Training in progress, epoch 1, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/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 %}

last-checkpoint/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    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,
+  "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": "4.53.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.53.3"
+}

last-checkpoint/global_step1309/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec0f140851089e77ca211235d4ee7ad28723210afe9791ce2ea4cf7b7aea62f
+size 16060528257

last-checkpoint/global_step1309/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d55684a31b1ad15008ded7e00abbd0e4b4b271f5715a82886ee63a319272c5
+size 16060528257

last-checkpoint/global_step1309/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d5efe66e273c80c2006455e1af82df43f35f1c48ad8428e74b1cd1cbeef1a3
+size 16060528257

last-checkpoint/global_step1309/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f874b558195979794530a922da83ce6087fee2c0f78796daa528def4d693b326
+size 16060528257

last-checkpoint/global_step1309/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debf6add4d1066735aa16ade001048f3eea94f5fe16830376e514821992118f8
+size 149232

last-checkpoint/global_step1309/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d75575a06e352a5fe63e55cfe74acf6c0ff4c43fa5456cc4a5708f88cb41eb
+size 149232

last-checkpoint/global_step1309/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b619c69af08827b06536c03d59bd540e5af74b328f7582058a43590340430f76
+size 149232

last-checkpoint/global_step1309/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0156e4d12e69b4e6ac7b74e97886238c54b845fd4e62d6938e8edaa53919bba
+size 149232

last-checkpoint/latest

@@ -0,0 +1 @@
+global_step1309

last-checkpoint/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7fb3beaca562087375808ca6ba4564ba334cb82fa6ee6449efe546caec6012
+size 4976698672

last-checkpoint/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78be0c29d6e524f532783efba8ffef669a1211b0b8d555f428bda4c2f6d89815
+size 4999802720

last-checkpoint/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a656edf59c23bd76c646e863bf1e6d0587bb3c67f3f8d737623184cd99e51d99
+size 4915916176

last-checkpoint/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1abf85bded69603343dc8fd55a7fc4f646240b7d049e794f14ad9ef3038427b
+size 1168138808

last-checkpoint/model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_parameters": 266240,
+    "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"
+  }
+}

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe6b873f1da64bb980afe982fc1c6b6bc461ad8c33073d856804323f64b26d9
+size 15429

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13db4dd10b22b5464f5ef0b539152b46390eae6a827b355108cb54b1af2eb830
+size 15429

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e293f13fb6e873e8081636b6b07115410b397c55f1ed08b8772b059c8eb74e
+size 15429

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c595c077664f94b7f91088561951be20e39483e01865774a83bc46f3971a3152
+size 15429

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe9b5c3da8f5230d5ecf3f9ce13d3af1edf38230c19625ec5ebaee6d2946601
+size 1465

last-checkpoint/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": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

