Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: meta-llama/Llama-3.2-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: helpsteer3_llama32_3b_dpo_nemotron_ml
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# helpsteer3_llama32_3b_dpo_nemotron_ml
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the dpo_helpsteer3_llama32_3b_nemotron_ml dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0
+- Datasets 3.6.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 160109785841664.0,
+    "train_loss": 0.5976956401903605,
+    "train_runtime": 14200.9584,
+    "train_samples_per_second": 6.554,
+    "train_steps_per_second": 0.102
+}

chat_template.jinja

@@ -0,0 +1,93 @@
+{{- 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 %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- 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 #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\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 %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,39 @@
+{
+  "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": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "vocab_size": 128256
+}

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": "4.52.4"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6de24935ae1a84fa7c563e800ae6df3fcafe12ff9c49f962807cd216fe35ec
+size 4965841415

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579cb6c398451aea4f437d370cdccf53075178357406ee78fa6183df846ca8fb
+size 1459745184

pytorch_model.bin.index.json

@@ -0,0 +1,262 @@
+{
+  "metadata": {
+    "total_size": 6425499648
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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": "<|eot_id|>"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,2068 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 160109785841664.0,
+    "train_loss": 0.5976956401903605,
+    "train_runtime": 14200.9584,
+    "train_samples_per_second": 6.554,
+    "train_steps_per_second": 0.102
+}

trainer_log.jsonl

@@ -0,0 +1,146 @@
+{"current_steps": 10, "total_steps": 1455, "loss": 0.6926, "accuracy": 0.4078124761581421, "lr": 6.164383561643836e-08, "epoch": 0.0068766923109984095, "percentage": 0.69, "elapsed_time": "0:01:40", "remaining_time": "4:00:58"}
+{"current_steps": 20, "total_steps": 1455, "loss": 0.6939, "accuracy": 0.4843750298023224, "lr": 1.3013698630136985e-07, "epoch": 0.013753384621996819, "percentage": 1.37, "elapsed_time": "0:03:17", "remaining_time": "3:56:18"}
+{"current_steps": 30, "total_steps": 1455, "loss": 0.6928, "accuracy": 0.5046875476837158, "lr": 1.9863013698630135e-07, "epoch": 0.02063007693299523, "percentage": 2.06, "elapsed_time": "0:04:57", "remaining_time": "3:55:54"}
+{"current_steps": 40, "total_steps": 1455, "loss": 0.6936, "accuracy": 0.4859375059604645, "lr": 2.671232876712329e-07, "epoch": 0.027506769243993638, "percentage": 2.75, "elapsed_time": "0:06:36", "remaining_time": "3:53:51"}
+{"current_steps": 50, "total_steps": 1455, "loss": 0.6931, "accuracy": 0.510937511920929, "lr": 3.3561643835616436e-07, "epoch": 0.03438346155499205, "percentage": 3.44, "elapsed_time": "0:08:15", "remaining_time": "3:52:03"}
+{"current_steps": 60, "total_steps": 1455, "loss": 0.6926, "accuracy": 0.510937511920929, "lr": 4.041095890410959e-07, "epoch": 0.04126015386599046, "percentage": 4.12, "elapsed_time": "0:09:55", "remaining_time": "3:50:35"}
+{"current_steps": 70, "total_steps": 1455, "loss": 0.6929, "accuracy": 0.504687488079071, "lr": 4.726027397260274e-07, "epoch": 0.048136846176988865, "percentage": 4.81, "elapsed_time": "0:11:32", "remaining_time": "3:48:27"}
+{"current_steps": 80, "total_steps": 1455, "loss": 0.6907, "accuracy": 0.5718749761581421, "lr": 5.410958904109589e-07, "epoch": 0.055013538487987276, "percentage": 5.5, "elapsed_time": "0:13:09", "remaining_time": "3:46:17"}
+{"current_steps": 90, "total_steps": 1455, "loss": 0.6918, "accuracy": 0.5234375, "lr": 6.095890410958904e-07, "epoch": 0.06189023079898569, "percentage": 6.19, "elapsed_time": "0:14:48", "remaining_time": "3:44:33"}
+{"current_steps": 100, "total_steps": 1455, "loss": 0.6881, "accuracy": 0.5750000476837158, "lr": 6.78082191780822e-07, "epoch": 0.0687669231099841, "percentage": 6.87, "elapsed_time": "0:16:28", "remaining_time": "3:43:08"}
+{"current_steps": 110, "total_steps": 1455, "loss": 0.6889, "accuracy": 0.5562500357627869, "lr": 7.465753424657533e-07, "epoch": 0.07564361542098251, "percentage": 7.56, "elapsed_time": "0:18:05", "remaining_time": "3:41:17"}
+{"current_steps": 120, "total_steps": 1455, "loss": 0.686, "accuracy": 0.5703125, "lr": 8.150684931506849e-07, "epoch": 0.08252030773198092, "percentage": 8.25, "elapsed_time": "0:19:47", "remaining_time": "3:40:07"}
+{"current_steps": 130, "total_steps": 1455, "loss": 0.6825, "accuracy": 0.5765625238418579, "lr": 8.835616438356164e-07, "epoch": 0.08939700004297933, "percentage": 8.93, "elapsed_time": "0:21:25", "remaining_time": "3:38:18"}
+{"current_steps": 140, "total_steps": 1455, "loss": 0.6835, "accuracy": 0.596875011920929, "lr": 9.520547945205479e-07, "epoch": 0.09627369235397773, "percentage": 9.62, "elapsed_time": "0:23:02", "remaining_time": "3:36:23"}
+{"current_steps": 150, "total_steps": 1455, "loss": 0.6789, "accuracy": 0.5828125476837158, "lr": 9.977081741787625e-07, "epoch": 0.10315038466497614, "percentage": 10.31, "elapsed_time": "0:24:42", "remaining_time": "3:35:00"}
+{"current_steps": 160, "total_steps": 1455, "loss": 0.6785, "accuracy": 0.5843750238418579, "lr": 9.90068754774637e-07, "epoch": 0.11002707697597455, "percentage": 11.0, "elapsed_time": "0:26:21", "remaining_time": "3:33:18"}
+{"current_steps": 170, "total_steps": 1455, "loss": 0.6697, "accuracy": 0.6453125476837158, "lr": 9.824293353705118e-07, "epoch": 0.11690376928697296, "percentage": 11.68, "elapsed_time": "0:27:57", "remaining_time": "3:31:21"}
+{"current_steps": 180, "total_steps": 1455, "loss": 0.6673, "accuracy": 0.6093750596046448, "lr": 9.747899159663866e-07, "epoch": 0.12378046159797138, "percentage": 12.37, "elapsed_time": "0:29:35", "remaining_time": "3:29:38"}
+{"current_steps": 190, "total_steps": 1455, "loss": 0.672, "accuracy": 0.6109375357627869, "lr": 9.671504965622611e-07, "epoch": 0.1306571539089698, "percentage": 13.06, "elapsed_time": "0:31:16", "remaining_time": "3:28:11"}
+{"current_steps": 200, "total_steps": 1455, "loss": 0.6656, "accuracy": 0.614062488079071, "lr": 9.59511077158136e-07, "epoch": 0.1375338462199682, "percentage": 13.75, "elapsed_time": "0:32:55", "remaining_time": "3:26:34"}
+{"current_steps": 210, "total_steps": 1455, "loss": 0.6553, "accuracy": 0.628125011920929, "lr": 9.518716577540107e-07, "epoch": 0.1444105385309666, "percentage": 14.43, "elapsed_time": "0:34:33", "remaining_time": "3:24:50"}
+{"current_steps": 220, "total_steps": 1455, "loss": 0.6632, "accuracy": 0.6031250357627869, "lr": 9.442322383498854e-07, "epoch": 0.15128723084196502, "percentage": 15.12, "elapsed_time": "0:36:11", "remaining_time": "3:23:09"}
+{"current_steps": 230, "total_steps": 1455, "loss": 0.6768, "accuracy": 0.606249988079071, "lr": 9.3659281894576e-07, "epoch": 0.15816392315296343, "percentage": 15.81, "elapsed_time": "0:37:49", "remaining_time": "3:21:27"}
+{"current_steps": 240, "total_steps": 1455, "loss": 0.6448, "accuracy": 0.660937488079071, "lr": 9.289533995416348e-07, "epoch": 0.16504061546396184, "percentage": 16.49, "elapsed_time": "0:39:27", "remaining_time": "3:19:47"}
+{"current_steps": 250, "total_steps": 1455, "loss": 0.672, "accuracy": 0.604687511920929, "lr": 9.213139801375095e-07, "epoch": 0.17191730777496025, "percentage": 17.18, "elapsed_time": "0:41:05", "remaining_time": "3:18:04"}
+{"current_steps": 260, "total_steps": 1455, "loss": 0.6455, "accuracy": 0.6234374642372131, "lr": 9.136745607333842e-07, "epoch": 0.17879400008595867, "percentage": 17.87, "elapsed_time": "0:42:43", "remaining_time": "3:16:24"}
+{"current_steps": 270, "total_steps": 1455, "loss": 0.6469, "accuracy": 0.6265625357627869, "lr": 9.060351413292589e-07, "epoch": 0.18567069239695708, "percentage": 18.56, "elapsed_time": "0:44:23", "remaining_time": "3:14:49"}
