      "complexity_score": 6.0,
+      "epoch": 0.14,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": -0.0804,
+      "num_customer_asks": 4.25,
+      "reward": 1.7500000447034836,
+      "reward_std": 2.3562310338020325,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.5000000111758709,
+      "step": 21
+    },
+    {
+      "Per_token_kl_mean": 0.021484375,
+      "Unclipped Grad Norm": 2.7404944896698,
+      "clip_ratio/high_max": 0.003064427903154865,
+      "clip_ratio/high_mean": 0.0022258827375480905,
+      "clip_ratio/low_mean": 0.0012874454841949046,
+      "clip_ratio/low_min": 0.0005756000900873914,
+      "clip_ratio/region_mean": 0.0035133282653987408,
+      "epoch": 0.14666666666666667,
+      "learning_rate": 7e-07,
+      "loss": -0.0818,
+      "step": 22
+    },
+    {
+      "Per_token_kl_mean": 0.044525146484375,
+      "Unclipped Grad Norm": 3.3428354263305664,
+      "average_num_turns": 32.833333333333336,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2158.0000915527344,
+      "complexity_score": 7.0,
+      "epoch": 0.15333333333333332,
+      "learning_rate": 7.333333333333332e-07,
+      "loss": 0.147,
+      "num_customer_asks": 1.5,
+      "reward": 2.1388889253139496,
+      "reward_std": 1.9457058608531952,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.5555555671453476,
+      "step": 23
+    },
+    {
+      "Per_token_kl_mean": 0.0443267822265625,
+      "Unclipped Grad Norm": 3.2817952632904053,
+      "clip_ratio/high_max": 0.0036744638928212225,
+      "clip_ratio/high_mean": 0.002176330774091184,
+      "clip_ratio/low_mean": 0.0013749823083344381,
+      "clip_ratio/low_min": 0.00026823754888027906,
+      "clip_ratio/region_mean": 0.003551312955096364,
+      "epoch": 0.16,
+      "learning_rate": 7.666666666666667e-07,
+      "loss": 0.1461,
+      "step": 24
+    },
+    {
+      "Per_token_kl_mean": 0.040771484375,
+      "Unclipped Grad Norm": 1.6524800062179565,
+      "average_num_turns": 40.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 3175.0001220703125,
+      "complexity_score": 7.0,
+      "epoch": 0.16666666666666666,
+      "learning_rate": 8e-07,
+      "loss": -0.0746,
+      "num_customer_asks": 2.0,
+      "reward": -0.1666666641831398,
+      "reward_std": 1.4557189047336578,
+      "rewards/format_error_penalty": -0.16666666977107525,
+      "rewards/task_completion_reward": 0.0833333358168602,
+      "step": 25
+    },
+    {
+      "Per_token_kl_mean": 0.049560546875,
+      "Unclipped Grad Norm": 2.355365514755249,
+      "clip_ratio/high_max": 0.0034084554645232856,
+      "clip_ratio/high_mean": 0.0027010383491870016,
+      "clip_ratio/low_mean": 0.0010280147253070027,
+      "clip_ratio/low_min": 0.0003075030690524727,
+      "clip_ratio/region_mean": 0.003729053132701665,
+      "epoch": 0.17333333333333334,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": -0.0752,
+      "step": 26
+    },
+    {
+      "Per_token_kl_mean": 0.0283355712890625,
+      "Unclipped Grad Norm": 2.511045455932617,
+      "average_num_turns": 28.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1695.2500610351562,
+      "complexity_score": 7.0,
+      "epoch": 0.18,
+      "learning_rate": 8.666666666666667e-07,
+      "loss": -0.1449,
+      "num_customer_asks": 2.0,
+      "reward": 3.583333373069763,
+      "reward_std": 0.9679810702800751,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.9166666716337204,
+      "step": 27
+    },
+    {
+      "Per_token_kl_mean": 0.0290679931640625,
+      "Unclipped Grad Norm": 1.98232102394104,
+      "clip_ratio/high_max": 0.0042047875467687845,
+      "clip_ratio/high_mean": 0.003447328577749431,
+      "clip_ratio/low_mean": 0.00021598533930955455,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0036633139243349433,
+      "epoch": 0.18666666666666668,
+      "learning_rate": 9e-07,
+      "loss": -0.1466,
+      "step": 28
+    },
+    {
+      "Per_token_kl_mean": 0.0350799560546875,
+      "Unclipped Grad Norm": 2.7602415084838867,
+      "average_num_turns": 35.16666666666667,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2401.2500610351562,
+      "complexity_score": 7.0,
+      "epoch": 0.19333333333333333,
+      "learning_rate": 9.333333333333333e-07,
+      "loss": -0.1664,
+      "num_customer_asks": 2.0,
+      "reward": 0.9722222127020359,
+      "reward_std": 1.7836538553237915,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.3055555634200573,
+      "step": 29
+    },
+    {
+      "Per_token_kl_mean": 0.0365753173828125,
+      "Unclipped Grad Norm": 2.590303897857666,
+      "clip_ratio/high_max": 0.004933911259286106,
+      "clip_ratio/high_mean": 0.0028300698613747954,
+      "clip_ratio/low_mean": 0.0010839288734132424,
+      "clip_ratio/low_min": 0.0008930626790970564,
+      "clip_ratio/region_mean": 0.003913998720236123,
+      "epoch": 0.2,
+      "learning_rate": 9.666666666666666e-07,
+      "loss": -0.1688,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "eval_Per_token_kl_mean": 0.03177584134615385,
+      "eval_average_num_turns": 32.87179487179487,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completion_length": 2205.0769981971152,
+      "eval_loss": 0.2109963297843933,
+      "eval_reward": 1.2564102720755796,
+      "eval_reward_std": 2.1476430342747617,
+      "eval_rewards/format_error_penalty": -0.09401709529069754,
+      "eval_rewards/task_completion_reward": 0.3846153926390868,
+      "eval_runtime": 2674.1691,
+      "eval_samples_per_second": 0.043,
+      "eval_steps_per_second": 0.005,
+      "step": 30
+    },
+    {
+      "Per_token_kl_mean": 0.01141357421875,
+      "Unclipped Grad Norm": 1.8682786226272583,
+      "average_num_turns": 36.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2515.5000610351562,
+      "complexity_score": 7.0,
+      "epoch": 0.20666666666666667,
+      "learning_rate": 1e-06,
+      "loss": 0.0785,
+      "num_customer_asks": 2.0,
+      "reward": 1.4722222536802292,