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

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "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": 2048,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,2147 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1309,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007639419404125286,
+      "grad_norm": 258.47398808043715,
+      "learning_rate": 0.0,
+      "logits/chosen": -0.5703125,
+      "logits/rejected": -0.5234375,
+      "logps/chosen": -540.0,
+      "logps/rejected": -464.0,
+      "loss": 0.6924,
+      "nll_loss": 1.2421875,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.007639419404125287,
+      "grad_norm": 314.4150784740708,
+      "learning_rate": 3.435114503816794e-08,
+      "logits/chosen": -0.3402777910232544,
+      "logits/rejected": -0.34063720703125,
+      "logps/chosen": -493.77777099609375,
+      "logps/rejected": -482.8888854980469,
+      "loss": 0.6921,
+      "nll_loss": 0.9296875,
+      "rewards/accuracies": 0.2083333283662796,
+      "rewards/chosen": -0.00835503451526165,
+      "rewards/margins": 0.00830756314098835,
+      "rewards/rejected": -0.0166490338742733,
+      "step": 10
+    },
+    {
+      "epoch": 0.015278838808250574,
+      "grad_norm": 260.33930694178486,
+      "learning_rate": 7.251908396946564e-08,
+      "logits/chosen": -0.4122558534145355,
+      "logits/rejected": -0.42744141817092896,
+      "logps/chosen": -515.4000244140625,
+      "logps/rejected": -470.3999938964844,
+      "loss": 0.7081,
+      "nll_loss": 0.98046875,
+      "rewards/accuracies": 0.20000000298023224,
+      "rewards/chosen": -0.02316894568502903,
+      "rewards/margins": -0.0243988037109375,
+      "rewards/rejected": 0.0012573242420330644,
+      "step": 20
+    },
+    {
+      "epoch": 0.02291825821237586,
+      "grad_norm": 231.79105073106817,
+      "learning_rate": 1.1068702290076336e-07,
+      "logits/chosen": -0.38813477754592896,
+      "logits/rejected": -0.3990234434604645,
+      "logps/chosen": -586.2000122070312,
+      "logps/rejected": -565.2000122070312,
+      "loss": 0.6695,
+      "nll_loss": 0.967968761920929,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 0.07893677055835724,
+      "rewards/margins": 0.06370849907398224,
+      "rewards/rejected": 0.01502075232565403,
+      "step": 30
+    },
+    {
+      "epoch": 0.030557677616501147,
+      "grad_norm": 207.3625348390448,
+      "learning_rate": 1.4885496183206107e-07,
+      "logits/chosen": -0.4215331971645355,
+      "logits/rejected": -0.3983154296875,
+      "logps/chosen": -525.5999755859375,
+      "logps/rejected": -436.20001220703125,
+      "loss": 0.6524,
+      "nll_loss": 0.9371093511581421,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 0.13503417372703552,
+      "rewards/margins": 0.10765381157398224,
+      "rewards/rejected": 0.02747192420065403,
+      "step": 40
+    },
+    {
+      "epoch": 0.03819709702062643,
+      "grad_norm": 226.87256558590633,
+      "learning_rate": 1.8702290076335877e-07,
+      "logits/chosen": -0.176025390625,
+      "logits/rejected": -0.181396484375,
+      "logps/chosen": -536.4000244140625,
+      "logps/rejected": -475.20001220703125,
+      "loss": 0.6743,
+      "nll_loss": 0.833984375,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": 0.20390625298023224,
+      "rewards/margins": 0.06151122972369194,
+      "rewards/rejected": 0.14276733994483948,
+      "step": 50
+    },
+    {
+      "epoch": 0.04583651642475172,
+      "grad_norm": 183.79471712514464,
+      "learning_rate": 2.2519083969465648e-07,
+      "logits/chosen": -0.36970216035842896,
+      "logits/rejected": -0.38398438692092896,
+      "logps/chosen": -692.4000244140625,
+      "logps/rejected": -639.5999755859375,
+      "loss": 0.5822,
+      "nll_loss": 0.9417968988418579,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": 0.377685546875,
+      "rewards/margins": 0.3079589903354645,
+      "rewards/rejected": 0.07008667290210724,
+      "step": 60
+    },
+    {
+      "epoch": 0.053475935828877004,
+      "grad_norm": 193.89130497070676,
+      "learning_rate": 2.633587786259542e-07,
+      "logits/chosen": -0.397705078125,
+      "logits/rejected": -0.43745118379592896,
+      "logps/chosen": -535.7999877929688,
+      "logps/rejected": -487.3999938964844,
+      "loss": 0.5212,
+      "nll_loss": 0.9515625238418579,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.46650391817092896,
+      "rewards/margins": 0.5068359375,
+      "rewards/rejected": -0.0400390625,
+      "step": 70
+    },
+    {
+      "epoch": 0.061115355233002294,
+      "grad_norm": 204.2303212377364,
+      "learning_rate": 3.015267175572519e-07,
+      "logits/chosen": -0.32470703125,
+      "logits/rejected": -0.3303466737270355,
+      "logps/chosen": -473.6000061035156,
+      "logps/rejected": -454.0,
+      "loss": 0.5459,
+      "nll_loss": 0.876171886920929,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": 0.556835949420929,
+      "rewards/margins": 0.4847656190395355,
+      "rewards/rejected": 0.07137451320886612,
+      "step": 80
+    },
+    {
+      "epoch": 0.06875477463712758,
+      "grad_norm": 155.46344646489163,
+      "learning_rate": 3.396946564885496e-07,
+      "logits/chosen": -0.32172852754592896,
+      "logits/rejected": -0.33759766817092896,
+      "logps/chosen": -715.7999877929688,
+      "logps/rejected": -700.5999755859375,
+      "loss": 0.5522,
+      "nll_loss": 1.0656249523162842,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.6611328125,
+      "rewards/margins": 0.5273803472518921,
+      "rewards/rejected": 0.1341552734375,
+      "step": 90
+    },
+    {
+      "epoch": 0.07639419404125286,
+      "grad_norm": 141.18575275944212,
+      "learning_rate": 3.7786259541984735e-07,
+      "logits/chosen": -0.3919433653354645,
+      "logits/rejected": -0.40632325410842896,
+      "logps/chosen": -533.0,
+      "logps/rejected": -520.7999877929688,
+      "loss": 0.5137,
+      "nll_loss": 0.940234363079071,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.7120116949081421,
+      "rewards/margins": 0.7798827886581421,
+      "rewards/rejected": -0.06877441704273224,
+      "step": 100
+    },
+    {
+      "epoch": 0.08403361344537816,
+      "grad_norm": 231.1316603751942,
+      "learning_rate": 4.1603053435114506e-07,
+      "logits/chosen": -0.2874999940395355,
+      "logits/rejected": -0.3013549745082855,
+      "logps/chosen": -599.2000122070312,
+      "logps/rejected": -513.0,
+      "loss": 0.4408,
+      "nll_loss": 0.859375,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 1.0283203125,
+      "rewards/margins": 1.157617211341858,
+      "rewards/rejected": -0.12840576469898224,
+      "step": 110
+    },
+    {
+      "epoch": 0.09167303284950344,
+      "grad_norm": 132.89992060448196,
+      "learning_rate": 4.541984732824427e-07,
+      "logits/chosen": -0.25129395723342896,
+      "logits/rejected": -0.27121275663375854,
+      "logps/chosen": -602.4000244140625,
+      "logps/rejected": -581.7999877929688,
+      "loss": 0.4933,
+      "nll_loss": 0.8753906488418579,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.906445324420929,
+      "rewards/margins": 1.029296875,
+      "rewards/rejected": -0.121826171875,
+      "step": 120
+    },
+    {
+      "epoch": 0.09931245225362872,
+      "grad_norm": 133.95238732292788,
+      "learning_rate": 4.923664122137405e-07,
+      "logits/chosen": -0.21683350205421448,
+      "logits/rejected": -0.2558349668979645,
+      "logps/chosen": -614.2000122070312,
+      "logps/rejected": -569.5999755859375,
+      "loss": 0.3928,
+      "nll_loss": 0.8531249761581421,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.694927990436554,
+      "rewards/margins": 1.353906273841858,
+      "rewards/rejected": -0.658007800579071,
+      "step": 130
+    },
+    {
+      "epoch": 0.10695187165775401,
+      "grad_norm": 168.1618677127587,
+      "learning_rate": 4.966044142614601e-07,
+      "logits/chosen": -0.3291992247104645,
+      "logits/rejected": -0.2532714903354645,
+      "logps/chosen": -496.79998779296875,
+      "logps/rejected": -428.79998779296875,
+      "loss": 0.5624,
+      "nll_loss": 0.9046875238418579,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.8631836175918579,
+      "rewards/margins": 1.0146484375,
+      "rewards/rejected": -0.15104980766773224,
+      "step": 140
+    },
+    {
+      "epoch": 0.11459129106187929,
+      "grad_norm": 162.0020969653275,
+      "learning_rate": 4.923599320882851e-07,
+      "logits/chosen": -0.3076171875,
+      "logits/rejected": -0.3332763612270355,
+      "logps/chosen": -540.4000244140625,
+      "logps/rejected": -498.20001220703125,
+      "loss": 0.4469,
+      "nll_loss": 0.893750011920929,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.2221190929412842,
+      "rewards/margins": 1.4638671875,
+      "rewards/rejected": -0.24140624701976776,
+      "step": 150
+    },
+    {
+      "epoch": 0.12223071046600459,
+      "grad_norm": 174.01769486132392,
+      "learning_rate": 4.881154499151103e-07,
+      "logits/chosen": -0.32622069120407104,
+      "logits/rejected": -0.3348449766635895,
+      "logps/chosen": -591.0,
+      "logps/rejected": -580.7999877929688,
+      "loss": 0.5754,
+      "nll_loss": 1.0691406726837158,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 1.2189452648162842,
+      "rewards/margins": 1.0265624523162842,
+      "rewards/rejected": 0.19337157905101776,
+      "step": 160
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 190.37882731718457,
+      "learning_rate": 4.838709677419355e-07,
+      "logits/chosen": -0.2706542909145355,
+      "logits/rejected": -0.33831483125686646,
+      "logps/chosen": -535.5999755859375,
+      "logps/rejected": -530.2000122070312,
+      "loss": 0.5538,
+      "nll_loss": 0.8460937738418579,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 1.3611328601837158,
+      "rewards/margins": 0.967968761920929,
+      "rewards/rejected": 0.3932128846645355,
+      "step": 170
+    },
+    {
+      "epoch": 0.13750954927425516,
+      "grad_norm": 145.8998739490587,
+      "learning_rate": 4.796264855687606e-07,
+      "logits/chosen": -0.2790161073207855,
+      "logits/rejected": -0.29090577363967896,
+      "logps/chosen": -595.5999755859375,
+      "logps/rejected": -568.4000244140625,