+{"current_steps": 280, "total_steps": 1455, "loss": 0.637, "accuracy": 0.6578124761581421, "lr": 8.983957219251337e-07, "epoch": 0.19254738470795546, "percentage": 19.24, "elapsed_time": "0:46:01", "remaining_time": "3:13:09"}
+{"current_steps": 290, "total_steps": 1455, "loss": 0.6617, "accuracy": 0.6078125238418579, "lr": 8.907563025210084e-07, "epoch": 0.19942407701895387, "percentage": 19.93, "elapsed_time": "0:47:39", "remaining_time": "3:11:28"}
+{"current_steps": 300, "total_steps": 1455, "loss": 0.6393, "accuracy": 0.6484375, "lr": 8.83116883116883e-07, "epoch": 0.20630076932995228, "percentage": 20.62, "elapsed_time": "0:49:20", "remaining_time": "3:09:56"}
+{"current_steps": 310, "total_steps": 1455, "loss": 0.6353, "accuracy": 0.660937488079071, "lr": 8.754774637127578e-07, "epoch": 0.2131774616409507, "percentage": 21.31, "elapsed_time": "0:50:58", "remaining_time": "3:08:15"}
+{"current_steps": 320, "total_steps": 1455, "loss": 0.6592, "accuracy": 0.604687511920929, "lr": 8.678380443086325e-07, "epoch": 0.2200541539519491, "percentage": 21.99, "elapsed_time": "0:52:34", "remaining_time": "3:06:29"}
+{"current_steps": 330, "total_steps": 1455, "loss": 0.6347, "accuracy": 0.653124988079071, "lr": 8.601986249045072e-07, "epoch": 0.22693084626294752, "percentage": 22.68, "elapsed_time": "0:54:13", "remaining_time": "3:04:50"}
+{"current_steps": 340, "total_steps": 1455, "loss": 0.6401, "accuracy": 0.6484375, "lr": 8.52559205500382e-07, "epoch": 0.23380753857394593, "percentage": 23.37, "elapsed_time": "0:55:50", "remaining_time": "3:03:08"}
+{"current_steps": 350, "total_steps": 1455, "loss": 0.6335, "accuracy": 0.671875, "lr": 8.449197860962567e-07, "epoch": 0.24068423088494434, "percentage": 24.05, "elapsed_time": "0:57:29", "remaining_time": "3:01:30"}
+{"current_steps": 360, "total_steps": 1455, "loss": 0.6413, "accuracy": 0.6359375715255737, "lr": 8.372803666921313e-07, "epoch": 0.24756092319594275, "percentage": 24.74, "elapsed_time": "0:59:06", "remaining_time": "2:59:46"}
+{"current_steps": 370, "total_steps": 1455, "loss": 0.6349, "accuracy": 0.651562511920929, "lr": 8.296409472880061e-07, "epoch": 0.25443761550694116, "percentage": 25.43, "elapsed_time": "1:00:45", "remaining_time": "2:58:08"}
+{"current_steps": 380, "total_steps": 1455, "loss": 0.6278, "accuracy": 0.6578125357627869, "lr": 8.220015278838807e-07, "epoch": 0.2613143078179396, "percentage": 26.12, "elapsed_time": "1:02:22", "remaining_time": "2:56:28"}
+{"current_steps": 390, "total_steps": 1455, "loss": 0.6311, "accuracy": 0.6484375, "lr": 8.143621084797555e-07, "epoch": 0.268191000128938, "percentage": 26.8, "elapsed_time": "1:04:00", "remaining_time": "2:54:47"}
+{"current_steps": 400, "total_steps": 1455, "loss": 0.6176, "accuracy": 0.6703125238418579, "lr": 8.067226890756303e-07, "epoch": 0.2750676924399364, "percentage": 27.49, "elapsed_time": "1:05:38", "remaining_time": "2:53:09"}
+{"current_steps": 410, "total_steps": 1455, "loss": 0.654, "accuracy": 0.6562500596046448, "lr": 7.990832696715049e-07, "epoch": 0.2819443847509348, "percentage": 28.18, "elapsed_time": "1:07:15", "remaining_time": "2:51:24"}
+{"current_steps": 420, "total_steps": 1455, "loss": 0.6166, "accuracy": 0.6484375, "lr": 7.914438502673797e-07, "epoch": 0.2888210770619332, "percentage": 28.87, "elapsed_time": "1:08:53", "remaining_time": "2:49:45"}
+{"current_steps": 430, "total_steps": 1455, "loss": 0.6121, "accuracy": 0.6812499761581421, "lr": 7.838044308632544e-07, "epoch": 0.29569776937293163, "percentage": 29.55, "elapsed_time": "1:10:33", "remaining_time": "2:48:11"}
+{"current_steps": 440, "total_steps": 1455, "loss": 0.6397, "accuracy": 0.65625, "lr": 7.76165011459129e-07, "epoch": 0.30257446168393004, "percentage": 30.24, "elapsed_time": "1:12:12", "remaining_time": "2:46:34"}
+{"current_steps": 450, "total_steps": 1455, "loss": 0.6273, "accuracy": 0.6640625, "lr": 7.685255920550038e-07, "epoch": 0.30945115399492845, "percentage": 30.93, "elapsed_time": "1:13:50", "remaining_time": "2:44:54"}
+{"current_steps": 460, "total_steps": 1455, "loss": 0.6276, "accuracy": 0.6343749761581421, "lr": 7.608861726508786e-07, "epoch": 0.31632784630592686, "percentage": 31.62, "elapsed_time": "1:15:26", "remaining_time": "2:43:10"}
+{"current_steps": 470, "total_steps": 1455, "loss": 0.6153, "accuracy": 0.6609375476837158, "lr": 7.532467532467532e-07, "epoch": 0.3232045386169253, "percentage": 32.3, "elapsed_time": "1:17:03", "remaining_time": "2:41:30"}
+{"current_steps": 480, "total_steps": 1455, "loss": 0.6265, "accuracy": 0.667187511920929, "lr": 7.45607333842628e-07, "epoch": 0.3300812309279237, "percentage": 32.99, "elapsed_time": "1:18:44", "remaining_time": "2:39:55"}
+{"current_steps": 490, "total_steps": 1455, "loss": 0.5946, "accuracy": 0.6828124523162842, "lr": 7.379679144385026e-07, "epoch": 0.3369579232389221, "percentage": 33.68, "elapsed_time": "1:20:22", "remaining_time": "2:38:17"}
+{"current_steps": 500, "total_steps": 1455, "loss": 0.6099, "accuracy": 0.6796875, "lr": 7.303284950343773e-07, "epoch": 0.3438346155499205, "percentage": 34.36, "elapsed_time": "1:22:01", "remaining_time": "2:36:39"}
+{"current_steps": 510, "total_steps": 1455, "loss": 0.6174, "accuracy": 0.660937488079071, "lr": 7.226890756302521e-07, "epoch": 0.3507113078609189, "percentage": 35.05, "elapsed_time": "1:24:04", "remaining_time": "2:35:47"}
+{"current_steps": 520, "total_steps": 1455, "loss": 0.5978, "accuracy": 0.6890624761581421, "lr": 7.150496562261268e-07, "epoch": 0.35758800017191733, "percentage": 35.74, "elapsed_time": "1:25:42", "remaining_time": "2:34:06"}
+{"current_steps": 530, "total_steps": 1455, "loss": 0.5866, "accuracy": 0.7171875238418579, "lr": 7.074102368220015e-07, "epoch": 0.36446469248291574, "percentage": 36.43, "elapsed_time": "1:27:21", "remaining_time": "2:32:27"}
+{"current_steps": 540, "total_steps": 1455, "loss": 0.6108, "accuracy": 0.6937500238418579, "lr": 6.997708174178763e-07, "epoch": 0.37134138479391415, "percentage": 37.11, "elapsed_time": "1:28:57", "remaining_time": "2:30:44"}
+{"current_steps": 550, "total_steps": 1455, "loss": 0.6143, "accuracy": 0.6703125238418579, "lr": 6.92131398013751e-07, "epoch": 0.37821807710491256, "percentage": 37.8, "elapsed_time": "1:30:34", "remaining_time": "2:29:01"}
+{"current_steps": 560, "total_steps": 1455, "loss": 0.6138, "accuracy": 0.6750000715255737, "lr": 6.844919786096256e-07, "epoch": 0.3850947694159109, "percentage": 38.49, "elapsed_time": "1:32:11", "remaining_time": "2:27:20"}
+{"current_steps": 570, "total_steps": 1455, "loss": 0.6166, "accuracy": 0.667187511920929, "lr": 6.768525592055004e-07, "epoch": 0.39197146172690933, "percentage": 39.18, "elapsed_time": "1:33:48", "remaining_time": "2:25:39"}
+{"current_steps": 580, "total_steps": 1455, "loss": 0.5786, "accuracy": 0.6968749761581421, "lr": 6.69213139801375e-07, "epoch": 0.39884815403790774, "percentage": 39.86, "elapsed_time": "1:35:25", "remaining_time": "2:23:57"}
+{"current_steps": 590, "total_steps": 1455, "loss": 0.6123, "accuracy": 0.6640625, "lr": 6.615737203972498e-07, "epoch": 0.40572484634890615, "percentage": 40.55, "elapsed_time": "1:37:00", "remaining_time": "2:22:13"}
+{"current_steps": 600, "total_steps": 1455, "loss": 0.5818, "accuracy": 0.6875, "lr": 6.539343009931245e-07, "epoch": 0.41260153865990457, "percentage": 41.24, "elapsed_time": "1:38:36", "remaining_time": "2:20:30"}
+{"current_steps": 610, "total_steps": 1455, "loss": 0.5839, "accuracy": 0.7078125476837158, "lr": 6.462948815889992e-07, "epoch": 0.419478230970903, "percentage": 41.92, "elapsed_time": "1:40:15", "remaining_time": "2:18:52"}
+{"current_steps": 620, "total_steps": 1455, "loss": 0.6254, "accuracy": 0.6593750715255737, "lr": 6.386554621848739e-07, "epoch": 0.4263549232819014, "percentage": 42.61, "elapsed_time": "1:41:51", "remaining_time": "2:17:10"}
+{"current_steps": 630, "total_steps": 1455, "loss": 0.6031, "accuracy": 0.7062500715255737, "lr": 6.310160427807486e-07, "epoch": 0.4332316155928998, "percentage": 43.3, "elapsed_time": "1:43:28", "remaining_time": "2:15:30"}