+      "reward_std": 1.3588728606700897,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.3888888917863369,
+      "step": 31
+    },
+    {
+      "Per_token_kl_mean": 0.0116729736328125,
+      "Unclipped Grad Norm": 1.7776020765304565,
+      "clip_ratio/high_max": 0.003931889601517469,
+      "clip_ratio/high_mean": 0.002635647193528712,
+      "clip_ratio/low_mean": 0.001012774337141309,
+      "clip_ratio/low_min": 0.0003813192088273354,
+      "clip_ratio/region_mean": 0.0036484214942902327,
+      "epoch": 0.21333333333333335,
+      "learning_rate": 1e-06,
+      "loss": 0.077,
+      "step": 32
+    },
+    {
+      "Per_token_kl_mean": 0.0507965087890625,
+      "Unclipped Grad Norm": 2.096468687057495,
+      "average_num_turns": 27.666666666666668,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1520.7500305175781,
+      "complexity_score": 7.0,
+      "epoch": 0.22,
+      "learning_rate": 1e-06,
+      "loss": -0.0384,
+      "num_customer_asks": 2.0,
+      "reward": 2.6666666865348816,
+      "reward_std": 0.7742919027805328,
+      "rewards/format_error_penalty": 0.0,
+      "rewards/task_completion_reward": 0.6666666716337204,
+      "step": 33
+    },
+    {
+      "Per_token_kl_mean": 0.0504150390625,
+      "Unclipped Grad Norm": 1.9674818515777588,
+      "clip_ratio/high_max": 0.003622451680712402,
+      "clip_ratio/high_mean": 0.003039544215425849,
+      "clip_ratio/low_mean": 0.0006066844071028754,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0036462285788729787,
+      "epoch": 0.22666666666666666,
+      "learning_rate": 1e-06,
+      "loss": -0.0396,
+      "step": 34
+    },
+    {
+      "Per_token_kl_mean": 0.0401458740234375,
+      "Unclipped Grad Norm": 2.4924075603485107,
+      "average_num_turns": 30.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2005.5834045410156,
+      "complexity_score": 7.0,
+      "epoch": 0.23333333333333334,
+      "learning_rate": 1e-06,
+      "loss": -0.1498,
+      "num_customer_asks": 2.0,
+      "reward": 1.583333358168602,
+      "reward_std": 1.4166666865348816,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.41666667349636555,
+      "step": 35
+    },
+    {
+      "Per_token_kl_mean": 0.041046142578125,
+      "Unclipped Grad Norm": 2.228349447250366,
+      "clip_ratio/high_max": 0.005987928016111255,
+      "clip_ratio/high_mean": 0.004077079560374841,
+      "clip_ratio/low_mean": 0.0009926966158673167,
+      "clip_ratio/low_min": 0.0003007820341736078,
+      "clip_ratio/region_mean": 0.005069775914307684,
+      "epoch": 0.24,
+      "learning_rate": 1e-06,
+      "loss": -0.1525,
+      "step": 36
+    },
+    {
+      "Per_token_kl_mean": 0.0146331787109375,
+      "Unclipped Grad Norm": 2.172025203704834,
+      "average_num_turns": 29.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1905.5833740234375,
+      "complexity_score": 7.0,
+      "epoch": 0.24666666666666667,
+      "learning_rate": 1e-06,
+      "loss": 0.0857,
+      "num_customer_asks": 2.5,
+      "reward": 1.6666666865348816,
+      "reward_std": 1.143900990486145,
+      "rewards/format_error_penalty": -0.11111111380159855,
+      "rewards/task_completion_reward": 0.5000000018626451,
+      "step": 37
+    },
+    {
+      "Per_token_kl_mean": 0.0159149169921875,
+      "Unclipped Grad Norm": 1.9654333591461182,
+      "clip_ratio/high_max": 0.004182191623840481,
+      "clip_ratio/high_mean": 0.002845426555722952,
+      "clip_ratio/low_mean": 0.000675506453262642,
+      "clip_ratio/low_min": 0.00022825838823337108,
+      "clip_ratio/region_mean": 0.0035209329798817635,
+      "epoch": 0.25333333333333335,
+      "learning_rate": 1e-06,
+      "loss": 0.0833,
+      "step": 38
+    },
+    {
+      "Per_token_kl_mean": 0.032379150390625,
+      "Unclipped Grad Norm": 1.6024987697601318,
+      "average_num_turns": 32.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2024.2500610351562,
+      "complexity_score": 7.0,
+      "epoch": 0.26,
+      "learning_rate": 1e-06,
+      "loss": -0.0089,
+      "num_customer_asks": 3.0,
+      "reward": 1.7500000465661287,
+      "reward_std": 1.081826627254486,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.5000000018626451,
+      "step": 39
+    },
+    {
+      "Per_token_kl_mean": 0.03466796875,
+      "Unclipped Grad Norm": 1.5069187879562378,
+      "clip_ratio/high_max": 0.004447502666153014,
+      "clip_ratio/high_mean": 0.0026117509696632624,
+      "clip_ratio/low_mean": 0.0008172642919817008,
+      "clip_ratio/low_min": 0.0003601152275223285,
+      "clip_ratio/region_mean": 0.003429015283472836,
+      "epoch": 0.26666666666666666,
+      "learning_rate": 1e-06,
+      "loss": -0.0102,
+      "step": 40
+    },
+    {
+      "Per_token_kl_mean": 0.025054931640625,
+      "Unclipped Grad Norm": 2.84529185295105,
+      "average_num_turns": 28.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1698.6667175292969,
+      "complexity_score": 7.0,
+      "epoch": 0.2733333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.0268,
+      "num_customer_asks": 3.0,
+      "reward": 3.138888955116272,
+      "reward_std": 1.5513382852077484,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.8055555671453476,
+      "step": 41
+    },
+    {
+      "Per_token_kl_mean": 0.027740478515625,
+      "Unclipped Grad Norm": 2.721637487411499,
+      "clip_ratio/high_max": 0.005568365100771189,
+      "clip_ratio/high_mean": 0.0038201200077310205,
+      "clip_ratio/low_mean": 0.0012431106879375875,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.005063230404630303,
+      "epoch": 0.28,
+      "learning_rate": 1e-06,
+      "loss": -0.0303,
+      "step": 42
+    },
+    {
+      "Per_token_kl_mean": 0.0250244140625,
+      "Unclipped Grad Norm": 2.3850605487823486,
+      "average_num_turns": 33.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2232.3333740234375,
+      "complexity_score": 7.0,
+      "epoch": 0.2866666666666667,