+      "loss": 0.4184,
+      "nll_loss": 0.8812500238418579,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.9041992425918579,
+      "rewards/margins": 1.43359375,
+      "rewards/rejected": -0.53125,
+      "step": 180
+    },
+    {
+      "epoch": 0.14514896867838045,
+      "grad_norm": 102.7664998097143,
+      "learning_rate": 4.753820033955857e-07,
+      "logits/chosen": -0.36333006620407104,
+      "logits/rejected": -0.30805665254592896,
+      "logps/chosen": -529.4000244140625,
+      "logps/rejected": -484.79998779296875,
+      "loss": 0.3831,
+      "nll_loss": 0.8929687738418579,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.4363281726837158,
+      "rewards/margins": 1.766992211341858,
+      "rewards/rejected": -0.33027344942092896,
+      "step": 190
+    },
+    {
+      "epoch": 0.15278838808250572,
+      "grad_norm": 62.90690254682499,
+      "learning_rate": 4.7113752122241087e-07,
+      "logits/chosen": -0.16816405951976776,
+      "logits/rejected": -0.15498046576976776,
+      "logps/chosen": -583.4000244140625,
+      "logps/rejected": -536.5999755859375,
+      "loss": 0.4999,
+      "nll_loss": 0.892578125,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.306249976158142,
+      "rewards/margins": 1.3748047351837158,
+      "rewards/rejected": -0.06831054389476776,
+      "step": 200
+    },
+    {
+      "epoch": 0.16042780748663102,
+      "grad_norm": 84.68520470211422,
+      "learning_rate": 4.66893039049236e-07,
+      "logits/chosen": -0.19780273735523224,
+      "logits/rejected": -0.24296875298023224,
+      "logps/chosen": -525.0,
+      "logps/rejected": -510.79998779296875,
+      "loss": 0.6017,
+      "nll_loss": 0.946093738079071,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": 0.9354492425918579,
+      "rewards/margins": 1.27734375,
+      "rewards/rejected": -0.34150391817092896,
+      "step": 210
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 185.43708476964164,
+      "learning_rate": 4.6264855687606106e-07,
+      "logits/chosen": -0.27099609375,
+      "logits/rejected": -0.23505859076976776,
+      "logps/chosen": -484.3999938964844,
+      "logps/rejected": -489.20001220703125,
+      "loss": 0.487,
+      "nll_loss": 0.8511718511581421,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.3269897401332855,
+      "rewards/margins": 1.3175780773162842,
+      "rewards/rejected": -0.990429699420929,
+      "step": 220
+    },
+    {
+      "epoch": 0.17570664629488159,
+      "grad_norm": 108.47585085006368,
+      "learning_rate": 4.5840407470288624e-07,
+      "logits/chosen": -0.2373046875,
+      "logits/rejected": -0.26665037870407104,
+      "logps/chosen": -519.2000122070312,
+      "logps/rejected": -494.6000061035156,
+      "loss": 0.3942,
+      "nll_loss": 0.8656250238418579,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.721728503704071,
+      "rewards/margins": 2.1226563453674316,
+      "rewards/rejected": -1.4031250476837158,
+      "step": 230
+    },
+    {
+      "epoch": 0.18334606569900688,
+      "grad_norm": 167.38681415802225,
+      "learning_rate": 4.5415959252971136e-07,
+      "logits/chosen": -0.18267822265625,
+      "logits/rejected": -0.17292480170726776,
+      "logps/chosen": -525.0,
+      "logps/rejected": -501.6000061035156,
+      "loss": 0.5013,
+      "nll_loss": 0.892578125,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.698437511920929,
+      "rewards/margins": 1.597265601158142,
+      "rewards/rejected": -0.89697265625,
+      "step": 240
+    },
+    {
+      "epoch": 0.19098548510313215,
+      "grad_norm": 101.64538233833237,
+      "learning_rate": 4.499151103565365e-07,
+      "logits/chosen": -0.15837402641773224,
+      "logits/rejected": -0.19194336235523224,
+      "logps/chosen": -677.4000244140625,
+      "logps/rejected": -586.4000244140625,
+      "loss": 0.4529,
+      "nll_loss": 0.887890636920929,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.6534668207168579,
+      "rewards/margins": 1.8076171875,
+      "rewards/rejected": -1.1537597179412842,
+      "step": 250
+    },
+    {
+      "epoch": 0.19862490450725745,
+      "grad_norm": 294.75439921434145,
+      "learning_rate": 4.456706281833616e-07,
+      "logits/chosen": -0.2868896424770355,
+      "logits/rejected": -0.22414550185203552,
+      "logps/chosen": -544.0,
+      "logps/rejected": -496.3999938964844,
+      "loss": 0.4019,
+      "nll_loss": 0.926562488079071,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 1.142968773841858,
+      "rewards/margins": 1.655859351158142,
+      "rewards/rejected": -0.5120483636856079,
+      "step": 260
+    },
+    {
+      "epoch": 0.20626432391138275,
+      "grad_norm": 117.11210831501775,
+      "learning_rate": 4.4142614601018673e-07,
+      "logits/chosen": -0.19429931044578552,
+      "logits/rejected": -0.218994140625,
+      "logps/chosen": -575.2000122070312,
+      "logps/rejected": -544.2000122070312,
+      "loss": 0.5657,
+      "nll_loss": 0.871874988079071,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.008203148841858,
+      "rewards/margins": 1.3722655773162842,
+      "rewards/rejected": -0.3637451231479645,
+      "step": 270
+    },
+    {
+      "epoch": 0.21390374331550802,
+      "grad_norm": 163.8676544002689,
+      "learning_rate": 4.3718166383701186e-07,
+      "logits/chosen": -0.25664061307907104,
+      "logits/rejected": -0.23786620795726776,
+      "logps/chosen": -637.7999877929688,
+      "logps/rejected": -592.0,
+      "loss": 0.3987,
+      "nll_loss": 0.989453136920929,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.5733398199081421,
+      "rewards/margins": 1.9832031726837158,
+      "rewards/rejected": -1.4110839366912842,
+      "step": 280
+    },
+    {
+      "epoch": 0.2215431627196333,
+      "grad_norm": 264.70174523111024,
+      "learning_rate": 4.32937181663837e-07,
+      "logits/chosen": -0.16657714545726776,
+      "logits/rejected": -0.16425780951976776,
+      "logps/chosen": -623.0,
+      "logps/rejected": -573.7999877929688,
+      "loss": 0.5026,
+      "nll_loss": 0.8687499761581421,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.6055663824081421,
+      "rewards/margins": 1.7492187023162842,
+      "rewards/rejected": -1.142822265625,
+      "step": 290
+    },
+    {
+      "epoch": 0.22918258212375858,
+      "grad_norm": 188.9470989355876,
+      "learning_rate": 4.286926994906621e-07,
+      "logits/chosen": -0.35651856660842896,
+      "logits/rejected": -0.402099609375,
+      "logps/chosen": -510.6000061035156,
+      "logps/rejected": -459.3999938964844,
+      "loss": 0.4784,
+      "nll_loss": 0.896484375,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.013574242591858,
+      "rewards/margins": 1.8142578601837158,
+      "rewards/rejected": -0.8011718988418579,
+      "step": 300
+    },
+    {
+      "epoch": 0.23682200152788388,
+      "grad_norm": 225.67003396669838,
+      "learning_rate": 4.244482173174873e-07,
+      "logits/chosen": -0.1279296875,
+      "logits/rejected": -0.13811035454273224,
+      "logps/chosen": -545.0,
+      "logps/rejected": -516.7999877929688,
+      "loss": 0.4794,
+      "nll_loss": 0.8207031488418579,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.391210913658142,
+      "rewards/margins": 1.7058594226837158,
+      "rewards/rejected": -0.3139282166957855,
+      "step": 310
+    },
+    {
+      "epoch": 0.24446142093200918,
+      "grad_norm": 105.64614366845814,
+      "learning_rate": 4.202037351443124e-07,
+      "logits/chosen": -0.16025391221046448,
+      "logits/rejected": -0.19588622450828552,
+      "logps/chosen": -463.79998779296875,
+      "logps/rejected": -460.6000061035156,
+      "loss": 0.2819,
+      "nll_loss": 0.8589843511581421,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": 1.2197265625,
+      "rewards/margins": 2.479687452316284,
+      "rewards/rejected": -1.260498046875,
+      "step": 320
+    },
+    {
+      "epoch": 0.25210084033613445,
+      "grad_norm": 287.90740376642924,
+      "learning_rate": 4.159592529711375e-07,
+      "logits/chosen": -0.2608642578125,
+      "logits/rejected": -0.25861817598342896,
+      "logps/chosen": -548.4000244140625,
+      "logps/rejected": -534.7999877929688,
+      "loss": 0.6499,
+      "nll_loss": 0.977734386920929,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.809765636920929,
+      "rewards/margins": 1.789453148841858,
+      "rewards/rejected": -0.979785144329071,
+      "step": 330
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 184.4996723823412,
+      "learning_rate": 4.1171477079796265e-07,
+      "logits/chosen": -0.15278320014476776,
+      "logits/rejected": -0.20881347358226776,
+      "logps/chosen": -534.4000244140625,
+      "logps/rejected": -502.20001220703125,
+      "loss": 0.3265,
+      "nll_loss": 0.8968750238418579,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.8492431640625,
+      "rewards/margins": 2.390625,
+      "rewards/rejected": -1.5436522960662842,
+      "step": 340
+    },
+    {
+      "epoch": 0.26737967914438504,
+      "grad_norm": 176.1001324023726,
+      "learning_rate": 4.074702886247878e-07,
+      "logits/chosen": -0.291748046875,
+      "logits/rejected": -0.30827635526657104,
+      "logps/chosen": -536.7999877929688,
+      "logps/rejected": -502.20001220703125,
+      "loss": 0.5069,
+      "nll_loss": 0.903124988079071,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.542651355266571,
+      "rewards/margins": 1.62109375,
+      "rewards/rejected": -1.079248070716858,
+      "step": 350
+    },
+    {
+      "epoch": 0.2750190985485103,
+      "grad_norm": 215.75426907278032,
+      "learning_rate": 4.0322580645161285e-07,
+      "logits/chosen": -0.19513702392578125,
+      "logits/rejected": -0.18853148818016052,
+      "logps/chosen": -659.4000244140625,
+      "logps/rejected": -631.2000122070312,
+      "loss": 0.4296,
+      "nll_loss": 0.93359375,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.0828125476837158,
+      "rewards/margins": 1.869531273841858,
+      "rewards/rejected": -0.787548840045929,
+      "step": 360
+    },
+    {
+      "epoch": 0.2826585179526356,
+      "grad_norm": 108.88771986132863,
+      "learning_rate": 3.98981324278438e-07,
+      "logits/chosen": -0.3078857362270355,
+      "logits/rejected": -0.29511719942092896,