+{"current_steps": 640, "total_steps": 1455, "loss": 0.5985, "accuracy": 0.7140624523162842, "lr": 6.233766233766233e-07, "epoch": 0.4401083079038982, "percentage": 43.99, "elapsed_time": "1:45:07", "remaining_time": "2:13:51"}
+{"current_steps": 650, "total_steps": 1455, "loss": 0.599, "accuracy": 0.6578125357627869, "lr": 6.157372039724981e-07, "epoch": 0.4469850002148966, "percentage": 44.67, "elapsed_time": "1:46:42", "remaining_time": "2:12:09"}
+{"current_steps": 660, "total_steps": 1455, "loss": 0.6192, "accuracy": 0.6859375238418579, "lr": 6.080977845683728e-07, "epoch": 0.45386169252589503, "percentage": 45.36, "elapsed_time": "1:48:18", "remaining_time": "2:10:27"}
+{"current_steps": 670, "total_steps": 1455, "loss": 0.5748, "accuracy": 0.6937500238418579, "lr": 6.004583651642475e-07, "epoch": 0.46073838483689344, "percentage": 46.05, "elapsed_time": "1:49:54", "remaining_time": "2:08:46"}
+{"current_steps": 680, "total_steps": 1455, "loss": 0.5868, "accuracy": 0.6843750476837158, "lr": 5.928189457601223e-07, "epoch": 0.46761507714789186, "percentage": 46.74, "elapsed_time": "1:51:31", "remaining_time": "2:07:05"}
+{"current_steps": 690, "total_steps": 1455, "loss": 0.5795, "accuracy": 0.6875, "lr": 5.851795263559969e-07, "epoch": 0.47449176945889027, "percentage": 47.42, "elapsed_time": "1:53:07", "remaining_time": "2:05:25"}
+{"current_steps": 700, "total_steps": 1455, "loss": 0.6131, "accuracy": 0.7015625238418579, "lr": 5.775401069518716e-07, "epoch": 0.4813684617698887, "percentage": 48.11, "elapsed_time": "1:54:41", "remaining_time": "2:03:42"}
+{"current_steps": 710, "total_steps": 1455, "loss": 0.5876, "accuracy": 0.692187488079071, "lr": 5.699006875477463e-07, "epoch": 0.4882451540808871, "percentage": 48.8, "elapsed_time": "1:56:18", "remaining_time": "2:02:02"}
+{"current_steps": 720, "total_steps": 1455, "loss": 0.5791, "accuracy": 0.7000000476837158, "lr": 5.622612681436211e-07, "epoch": 0.4951218463918855, "percentage": 49.48, "elapsed_time": "1:57:55", "remaining_time": "2:00:22"}
+{"current_steps": 730, "total_steps": 1455, "loss": 0.7215, "accuracy": 0.6953125, "lr": 5.546218487394958e-07, "epoch": 0.5019985387028839, "percentage": 50.17, "elapsed_time": "1:59:32", "remaining_time": "1:58:43"}
+{"current_steps": 740, "total_steps": 1455, "loss": 0.5916, "accuracy": 0.6875, "lr": 5.469824293353705e-07, "epoch": 0.5088752310138823, "percentage": 50.86, "elapsed_time": "2:01:08", "remaining_time": "1:57:03"}
+{"current_steps": 750, "total_steps": 1455, "loss": 0.6025, "accuracy": 0.671875, "lr": 5.393430099312452e-07, "epoch": 0.5157519233248807, "percentage": 51.55, "elapsed_time": "2:02:46", "remaining_time": "1:55:24"}
+{"current_steps": 760, "total_steps": 1455, "loss": 0.5554, "accuracy": 0.7125000357627869, "lr": 5.317035905271199e-07, "epoch": 0.5226286156358791, "percentage": 52.23, "elapsed_time": "2:04:23", "remaining_time": "1:53:45"}
+{"current_steps": 770, "total_steps": 1455, "loss": 0.6091, "accuracy": 0.6609375476837158, "lr": 5.240641711229946e-07, "epoch": 0.5295053079468776, "percentage": 52.92, "elapsed_time": "2:05:58", "remaining_time": "1:52:04"}
+{"current_steps": 780, "total_steps": 1455, "loss": 0.5884, "accuracy": 0.7109375, "lr": 5.164247517188694e-07, "epoch": 0.536382000257876, "percentage": 53.61, "elapsed_time": "2:07:34", "remaining_time": "1:50:24"}
+{"current_steps": 790, "total_steps": 1455, "loss": 0.5752, "accuracy": 0.715624988079071, "lr": 5.08785332314744e-07, "epoch": 0.5432586925688744, "percentage": 54.3, "elapsed_time": "2:09:08", "remaining_time": "1:48:42"}
+{"current_steps": 800, "total_steps": 1455, "loss": 0.5837, "accuracy": 0.7171875238418579, "lr": 5.011459129106188e-07, "epoch": 0.5501353848798728, "percentage": 54.98, "elapsed_time": "2:10:43", "remaining_time": "1:47:01"}
+{"current_steps": 810, "total_steps": 1455, "loss": 0.5731, "accuracy": 0.684374988079071, "lr": 4.935064935064935e-07, "epoch": 0.5570120771908712, "percentage": 55.67, "elapsed_time": "2:12:19", "remaining_time": "1:45:21"}
+{"current_steps": 820, "total_steps": 1455, "loss": 0.5683, "accuracy": 0.7140624523162842, "lr": 4.858670741023682e-07, "epoch": 0.5638887695018696, "percentage": 56.36, "elapsed_time": "2:13:55", "remaining_time": "1:43:42"}
+{"current_steps": 830, "total_steps": 1455, "loss": 0.5698, "accuracy": 0.698437511920929, "lr": 4.782276546982429e-07, "epoch": 0.570765461812868, "percentage": 57.04, "elapsed_time": "2:15:31", "remaining_time": "1:42:02"}
+{"current_steps": 840, "total_steps": 1455, "loss": 0.5546, "accuracy": 0.729687511920929, "lr": 4.705882352941176e-07, "epoch": 0.5776421541238664, "percentage": 57.73, "elapsed_time": "2:17:05", "remaining_time": "1:40:21"}
+{"current_steps": 850, "total_steps": 1455, "loss": 0.5735, "accuracy": 0.7265625, "lr": 4.6294881588999233e-07, "epoch": 0.5845188464348648, "percentage": 58.42, "elapsed_time": "2:18:41", "remaining_time": "1:38:42"}
+{"current_steps": 860, "total_steps": 1455, "loss": 0.5697, "accuracy": 0.706250011920929, "lr": 4.553093964858671e-07, "epoch": 0.5913955387458633, "percentage": 59.11, "elapsed_time": "2:20:16", "remaining_time": "1:37:03"}
+{"current_steps": 870, "total_steps": 1455, "loss": 0.5685, "accuracy": 0.7234375476837158, "lr": 4.4766997708174176e-07, "epoch": 0.5982722310568617, "percentage": 59.79, "elapsed_time": "2:21:54", "remaining_time": "1:35:25"}
+{"current_steps": 880, "total_steps": 1455, "loss": 0.5899, "accuracy": 0.6812500357627869, "lr": 4.4003055767761647e-07, "epoch": 0.6051489233678601, "percentage": 60.48, "elapsed_time": "2:23:33", "remaining_time": "1:33:48"}
+{"current_steps": 890, "total_steps": 1455, "loss": 0.5723, "accuracy": 0.715624988079071, "lr": 4.3239113827349124e-07, "epoch": 0.6120256156788585, "percentage": 61.17, "elapsed_time": "2:25:10", "remaining_time": "1:32:10"}
+{"current_steps": 900, "total_steps": 1455, "loss": 0.5815, "accuracy": 0.7140624523162842, "lr": 4.247517188693659e-07, "epoch": 0.6189023079898569, "percentage": 61.86, "elapsed_time": "2:26:48", "remaining_time": "1:30:31"}
+{"current_steps": 910, "total_steps": 1455, "loss": 0.5716, "accuracy": 0.690625011920929, "lr": 4.171122994652406e-07, "epoch": 0.6257790003008553, "percentage": 62.54, "elapsed_time": "2:28:25", "remaining_time": "1:28:53"}
+{"current_steps": 920, "total_steps": 1455, "loss": 0.5365, "accuracy": 0.734375, "lr": 4.094728800611154e-07, "epoch": 0.6326556926118537, "percentage": 63.23, "elapsed_time": "2:30:00", "remaining_time": "1:27:14"}
+{"current_steps": 930, "total_steps": 1455, "loss": 0.532, "accuracy": 0.765625, "lr": 4.0183346065699004e-07, "epoch": 0.6395323849228521, "percentage": 63.92, "elapsed_time": "2:31:36", "remaining_time": "1:25:35"}
+{"current_steps": 940, "total_steps": 1455, "loss": 0.5656, "accuracy": 0.7203125357627869, "lr": 3.9419404125286475e-07, "epoch": 0.6464090772338505, "percentage": 64.6, "elapsed_time": "2:33:13", "remaining_time": "1:23:56"}
+{"current_steps": 950, "total_steps": 1455, "loss": 0.5528, "accuracy": 0.7171875238418579, "lr": 3.865546218487395e-07, "epoch": 0.653285769544849, "percentage": 65.29, "elapsed_time": "2:34:49", "remaining_time": "1:22:18"}
+{"current_steps": 960, "total_steps": 1455, "loss": 0.5699, "accuracy": 0.7000000476837158, "lr": 3.789152024446142e-07, "epoch": 0.6601624618558474, "percentage": 65.98, "elapsed_time": "2:36:25", "remaining_time": "1:20:39"}
+{"current_steps": 970, "total_steps": 1455, "loss": 0.5486, "accuracy": 0.7187500596046448, "lr": 3.712757830404889e-07, "epoch": 0.6670391541668458, "percentage": 66.67, "elapsed_time": "2:38:01", "remaining_time": "1:19:00"}
+{"current_steps": 980, "total_steps": 1455, "loss": 0.575, "accuracy": 0.7078125476837158, "lr": 3.636363636363636e-07, "epoch": 0.6739158464778442, "percentage": 67.35, "elapsed_time": "2:39:38", "remaining_time": "1:17:22"}
+{"current_steps": 990, "total_steps": 1455, "loss": 0.5489, "accuracy": 0.714062511920929, "lr": 3.5599694423223837e-07, "epoch": 0.6807925387888426, "percentage": 68.04, "elapsed_time": "2:41:15", "remaining_time": "1:15:44"}