+      "learning_rate": 1e-06,
+      "loss": 0.1268,
+      "num_customer_asks": 3.0,
+      "reward": 1.8055555745959282,
+      "reward_std": 1.4652505218982697,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.4722222276031971,
+      "step": 43
+    },
+    {
+      "Per_token_kl_mean": 0.088653564453125,
+      "Unclipped Grad Norm": 6.797647953033447,
+      "clip_ratio/high_max": 0.0052433834644034505,
+      "clip_ratio/high_mean": 0.0035476955818012357,
+      "clip_ratio/low_mean": 0.0017024853586917743,
+      "clip_ratio/low_min": 0.0002615366829559207,
+      "clip_ratio/region_mean": 0.0052501807222142816,
+      "epoch": 0.29333333333333333,
+      "learning_rate": 1e-06,
+      "loss": 0.1244,
+      "step": 44
+    },
+    {
+      "Per_token_kl_mean": 0.028900146484375,
+      "Unclipped Grad Norm": 2.410104751586914,
+      "average_num_turns": 28.666666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1883.5834045410156,
+      "complexity_score": 7.0,
+      "epoch": 0.3,
+      "learning_rate": 1e-06,
+      "loss": -0.081,
+      "num_customer_asks": 3.0,
+      "reward": 1.1666666641831398,
+      "reward_std": 1.4991175830364227,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.33333333767950535,
+      "step": 45
+    },
+    {
+      "epoch": 0.3,
+      "eval_Per_token_kl_mean": 0.04253680889423077,
+      "eval_average_num_turns": 32.46153846153846,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completion_length": 2098.512920673077,
+      "eval_loss": 0.19239191710948944,
+      "eval_reward": 1.6666667071672587,
+      "eval_reward_std": 1.7795228224534254,
+      "eval_rewards/format_error_penalty": -0.02564102583206617,
+      "eval_rewards/task_completion_reward": 0.4358974460225839,
+      "eval_runtime": 2230.4343,
+      "eval_samples_per_second": 0.052,
+      "eval_steps_per_second": 0.006,
+      "step": 45
+    },
+    {
+      "Per_token_kl_mean": 0.031219482421875,
+      "Unclipped Grad Norm": 2.1263623237609863,
+      "clip_ratio/high_max": 0.0040246553253382444,
+      "clip_ratio/high_mean": 0.002286915056174621,
+      "clip_ratio/low_mean": 0.0020354260341264307,
+      "clip_ratio/low_min": 0.0011469830642454326,
+      "clip_ratio/region_mean": 0.0043223409447818995,
+      "epoch": 0.30666666666666664,
+      "learning_rate": 1e-06,
+      "loss": -0.084,
+      "step": 46
+    },
+    {
+      "Per_token_kl_mean": 0.039947509765625,
+      "Unclipped Grad Norm": 1.3583661317825317,
+      "average_num_turns": 35.83333333333333,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2312.2501220703125,
+      "complexity_score": 7.0,
+      "epoch": 0.31333333333333335,
+      "learning_rate": 1e-06,
+      "loss": -0.0855,
+      "num_customer_asks": 3.0,
+      "reward": 0.6111111287027597,
+      "reward_std": 0.8333333358168602,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.19444444961845875,
+      "step": 47
+    },
+    {
+      "Per_token_kl_mean": 0.04205322265625,
+      "Unclipped Grad Norm": 1.2028133869171143,
+      "clip_ratio/high_max": 0.003269302542321384,
+      "clip_ratio/high_mean": 0.0027497120172483847,
+      "clip_ratio/low_mean": 0.0008293144674098585,
+      "clip_ratio/low_min": 0.0005048496241215616,
+      "clip_ratio/region_mean": 0.0035790265537798405,
+      "epoch": 0.32,
+      "learning_rate": 1e-06,
+      "loss": -0.0863,
+      "step": 48
+    },
+    {
+      "Per_token_kl_mean": 0.0615234375,
+      "Unclipped Grad Norm": 2.35026216506958,
+      "average_num_turns": 36.83333333333333,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2585.2500610351562,
+      "complexity_score": 7.0,
+      "epoch": 0.32666666666666666,
+      "learning_rate": 1e-06,
+      "loss": 0.055,
+      "num_customer_asks": 3.0,
+      "reward": 1.027777798473835,
+      "reward_std": 1.2770463228225708,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.2777777835726738,
+      "step": 49
+    },
+    {
+      "Per_token_kl_mean": 0.08062744140625,
+      "Unclipped Grad Norm": 2.707611560821533,
+      "clip_ratio/high_max": 0.0038470617728307843,
+      "clip_ratio/high_mean": 0.002755116031039506,
+      "clip_ratio/low_mean": 0.0011798873456427827,
+      "clip_ratio/low_min": 0.0003029486979357898,
+      "clip_ratio/region_mean": 0.003935003420338035,
+      "epoch": 0.3333333333333333,
+      "learning_rate": 1e-06,
+      "loss": 0.053,
+      "step": 50
+    },
+    {
+      "Per_token_kl_mean": 0.08648681640625,
+      "Unclipped Grad Norm": 1.89194917678833,
+      "average_num_turns": 37.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2428.2501220703125,
+      "complexity_score": 7.0,
+      "epoch": 0.34,
+      "learning_rate": 1e-06,
+      "loss": -0.0375,
+      "num_customer_asks": 3.0,
+      "reward": 1.6388889104127884,
+      "reward_std": 0.9140522480010986,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.4722222238779068,
+      "step": 51
+    },
+    {
+      "Per_token_kl_mean": 0.0887451171875,
+      "Unclipped Grad Norm": 1.7692519426345825,
+      "clip_ratio/high_max": 0.003831716370768845,
+      "clip_ratio/high_mean": 0.0030283391824923456,
+      "clip_ratio/low_mean": 0.0004408868044265546,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.003469225892331451,
+      "epoch": 0.3466666666666667,
+      "learning_rate": 1e-06,
+      "loss": -0.0385,
+      "step": 52
+    },
+    {
+      "Per_token_kl_mean": 0.07135009765625,
+      "Unclipped Grad Norm": 3.6761016845703125,
+      "average_num_turns": 35.666666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2346.916717529297,
+      "complexity_score": 7.0,
+      "epoch": 0.35333333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.0323,
+      "num_customer_asks": 3.25,
+      "reward": 1.416666679084301,
+      "reward_std": 1.9870441555976868,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.4166666753590107,
+      "step": 53
+    },
+    {
+      "Per_token_kl_mean": 0.08929443359375,