+      "logps/chosen": -550.2000122070312,
+      "logps/rejected": -524.5999755859375,
+      "loss": 0.4382,
+      "nll_loss": 0.8999999761581421,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.9032226800918579,
+      "rewards/margins": 1.9148437976837158,
+      "rewards/rejected": -1.0095703601837158,
+      "step": 370
+    },
+    {
+      "epoch": 0.2902979373567609,
+      "grad_norm": 157.57914105986907,
+      "learning_rate": 3.9473684210526315e-07,
+      "logits/chosen": -0.24609375,
+      "logits/rejected": -0.2859863340854645,
+      "logps/chosen": -623.5999755859375,
+      "logps/rejected": -571.5999755859375,
+      "loss": 0.4434,
+      "nll_loss": 0.9203125238418579,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.6277344226837158,
+      "rewards/margins": 1.9421875476837158,
+      "rewards/rejected": -0.314453125,
+      "step": 380
+    },
+    {
+      "epoch": 0.2979373567608862,
+      "grad_norm": 95.48144608914365,
+      "learning_rate": 3.9049235993208827e-07,
+      "logits/chosen": -0.24777832627296448,
+      "logits/rejected": -0.23862305283546448,
+      "logps/chosen": -589.5999755859375,
+      "logps/rejected": -546.5999755859375,
+      "loss": 0.414,
+      "nll_loss": 0.923046886920929,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.652441382408142,
+      "rewards/margins": 2.092968702316284,
+      "rewards/rejected": -0.43925780057907104,
+      "step": 390
+    },
+    {
+      "epoch": 0.30557677616501144,
+      "grad_norm": 132.87548084265904,
+      "learning_rate": 3.862478777589134e-07,
+      "logits/chosen": -0.21234130859375,
+      "logits/rejected": -0.22281494736671448,
+      "logps/chosen": -596.5999755859375,
+      "logps/rejected": -545.7999877929688,
+      "loss": 0.5241,
+      "nll_loss": 1.0109374523162842,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 1.0762450695037842,
+      "rewards/margins": 1.8078124523162842,
+      "rewards/rejected": -0.730297863483429,
+      "step": 400
+    },
+    {
+      "epoch": 0.31321619556913677,
+      "grad_norm": 94.35786051595302,
+      "learning_rate": 3.820033955857385e-07,
+      "logits/chosen": -0.16411133110523224,
+      "logits/rejected": -0.12357177585363388,
+      "logps/chosen": -545.5999755859375,
+      "logps/rejected": -495.0,
+      "loss": 0.4153,
+      "nll_loss": 0.915234386920929,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 1.5988280773162842,
+      "rewards/margins": 2.166015625,
+      "rewards/rejected": -0.5667968988418579,
+      "step": 410
+    },
+    {
+      "epoch": 0.32085561497326204,
+      "grad_norm": 136.65656778443866,
+      "learning_rate": 3.7775891341256364e-07,
+      "logits/chosen": -0.20586547255516052,
+      "logits/rejected": -0.18314209580421448,
+      "logps/chosen": -649.5999755859375,
+      "logps/rejected": -575.4000244140625,
+      "loss": 0.3882,
+      "nll_loss": 0.908984363079071,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 1.666894555091858,
+      "rewards/margins": 2.0859375,
+      "rewards/rejected": -0.41822510957717896,
+      "step": 420
+    },
+    {
+      "epoch": 0.3284950343773873,
+      "grad_norm": 245.401265321346,
+      "learning_rate": 3.735144312393888e-07,
+      "logits/chosen": -0.11831054836511612,
+      "logits/rejected": -0.17479248344898224,
+      "logps/chosen": -665.5999755859375,
+      "logps/rejected": -618.4000244140625,
+      "loss": 0.5723,
+      "nll_loss": 0.8828125,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.431249976158142,
+      "rewards/margins": 1.7414062023162842,
+      "rewards/rejected": -0.3086914122104645,
+      "step": 430
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 78.84105453853267,
+      "learning_rate": 3.692699490662139e-07,
+      "logits/chosen": -0.07949218899011612,
+      "logits/rejected": -0.07717285305261612,
+      "logps/chosen": -481.79998779296875,
+      "logps/rejected": -444.20001220703125,
+      "loss": 0.3382,
+      "nll_loss": 0.89453125,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.306640625,
+      "rewards/margins": 2.328125,
+      "rewards/rejected": -1.0234375,
+      "step": 440
+    },
+    {
+      "epoch": 0.3437738731856379,
+      "grad_norm": 126.23202663934781,
+      "learning_rate": 3.65025466893039e-07,
+      "logits/chosen": -0.29511719942092896,
+      "logits/rejected": -0.2608398497104645,
+      "logps/chosen": -547.5999755859375,
+      "logps/rejected": -525.5999755859375,
+      "loss": 0.4856,
+      "nll_loss": 0.9339843988418579,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.1731445789337158,
+      "rewards/margins": 1.9373047351837158,
+      "rewards/rejected": -0.7630859613418579,
+      "step": 450
+    },
+    {
+      "epoch": 0.35141329258976317,
+      "grad_norm": 76.23435884387047,
+      "learning_rate": 3.607809847198642e-07,
+      "logits/chosen": -0.3000244200229645,
+      "logits/rejected": -0.30839842557907104,
+      "logps/chosen": -572.4000244140625,
+      "logps/rejected": -551.7999877929688,
+      "loss": 0.3774,
+      "nll_loss": 0.9281250238418579,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 2.0835938453674316,
+      "rewards/margins": 2.276562452316284,
+      "rewards/rejected": -0.19318847358226776,
+      "step": 460
+    },
+    {
+      "epoch": 0.35905271199388844,
+      "grad_norm": 114.53029164371587,
+      "learning_rate": 3.5653650254668926e-07,
+      "logits/chosen": -0.17070312798023224,
+      "logits/rejected": -0.16102905571460724,
+      "logps/chosen": -531.2000122070312,
+      "logps/rejected": -517.7999877929688,
+      "loss": 0.4004,
+      "nll_loss": 0.873046875,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.2610352039337158,
+      "rewards/margins": 1.8546874523162842,
+      "rewards/rejected": -0.590991199016571,
+      "step": 470
+    },
+    {
+      "epoch": 0.36669213139801377,
+      "grad_norm": 243.54108183416537,
+      "learning_rate": 3.5229202037351443e-07,
+      "logits/chosen": -0.30506592988967896,
+      "logits/rejected": -0.24588623642921448,
+      "logps/chosen": -532.5999755859375,
+      "logps/rejected": -517.0,
+      "loss": 0.3923,
+      "nll_loss": 0.908203125,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.15625,
+      "rewards/margins": 2.299999952316284,
+      "rewards/rejected": -1.144677758216858,
+      "step": 480
+    },
+    {
+      "epoch": 0.37433155080213903,
+      "grad_norm": 174.36984130018106,
+      "learning_rate": 3.4804753820033956e-07,
+      "logits/chosen": -0.29462891817092896,
+      "logits/rejected": -0.34052735567092896,
+      "logps/chosen": -650.7999877929688,
+      "logps/rejected": -604.5999755859375,
+      "loss": 0.3593,
+      "nll_loss": 0.997265636920929,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 1.580468773841858,
+      "rewards/margins": 2.7640624046325684,
+      "rewards/rejected": -1.182226538658142,
+      "step": 490
+    },
+    {
+      "epoch": 0.3819709702062643,
+      "grad_norm": 161.0508842577597,
+      "learning_rate": 3.438030560271647e-07,
+      "logits/chosen": -0.2794433534145355,
+      "logits/rejected": -0.26513671875,
+      "logps/chosen": -607.2000122070312,
+      "logps/rejected": -620.0,
+      "loss": 0.4101,
+      "nll_loss": 0.9351562261581421,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.4298827648162842,
+      "rewards/margins": 2.234375,
+      "rewards/rejected": -0.80517578125,
+      "step": 500
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 110.76591319339768,
+      "learning_rate": 3.395585738539898e-07,
+      "logits/chosen": -0.16807861626148224,
+      "logits/rejected": -0.12810058891773224,
+      "logps/chosen": -636.5999755859375,
+      "logps/rejected": -607.4000244140625,
+      "loss": 0.3684,
+      "nll_loss": 0.936718761920929,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.9383300542831421,
+      "rewards/margins": 2.294921875,
+      "rewards/rejected": -1.353674292564392,
+      "step": 510
+    },
+    {
+      "epoch": 0.3972498090145149,
+      "grad_norm": 180.59465535461902,
+      "learning_rate": 3.3531409168081493e-07,
+      "logits/chosen": -0.18726806342601776,
+      "logits/rejected": -0.16033935546875,
+      "logps/chosen": -668.2000122070312,
+      "logps/rejected": -634.5999755859375,
+      "loss": 0.4376,
+      "nll_loss": 0.938671886920929,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.7078125476837158,
+      "rewards/margins": 2.2789063453674316,
+      "rewards/rejected": -0.5711914300918579,
+      "step": 520
+    },
+    {
+      "epoch": 0.40488922841864017,
+      "grad_norm": 138.49457254902308,
+      "learning_rate": 3.3106960950764005e-07,
+      "logits/chosen": -0.2599121034145355,
+      "logits/rejected": -0.22050781548023224,
+      "logps/chosen": -661.5999755859375,
+      "logps/rejected": -634.5999755859375,
+      "loss": 0.4448,
+      "nll_loss": 1.0085937976837158,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.7669922113418579,
+      "rewards/margins": 1.933203101158142,
+      "rewards/rejected": -1.1654784679412842,
+      "step": 530
+    },
+    {
+      "epoch": 0.4125286478227655,
+      "grad_norm": 231.1850522757914,
+      "learning_rate": 3.268251273344652e-07,
+      "logits/chosen": -0.17841796576976776,
+      "logits/rejected": -0.18508300185203552,
+      "logps/chosen": -628.2000122070312,
+      "logps/rejected": -584.2000122070312,
+      "loss": 0.4491,
+      "nll_loss": 1.060546875,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.76904296875,
+      "rewards/margins": 2.246875047683716,
+      "rewards/rejected": -1.480224609375,
+      "step": 540
+    },
+    {
+      "epoch": 0.42016806722689076,
+      "grad_norm": 160.7987831948394,
+      "learning_rate": 3.225806451612903e-07,
+      "logits/chosen": -0.14698180556297302,
+      "logits/rejected": -0.19716796278953552,
+      "logps/chosen": -602.2000122070312,
+      "logps/rejected": -539.7999877929688,
+      "loss": 0.3708,
+      "nll_loss": 0.871874988079071,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.7313476800918579,
+      "rewards/margins": 2.765625,
+      "rewards/rejected": -2.0337891578674316,
+      "step": 550
+    },
+    {
+      "epoch": 0.42780748663101603,
+      "grad_norm": 90.82442844767456,
+      "learning_rate": 3.183361629881154e-07,
+      "logits/chosen": -0.16887207329273224,