+{"current_steps": 1000, "total_steps": 1455, "loss": 0.5568, "accuracy": 0.7250000238418579, "lr": 3.4835752482811303e-07, "epoch": 0.687669231099841, "percentage": 68.73, "elapsed_time": "2:42:52", "remaining_time": "1:14:06"}
+{"current_steps": 1010, "total_steps": 1455, "loss": 0.5783, "accuracy": 0.7125000357627869, "lr": 3.4071810542398775e-07, "epoch": 0.6945459234108394, "percentage": 69.42, "elapsed_time": "2:44:52", "remaining_time": "1:12:38"}
+{"current_steps": 1020, "total_steps": 1455, "loss": 0.515, "accuracy": 0.7718750238418579, "lr": 3.330786860198625e-07, "epoch": 0.7014226157218378, "percentage": 70.1, "elapsed_time": "2:46:28", "remaining_time": "1:10:59"}
+{"current_steps": 1030, "total_steps": 1455, "loss": 0.5566, "accuracy": 0.6984374523162842, "lr": 3.2543926661573717e-07, "epoch": 0.7082993080328363, "percentage": 70.79, "elapsed_time": "2:48:03", "remaining_time": "1:09:20"}
+{"current_steps": 1040, "total_steps": 1455, "loss": 0.5525, "accuracy": 0.7218750715255737, "lr": 3.177998472116119e-07, "epoch": 0.7151760003438347, "percentage": 71.48, "elapsed_time": "2:49:41", "remaining_time": "1:07:42"}
+{"current_steps": 1050, "total_steps": 1455, "loss": 0.5688, "accuracy": 0.7000000476837158, "lr": 3.1016042780748665e-07, "epoch": 0.7220526926548331, "percentage": 72.16, "elapsed_time": "2:51:15", "remaining_time": "1:06:03"}
+{"current_steps": 1060, "total_steps": 1455, "loss": 0.5763, "accuracy": 0.7000000476837158, "lr": 3.025210084033613e-07, "epoch": 0.7289293849658315, "percentage": 72.85, "elapsed_time": "2:52:52", "remaining_time": "1:04:25"}
+{"current_steps": 1070, "total_steps": 1455, "loss": 0.5514, "accuracy": 0.721875011920929, "lr": 2.9488158899923603e-07, "epoch": 0.7358060772768299, "percentage": 73.54, "elapsed_time": "2:54:28", "remaining_time": "1:02:46"}
+{"current_steps": 1080, "total_steps": 1455, "loss": 0.57, "accuracy": 0.71875, "lr": 2.872421695951108e-07, "epoch": 0.7426827695878283, "percentage": 74.23, "elapsed_time": "2:56:03", "remaining_time": "1:01:07"}
+{"current_steps": 1090, "total_steps": 1455, "loss": 0.5452, "accuracy": 0.7000000476837158, "lr": 2.7960275019098545e-07, "epoch": 0.7495594618988267, "percentage": 74.91, "elapsed_time": "2:57:40", "remaining_time": "0:59:29"}
+{"current_steps": 1100, "total_steps": 1455, "loss": 0.545, "accuracy": 0.745312511920929, "lr": 2.7196333078686017e-07, "epoch": 0.7564361542098251, "percentage": 75.6, "elapsed_time": "2:59:17", "remaining_time": "0:57:51"}
+{"current_steps": 1110, "total_steps": 1455, "loss": 0.5584, "accuracy": 0.7250000238418579, "lr": 2.6432391138273493e-07, "epoch": 0.7633128465208234, "percentage": 76.29, "elapsed_time": "3:00:53", "remaining_time": "0:56:13"}
+{"current_steps": 1120, "total_steps": 1455, "loss": 0.5507, "accuracy": 0.7468750476837158, "lr": 2.5668449197860965e-07, "epoch": 0.7701895388318218, "percentage": 76.98, "elapsed_time": "3:02:31", "remaining_time": "0:54:35"}
+{"current_steps": 1130, "total_steps": 1455, "loss": 0.5454, "accuracy": 0.7421875596046448, "lr": 2.490450725744843e-07, "epoch": 0.7770662311428203, "percentage": 77.66, "elapsed_time": "3:04:05", "remaining_time": "0:52:56"}
+{"current_steps": 1140, "total_steps": 1455, "loss": 0.5633, "accuracy": 0.7250000238418579, "lr": 2.41405653170359e-07, "epoch": 0.7839429234538187, "percentage": 78.35, "elapsed_time": "3:05:41", "remaining_time": "0:51:18"}
+{"current_steps": 1150, "total_steps": 1455, "loss": 0.549, "accuracy": 0.739062488079071, "lr": 2.3376623376623376e-07, "epoch": 0.7908196157648171, "percentage": 79.04, "elapsed_time": "3:07:18", "remaining_time": "0:49:40"}
+{"current_steps": 1160, "total_steps": 1455, "loss": 0.5541, "accuracy": 0.714062511920929, "lr": 2.2612681436210848e-07, "epoch": 0.7976963080758155, "percentage": 79.73, "elapsed_time": "3:08:54", "remaining_time": "0:48:02"}
+{"current_steps": 1170, "total_steps": 1455, "loss": 0.5306, "accuracy": 0.737500011920929, "lr": 2.184873949579832e-07, "epoch": 0.8045730003868139, "percentage": 80.41, "elapsed_time": "3:10:29", "remaining_time": "0:46:24"}
+{"current_steps": 1180, "total_steps": 1455, "loss": 0.5633, "accuracy": 0.7171875238418579, "lr": 2.1084797555385788e-07, "epoch": 0.8114496926978123, "percentage": 81.1, "elapsed_time": "3:12:06", "remaining_time": "0:44:46"}
+{"current_steps": 1190, "total_steps": 1455, "loss": 0.5521, "accuracy": 0.721875011920929, "lr": 2.0320855614973262e-07, "epoch": 0.8183263850088107, "percentage": 81.79, "elapsed_time": "3:13:43", "remaining_time": "0:43:08"}
+{"current_steps": 1200, "total_steps": 1455, "loss": 0.5702, "accuracy": 0.7093750238418579, "lr": 1.9556913674560733e-07, "epoch": 0.8252030773198091, "percentage": 82.47, "elapsed_time": "3:15:21", "remaining_time": "0:41:30"}
+{"current_steps": 1210, "total_steps": 1455, "loss": 0.543, "accuracy": 0.7593749761581421, "lr": 1.8792971734148204e-07, "epoch": 0.8320797696308075, "percentage": 83.16, "elapsed_time": "3:16:56", "remaining_time": "0:39:52"}
+{"current_steps": 1220, "total_steps": 1455, "loss": 0.5449, "accuracy": 0.739062488079071, "lr": 1.8029029793735676e-07, "epoch": 0.838956461941806, "percentage": 83.85, "elapsed_time": "3:18:31", "remaining_time": "0:38:14"}
+{"current_steps": 1230, "total_steps": 1455, "loss": 0.535, "accuracy": 0.7484375238418579, "lr": 1.7265087853323147e-07, "epoch": 0.8458331542528044, "percentage": 84.54, "elapsed_time": "3:20:09", "remaining_time": "0:36:36"}
+{"current_steps": 1240, "total_steps": 1455, "loss": 0.5723, "accuracy": 0.7109375596046448, "lr": 1.6501145912910618e-07, "epoch": 0.8527098465638028, "percentage": 85.22, "elapsed_time": "3:21:46", "remaining_time": "0:34:59"}
+{"current_steps": 1250, "total_steps": 1455, "loss": 0.5395, "accuracy": 0.745312511920929, "lr": 1.573720397249809e-07, "epoch": 0.8595865388748012, "percentage": 85.91, "elapsed_time": "3:23:21", "remaining_time": "0:33:21"}
+{"current_steps": 1260, "total_steps": 1455, "loss": 0.5582, "accuracy": 0.7328125238418579, "lr": 1.4973262032085558e-07, "epoch": 0.8664632311857996, "percentage": 86.6, "elapsed_time": "3:24:58", "remaining_time": "0:31:43"}
+{"current_steps": 1270, "total_steps": 1455, "loss": 0.5413, "accuracy": 0.7421875, "lr": 1.4209320091673032e-07, "epoch": 0.873339923496798, "percentage": 87.29, "elapsed_time": "3:26:35", "remaining_time": "0:30:05"}
+{"current_steps": 1280, "total_steps": 1455, "loss": 0.5304, "accuracy": 0.7390625476837158, "lr": 1.3445378151260504e-07, "epoch": 0.8802166158077964, "percentage": 87.97, "elapsed_time": "3:28:12", "remaining_time": "0:28:27"}
+{"current_steps": 1290, "total_steps": 1455, "loss": 0.5305, "accuracy": 0.7437500357627869, "lr": 1.2681436210847975e-07, "epoch": 0.8870933081187948, "percentage": 88.66, "elapsed_time": "3:29:49", "remaining_time": "0:26:50"}
+{"current_steps": 1300, "total_steps": 1455, "loss": 0.5503, "accuracy": 0.7234375476837158, "lr": 1.1917494270435446e-07, "epoch": 0.8939700004297932, "percentage": 89.35, "elapsed_time": "3:31:27", "remaining_time": "0:25:12"}
+{"current_steps": 1310, "total_steps": 1455, "loss": 0.5439, "accuracy": 0.721875011920929, "lr": 1.1153552330022918e-07, "epoch": 0.9008466927407917, "percentage": 90.03, "elapsed_time": "3:33:03", "remaining_time": "0:23:34"}
+{"current_steps": 1320, "total_steps": 1455, "loss": 0.5547, "accuracy": 0.7437499761581421, "lr": 1.038961038961039e-07, "epoch": 0.9077233850517901, "percentage": 90.72, "elapsed_time": "3:34:40", "remaining_time": "0:21:57"}
+{"current_steps": 1330, "total_steps": 1455, "loss": 0.5265, "accuracy": 0.7484375238418579, "lr": 9.62566844919786e-08, "epoch": 0.9146000773627885, "percentage": 91.41, "elapsed_time": "3:36:16", "remaining_time": "0:20:19"}
+{"current_steps": 1340, "total_steps": 1455, "loss": 0.5739, "accuracy": 0.7109375596046448, "lr": 8.861726508785332e-08, "epoch": 0.9214767696737869, "percentage": 92.1, "elapsed_time": "3:37:54", "remaining_time": "0:18:42"}