+      "Unclipped Grad Norm": 3.3974955081939697,
+      "clip_ratio/high_max": 0.005840508965775371,
+      "clip_ratio/high_mean": 0.003950563375838101,
+      "clip_ratio/low_mean": 0.0012561175899463706,
+      "clip_ratio/low_min": 0.00024885421589715406,
+      "clip_ratio/region_mean": 0.005206680856645107,
+      "epoch": 0.36,
+      "learning_rate": 1e-06,
+      "loss": -0.036,
+      "step": 54
+    },
+    {
+      "Per_token_kl_mean": 0.0625,
+      "Unclipped Grad Norm": 2.224308729171753,
+      "average_num_turns": 35.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2021.5834350585938,
+      "complexity_score": 7.0,
+      "epoch": 0.36666666666666664,
+      "learning_rate": 1e-06,
+      "loss": -0.0121,
+      "num_customer_asks": 4.0,
+      "reward": 2.833333358168602,
+      "reward_std": 1.6959705650806427,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.7500000074505806,
+      "step": 55
+    },
+    {
+      "Per_token_kl_mean": 0.06463623046875,
+      "Unclipped Grad Norm": 1.968030571937561,
+      "clip_ratio/high_max": 0.006955544929951429,
+      "clip_ratio/high_mean": 0.004576037579681724,
+      "clip_ratio/low_mean": 0.0009624737140256912,
+      "clip_ratio/low_min": 0.0003805175074376166,
+      "clip_ratio/region_mean": 0.005538511089980602,
+      "epoch": 0.37333333333333335,
+      "learning_rate": 1e-06,
+      "loss": -0.0152,
+      "step": 56
+    },
+    {
+      "Per_token_kl_mean": 0.07952880859375,
+      "Unclipped Grad Norm": 2.43376088142395,
+      "average_num_turns": 36.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2339.0834045410156,
+      "complexity_score": 7.0,
+      "epoch": 0.38,
+      "learning_rate": 1e-06,
+      "loss": -0.0063,
+      "num_customer_asks": 4.0,
+      "reward": 0.8611111491918564,
+      "reward_std": 1.8430048823356628,
+      "rewards/format_error_penalty": -0.0833333358168602,
+      "rewards/task_completion_reward": 0.2777777872979641,
+      "step": 57
+    },
+    {
+      "Per_token_kl_mean": 0.07452392578125,
+      "Unclipped Grad Norm": 2.115501880645752,
+      "clip_ratio/high_max": 0.006117001874372363,
+      "clip_ratio/high_mean": 0.0034212094615213573,
+      "clip_ratio/low_mean": 0.001921181712532416,
+      "clip_ratio/low_min": 0.0009523867629468441,
+      "clip_ratio/region_mean": 0.00534239097032696,
+      "epoch": 0.38666666666666666,
+      "learning_rate": 1e-06,
+      "loss": -0.0096,
+      "step": 58
+    },
+    {
+      "Per_token_kl_mean": 0.1324462890625,
+      "Unclipped Grad Norm": 2.6459884643554688,
+      "average_num_turns": 34.166666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1979.1667175292969,
+      "complexity_score": 7.75,
+      "epoch": 0.3933333333333333,
+      "learning_rate": 1e-06,
+      "loss": 0.0642,
+      "num_customer_asks": 1.75,
+      "reward": 2.444444462656975,
+      "reward_std": 1.6346715986728668,
+      "rewards/format_error_penalty": 0.0,
+      "rewards/task_completion_reward": 0.6111111156642437,
+      "step": 59
+    },
+    {
+      "Per_token_kl_mean": 0.0872802734375,
+      "Unclipped Grad Norm": 2.2109076976776123,
+      "clip_ratio/high_max": 0.005360481911338866,
+      "clip_ratio/high_mean": 0.0037416539853438735,
+      "clip_ratio/low_mean": 0.0017667427600827068,
+      "clip_ratio/low_min": 0.0005991098587401211,
+      "clip_ratio/region_mean": 0.005508396774530411,
+      "epoch": 0.4,
+      "learning_rate": 1e-06,
+      "loss": 0.0606,
+      "step": 60
+    },
+    {
+      "epoch": 0.4,
+      "eval_Per_token_kl_mean": 0.01824951171875,
+      "eval_average_num_turns": 34.30769230769231,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completion_length": 2164.897479717548,
+      "eval_loss": 0.24680586159229279,
+      "eval_reward": 1.4017094236153822,
+      "eval_reward_std": 2.2400029714290914,
+      "eval_rewards/format_error_penalty": -0.06837606888550979,
+      "eval_rewards/task_completion_reward": 0.4017094121529506,
+      "eval_runtime": 2425.5,
+      "eval_samples_per_second": 0.047,
+      "eval_steps_per_second": 0.005,
+      "step": 60
+    },
+    {
+      "Per_token_kl_mean": 0.0643310546875,
+      "Unclipped Grad Norm": 1.5676761865615845,
+      "average_num_turns": 32.833333333333336,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1933.7500610351562,
+      "complexity_score": 8.0,
+      "epoch": 0.4066666666666667,
+      "learning_rate": 1e-06,
+      "loss": -0.0075,
+      "num_customer_asks": 1.5,
+      "reward": 2.5833333283662796,
+      "reward_std": 0.9268712103366852,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.6666666679084301,
+      "step": 61
+    },
+    {
+      "Per_token_kl_mean": 0.063873291015625,
+      "Unclipped Grad Norm": 1.457779884338379,
+      "clip_ratio/high_max": 0.0012671419535763562,
+      "clip_ratio/high_mean": 0.0008937974635045975,
+      "clip_ratio/low_mean": 0.0012637204490602016,
+      "clip_ratio/low_min": 0.0009391065395902842,
+      "clip_ratio/region_mean": 0.0021575178834609687,
+      "epoch": 0.41333333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.009,
+      "step": 62
+    },
+    {
+      "Per_token_kl_mean": 0.0184478759765625,
+      "Unclipped Grad Norm": 2.0028326511383057,
+      "average_num_turns": 37.666666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2159.916717529297,
+      "complexity_score": 8.0,
+      "epoch": 0.42,
+      "learning_rate": 1e-06,
+      "loss": 0.0224,
+      "num_customer_asks": 2.0,
+      "reward": 0.805555559694767,
+      "reward_std": 1.3040926456451416,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.2222222238779068,
+      "step": 63
+    },
+    {
+      "Per_token_kl_mean": 0.0194854736328125,
+      "Unclipped Grad Norm": 1.8710606098175049,
+      "clip_ratio/high_max": 0.00407925492618233,
+      "clip_ratio/high_mean": 0.0025825222255662084,
+      "clip_ratio/low_mean": 0.0014541190466843545,
+      "clip_ratio/low_min": 0.0005381604423746467,