+      "logits/rejected": -0.19123534858226776,
+      "logps/chosen": -600.2000122070312,
+      "logps/rejected": -548.5999755859375,
+      "loss": 0.4537,
+      "nll_loss": 0.9097656011581421,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.8675781488418579,
+      "rewards/margins": 2.024218797683716,
+      "rewards/rejected": -1.1591796875,
+      "step": 560
+    },
+    {
+      "epoch": 0.43544690603514136,
+      "grad_norm": 138.92459223223193,
+      "learning_rate": 3.140916808149406e-07,
+      "logits/chosen": -0.11478271335363388,
+      "logits/rejected": -0.1641845703125,
+      "logps/chosen": -657.2000122070312,
+      "logps/rejected": -604.2000122070312,
+      "loss": 0.5563,
+      "nll_loss": 0.9136718511581421,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 1.17626953125,
+      "rewards/margins": 1.947656273841858,
+      "rewards/rejected": -0.772656261920929,
+      "step": 570
+    },
+    {
+      "epoch": 0.4430863254392666,
+      "grad_norm": 123.1501820354294,
+      "learning_rate": 3.0984719864176567e-07,
+      "logits/chosen": -0.11948242038488388,
+      "logits/rejected": -0.10875244438648224,
+      "logps/chosen": -553.0,
+      "logps/rejected": -479.79998779296875,
+      "loss": 0.3869,
+      "nll_loss": 0.857421875,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 1.2839844226837158,
+      "rewards/margins": 2.4769530296325684,
+      "rewards/rejected": -1.1936523914337158,
+      "step": 580
+    },
+    {
+      "epoch": 0.4507257448433919,
+      "grad_norm": 127.32337855269951,
+      "learning_rate": 3.056027164685908e-07,
+      "logits/chosen": -0.2039794921875,
+      "logits/rejected": -0.17943115532398224,
+      "logps/chosen": -564.4000244140625,
+      "logps/rejected": -573.7999877929688,
+      "loss": 0.4879,
+      "nll_loss": 0.991015613079071,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.6973632574081421,
+      "rewards/margins": 1.755468726158142,
+      "rewards/rejected": -1.059179663658142,
+      "step": 590
+    },
+    {
+      "epoch": 0.45836516424751717,
+      "grad_norm": 107.25927292937021,
+      "learning_rate": 3.0135823429541597e-07,
+      "logits/chosen": -0.18730469048023224,
+      "logits/rejected": -0.17886963486671448,
+      "logps/chosen": -597.2000122070312,
+      "logps/rejected": -592.0,
+      "loss": 0.4284,
+      "nll_loss": 1.019140601158142,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.826953113079071,
+      "rewards/margins": 2.2720704078674316,
+      "rewards/rejected": -1.450781226158142,
+      "step": 600
+    },
+    {
+      "epoch": 0.4660045836516425,
+      "grad_norm": 181.85392573395544,
+      "learning_rate": 2.9711375212224104e-07,
+      "logits/chosen": -0.10260009765625,
+      "logits/rejected": -0.1400146484375,
+      "logps/chosen": -596.7999877929688,
+      "logps/rejected": -581.5999755859375,
+      "loss": 0.4928,
+      "nll_loss": 0.938281238079071,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.825878918170929,
+      "rewards/margins": 1.986718773841858,
+      "rewards/rejected": -1.161718726158142,
+      "step": 610
+    },
+    {
+      "epoch": 0.47364400305576776,
+      "grad_norm": 498.482891329986,
+      "learning_rate": 2.928692699490662e-07,
+      "logits/chosen": -0.32451170682907104,
+      "logits/rejected": -0.33247071504592896,
+      "logps/chosen": -636.5999755859375,
+      "logps/rejected": -602.7999877929688,
+      "loss": 0.4174,
+      "nll_loss": 1.0402343273162842,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.42646485567092896,
+      "rewards/margins": 2.5859375,
+      "rewards/rejected": -2.1615233421325684,
+      "step": 620
+    },
+    {
+      "epoch": 0.48128342245989303,
+      "grad_norm": 90.59697238922614,
+      "learning_rate": 2.8862478777589134e-07,
+      "logits/chosen": -0.2081756591796875,
+      "logits/rejected": -0.24516601860523224,
+      "logps/chosen": -705.7999877929688,
+      "logps/rejected": -635.5999755859375,
+      "loss": 0.475,
+      "nll_loss": 0.9750000238418579,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.801025390625,
+      "rewards/margins": 2.24609375,
+      "rewards/rejected": -1.4406249523162842,
+      "step": 630
+    },
+    {
+      "epoch": 0.48892284186401835,
+      "grad_norm": 70.07533244919708,
+      "learning_rate": 2.8438030560271646e-07,
+      "logits/chosen": -0.23149414360523224,
+      "logits/rejected": -0.24143067002296448,
+      "logps/chosen": -601.7999877929688,
+      "logps/rejected": -607.0,
+      "loss": 0.4966,
+      "nll_loss": 1.02734375,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.388671875,
+      "rewards/margins": 2.166015625,
+      "rewards/rejected": -1.7734375,
+      "step": 640
+    },
+    {
+      "epoch": 0.4965622612681436,
+      "grad_norm": 155.4435454773161,
+      "learning_rate": 2.801358234295416e-07,
+      "logits/chosen": -0.12587890028953552,
+      "logits/rejected": -0.12092284858226776,
+      "logps/chosen": -496.6000061035156,
+      "logps/rejected": -498.20001220703125,
+      "loss": 0.4247,
+      "nll_loss": 0.916015625,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.5431762933731079,
+      "rewards/margins": 2.1624999046325684,
+      "rewards/rejected": -1.619140625,
+      "step": 650
+    },
+    {
+      "epoch": 0.5042016806722689,
+      "grad_norm": 262.5809391278708,
+      "learning_rate": 2.758913412563667e-07,
+      "logits/chosen": -0.12770995497703552,
+      "logits/rejected": -0.14760741591453552,
+      "logps/chosen": -530.4000244140625,
+      "logps/rejected": -482.0,
+      "loss": 0.5208,
+      "nll_loss": 0.903515636920929,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.02490234375,
+      "rewards/margins": 1.9609375,
+      "rewards/rejected": -0.9371093511581421,
+      "step": 660
+    },
+    {
+      "epoch": 0.5118411000763942,
+      "grad_norm": 116.54142626086018,
+      "learning_rate": 2.7164685908319183e-07,
+      "logits/chosen": -0.09782715141773224,
+      "logits/rejected": -0.11018066108226776,
+      "logps/chosen": -588.2000122070312,
+      "logps/rejected": -562.0,
+      "loss": 0.4879,
+      "nll_loss": 0.98828125,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.236718773841858,
+      "rewards/margins": 2.2178711891174316,
+      "rewards/rejected": -0.982714831829071,
+      "step": 670
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 147.62557960833126,
+      "learning_rate": 2.67402376910017e-07,
+      "logits/chosen": -0.2564453184604645,
+      "logits/rejected": -0.24064941704273224,
+      "logps/chosen": -534.0,
+      "logps/rejected": -507.79998779296875,
+      "loss": 0.3249,
+      "nll_loss": 0.9417968988418579,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.764941394329071,
+      "rewards/margins": 2.680859327316284,
+      "rewards/rejected": -1.916015625,
+      "step": 680
+    },
+    {
+      "epoch": 0.5271199388846448,
+      "grad_norm": 73.38717469252549,
+      "learning_rate": 2.631578947368421e-07,
+      "logits/chosen": -0.169677734375,
+      "logits/rejected": -0.21303710341453552,
+      "logps/chosen": -604.7999877929688,
+      "logps/rejected": -589.5999755859375,
+      "loss": 0.5577,
+      "nll_loss": 0.919921875,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.28046876192092896,
+      "rewards/margins": 1.9656250476837158,
+      "rewards/rejected": -1.6857421398162842,
+      "step": 690
+    },
+    {
+      "epoch": 0.5347593582887701,
+      "grad_norm": 125.30928463570962,
+      "learning_rate": 2.589134125636672e-07,
+      "logits/chosen": -0.24868163466453552,
+      "logits/rejected": -0.21337890625,
+      "logps/chosen": -669.7999877929688,
+      "logps/rejected": -607.0,
+      "loss": 0.5241,
+      "nll_loss": 0.987109363079071,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.698010265827179,
+      "rewards/margins": 2.317578077316284,
+      "rewards/rejected": -1.62060546875,
+      "step": 700
+    },
+    {
+      "epoch": 0.5423987776928954,
+      "grad_norm": 86.47824062520769,
+      "learning_rate": 2.546689303904924e-07,
+      "logits/chosen": -0.15998534858226776,
+      "logits/rejected": -0.13544921576976776,
+      "logps/chosen": -527.0,
+      "logps/rejected": -507.3999938964844,
+      "loss": 0.4433,
+      "nll_loss": 0.8832031488418579,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.833325207233429,
+      "rewards/margins": 1.917578101158142,
+      "rewards/rejected": -1.0823242664337158,
+      "step": 710
+    },
+    {
+      "epoch": 0.5500381970970206,
+      "grad_norm": 241.9764128861329,
+      "learning_rate": 2.5042444821731745e-07,
+      "logits/chosen": -0.23203125596046448,
+      "logits/rejected": -0.15019531548023224,
+      "logps/chosen": -623.2000122070312,
+      "logps/rejected": -519.4000244140625,
+      "loss": 0.4256,
+      "nll_loss": 0.934374988079071,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.8759765625,
+      "rewards/margins": 2.4292969703674316,
+      "rewards/rejected": -1.5539062023162842,
+      "step": 720
+    },
+    {
+      "epoch": 0.5576776165011459,
+      "grad_norm": 199.54510567975194,
+      "learning_rate": 2.4617996604414257e-07,
+      "logits/chosen": -0.20654296875,
+      "logits/rejected": -0.18228760361671448,
+      "logps/chosen": -569.5999755859375,
+      "logps/rejected": -539.2000122070312,
+      "loss": 0.44,
+      "nll_loss": 0.9097656011581421,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.22563476860523224,
+      "rewards/margins": 2.035937547683716,
+      "rewards/rejected": -1.8076171875,
+      "step": 730
+    },
+    {
+      "epoch": 0.5653170359052712,
+      "grad_norm": 57.705062448013685,
+      "learning_rate": 2.4193548387096775e-07,
+      "logits/chosen": -0.29963380098342896,
+      "logits/rejected": -0.2674804627895355,
+      "logps/chosen": -658.4000244140625,
+      "logps/rejected": -642.4000244140625,
+      "loss": 0.395,
+      "nll_loss": 0.998046875,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.02570800855755806,
+      "rewards/margins": 2.359375,
+      "rewards/rejected": -2.383593797683716,
+      "step": 740
+    },
+    {
+      "epoch": 0.5729564553093965,
+      "grad_norm": 90.1800130721227,
+      "learning_rate": 2.3769100169779285e-07,
+      "logits/chosen": -0.17238768935203552,