+{"current_steps": 1350, "total_steps": 1455, "loss": 0.5575, "accuracy": 0.71875, "lr": 8.097784568372803e-08, "epoch": 0.9283534619847853, "percentage": 92.78, "elapsed_time": "3:39:32", "remaining_time": "0:17:04"}
+{"current_steps": 1360, "total_steps": 1455, "loss": 0.5149, "accuracy": 0.7828125357627869, "lr": 7.333842627960276e-08, "epoch": 0.9352301542957837, "percentage": 93.47, "elapsed_time": "3:41:09", "remaining_time": "0:15:26"}
+{"current_steps": 1370, "total_steps": 1455, "loss": 0.5774, "accuracy": 0.7015625238418579, "lr": 6.569900687547746e-08, "epoch": 0.9421068466067821, "percentage": 94.16, "elapsed_time": "3:42:47", "remaining_time": "0:13:49"}
+{"current_steps": 1380, "total_steps": 1455, "loss": 0.5551, "accuracy": 0.723437488079071, "lr": 5.805958747135217e-08, "epoch": 0.9489835389177805, "percentage": 94.85, "elapsed_time": "3:44:24", "remaining_time": "0:12:11"}
+{"current_steps": 1390, "total_steps": 1455, "loss": 0.5424, "accuracy": 0.7109375, "lr": 5.042016806722689e-08, "epoch": 0.955860231228779, "percentage": 95.53, "elapsed_time": "3:46:02", "remaining_time": "0:10:34"}
+{"current_steps": 1400, "total_steps": 1455, "loss": 0.5252, "accuracy": 0.753125011920929, "lr": 4.27807486631016e-08, "epoch": 0.9627369235397774, "percentage": 96.22, "elapsed_time": "3:47:37", "remaining_time": "0:08:56"}
+{"current_steps": 1410, "total_steps": 1455, "loss": 0.4938, "accuracy": 0.792187511920929, "lr": 3.514132925897632e-08, "epoch": 0.9696136158507758, "percentage": 96.91, "elapsed_time": "3:49:13", "remaining_time": "0:07:18"}
+{"current_steps": 1420, "total_steps": 1455, "loss": 0.5229, "accuracy": 0.7468750476837158, "lr": 2.750190985485103e-08, "epoch": 0.9764903081617742, "percentage": 97.59, "elapsed_time": "3:50:49", "remaining_time": "0:05:41"}
+{"current_steps": 1430, "total_steps": 1455, "loss": 0.5485, "accuracy": 0.7250000238418579, "lr": 1.9862490450725743e-08, "epoch": 0.9833670004727726, "percentage": 98.28, "elapsed_time": "3:52:24", "remaining_time": "0:04:03"}
+{"current_steps": 1440, "total_steps": 1455, "loss": 0.5481, "accuracy": 0.715624988079071, "lr": 1.2223071046600458e-08, "epoch": 0.990243692783771, "percentage": 98.97, "elapsed_time": "3:54:00", "remaining_time": "0:02:26"}
+{"current_steps": 1450, "total_steps": 1455, "loss": 0.5363, "accuracy": 0.7593749761581421, "lr": 4.583651642475172e-09, "epoch": 0.9971203850947694, "percentage": 99.66, "elapsed_time": "3:55:36", "remaining_time": "0:00:48"}
+{"current_steps": 1455, "total_steps": 1455, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:56:40", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2218 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1455,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0068766923109984095,
+      "grad_norm": 19.513351103252234,
+      "learning_rate": 6.164383561643836e-08,
+      "logits/chosen": 0.036775026470422745,
+      "logits/rejected": 0.046910036355257034,
+      "logps/chosen": -190.58827209472656,
+      "logps/rejected": -191.73072814941406,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4078124761581421,
+      "rewards/chosen": 0.0005772202857770026,
+      "rewards/margins": 0.0013222144916653633,
+      "rewards/rejected": -0.0007449942640960217,
+      "step": 10
+    },
+    {
+      "epoch": 0.013753384621996819,
+      "grad_norm": 19.733804967529558,
+      "learning_rate": 1.3013698630136985e-07,
+      "logits/chosen": 0.05084426328539848,
+      "logits/rejected": 0.05570922791957855,
+      "logps/chosen": -189.29241943359375,
+      "logps/rejected": -189.13442993164062,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4843750298023224,
+      "rewards/chosen": -0.0005333187873475254,
+      "rewards/margins": -0.0012226278195157647,
+      "rewards/rejected": 0.0006893089739605784,
+      "step": 20
+    },
+    {
+      "epoch": 0.02063007693299523,
+      "grad_norm": 20.968724767768286,
+      "learning_rate": 1.9863013698630135e-07,
+      "logits/chosen": 0.07122799009084702,
+      "logits/rejected": 0.059470705687999725,
+      "logps/chosen": -200.34930419921875,
+      "logps/rejected": -197.34397888183594,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5046875476837158,
+      "rewards/chosen": -0.0008399286889471114,
+      "rewards/margins": 0.0011575755197554827,
+      "rewards/rejected": -0.0019975043833255768,
+      "step": 30
+    },
+    {
+      "epoch": 0.027506769243993638,
+      "grad_norm": 22.344037151449587,
+      "learning_rate": 2.671232876712329e-07,
+      "logits/chosen": 0.02660662867128849,
+      "logits/rejected": 0.02818603627383709,
+      "logps/chosen": -198.3375244140625,
+      "logps/rejected": -197.72930908203125,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4859375059604645,
+      "rewards/chosen": -0.0005683950148522854,
+      "rewards/margins": -0.0004704779712483287,
+      "rewards/rejected": -9.791657794266939e-05,
+      "step": 40
+    },
+    {
+      "epoch": 0.03438346155499205,
+      "grad_norm": 20.521372371749262,
+      "learning_rate": 3.3561643835616436e-07,
+      "logits/chosen": 0.06722528487443924,
+      "logits/rejected": 0.08071392774581909,
+      "logps/chosen": -187.2486114501953,
+      "logps/rejected": -185.5479278564453,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.510937511920929,
+      "rewards/chosen": 0.0029008188284933567,
+      "rewards/margins": 0.0005296532763168216,
+      "rewards/rejected": 0.0023711654357612133,
+      "step": 50
+    },
+    {
+      "epoch": 0.04126015386599046,
+      "grad_norm": 22.181250645349447,
+      "learning_rate": 4.041095890410959e-07,
+      "logits/chosen": 0.006281435955315828,
+      "logits/rejected": 0.010298961773514748,
+      "logps/chosen": -198.05947875976562,
+      "logps/rejected": -200.37185668945312,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.510937511920929,
+      "rewards/chosen": 0.006992017850279808,
+      "rewards/margins": 0.0015909502981230617,
+      "rewards/rejected": 0.005401067901402712,
+      "step": 60
+    },
+    {
+      "epoch": 0.048136846176988865,
+      "grad_norm": 19.169872791194972,
+      "learning_rate": 4.726027397260274e-07,
+      "logits/chosen": -0.01618768647313118,
+      "logits/rejected": 0.0075270626693964005,
+      "logps/chosen": -202.3906707763672,
+      "logps/rejected": -200.06686401367188,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.504687488079071,
+      "rewards/chosen": 0.009140972048044205,
+      "rewards/margins": 0.0010492438450455666,
+      "rewards/rejected": 0.008091727271676064,
+      "step": 70
+    },
+    {
+      "epoch": 0.055013538487987276,
+      "grad_norm": 19.758724828653662,
+      "learning_rate": 5.410958904109589e-07,
+      "logits/chosen": 0.06360562890768051,
+      "logits/rejected": 0.054235585033893585,
+      "logps/chosen": -188.7932586669922,
+      "logps/rejected": -184.00587463378906,
+      "loss": 0.6907,
+      "rewards/accuracies": 0.5718749761581421,
+      "rewards/chosen": 0.01619785837829113,
+      "rewards/margins": 0.005430372431874275,
+      "rewards/rejected": 0.010767485946416855,
+      "step": 80
+    },
+    {
+      "epoch": 0.06189023079898569,
+      "grad_norm": 20.213997991248295,
+      "learning_rate": 6.095890410958904e-07,
+      "logits/chosen": 0.042256779968738556,
+      "logits/rejected": 0.03444061055779457,
+      "logps/chosen": -196.16871643066406,
+      "logps/rejected": -194.0621337890625,
+      "loss": 0.6918,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": 0.02520076185464859,
+      "rewards/margins": 0.0032487791031599045,
+      "rewards/rejected": 0.021951984614133835,
+      "step": 90
+    },
+    {
+      "epoch": 0.0687669231099841,
+      "grad_norm": 21.372464813538276,
+      "learning_rate": 6.78082191780822e-07,
+      "logits/chosen": -0.018003107979893684,
+      "logits/rejected": -0.023832082748413086,
+      "logps/chosen": -197.95404052734375,
+      "logps/rejected": -195.9728546142578,
+      "loss": 0.6881,
+      "rewards/accuracies": 0.5750000476837158,