+      "clip_ratio/region_mean": 0.004036641330458224,
+      "epoch": 0.4266666666666667,
+      "learning_rate": 1e-06,
+      "loss": 0.0196,
+      "step": 64
+    },
+    {
+      "Per_token_kl_mean": 0.081573486328125,
+      "Unclipped Grad Norm": 2.2034525871276855,
+      "average_num_turns": 37.833333333333336,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2969.000030517578,
+      "complexity_score": 8.0,
+      "epoch": 0.43333333333333335,
+      "learning_rate": 1e-06,
+      "loss": 0.0195,
+      "num_customer_asks": 2.0,
+      "reward": 0.4999999776482582,
+      "reward_std": 0.9114378094673157,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.1666666716337204,
+      "step": 65
+    },
+    {
+      "Per_token_kl_mean": 0.083404541015625,
+      "Unclipped Grad Norm": 1.9130369424819946,
+      "clip_ratio/high_max": 0.0030444926815107465,
+      "clip_ratio/high_mean": 0.0020603954326361418,
+      "clip_ratio/low_mean": 0.0010586934513412416,
+      "clip_ratio/low_min": 0.0005784977111034095,
+      "clip_ratio/region_mean": 0.0031190887093544006,
+      "epoch": 0.44,
+      "learning_rate": 1e-06,
+      "loss": 0.0165,
+      "step": 66
+    },
+    {
+      "Per_token_kl_mean": 0.0191650390625,
+      "Unclipped Grad Norm": 2.2776553630828857,
+      "average_num_turns": 34.166666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2417.7500610351562,
+      "complexity_score": 8.0,
+      "epoch": 0.44666666666666666,
+      "learning_rate": 1e-06,
+      "loss": -0.0766,
+      "num_customer_asks": 2.75,
+      "reward": 0.5833333376795053,
+      "reward_std": 1.3013382256031036,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.1666666679084301,
+      "step": 67
+    },
+    {
+      "Per_token_kl_mean": 0.0244140625,
+      "Unclipped Grad Norm": 2.078873872756958,
+      "clip_ratio/high_max": 0.004014529753476381,
+      "clip_ratio/high_mean": 0.0018268455751240253,
+      "clip_ratio/low_mean": 0.0033395609352737665,
+      "clip_ratio/low_min": 0.0017342398641631007,
+      "clip_ratio/region_mean": 0.005166406626813114,
+      "epoch": 0.4533333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.08,
+      "step": 68
+    },
+    {
+      "Per_token_kl_mean": 0.025482177734375,
+      "Unclipped Grad Norm": 1.9708870649337769,
+      "average_num_turns": 38.166666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2564.333465576172,
+      "complexity_score": 8.0,
+      "epoch": 0.46,
+      "learning_rate": 1e-06,
+      "loss": -0.0782,
+      "num_customer_asks": 3.0,
+      "reward": 0.5277777761220932,
+      "reward_std": 1.470137745141983,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.1944444477558136,
+      "step": 69
+    },
+    {
+      "Per_token_kl_mean": 0.028045654296875,
+      "Unclipped Grad Norm": 1.821679711341858,
+      "clip_ratio/high_max": 0.0037925440701656044,
+      "clip_ratio/high_mean": 0.002444355108309537,
+      "clip_ratio/low_mean": 0.001842683384893462,
+      "clip_ratio/low_min": 0.0008508413011441007,
+      "clip_ratio/region_mean": 0.004287038464099169,
+      "epoch": 0.4666666666666667,
+      "learning_rate": 1e-06,
+      "loss": -0.0817,
+      "step": 70
+    },
+    {
+      "Per_token_kl_mean": 0.037200927734375,
+      "Unclipped Grad Norm": 3.7169013023376465,
+      "average_num_turns": 29.666666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1839.8333740234375,
+      "complexity_score": 8.0,
+      "epoch": 0.47333333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.1533,
+      "num_customer_asks": 3.0,
+      "reward": 1.3888889122754335,
+      "reward_std": 1.4409586191177368,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.38888889737427235,
+      "step": 71
+    },
+    {
+      "Per_token_kl_mean": 0.038604736328125,
+      "Unclipped Grad Norm": 3.5108487606048584,
+      "clip_ratio/high_max": 0.004673434421420097,
+      "clip_ratio/high_mean": 0.0030114339606370777,
+      "clip_ratio/low_mean": 0.0015908468194538727,
+      "clip_ratio/low_min": 0.0009505753114353865,
+      "clip_ratio/region_mean": 0.004602280852850527,
+      "epoch": 0.48,
+      "learning_rate": 1e-06,
+      "loss": -0.1565,
+      "step": 72
+    },
+    {
+      "Per_token_kl_mean": 0.042572021484375,
+      "Unclipped Grad Norm": 2.4610419273376465,
+      "average_num_turns": 41.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2755.166778564453,
+      "complexity_score": 8.0,
+      "epoch": 0.4866666666666667,
+      "learning_rate": 1e-06,
+      "loss": -0.1163,
+      "num_customer_asks": 3.0,
+      "reward": 0.5277777928858995,
+      "reward_std": 1.4409585893154144,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.19444444961845875,
+      "step": 73
+    },
+    {
+      "Per_token_kl_mean": 0.043304443359375,
+      "Unclipped Grad Norm": 2.216001272201538,
+      "clip_ratio/high_max": 0.006888842326588929,
+      "clip_ratio/high_mean": 0.004849603254115209,
+      "clip_ratio/low_mean": 0.0012642452893487643,
+      "clip_ratio/low_min": 0.0004576289502438158,
+      "clip_ratio/region_mean": 0.0061138488235883415,
+      "epoch": 0.49333333333333335,
+      "learning_rate": 1e-06,
+      "loss": -0.1197,
+      "step": 74
+    },
+    {
+      "Per_token_kl_mean": 0.11602783203125,
+      "Unclipped Grad Norm": 3.582536220550537,
+      "average_num_turns": 43.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2681.2500610351562,
+      "complexity_score": 8.0,
+      "epoch": 0.5,
+      "learning_rate": 1e-06,
+      "loss": 0.0475,
+      "num_customer_asks": 3.0,
+      "reward": 0.6666666809469461,
+      "reward_std": 1.5902504920959473,
+      "rewards/format_error_penalty": -0.11111111380159855,
+      "rewards/task_completion_reward": 0.2500000037252903,
+      "step": 75
+    },
+    {
+      "epoch": 0.5,
+      "eval_Per_token_kl_mean": 0.06984299879807693,
+      "eval_average_num_turns": 32.76923076923077,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completion_length": 2144.718008188101,