+      "logits/rejected": -0.21173095703125,
+      "logps/chosen": -690.4000244140625,
+      "logps/rejected": -671.0,
+      "loss": 0.4136,
+      "nll_loss": 0.9566406011581421,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.26005858182907104,
+      "rewards/margins": 2.177929639816284,
+      "rewards/rejected": -1.918359398841858,
+      "step": 750
+    },
+    {
+      "epoch": 0.5805958747135218,
+      "grad_norm": 128.16902765016945,
+      "learning_rate": 2.33446519524618e-07,
+      "logits/chosen": -0.18836669623851776,
+      "logits/rejected": -0.13487549126148224,
+      "logps/chosen": -570.0,
+      "logps/rejected": -552.4000244140625,
+      "loss": 0.4234,
+      "nll_loss": 0.950390636920929,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.518481433391571,
+      "rewards/margins": 2.1351561546325684,
+      "rewards/rejected": -1.615625023841858,
+      "step": 760
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 179.91151487829103,
+      "learning_rate": 2.2920203735144312e-07,
+      "logits/chosen": -0.15025635063648224,
+      "logits/rejected": -0.20454101264476776,
+      "logps/chosen": -590.5999755859375,
+      "logps/rejected": -570.7999877929688,
+      "loss": 0.3452,
+      "nll_loss": 0.905078113079071,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.132714867591858,
+      "rewards/margins": 2.6820311546325684,
+      "rewards/rejected": -1.5529296398162842,
+      "step": 770
+    },
+    {
+      "epoch": 0.5958747135217723,
+      "grad_norm": 147.28111171420568,
+      "learning_rate": 2.2495755517826824e-07,
+      "logits/chosen": -0.2244003266096115,
+      "logits/rejected": -0.20163574814796448,
+      "logps/chosen": -580.0,
+      "logps/rejected": -517.0,
+      "loss": 0.4638,
+      "nll_loss": 0.9203125238418579,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.217919945716858,
+      "rewards/margins": 2.2210936546325684,
+      "rewards/rejected": -1.00244140625,
+      "step": 780
+    },
+    {
+      "epoch": 0.6035141329258976,
+      "grad_norm": 148.2346332858827,
+      "learning_rate": 2.2071307300509337e-07,
+      "logits/chosen": -0.2839111387729645,
+      "logits/rejected": -0.26567381620407104,
+      "logps/chosen": -589.5999755859375,
+      "logps/rejected": -557.0,
+      "loss": 0.3842,
+      "nll_loss": 0.866406261920929,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.83984375,
+      "rewards/margins": 2.340625047683716,
+      "rewards/rejected": -1.5037109851837158,
+      "step": 790
+    },
+    {
+      "epoch": 0.6111535523300229,
+      "grad_norm": 88.75284081371973,
+      "learning_rate": 2.164685908319185e-07,
+      "logits/chosen": -0.23496094346046448,
+      "logits/rejected": -0.19589844346046448,
+      "logps/chosen": -686.0,
+      "logps/rejected": -661.2000122070312,
+      "loss": 0.4166,
+      "nll_loss": 1.068359375,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.013671875,
+      "rewards/margins": 2.171875,
+      "rewards/rejected": -1.1590087413787842,
+      "step": 800
+    },
+    {
+      "epoch": 0.6187929717341482,
+      "grad_norm": 145.23948778484626,
+      "learning_rate": 2.1222410865874364e-07,
+      "logits/chosen": -0.20212402939796448,
+      "logits/rejected": -0.20252685248851776,
+      "logps/chosen": -539.0,
+      "logps/rejected": -484.6000061035156,
+      "loss": 0.3318,
+      "nll_loss": 0.8890625238418579,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.648242175579071,
+      "rewards/margins": 2.7249999046325684,
+      "rewards/rejected": -2.0816407203674316,
+      "step": 810
+    },
+    {
+      "epoch": 0.6264323911382735,
+      "grad_norm": 128.52828674770328,
+      "learning_rate": 2.0797962648556874e-07,
+      "logits/chosen": -0.11715392768383026,
+      "logits/rejected": -0.13743896782398224,
+      "logps/chosen": -547.0,
+      "logps/rejected": -538.2000122070312,
+      "loss": 0.4387,
+      "nll_loss": 0.813671886920929,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.023046851158142,
+      "rewards/margins": 2.3441405296325684,
+      "rewards/rejected": -1.322265625,
+      "step": 820
+    },
+    {
+      "epoch": 0.6340718105423988,
+      "grad_norm": 144.47861170444614,
+      "learning_rate": 2.037351443123939e-07,
+      "logits/chosen": -0.06186523288488388,
+      "logits/rejected": -0.10273437201976776,
+      "logps/chosen": -533.4000244140625,
+      "logps/rejected": -495.0,
+      "loss": 0.3348,
+      "nll_loss": 0.8785156011581421,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.628613293170929,
+      "rewards/margins": 2.4515624046325684,
+      "rewards/rejected": -1.8227050304412842,
+      "step": 830
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": 231.8284171525199,
+      "learning_rate": 1.99490662139219e-07,
+      "logits/chosen": -0.2966064512729645,
+      "logits/rejected": -0.3492675721645355,
+      "logps/chosen": -563.2000122070312,
+      "logps/rejected": -554.5999755859375,
+      "loss": 0.4784,
+      "nll_loss": 1.038671851158142,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.3266967833042145,
+      "rewards/margins": 2.3394532203674316,
+      "rewards/rejected": -2.016064405441284,
+      "step": 840
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "grad_norm": 95.18920210483807,
+      "learning_rate": 1.9524617996604413e-07,
+      "logits/chosen": -0.2720703184604645,
+      "logits/rejected": -0.21528320014476776,
+      "logps/chosen": -639.4000244140625,
+      "logps/rejected": -599.4000244140625,
+      "loss": 0.4277,
+      "nll_loss": 0.913281261920929,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.0625,
+      "rewards/margins": 2.268261671066284,
+      "rewards/rejected": -1.204687476158142,
+      "step": 850
+    },
+    {
+      "epoch": 0.6569900687547746,
+      "grad_norm": 179.17446116841967,
+      "learning_rate": 1.9100169779286926e-07,
+      "logits/chosen": -0.28715819120407104,
+      "logits/rejected": -0.2583984434604645,
+      "logps/chosen": -548.5999755859375,
+      "logps/rejected": -489.3999938964844,
+      "loss": 0.4577,
+      "nll_loss": 0.846875011920929,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.1994140148162842,
+      "rewards/margins": 2.366015672683716,
+      "rewards/rejected": -1.167578101158142,
+      "step": 860
+    },
+    {
+      "epoch": 0.6646294881588999,
+      "grad_norm": 176.32245150389784,
+      "learning_rate": 1.867572156196944e-07,
+      "logits/chosen": -0.2516418397426605,
+      "logits/rejected": -0.24804076552391052,
+      "logps/chosen": -462.0,
+      "logps/rejected": -476.0,
+      "loss": 0.5009,
+      "nll_loss": 0.921875,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.588671863079071,
+      "rewards/margins": 2.198046922683716,
+      "rewards/rejected": -1.612036108970642,
+      "step": 870
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 154.3222829630188,
+      "learning_rate": 1.825127334465195e-07,
+      "logits/chosen": -0.10764160007238388,
+      "logits/rejected": -0.10710449516773224,
+      "logps/chosen": -545.4000244140625,
+      "logps/rejected": -537.0,
+      "loss": 0.4212,
+      "nll_loss": 0.8804687261581421,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.8570312261581421,
+      "rewards/margins": 2.375781297683716,
+      "rewards/rejected": -1.517333984375,
+      "step": 880
+    },
+    {
+      "epoch": 0.6799083269671505,
+      "grad_norm": 90.0921653237205,
+      "learning_rate": 1.7826825127334463e-07,
+      "logits/chosen": -0.2685546875,
+      "logits/rejected": -0.24018554389476776,
+      "logps/chosen": -573.0,
+      "logps/rejected": -550.0,
+      "loss": 0.3369,
+      "nll_loss": 0.922656238079071,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.4517578184604645,
+      "rewards/margins": 2.914843797683716,
+      "rewards/rejected": -2.46484375,
+      "step": 890
+    },
+    {
+      "epoch": 0.6875477463712758,
+      "grad_norm": 90.60087330499096,
+      "learning_rate": 1.7402376910016978e-07,
+      "logits/chosen": -0.17197266221046448,
+      "logits/rejected": -0.16635742783546448,
+      "logps/chosen": -646.5999755859375,
+      "logps/rejected": -654.0,
+      "loss": 0.5631,
+      "nll_loss": 1.0390625,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.09462890774011612,
+      "rewards/margins": 2.5414061546325684,
+      "rewards/rejected": -2.447265625,
+      "step": 900
+    },
+    {
+      "epoch": 0.6951871657754011,
+      "grad_norm": 411.9292153674767,
+      "learning_rate": 1.697792869269949e-07,
+      "logits/chosen": -0.21950682997703552,
+      "logits/rejected": -0.14067383110523224,
+      "logps/chosen": -782.4000244140625,
+      "logps/rejected": -746.5999755859375,
+      "loss": 0.5727,
+      "nll_loss": 0.967968761920929,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.3875488340854645,
+      "rewards/margins": 1.941015601158142,
+      "rewards/rejected": -1.554296851158142,
+      "step": 910
+    },
+    {
+      "epoch": 0.7028265851795263,
+      "grad_norm": 96.59177093218652,
+      "learning_rate": 1.6553480475382003e-07,
+      "logits/chosen": -0.17082519829273224,
+      "logits/rejected": -0.24100342392921448,
+      "logps/chosen": -523.4000244140625,
+      "logps/rejected": -496.79998779296875,
+      "loss": 0.4115,
+      "nll_loss": 0.9515625238418579,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.02167968824505806,
+      "rewards/margins": 2.335156202316284,
+      "rewards/rejected": -2.3140625953674316,
+      "step": 920
+    },
+    {
+      "epoch": 0.7104660045836516,
+      "grad_norm": 114.00603134519599,
+      "learning_rate": 1.6129032258064515e-07,
+      "logits/chosen": -0.0623779296875,
+      "logits/rejected": -0.03818359225988388,
+      "logps/chosen": -604.7999877929688,
+      "logps/rejected": -563.4000244140625,
+      "loss": 0.374,
+      "nll_loss": 0.859375,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.599719226360321,
+      "rewards/margins": 2.612499952316284,
+      "rewards/rejected": -2.0126953125,
+      "step": 930
+    },
+    {
+      "epoch": 0.7181054239877769,
+      "grad_norm": 46.449877624622495,
+      "learning_rate": 1.570458404074703e-07,
+      "logits/chosen": -0.20942382514476776,
+      "logits/rejected": -0.23570556938648224,
+      "logps/chosen": -527.4000244140625,
+      "logps/rejected": -528.4000244140625,