+      "rewards/chosen": 0.046728331595659256,
+      "rewards/margins": 0.011084327474236488,
+      "rewards/rejected": 0.03564400225877762,
+      "step": 100
+    },
+    {
+      "epoch": 0.07564361542098251,
+      "grad_norm": 20.643367976648022,
+      "learning_rate": 7.465753424657533e-07,
+      "logits/chosen": 0.0021628281101584435,
+      "logits/rejected": 0.010397136211395264,
+      "logps/chosen": -191.6479949951172,
+      "logps/rejected": -194.17164611816406,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.5562500357627869,
+      "rewards/chosen": 0.05788281559944153,
+      "rewards/margins": 0.01013133954256773,
+      "rewards/rejected": 0.04775147885084152,
+      "step": 110
+    },
+    {
+      "epoch": 0.08252030773198092,
+      "grad_norm": 21.164397049657207,
+      "learning_rate": 8.150684931506849e-07,
+      "logits/chosen": -0.03978746384382248,
+      "logits/rejected": -0.023968348279595375,
+      "logps/chosen": -200.37274169921875,
+      "logps/rejected": -199.3896942138672,
+      "loss": 0.686,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": 0.07369903475046158,
+      "rewards/margins": 0.016540035605430603,
+      "rewards/rejected": 0.057159002870321274,
+      "step": 120
+    },
+    {
+      "epoch": 0.08939700004297933,
+      "grad_norm": 20.81088307270136,
+      "learning_rate": 8.835616438356164e-07,
+      "logits/chosen": -0.004022962413728237,
+      "logits/rejected": 0.006641650106757879,
+      "logps/chosen": -198.2274627685547,
+      "logps/rejected": -198.31088256835938,
+      "loss": 0.6825,
+      "rewards/accuracies": 0.5765625238418579,
+      "rewards/chosen": 0.07722726464271545,
+      "rewards/margins": 0.024418998509645462,
+      "rewards/rejected": 0.05280826985836029,
+      "step": 130
+    },
+    {
+      "epoch": 0.09627369235397773,
+      "grad_norm": 20.466753738955518,
+      "learning_rate": 9.520547945205479e-07,
+      "logits/chosen": -0.030300267040729523,
+      "logits/rejected": -0.027351014316082,
+      "logps/chosen": -187.5103302001953,
+      "logps/rejected": -186.61094665527344,
+      "loss": 0.6835,
+      "rewards/accuracies": 0.596875011920929,
+      "rewards/chosen": 0.08767089992761612,
+      "rewards/margins": 0.02380959689617157,
+      "rewards/rejected": 0.06386130303144455,
+      "step": 140
+    },
+    {
+      "epoch": 0.10315038466497614,
+      "grad_norm": 21.625750402342522,
+      "learning_rate": 9.977081741787625e-07,
+      "logits/chosen": -0.055144187062978745,
+      "logits/rejected": -0.039117198437452316,
+      "logps/chosen": -194.8080596923828,
+      "logps/rejected": -191.05648803710938,
+      "loss": 0.6789,
+      "rewards/accuracies": 0.5828125476837158,
+      "rewards/chosen": 0.08812759071588516,
+      "rewards/margins": 0.03495479375123978,
+      "rewards/rejected": 0.05317278951406479,
+      "step": 150
+    },
+    {
+      "epoch": 0.11002707697597455,
+      "grad_norm": 22.141057438202445,
+      "learning_rate": 9.90068754774637e-07,
+      "logits/chosen": -0.0353374183177948,
+      "logits/rejected": -0.03970889374613762,
+      "logps/chosen": -191.93936157226562,
+      "logps/rejected": -189.392333984375,
+      "loss": 0.6785,
+      "rewards/accuracies": 0.5843750238418579,
+      "rewards/chosen": 0.08410216122865677,
+      "rewards/margins": 0.038218073546886444,
+      "rewards/rejected": 0.04588409140706062,
+      "step": 160
+    },
+    {
+      "epoch": 0.11690376928697296,
+      "grad_norm": 22.165325017656897,
+      "learning_rate": 9.824293353705118e-07,
+      "logits/chosen": -0.07139798998832703,
+      "logits/rejected": -0.05791984125971794,
+      "logps/chosen": -193.04006958007812,
+      "logps/rejected": -190.68820190429688,
+      "loss": 0.6697,
+      "rewards/accuracies": 0.6453125476837158,
+      "rewards/chosen": 0.09184054285287857,
+      "rewards/margins": 0.0603640116751194,
+      "rewards/rejected": 0.031476523727178574,
+      "step": 170
+    },
+    {
+      "epoch": 0.12378046159797138,
+      "grad_norm": 20.869054112054222,
+      "learning_rate": 9.747899159663866e-07,
+      "logits/chosen": -0.06488940119743347,
+      "logits/rejected": -0.07598251849412918,
+      "logps/chosen": -186.8896484375,
+      "logps/rejected": -184.165283203125,
+      "loss": 0.6673,
+      "rewards/accuracies": 0.6093750596046448,
+      "rewards/chosen": 0.11738091707229614,
+      "rewards/margins": 0.06726492196321487,
+      "rewards/rejected": 0.05011599883437157,
+      "step": 180
+    },
+    {
+      "epoch": 0.1306571539089698,
+      "grad_norm": 22.08932184958235,
+      "learning_rate": 9.671504965622611e-07,
+      "logits/chosen": -0.11792731285095215,
+      "logits/rejected": -0.10376260429620743,
+      "logps/chosen": -194.56234741210938,
+      "logps/rejected": -199.22845458984375,
+      "loss": 0.672,
+      "rewards/accuracies": 0.6109375357627869,
+      "rewards/chosen": 0.14032624661922455,
+      "rewards/margins": 0.06233515962958336,
+      "rewards/rejected": 0.07799109071493149,
+      "step": 190
+    },
+    {
+      "epoch": 0.1375338462199682,
+      "grad_norm": 22.536330265073364,
+      "learning_rate": 9.59511077158136e-07,
+      "logits/chosen": -0.14459270238876343,
+      "logits/rejected": -0.14901231229305267,
+      "logps/chosen": -183.6916961669922,
+      "logps/rejected": -185.39944458007812,
+      "loss": 0.6656,
+      "rewards/accuracies": 0.614062488079071,
+      "rewards/chosen": 0.14809665083885193,
+      "rewards/margins": 0.07755547016859055,
+      "rewards/rejected": 0.07054118812084198,
+      "step": 200
+    },
+    {
+      "epoch": 0.1444105385309666,
+      "grad_norm": 22.36629380857143,
+      "learning_rate": 9.518716577540107e-07,
+      "logits/chosen": -0.15250758826732635,
+      "logits/rejected": -0.1362263560295105,
+      "logps/chosen": -184.0275421142578,
+      "logps/rejected": -182.7425079345703,
+      "loss": 0.6553,
+      "rewards/accuracies": 0.628125011920929,
+      "rewards/chosen": 0.12464237958192825,
+      "rewards/margins": 0.10570727288722992,
+      "rewards/rejected": 0.018935102969408035,
+      "step": 210
+    },
+    {
+      "epoch": 0.15128723084196502,
+      "grad_norm": 22.46675762870305,
+      "learning_rate": 9.442322383498854e-07,
+      "logits/chosen": -0.12515884637832642,
+      "logits/rejected": -0.10421467572450638,
+      "logps/chosen": -182.95225524902344,
+      "logps/rejected": -182.8366241455078,
+      "loss": 0.6632,
+      "rewards/accuracies": 0.6031250357627869,
+      "rewards/chosen": 0.1099134311079979,
+      "rewards/margins": 0.08599118143320084,
+      "rewards/rejected": 0.02392224781215191,
+      "step": 220
+    },
+    {
+      "epoch": 0.15816392315296343,
+      "grad_norm": 21.12786861273902,
+      "learning_rate": 9.3659281894576e-07,
+      "logits/chosen": -0.17644798755645752,
+      "logits/rejected": -0.16624829173088074,
+      "logps/chosen": -188.5326385498047,
+      "logps/rejected": -194.2169952392578,
+      "loss": 0.6768,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": 0.08918297290802002,
+      "rewards/margins": 0.07856127619743347,
+      "rewards/rejected": 0.01062170509248972,
+      "step": 230
+    },
+    {
+      "epoch": 0.16504061546396184,
+      "grad_norm": 26.07540917024713,
+      "learning_rate": 9.289533995416348e-07,
+      "logits/chosen": -0.15431278944015503,
+      "logits/rejected": -0.12972977757453918,
+      "logps/chosen": -194.038818359375,
+      "logps/rejected": -197.2062530517578,
+      "loss": 0.6448,
+      "rewards/accuracies": 0.660937488079071,
+      "rewards/chosen": 0.08370951563119888,
+      "rewards/margins": 0.13731984794139862,
+      "rewards/rejected": -0.053610339760780334,
+      "step": 240
+    },
+    {
+      "epoch": 0.17191730777496025,
+      "grad_norm": 24.572284116149454,
+      "learning_rate": 9.213139801375095e-07,
+      "logits/chosen": -0.15322308242321014,
+      "logits/rejected": -0.13083471357822418,