+      "eval_loss": 0.1265711635351181,
+      "eval_reward": 1.7094017565250397,
+      "eval_reward_std": 2.0491558405069203,
+      "eval_rewards/format_error_penalty": -0.034188034442754894,
+      "eval_rewards/task_completion_reward": 0.45299146553644765,
+      "eval_runtime": 2322.0067,
+      "eval_samples_per_second": 0.05,
+      "eval_steps_per_second": 0.006,
+      "step": 75
+    },
+    {
+      "Per_token_kl_mean": 0.116912841796875,
+      "Unclipped Grad Norm": 3.497389316558838,
+      "clip_ratio/high_max": 0.005047270969953388,
+      "clip_ratio/high_mean": 0.0033578600850887597,
+      "clip_ratio/low_mean": 0.0015582542400807142,
+      "clip_ratio/low_min": 0.0007833734707674012,
+      "clip_ratio/region_mean": 0.004916114499792457,
+      "epoch": 0.5066666666666667,
+      "learning_rate": 1e-06,
+      "loss": 0.0451,
+      "step": 76
+    },
+    {
+      "Per_token_kl_mean": 0.043426513671875,
+      "Unclipped Grad Norm": 2.5462687015533447,
+      "average_num_turns": 35.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2257.0833740234375,
+      "complexity_score": 8.0,
+      "epoch": 0.5133333333333333,
+      "learning_rate": 1e-06,
+      "loss": 0.0176,
+      "num_customer_asks": 3.0,
+      "reward": 1.4722222462296486,
+      "reward_std": 1.8866644501686096,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.38888889737427235,
+      "step": 77
+    },
+    {
+      "Per_token_kl_mean": 0.046600341796875,
+      "Unclipped Grad Norm": 2.1783344745635986,
+      "clip_ratio/high_max": 0.004500846145674586,
+      "clip_ratio/high_mean": 0.0022655446809949353,
+      "clip_ratio/low_mean": 0.003629689570516348,
+      "clip_ratio/low_min": 0.0012793659989256412,
+      "clip_ratio/region_mean": 0.005895234295167029,
+      "epoch": 0.52,
+      "learning_rate": 1e-06,
+      "loss": 0.0132,
+      "step": 78
+    },
+    {
+      "Per_token_kl_mean": 0.0655517578125,
+      "Unclipped Grad Norm": 1.7014760971069336,
+      "average_num_turns": 39.166666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2544.666717529297,
+      "complexity_score": 8.0,
+      "epoch": 0.5266666666666666,
+      "learning_rate": 1e-06,
+      "loss": -0.0597,
+      "num_customer_asks": 3.0,
+      "reward": 0.1666666641831398,
+      "reward_std": 1.1050108075141907,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.08333333395421505,
+      "step": 79
+    },
+    {
+      "Per_token_kl_mean": 0.05706787109375,
+      "Unclipped Grad Norm": 1.7074480056762695,
+      "clip_ratio/high_max": 0.003349923819769174,
+      "clip_ratio/high_mean": 0.0018370240868534893,
+      "clip_ratio/low_mean": 0.001971315490663983,
+      "clip_ratio/low_min": 0.0014147880137898028,
+      "clip_ratio/region_mean": 0.0038083393592387438,
+      "epoch": 0.5333333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.0614,
+      "step": 80
+    },
+    {
+      "Per_token_kl_mean": 0.0863037109375,
+      "Unclipped Grad Norm": 2.5198090076446533,
+      "average_num_turns": 36.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2527.5834045410156,
+      "complexity_score": 8.0,
+      "epoch": 0.54,
+      "learning_rate": 1e-06,
+      "loss": -0.0381,
+      "num_customer_asks": 3.75,
+      "reward": 0.8055555671453476,
+      "reward_std": 1.6103796660900116,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.22222222574055195,
+      "step": 81
+    },
+    {
+      "Per_token_kl_mean": 0.089111328125,
+      "Unclipped Grad Norm": 4.5249457359313965,
+      "clip_ratio/high_max": 0.004900677595287561,
+      "clip_ratio/high_mean": 0.0032557058293605223,
+      "clip_ratio/low_mean": 0.0038194154913071543,
+      "clip_ratio/low_min": 0.0025489990948699415,
+      "clip_ratio/region_mean": 0.007075121160596609,
+      "epoch": 0.5466666666666666,
+      "learning_rate": 1e-06,
+      "loss": -0.0421,
+      "step": 82
+    },
+    {
+      "Per_token_kl_mean": 0.06439208984375,
+      "Unclipped Grad Norm": 2.3263447284698486,
+      "average_num_turns": 40.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2643.166748046875,
+      "complexity_score": 8.0,
+      "epoch": 0.5533333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.0735,
+      "num_customer_asks": 4.0,
+      "reward": 0.5000000018626451,
+      "reward_std": 1.5513382256031036,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.1666666679084301,
+      "step": 83
+    },
+    {
+      "Per_token_kl_mean": 0.06109619140625,
+      "Unclipped Grad Norm": 1.9366487264633179,
+      "clip_ratio/high_max": 0.005435149068944156,
+      "clip_ratio/high_mean": 0.0032434985623694956,
+      "clip_ratio/low_mean": 0.0024295587791129947,
+      "clip_ratio/low_min": 0.0016576671041548252,
+      "clip_ratio/region_mean": 0.005673057283274829,
+      "epoch": 0.56,
+      "learning_rate": 1e-06,
+      "loss": -0.0769,
+      "step": 84
+    },
+    {
+      "Per_token_kl_mean": 0.08013916015625,
+      "Unclipped Grad Norm": 1.7171117067337036,
+      "average_num_turns": 38.833333333333336,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2399.9168090820312,
+      "complexity_score": 8.0,
+      "epoch": 0.5666666666666667,
+      "learning_rate": 1e-06,
+      "loss": -0.0926,
+      "num_customer_asks": 4.0,
+      "reward": 1.8055555820465088,
+      "reward_std": 0.5833333730697632,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.4722222238779068,
+      "step": 85
+    },
+    {
+      "Per_token_kl_mean": 0.07293701171875,
+      "Unclipped Grad Norm": 1.0893405675888062,
+      "clip_ratio/high_max": 0.004440258257091045,
+      "clip_ratio/high_mean": 0.004142843186855316,
+      "clip_ratio/low_mean": 6.518055306514725e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00420802365988493,
+      "epoch": 0.5733333333333334,
+      "learning_rate": 1e-06,
+      "loss": -0.094,
+      "step": 86
+    },
+    {