+      "loss": 0.3851,
+      "nll_loss": 0.9398437738418579,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.19345703721046448,
+      "rewards/margins": 2.53125,
+      "rewards/rejected": -2.3375000953674316,
+      "step": 940
+    },
+    {
+      "epoch": 0.7257448433919023,
+      "grad_norm": 154.8870158247193,
+      "learning_rate": 1.528013582342954e-07,
+      "logits/chosen": -0.17775878310203552,
+      "logits/rejected": -0.15126952528953552,
+      "logps/chosen": -644.0,
+      "logps/rejected": -595.4000244140625,
+      "loss": 0.3593,
+      "nll_loss": 0.948046863079071,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.614453136920929,
+      "rewards/margins": 2.4710936546325684,
+      "rewards/rejected": -1.8585937023162842,
+      "step": 950
+    },
+    {
+      "epoch": 0.7333842627960275,
+      "grad_norm": 60.309689191140706,
+      "learning_rate": 1.4855687606112052e-07,
+      "logits/chosen": -0.20181885361671448,
+      "logits/rejected": -0.17143554985523224,
+      "logps/chosen": -614.2000122070312,
+      "logps/rejected": -502.20001220703125,
+      "loss": 0.2511,
+      "nll_loss": 0.9703124761581421,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 0.37763673067092896,
+      "rewards/margins": 2.9703125953674316,
+      "rewards/rejected": -2.592968702316284,
+      "step": 960
+    },
+    {
+      "epoch": 0.7410236822001528,
+      "grad_norm": 93.06951737576422,
+      "learning_rate": 1.4431239388794567e-07,
+      "logits/chosen": -0.11916504055261612,
+      "logits/rejected": -0.12851563096046448,
+      "logps/chosen": -522.0,
+      "logps/rejected": -478.20001220703125,
+      "loss": 0.3418,
+      "nll_loss": 0.948046863079071,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.33341675996780396,
+      "rewards/margins": 2.641406297683716,
+      "rewards/rejected": -2.311718702316284,
+      "step": 970
+    },
+    {
+      "epoch": 0.7486631016042781,
+      "grad_norm": 86.2530129397837,
+      "learning_rate": 1.400679117147708e-07,
+      "logits/chosen": -0.26170653104782104,
+      "logits/rejected": -0.27277833223342896,
+      "logps/chosen": -557.7999877929688,
+      "logps/rejected": -540.5999755859375,
+      "loss": 0.3527,
+      "nll_loss": 0.98046875,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.4949707090854645,
+      "rewards/margins": 2.564453125,
+      "rewards/rejected": -2.0708985328674316,
+      "step": 980
+    },
+    {
+      "epoch": 0.7563025210084033,
+      "grad_norm": 87.12906010791761,
+      "learning_rate": 1.3582342954159592e-07,
+      "logits/chosen": -0.26884764432907104,
+      "logits/rejected": -0.22690430283546448,
+      "logps/chosen": -634.4000244140625,
+      "logps/rejected": -615.5999755859375,
+      "loss": 0.3518,
+      "nll_loss": 1.00390625,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.05859375,
+      "rewards/margins": 3.135937452316284,
+      "rewards/rejected": -3.0796875953674316,
+      "step": 990
+    },
+    {
+      "epoch": 0.7639419404125286,
+      "grad_norm": 245.3625476453072,
+      "learning_rate": 1.3157894736842104e-07,
+      "logits/chosen": -0.20460815727710724,
+      "logits/rejected": -0.16091307997703552,
+      "logps/chosen": -667.5999755859375,
+      "logps/rejected": -630.4000244140625,
+      "loss": 0.5093,
+      "nll_loss": 0.916015625,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.29121094942092896,
+      "rewards/margins": 2.0160155296325684,
+      "rewards/rejected": -2.307812452316284,
+      "step": 1000
+    },
+    {
+      "epoch": 0.771581359816654,
+      "grad_norm": 124.28190362733702,
+      "learning_rate": 1.273344651952462e-07,
+      "logits/chosen": -0.11392822116613388,
+      "logits/rejected": -0.11372070014476776,
+      "logps/chosen": -574.0,
+      "logps/rejected": -589.5999755859375,
+      "loss": 0.2951,
+      "nll_loss": 0.9234374761581421,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.04301757737994194,
+      "rewards/margins": 2.9124999046325684,
+      "rewards/rejected": -2.962890625,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 100.0627026970796,
+      "learning_rate": 1.2308998302207129e-07,
+      "logits/chosen": -0.3117919862270355,
+      "logits/rejected": -0.27192384004592896,
+      "logps/chosen": -643.2000122070312,
+      "logps/rejected": -626.4000244140625,
+      "loss": 0.4462,
+      "nll_loss": 0.983203113079071,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.3858398497104645,
+      "rewards/margins": 2.7281250953674316,
+      "rewards/rejected": -2.3414063453674316,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7868601986249045,
+      "grad_norm": 99.33843951990231,
+      "learning_rate": 1.1884550084889642e-07,
+      "logits/chosen": -0.20637206733226776,
+      "logits/rejected": -0.17661133408546448,
+      "logps/chosen": -621.0,
+      "logps/rejected": -586.4000244140625,
+      "loss": 0.4063,
+      "nll_loss": 0.924609363079071,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.1715087890625,
+      "rewards/margins": 2.515625,
+      "rewards/rejected": -2.344531297683716,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7944996180290298,
+      "grad_norm": 173.70184429546075,
+      "learning_rate": 1.1460101867572156e-07,
+      "logits/chosen": -0.15251465141773224,
+      "logits/rejected": -0.12940673530101776,
+      "logps/chosen": -624.5999755859375,
+      "logps/rejected": -595.0,
+      "loss": 0.294,
+      "nll_loss": 0.928906261920929,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.10312499850988388,
+      "rewards/margins": 2.552734375,
+      "rewards/rejected": -2.452343702316284,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8021390374331551,
+      "grad_norm": 112.58127449933384,
+      "learning_rate": 1.1035653650254668e-07,
+      "logits/chosen": -0.202392578125,
+      "logits/rejected": -0.167236328125,
+      "logps/chosen": -592.7999877929688,
+      "logps/rejected": -562.0,
+      "loss": 0.4084,
+      "nll_loss": 0.884765625,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.49921876192092896,
+      "rewards/margins": 2.3228516578674316,
+      "rewards/rejected": -1.8244140148162842,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8097784568372803,
+      "grad_norm": 13.477126429230648,
+      "learning_rate": 1.0611205432937182e-07,
+      "logits/chosen": -0.06467285007238388,
+      "logits/rejected": -0.10791015625,
+      "logps/chosen": -637.5999755859375,
+      "logps/rejected": -594.4000244140625,
+      "loss": 0.4124,
+      "nll_loss": 0.9261718988418579,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.5888671875,
+      "rewards/margins": 2.6421875953674316,
+      "rewards/rejected": -2.053906202316284,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8174178762414056,
+      "grad_norm": 146.54916411561834,
+      "learning_rate": 1.0186757215619694e-07,
+      "logits/chosen": -0.02625732496380806,
+      "logits/rejected": -0.01333007775247097,
+      "logps/chosen": -607.2000122070312,
+      "logps/rejected": -569.0,
+      "loss": 0.3095,
+      "nll_loss": 0.8355468511581421,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.664257824420929,
+      "rewards/margins": 2.471874952316284,
+      "rewards/rejected": -1.8097655773162842,
+      "step": 1070
+    },
+    {
+      "epoch": 0.825057295645531,
+      "grad_norm": 27.03231972763934,
+      "learning_rate": 9.762308998302207e-08,
+      "logits/chosen": -0.2533203065395355,
+      "logits/rejected": -0.19873046875,
+      "logps/chosen": -530.2000122070312,
+      "logps/rejected": -508.79998779296875,
+      "loss": 0.363,
+      "nll_loss": 0.925000011920929,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.32301026582717896,
+      "rewards/margins": 2.681640625,
+      "rewards/rejected": -2.3609375953674316,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8326967150496563,
+      "grad_norm": 95.08593550485008,
+      "learning_rate": 9.33786078098472e-08,
+      "logits/chosen": -0.113616943359375,
+      "logits/rejected": -0.18590088188648224,
+      "logps/chosen": -522.0,
+      "logps/rejected": -463.0,
+      "loss": 0.3409,
+      "nll_loss": 0.901171863079071,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.597607433795929,
+      "rewards/margins": 2.7945313453674316,
+      "rewards/rejected": -2.1976561546325684,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 43.42987904751351,
+      "learning_rate": 8.913412563667231e-08,
+      "logits/chosen": -0.26826173067092896,
+      "logits/rejected": -0.2728515565395355,
+      "logps/chosen": -591.4000244140625,
+      "logps/rejected": -585.5999755859375,
+      "loss": 0.4074,
+      "nll_loss": 0.938281238079071,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.4159179627895355,
+      "rewards/margins": 2.444531202316284,
+      "rewards/rejected": -2.027539014816284,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8479755538579068,
+      "grad_norm": 130.2620800651245,
+      "learning_rate": 8.488964346349745e-08,
+      "logits/chosen": -0.11006774753332138,
+      "logits/rejected": -0.13276366889476776,
+      "logps/chosen": -505.20001220703125,
+      "logps/rejected": -493.0,
+      "loss": 0.3638,
+      "nll_loss": 0.8988281488418579,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.3427734375,
+      "rewards/margins": 2.474609375,
+      "rewards/rejected": -2.1343750953674316,
+      "step": 1110
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 258.0177244688908,
+      "learning_rate": 8.064516129032257e-08,
+      "logits/chosen": -0.17624512314796448,
+      "logits/rejected": -0.15255126357078552,
+      "logps/chosen": -585.5999755859375,
+      "logps/rejected": -592.5999755859375,
+      "loss": 0.4054,
+      "nll_loss": 0.9449218511581421,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.28657227754592896,
+      "rewards/margins": 2.617968797683716,
+      "rewards/rejected": -2.334765672683716,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8632543926661573,
+      "grad_norm": 167.06471829769077,
+      "learning_rate": 7.64006791171477e-08,
+      "logits/chosen": -0.01499023474752903,
+      "logits/rejected": -0.0026123046409338713,
+      "logps/chosen": -526.7999877929688,
+      "logps/rejected": -518.7999877929688,
+      "loss": 0.394,