+      "logps/chosen": -195.24945068359375,
+      "logps/rejected": -192.50152587890625,
+      "loss": 0.672,
+      "rewards/accuracies": 0.604687511920929,
+      "rewards/chosen": 0.03577382117509842,
+      "rewards/margins": 0.08709970116615295,
+      "rewards/rejected": -0.05132588744163513,
+      "step": 250
+    },
+    {
+      "epoch": 0.17879400008595867,
+      "grad_norm": 22.465487345289187,
+      "learning_rate": 9.136745607333842e-07,
+      "logits/chosen": -0.21423660218715668,
+      "logits/rejected": -0.20453476905822754,
+      "logps/chosen": -196.3953857421875,
+      "logps/rejected": -196.35653686523438,
+      "loss": 0.6455,
+      "rewards/accuracies": 0.6234374642372131,
+      "rewards/chosen": 0.043278180062770844,
+      "rewards/margins": 0.15055982768535614,
+      "rewards/rejected": -0.10728166252374649,
+      "step": 260
+    },
+    {
+      "epoch": 0.18567069239695708,
+      "grad_norm": 24.171028726439587,
+      "learning_rate": 9.060351413292589e-07,
+      "logits/chosen": -0.16084127128124237,
+      "logits/rejected": -0.1714678704738617,
+      "logps/chosen": -194.72898864746094,
+      "logps/rejected": -192.3715057373047,
+      "loss": 0.6469,
+      "rewards/accuracies": 0.6265625357627869,
+      "rewards/chosen": 0.0378761887550354,
+      "rewards/margins": 0.15679332613945007,
+      "rewards/rejected": -0.11891713738441467,
+      "step": 270
+    },
+    {
+      "epoch": 0.19254738470795546,
+      "grad_norm": 21.694031165646436,
+      "learning_rate": 8.983957219251337e-07,
+      "logits/chosen": -0.15633784234523773,
+      "logits/rejected": -0.139601469039917,
+      "logps/chosen": -196.56454467773438,
+      "logps/rejected": -196.92361450195312,
+      "loss": 0.637,
+      "rewards/accuracies": 0.6578124761581421,
+      "rewards/chosen": 0.03219035267829895,
+      "rewards/margins": 0.17698359489440918,
+      "rewards/rejected": -0.14479324221611023,
+      "step": 280
+    },
+    {
+      "epoch": 0.19942407701895387,
+      "grad_norm": 24.551730142560587,
+      "learning_rate": 8.907563025210084e-07,
+      "logits/chosen": -0.17860618233680725,
+      "logits/rejected": -0.172758549451828,
+      "logps/chosen": -191.48568725585938,
+      "logps/rejected": -193.51708984375,
+      "loss": 0.6617,
+      "rewards/accuracies": 0.6078125238418579,
+      "rewards/chosen": 0.02595115639269352,
+      "rewards/margins": 0.1463395208120346,
+      "rewards/rejected": -0.12038837373256683,
+      "step": 290
+    },
+    {
+      "epoch": 0.20630076932995228,
+      "grad_norm": 22.1511663675151,
+      "learning_rate": 8.83116883116883e-07,
+      "logits/chosen": -0.22528919577598572,
+      "logits/rejected": -0.2300284206867218,
+      "logps/chosen": -194.1256103515625,
+      "logps/rejected": -194.8380889892578,
+      "loss": 0.6393,
+      "rewards/accuracies": 0.6484375,
+      "rewards/chosen": 0.05988895148038864,
+      "rewards/margins": 0.19410541653633118,
+      "rewards/rejected": -0.13421647250652313,
+      "step": 300
+    },
+    {
+      "epoch": 0.2131774616409507,
+      "grad_norm": 22.898634448709206,
+      "learning_rate": 8.754774637127578e-07,
+      "logits/chosen": -0.17205068469047546,
+      "logits/rejected": -0.15463976562023163,
+      "logps/chosen": -192.48263549804688,
+      "logps/rejected": -199.1364288330078,
+      "loss": 0.6353,
+      "rewards/accuracies": 0.660937488079071,
+      "rewards/chosen": 0.06124072149395943,
+      "rewards/margins": 0.2011023461818695,
+      "rewards/rejected": -0.139861598610878,
+      "step": 310
+    },
+    {
+      "epoch": 0.2200541539519491,
+      "grad_norm": 21.26291555492832,
+      "learning_rate": 8.678380443086325e-07,
+      "logits/chosen": -0.1845797449350357,
+      "logits/rejected": -0.18274115025997162,
+      "logps/chosen": -194.61219787597656,
+      "logps/rejected": -195.93377685546875,
+      "loss": 0.6592,
+      "rewards/accuracies": 0.604687511920929,
+      "rewards/chosen": 0.0389692559838295,
+      "rewards/margins": 0.1638563871383667,
+      "rewards/rejected": -0.12488711625337601,
+      "step": 320
+    },
+    {
+      "epoch": 0.22693084626294752,
+      "grad_norm": 23.417446659141998,
+      "learning_rate": 8.601986249045072e-07,
+      "logits/chosen": -0.18124790489673615,
+      "logits/rejected": -0.15224400162696838,
+      "logps/chosen": -192.33811950683594,
+      "logps/rejected": -201.81790161132812,
+      "loss": 0.6347,
+      "rewards/accuracies": 0.653124988079071,
+      "rewards/chosen": 0.010530395433306694,
+      "rewards/margins": 0.3004379868507385,
+      "rewards/rejected": -0.2899076044559479,
+      "step": 330
+    },
+    {
+      "epoch": 0.23380753857394593,
+      "grad_norm": 23.853594643071567,
+      "learning_rate": 8.52559205500382e-07,
+      "logits/chosen": -0.15507660806179047,
+      "logits/rejected": -0.1385350376367569,
+      "logps/chosen": -193.850830078125,
+      "logps/rejected": -199.759521484375,
+      "loss": 0.6401,
+      "rewards/accuracies": 0.6484375,
+      "rewards/chosen": -0.01992304064333439,
+      "rewards/margins": 0.19967934489250183,
+      "rewards/rejected": -0.21960237622261047,
+      "step": 340
+    },
+    {
+      "epoch": 0.24068423088494434,
+      "grad_norm": 19.901838633792355,
+      "learning_rate": 8.449197860962567e-07,
+      "logits/chosen": -0.1355869621038437,
+      "logits/rejected": -0.12776578962802887,
+      "logps/chosen": -194.73104858398438,
+      "logps/rejected": -194.59083557128906,
+      "loss": 0.6335,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.022219305858016014,
+      "rewards/margins": 0.22338087856769562,
+      "rewards/rejected": -0.24560019373893738,
+      "step": 350
+    },
+    {
+      "epoch": 0.24756092319594275,
+      "grad_norm": 25.638966187406425,
+      "learning_rate": 8.372803666921313e-07,
+      "logits/chosen": -0.15089087188243866,
+      "logits/rejected": -0.1559664011001587,
+      "logps/chosen": -190.36236572265625,
+      "logps/rejected": -189.7425537109375,
+      "loss": 0.6413,
+      "rewards/accuracies": 0.6359375715255737,
+      "rewards/chosen": -0.05937535688281059,
+      "rewards/margins": 0.2122623175382614,
+      "rewards/rejected": -0.2716377079486847,
+      "step": 360
+    },
+    {
+      "epoch": 0.25443761550694116,
+      "grad_norm": 19.325413063698168,
+      "learning_rate": 8.296409472880061e-07,
+      "logits/chosen": -0.11108885705471039,
+      "logits/rejected": -0.08246968686580658,
+      "logps/chosen": -192.77230834960938,
+      "logps/rejected": -197.00479125976562,
+      "loss": 0.6349,
+      "rewards/accuracies": 0.651562511920929,
+      "rewards/chosen": -0.07588831335306168,
+      "rewards/margins": 0.23621290922164917,
+      "rewards/rejected": -0.31210121512413025,
+      "step": 370
+    },
+    {
+      "epoch": 0.2613143078179396,
+      "grad_norm": 22.275308373094646,
+      "learning_rate": 8.220015278838807e-07,
+      "logits/chosen": -0.13851581513881683,
+      "logits/rejected": -0.12797267735004425,
+      "logps/chosen": -202.27577209472656,
+      "logps/rejected": -202.86090087890625,
+      "loss": 0.6278,
+      "rewards/accuracies": 0.6578125357627869,
+      "rewards/chosen": -0.08238591253757477,
+      "rewards/margins": 0.2427002489566803,
+      "rewards/rejected": -0.32508617639541626,
+      "step": 380
+    },
+    {
+      "epoch": 0.268191000128938,
+      "grad_norm": 22.17811856676897,
+      "learning_rate": 8.143621084797555e-07,
+      "logits/chosen": -0.17540393769741058,
+      "logits/rejected": -0.1724541336297989,
+      "logps/chosen": -188.11595153808594,
+      "logps/rejected": -193.10107421875,
+      "loss": 0.6311,
+      "rewards/accuracies": 0.6484375,
+      "rewards/chosen": -0.09082019329071045,
+      "rewards/margins": 0.2361401468515396,
+      "rewards/rejected": -0.32696035504341125,
+      "step": 390
+    },
+    {
+      "epoch": 0.2750676924399364,
+      "grad_norm": 22.797709692683508,
+      "learning_rate": 8.067226890756303e-07,