+      "Per_token_kl_mean": 0.08697509765625,
+      "Unclipped Grad Norm": 2.7211594581604004,
+      "average_num_turns": 35.666666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 1960.0834350585938,
+      "complexity_score": 8.0,
+      "epoch": 0.58,
+      "learning_rate": 1e-06,
+      "loss": -0.11,
+      "num_customer_asks": 4.0,
+      "reward": 1.055555559694767,
+      "reward_std": 1.837636023759842,
+      "rewards/format_error_penalty": -0.16666666977107525,
+      "rewards/task_completion_reward": 0.3888888955116272,
+      "step": 87
+    },
+    {
+      "Per_token_kl_mean": 0.08966064453125,
+      "Unclipped Grad Norm": 2.437295436859131,
+      "clip_ratio/high_max": 0.010313277831301093,
+      "clip_ratio/high_mean": 0.0076583754271268845,
+      "clip_ratio/low_mean": 0.0014018206857144833,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.009060195763595402,
+      "epoch": 0.5866666666666667,
+      "learning_rate": 1e-06,
+      "loss": -0.1159,
+      "step": 88
+    },
+    {
+      "Per_token_kl_mean": 0.07257080078125,
+      "Unclipped Grad Norm": 1.6133537292480469,
+      "average_num_turns": 37.666666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2533.8333740234375,
+      "complexity_score": 8.0,
+      "epoch": 0.5933333333333334,
+      "learning_rate": 1e-06,
+      "loss": 0.0223,
+      "num_customer_asks": 4.0,
+      "reward": 2.2500000074505806,
+      "reward_std": 1.1103796660900116,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.5833333358168602,
+      "step": 89
+    },
+    {
+      "Per_token_kl_mean": 0.07061767578125,
+      "Unclipped Grad Norm": 1.4744434356689453,
+      "clip_ratio/high_max": 0.005269045475870371,
+      "clip_ratio/high_mean": 0.003768719732761383,
+      "clip_ratio/low_mean": 0.0007124328913050704,
+      "clip_ratio/low_min": 0.0001073422099580057,
+      "clip_ratio/region_mean": 0.004481152514927089,
+      "epoch": 0.6,
+      "learning_rate": 1e-06,
+      "loss": 0.0203,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "eval_Per_token_kl_mean": 0.014883188100961538,
+      "eval_average_num_turns": 31.076923076923077,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completion_length": 1997.6410663311299,
+      "eval_loss": 0.19968853890895844,
+      "eval_reward": 1.6752137014499078,
+      "eval_reward_std": 1.9828610787024865,
+      "eval_rewards/format_error_penalty": -0.034188034442754894,
+      "eval_rewards/task_completion_reward": 0.4444444529139079,
+      "eval_runtime": 2287.8452,
+      "eval_samples_per_second": 0.05,
+      "eval_steps_per_second": 0.006,
+      "step": 90
+    },
+    {
+      "Per_token_kl_mean": 0.0200653076171875,
+      "Unclipped Grad Norm": 1.8663575649261475,
+      "average_num_turns": 38.333333333333336,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2596.0000610351562,
+      "complexity_score": 8.0,
+      "epoch": 0.6066666666666667,
+      "learning_rate": 1e-06,
+      "loss": 0.0079,
+      "num_customer_asks": 4.0,
+      "reward": 2.9166666865348816,
+      "reward_std": 1.2131198644638062,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.7500000037252903,
+      "step": 91
+    },
+    {
+      "Per_token_kl_mean": 0.0223846435546875,
+      "Unclipped Grad Norm": 1.5770516395568848,
+      "clip_ratio/high_max": 0.003807312168646604,
+      "clip_ratio/high_mean": 0.0028527997492346913,
+      "clip_ratio/low_mean": 0.0014293328567873687,
+      "clip_ratio/low_min": 0.0005622837343253195,
+      "clip_ratio/region_mean": 0.004282132722437382,
+      "epoch": 0.6133333333333333,
+      "learning_rate": 1e-06,
+      "loss": 0.0053,
+      "step": 92
+    },
+    {
+      "Per_token_kl_mean": 0.0768280029296875,
+      "Unclipped Grad Norm": 1.3444591760635376,
+      "average_num_turns": 34.666666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2555.3333740234375,
+      "complexity_score": 8.5,
+      "epoch": 0.62,
+      "learning_rate": 1e-06,
+      "loss": -0.0202,
+      "num_customer_asks": 3.0,
+      "reward": -0.1666666716337204,
+      "reward_std": 0.33071890473365784,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.0,
+      "step": 93
+    },
+    {
+      "Per_token_kl_mean": 0.0771636962890625,
+      "Unclipped Grad Norm": 1.3709343671798706,
+      "clip_ratio/high_max": 0.0010879701003432274,
+      "clip_ratio/high_mean": 0.0008135852986015379,
+      "clip_ratio/low_mean": 0.00022934707521926612,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0010429323883727193,
+      "epoch": 0.6266666666666667,
+      "learning_rate": 1e-06,
+      "loss": -0.0205,
+      "step": 94
+    },
+    {
+      "Per_token_kl_mean": 0.0680084228515625,
+      "Unclipped Grad Norm": 2.3600056171417236,
+      "average_num_turns": 42.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 3388.0834350585938,
+      "complexity_score": 9.0,
+      "epoch": 0.6333333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.0755,
+      "num_customer_asks": 2.0,
+      "reward": 0.9166667014360428,
+      "reward_std": 1.6103796660900116,
+      "rewards/format_error_penalty": -0.02777777798473835,
+      "rewards/task_completion_reward": 0.25000000931322575,
+      "step": 95
+    },
+    {
+      "Per_token_kl_mean": 0.064605712890625,
+      "Unclipped Grad Norm": 2.0272347927093506,
+      "clip_ratio/high_max": 0.006581486319191754,
+      "clip_ratio/high_mean": 0.003741313674254343,
+      "clip_ratio/low_mean": 0.002004660287639126,
+      "clip_ratio/low_min": 0.0005876121285837144,
+      "clip_ratio/region_mean": 0.005745973787270486,
+      "epoch": 0.64,
+      "learning_rate": 1e-06,
+      "loss": -0.0794,
+      "step": 96
+    },
+    {
+      "Per_token_kl_mean": 0.019805908203125,
+      "Unclipped Grad Norm": 1.9410338401794434,
+      "average_num_turns": 43.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 3261.33349609375,
+      "complexity_score": 9.0,
+      "epoch": 0.6466666666666666,
+      "learning_rate": 1e-06,