+      "nll_loss": 0.834765613079071,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.09824218600988388,
+      "rewards/margins": 2.207812547683716,
+      "rewards/rejected": -2.3070311546325684,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8708938120702827,
+      "grad_norm": 203.27949384009779,
+      "learning_rate": 7.215619694397283e-08,
+      "logits/chosen": -0.04530029371380806,
+      "logits/rejected": -0.010485840030014515,
+      "logps/chosen": -570.4000244140625,
+      "logps/rejected": -554.0,
+      "loss": 0.3578,
+      "nll_loss": 0.8656250238418579,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.8838866949081421,
+      "rewards/margins": 2.2896485328674316,
+      "rewards/rejected": -1.40283203125,
+      "step": 1140
+    },
+    {
+      "epoch": 0.878533231474408,
+      "grad_norm": 91.28683779041214,
+      "learning_rate": 6.791171477079796e-08,
+      "logits/chosen": -0.158447265625,
+      "logits/rejected": -0.15849609673023224,
+      "logps/chosen": -659.4000244140625,
+      "logps/rejected": -620.0,
+      "loss": 0.3552,
+      "nll_loss": 1.006250023841858,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.120996117591858,
+      "rewards/margins": 2.5785155296325684,
+      "rewards/rejected": -1.453710913658142,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8861726508785333,
+      "grad_norm": 165.0639361803876,
+      "learning_rate": 6.36672325976231e-08,
+      "logits/chosen": -0.17514649033546448,
+      "logits/rejected": -0.22218628227710724,
+      "logps/chosen": -545.5999755859375,
+      "logps/rejected": -525.5999755859375,
+      "loss": 0.3801,
+      "nll_loss": 0.984375,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.7798827886581421,
+      "rewards/margins": 2.7671875953674316,
+      "rewards/rejected": -1.98876953125,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8938120702826585,
+      "grad_norm": 70.36211868043284,
+      "learning_rate": 5.942275042444821e-08,
+      "logits/chosen": -0.07485046237707138,
+      "logits/rejected": -0.07871093600988388,
+      "logps/chosen": -517.7999877929688,
+      "logps/rejected": -501.20001220703125,
+      "loss": 0.4365,
+      "nll_loss": 0.889453113079071,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.19501952826976776,
+      "rewards/margins": 2.075390577316284,
+      "rewards/rejected": -1.877343773841858,
+      "step": 1170
+    },
+    {
+      "epoch": 0.9014514896867838,
+      "grad_norm": 46.76470844821065,
+      "learning_rate": 5.517826825127334e-08,
+      "logits/chosen": -0.21860352158546448,
+      "logits/rejected": -0.21206054091453552,
+      "logps/chosen": -566.5999755859375,
+      "logps/rejected": -548.0,
+      "loss": 0.452,
+      "nll_loss": 0.876953125,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.6045898199081421,
+      "rewards/margins": 1.9511229991912842,
+      "rewards/rejected": -1.346093773841858,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 132.73200075615364,
+      "learning_rate": 5.093378607809847e-08,
+      "logits/chosen": -0.13608399033546448,
+      "logits/rejected": -0.16939696669578552,
+      "logps/chosen": -535.0,
+      "logps/rejected": -506.20001220703125,
+      "loss": 0.3551,
+      "nll_loss": 0.946093738079071,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.880932629108429,
+      "rewards/margins": 2.707812547683716,
+      "rewards/rejected": -1.8278319835662842,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9167303284950343,
+      "grad_norm": 141.55461267715054,
+      "learning_rate": 4.66893039049236e-08,
+      "logits/chosen": -0.20478515326976776,
+      "logits/rejected": -0.16940918564796448,
+      "logps/chosen": -531.7999877929688,
+      "logps/rejected": -499.6000061035156,
+      "loss": 0.3211,
+      "nll_loss": 0.9398437738418579,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.8980468511581421,
+      "rewards/margins": 2.780468702316284,
+      "rewards/rejected": -1.885156273841858,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9243697478991597,
+      "grad_norm": 188.7068399957901,
+      "learning_rate": 4.2444821731748725e-08,
+      "logits/chosen": -0.2447509765625,
+      "logits/rejected": -0.19533690810203552,
+      "logps/chosen": -581.2000122070312,
+      "logps/rejected": -552.2000122070312,
+      "loss": 0.3269,
+      "nll_loss": 0.961718738079071,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": 0.3602050840854645,
+      "rewards/margins": 2.5765624046325684,
+      "rewards/rejected": -2.2173829078674316,
+      "step": 1210
+    },
+    {
+      "epoch": 0.932009167303285,
+      "grad_norm": 104.70717258392624,
+      "learning_rate": 3.820033955857385e-08,
+      "logits/chosen": -0.21748046576976776,
+      "logits/rejected": -0.20539550483226776,
+      "logps/chosen": -736.5999755859375,
+      "logps/rejected": -709.7999877929688,
+      "loss": 0.4171,
+      "nll_loss": 1.0066406726837158,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.4925781190395355,
+      "rewards/margins": 2.092578172683716,
+      "rewards/rejected": -1.601171851158142,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9396485867074102,
+      "grad_norm": 120.69266491201337,
+      "learning_rate": 3.395585738539898e-08,
+      "logits/chosen": -0.16705322265625,
+      "logits/rejected": -0.20624999701976776,
+      "logps/chosen": -546.4000244140625,
+      "logps/rejected": -513.5999755859375,
+      "loss": 0.5148,
+      "nll_loss": 0.892578125,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.23613281548023224,
+      "rewards/margins": 2.397656202316284,
+      "rewards/rejected": -2.1617188453674316,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9472880061115355,
+      "grad_norm": 89.80554106184103,
+      "learning_rate": 2.9711375212224106e-08,
+      "logits/chosen": -0.22031250596046448,
+      "logits/rejected": -0.26923829317092896,
+      "logps/chosen": -567.2000122070312,
+      "logps/rejected": -513.0,
+      "loss": 0.3652,
+      "nll_loss": 0.949999988079071,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.590991199016571,
+      "rewards/margins": 2.520312547683716,
+      "rewards/rejected": -1.9285156726837158,
+      "step": 1240
+    },
+    {
+      "epoch": 0.9549274255156608,
+      "grad_norm": 68.44803041900859,
+      "learning_rate": 2.5466893039049236e-08,
+      "logits/chosen": -0.10751952975988388,
+      "logits/rejected": -0.10664062201976776,
+      "logps/chosen": -557.4000244140625,
+      "logps/rejected": -524.0,
+      "loss": 0.3961,
+      "nll_loss": 0.864062488079071,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.5328124761581421,
+      "rewards/margins": 2.385009765625,
+      "rewards/rejected": -1.853906273841858,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9625668449197861,
+      "grad_norm": 77.86404690618204,
+      "learning_rate": 2.1222410865874363e-08,
+      "logits/chosen": -0.23062744736671448,
+      "logits/rejected": -0.19792480766773224,
+      "logps/chosen": -579.0,
+      "logps/rejected": -549.4000244140625,
+      "loss": 0.3363,
+      "nll_loss": 0.908984363079071,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.6390625238418579,
+      "rewards/margins": 2.806640625,
+      "rewards/rejected": -2.1689453125,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9702062643239114,
+      "grad_norm": 92.2508879537955,
+      "learning_rate": 1.697792869269949e-08,
+      "logits/chosen": -0.243896484375,
+      "logits/rejected": -0.2039794921875,
+      "logps/chosen": -596.0,
+      "logps/rejected": -552.0,
+      "loss": 0.442,
+      "nll_loss": 0.9007812738418579,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.3742431700229645,
+      "rewards/margins": 2.436718702316284,
+      "rewards/rejected": -2.05859375,
+      "step": 1270
+    },
+    {
+      "epoch": 0.9778456837280367,
+      "grad_norm": 99.79262236865266,
+      "learning_rate": 1.2733446519524618e-08,
+      "logits/chosen": -0.23527832329273224,
+      "logits/rejected": -0.218994140625,
+      "logps/chosen": -552.2000122070312,
+      "logps/rejected": -540.0,
+      "loss": 0.4244,
+      "nll_loss": 0.8421875238418579,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.4585937559604645,
+      "rewards/margins": 2.216992139816284,
+      "rewards/rejected": -1.75732421875,
+      "step": 1280
+    },
+    {
+      "epoch": 0.985485103132162,
+      "grad_norm": 140.72925309996154,
+      "learning_rate": 8.488964346349745e-09,
+      "logits/chosen": -0.2117919921875,
+      "logits/rejected": -0.18214111030101776,
+      "logps/chosen": -638.5999755859375,
+      "logps/rejected": -619.7999877929688,
+      "loss": 0.4388,
+      "nll_loss": 0.943359375,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.4850097596645355,
+      "rewards/margins": 2.5679688453674316,
+      "rewards/rejected": -2.085156202316284,
+      "step": 1290
+    },
+    {
+      "epoch": 0.9931245225362872,
+      "grad_norm": 49.408062951712566,
+      "learning_rate": 4.244482173174872e-09,
+      "logits/chosen": -0.09760741889476776,
+      "logits/rejected": -0.031402587890625,
+      "logps/chosen": -593.2000122070312,
+      "logps/rejected": -587.0,
+      "loss": 0.4112,
+      "nll_loss": 0.869140625,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.6004394292831421,
+      "rewards/margins": 2.287890672683716,
+      "rewards/rejected": -1.6857421398162842,
+      "step": 1300
+    },
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": -0.10636549443006516,
+      "eval_logits/rejected": -0.1420053392648697,
+      "eval_logps/chosen": -509.3846130371094,
+      "eval_logps/rejected": -480.6153869628906,
+      "eval_loss": 0.3973870873451233,
+      "eval_nll_loss": 0.9269831776618958,
+      "eval_rewards/accuracies": 0.7211538553237915,
+      "eval_rewards/chosen": 0.2996356785297394,
+      "eval_rewards/margins": 2.412559986114502,
+      "eval_rewards/rejected": -2.112868070602417,
+      "eval_runtime": 8.7861,
+      "eval_samples_per_second": 11.382,
+      "eval_steps_per_second": 1.48,
+      "step": 1309
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1309,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b42a0f6ef699447089e151cd5c5f9f90cac51432a90679868bb708c7ebc9a00
+size 8401

last-checkpoint/zero_to_fp32.py

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