+      "loss": 0.1383,
+      "num_customer_asks": 2.5,
+      "reward": 0.38888888992369175,
+      "reward_std": 1.5728756785392761,
+      "rewards/format_error_penalty": -0.0555555559694767,
+      "rewards/task_completion_reward": 0.13888888992369175,
+      "step": 97
+    },
+    {
+      "Per_token_kl_mean": 0.02142333984375,
+      "Unclipped Grad Norm": 1.758843183517456,
+      "clip_ratio/high_max": 0.004393648763652891,
+      "clip_ratio/high_mean": 0.0024257415207102895,
+      "clip_ratio/low_mean": 0.0026695560081861913,
+      "clip_ratio/low_min": 0.001660002686548978,
+      "clip_ratio/region_mean": 0.005095297296065837,
+      "epoch": 0.6533333333333333,
+      "learning_rate": 1e-06,
+      "loss": 0.1354,
+      "step": 98
+    },
+    {
+      "Per_token_kl_mean": 0.0716552734375,
+      "Unclipped Grad Norm": 12.917512893676758,
+      "average_num_turns": 36.0,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2460.166748046875,
+      "complexity_score": 9.0,
+      "epoch": 0.66,
+      "learning_rate": 1e-06,
+      "loss": 0.1017,
+      "num_customer_asks": 3.0,
+      "reward": 1.138888891786337,
+      "reward_std": 2.480383574962616,
+      "rewards/format_error_penalty": -0.13888888992369175,
+      "rewards/task_completion_reward": 0.38888889737427235,
+      "step": 99
+    },
+    {
+      "Per_token_kl_mean": 0.02471923828125,
+      "Unclipped Grad Norm": 2.999737501144409,
+      "clip_ratio/high_max": 0.0038231764920055866,
+      "clip_ratio/high_mean": 0.0026635820395313203,
+      "clip_ratio/low_mean": 0.0019198434602003545,
+      "clip_ratio/low_min": 0.0009991089900722727,
+      "clip_ratio/region_mean": 0.004583425296004862,
+      "epoch": 0.6666666666666666,
+      "learning_rate": 1e-06,
+      "loss": 0.0995,
+      "step": 100
+    },
+    {
+      "Per_token_kl_mean": 0.03045654296875,
+      "Unclipped Grad Norm": 1.9564775228500366,
+      "average_num_turns": 42.666666666666664,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 3087.5001831054688,
+      "complexity_score": 9.0,
+      "epoch": 0.6733333333333333,
+      "learning_rate": 1e-06,
+      "loss": -0.085,
+      "num_customer_asks": 3.0,
+      "reward": -0.027777783572673798,
+      "reward_std": 1.190958559513092,
+      "rewards/format_error_penalty": -0.08333333395421505,
+      "rewards/task_completion_reward": 0.0555555559694767,
+      "step": 101
+    },
+    {
+      "Per_token_kl_mean": 0.031646728515625,
+      "Unclipped Grad Norm": 1.7730311155319214,
+      "clip_ratio/high_max": 0.005270454101264477,
+      "clip_ratio/high_mean": 0.004261315509211272,
+      "clip_ratio/low_mean": 0.0014705945595778758,
+      "clip_ratio/low_min": 0.0008361203945241868,
+      "clip_ratio/region_mean": 0.005731910117901862,
+      "epoch": 0.68,
+      "learning_rate": 1e-06,
+      "loss": -0.0872,
+      "step": 102
+    },
+    {
+      "Per_token_kl_mean": 0.04736328125,
+      "Unclipped Grad Norm": 1.8645439147949219,
+      "average_num_turns": 43.5,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 3629.666748046875,
+      "complexity_score": 9.0,
+      "epoch": 0.6866666666666666,
+      "learning_rate": 1e-06,
+      "loss": 0.083,
+      "num_customer_asks": 3.0,
+      "reward": 0.33333333767950535,
+      "reward_std": 1.670424461364746,
+      "rewards/format_error_penalty": -0.1111111119389534,
+      "rewards/task_completion_reward": 0.16666666977107525,
+      "step": 103
+    },
+    {
+      "Per_token_kl_mean": 0.04974365234375,
+      "Unclipped Grad Norm": 1.7132644653320312,
+      "clip_ratio/high_max": 0.0032740592141635716,
+      "clip_ratio/high_mean": 0.0020473826734814793,
+      "clip_ratio/low_mean": 0.0025954854136216454,
+      "clip_ratio/low_min": 0.0018629172700457275,
+      "clip_ratio/region_mean": 0.00464286794885993,
+      "epoch": 0.6933333333333334,
+      "learning_rate": 1e-06,
+      "loss": 0.0802,
+      "step": 104
+    },
+    {
+      "Per_token_kl_mean": 0.031097412109375,
+      "Unclipped Grad Norm": 2.467517852783203,
+      "average_num_turns": 36.66666666666667,
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 2286.5000610351562,
+      "complexity_score": 9.0,
+      "epoch": 0.7,
+      "learning_rate": 1e-06,
+      "loss": -0.0887,
+      "num_customer_asks": 3.0,
+      "reward": 1.1111111417412758,
+      "reward_std": 1.8159585893154144,
+      "rewards/format_error_penalty": -0.11111111380159855,
+      "rewards/task_completion_reward": 0.36111112125217915,
+      "step": 105
+    },
+    {
+      "epoch": 0.7,
+      "eval_Per_token_kl_mean": 0.045607346754807696,
+      "eval_average_num_turns": 30.82051282051282,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completion_length": 1949.3077486478364,
+      "eval_loss": 0.169514998793602,
+      "eval_reward": 1.709401751940067,
+      "eval_reward_std": 1.9157432042635405,
+      "eval_rewards/format_error_penalty": -0.03418803501587648,
+      "eval_rewards/task_completion_reward": 0.45299146553644765,
+      "eval_runtime": 2412.5332,
+      "eval_samples_per_second": 0.048,
+      "eval_steps_per_second": 0.005,
+      "step": 105
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ee9f978e05131a7018cd96caf130eb1694811b97bd3ec95bfb980b9a88f6df
+size 7608

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/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 json
+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)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in 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}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_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)
+
+    # 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")
+        state_dict_split = split_torch_state_dict_into_shards(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
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # 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)