+      "logits/chosen": -0.17259512841701508,
+      "logits/rejected": -0.16403602063655853,
+      "logps/chosen": -191.74493408203125,
+      "logps/rejected": -199.08279418945312,
+      "loss": 0.6176,
+      "rewards/accuracies": 0.6703125238418579,
+      "rewards/chosen": -0.12271551042795181,
+      "rewards/margins": 0.2966160476207733,
+      "rewards/rejected": -0.41933155059814453,
+      "step": 400
+    },
+    {
+      "epoch": 0.2819443847509348,
+      "grad_norm": 20.345985795599848,
+      "learning_rate": 7.990832696715049e-07,
+      "logits/chosen": -0.16652648150920868,
+      "logits/rejected": -0.1538589745759964,
+      "logps/chosen": -195.2452392578125,
+      "logps/rejected": -201.4396209716797,
+      "loss": 0.654,
+      "rewards/accuracies": 0.6562500596046448,
+      "rewards/chosen": -0.1387416571378708,
+      "rewards/margins": 0.19358447194099426,
+      "rewards/rejected": -0.33232617378234863,
+      "step": 410
+    },
+    {
+      "epoch": 0.2888210770619332,
+      "grad_norm": 22.597861375165436,
+      "learning_rate": 7.914438502673797e-07,
+      "logits/chosen": -0.19070886075496674,
+      "logits/rejected": -0.1932705044746399,
+      "logps/chosen": -189.9697265625,
+      "logps/rejected": -193.302734375,
+      "loss": 0.6166,
+      "rewards/accuracies": 0.6484375,
+      "rewards/chosen": -0.07254549115896225,
+      "rewards/margins": 0.27427053451538086,
+      "rewards/rejected": -0.3468160331249237,
+      "step": 420
+    },
+    {
+      "epoch": 0.29569776937293163,
+      "grad_norm": 19.163014642636924,
+      "learning_rate": 7.838044308632544e-07,
+      "logits/chosen": -0.19799278676509857,
+      "logits/rejected": -0.1733386218547821,
+      "logps/chosen": -189.64312744140625,
+      "logps/rejected": -192.6612548828125,
+      "loss": 0.6121,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.10480398684740067,
+      "rewards/margins": 0.3255974352359772,
+      "rewards/rejected": -0.43040144443511963,
+      "step": 430
+    },
+    {
+      "epoch": 0.30257446168393004,
+      "grad_norm": 23.83020212258771,
+      "learning_rate": 7.76165011459129e-07,
+      "logits/chosen": -0.23343642055988312,
+      "logits/rejected": -0.21432968974113464,
+      "logps/chosen": -190.7268829345703,
+      "logps/rejected": -194.999267578125,
+      "loss": 0.6397,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.1279398649930954,
+      "rewards/margins": 0.24956779181957245,
+      "rewards/rejected": -0.37750762701034546,
+      "step": 440
+    },
+    {
+      "epoch": 0.30945115399492845,
+      "grad_norm": 24.165057101867006,
+      "learning_rate": 7.685255920550038e-07,
+      "logits/chosen": -0.2023199200630188,
+      "logits/rejected": -0.19855788350105286,
+      "logps/chosen": -198.74795532226562,
+      "logps/rejected": -198.89248657226562,
+      "loss": 0.6273,
+      "rewards/accuracies": 0.6640625,
+      "rewards/chosen": -0.10882572084665298,
+      "rewards/margins": 0.29104942083358765,
+      "rewards/rejected": -0.39987513422966003,
+      "step": 450
+    },
+    {
+      "epoch": 0.31632784630592686,
+      "grad_norm": 19.17712769364233,
+      "learning_rate": 7.608861726508786e-07,
+      "logits/chosen": -0.23141232132911682,
+      "logits/rejected": -0.1951158493757248,
+      "logps/chosen": -189.33047485351562,
+      "logps/rejected": -193.03457641601562,
+      "loss": 0.6276,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": -0.11822903901338577,
+      "rewards/margins": 0.27355122566223145,
+      "rewards/rejected": -0.3917802572250366,
+      "step": 460
+    },
+    {
+      "epoch": 0.3232045386169253,
+      "grad_norm": 22.019435639102824,
+      "learning_rate": 7.532467532467532e-07,
+      "logits/chosen": -0.18933194875717163,
+      "logits/rejected": -0.1771559715270996,
+      "logps/chosen": -186.64694213867188,
+      "logps/rejected": -192.64498901367188,
+      "loss": 0.6153,
+      "rewards/accuracies": 0.6609375476837158,
+      "rewards/chosen": -0.13781782984733582,
+      "rewards/margins": 0.3126053214073181,
+      "rewards/rejected": -0.45042312145233154,
+      "step": 470
+    },
+    {
+      "epoch": 0.3300812309279237,
+      "grad_norm": 23.981246146235584,
+      "learning_rate": 7.45607333842628e-07,
+      "logits/chosen": -0.18081098794937134,
+      "logits/rejected": -0.159798726439476,
+      "logps/chosen": -196.7408905029297,
+      "logps/rejected": -201.7342071533203,
+      "loss": 0.6265,
+      "rewards/accuracies": 0.667187511920929,
+      "rewards/chosen": -0.14344578981399536,
+      "rewards/margins": 0.3393925428390503,
+      "rewards/rejected": -0.48283830285072327,
+      "step": 480
+    },
+    {
+      "epoch": 0.3369579232389221,
+      "grad_norm": 21.768637428940725,
+      "learning_rate": 7.379679144385026e-07,
+      "logits/chosen": -0.19270475208759308,
+      "logits/rejected": -0.17529691755771637,
+      "logps/chosen": -196.528564453125,
+      "logps/rejected": -198.35684204101562,
+      "loss": 0.5946,
+      "rewards/accuracies": 0.6828124523162842,
+      "rewards/chosen": -0.10522855073213577,
+      "rewards/margins": 0.3783465623855591,
+      "rewards/rejected": -0.48357510566711426,
+      "step": 490
+    },
+    {
+      "epoch": 0.3438346155499205,
+      "grad_norm": 24.44973419066558,
+      "learning_rate": 7.303284950343773e-07,
+      "logits/chosen": -0.23971419036388397,
+      "logits/rejected": -0.20786018669605255,
+      "logps/chosen": -197.9569854736328,
+      "logps/rejected": -203.95391845703125,
+      "loss": 0.6099,
+      "rewards/accuracies": 0.6796875,
+      "rewards/chosen": -0.19895704090595245,
+      "rewards/margins": 0.350207656621933,
+      "rewards/rejected": -0.5491647124290466,
+      "step": 500
+    },
+    {
+      "epoch": 0.3507113078609189,
+      "grad_norm": 20.47563026640517,
+      "learning_rate": 7.226890756302521e-07,
+      "logits/chosen": -0.23047102987766266,
+      "logits/rejected": -0.20306196808815002,
+      "logps/chosen": -185.67425537109375,
+      "logps/rejected": -194.40451049804688,
+      "loss": 0.6174,
+      "rewards/accuracies": 0.660937488079071,
+      "rewards/chosen": -0.12340579181909561,
+      "rewards/margins": 0.32509928941726685,
+      "rewards/rejected": -0.44850510358810425,
+      "step": 510
+    },
+    {
+      "epoch": 0.35758800017191733,
+      "grad_norm": 25.454418717569137,
+      "learning_rate": 7.150496562261268e-07,
+      "logits/chosen": -0.1873900145292282,
+      "logits/rejected": -0.15569299459457397,
+      "logps/chosen": -192.04225158691406,
+      "logps/rejected": -197.125732421875,
+      "loss": 0.5978,
+      "rewards/accuracies": 0.6890624761581421,
+      "rewards/chosen": -0.13839715719223022,
+      "rewards/margins": 0.3862819969654083,
+      "rewards/rejected": -0.5246791243553162,
+      "step": 520
+    },
+    {
+      "epoch": 0.36446469248291574,
+      "grad_norm": 24.079811094829985,
+      "learning_rate": 7.074102368220015e-07,
+      "logits/chosen": -0.17220811545848846,
+      "logits/rejected": -0.13604801893234253,
+      "logps/chosen": -195.03099060058594,
+      "logps/rejected": -202.47994995117188,
+      "loss": 0.5866,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": -0.1480688452720642,
+      "rewards/margins": 0.4154379665851593,
+      "rewards/rejected": -0.5635067224502563,
+      "step": 530
+    },
+    {
+      "epoch": 0.37134138479391415,
+      "grad_norm": 23.58498750162372,
+      "learning_rate": 6.997708174178763e-07,
+      "logits/chosen": -0.18907414376735687,
+      "logits/rejected": -0.1850075125694275,
+      "logps/chosen": -195.14674377441406,
+      "logps/rejected": -201.75511169433594,
+      "loss": 0.6108,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.16248857975006104,
+      "rewards/margins": 0.37109190225601196,
+      "rewards/rejected": -0.5335805416107178,
+      "step": 540
+    },
+    {
+      "epoch": 0.37821807710491256,
+      "grad_norm": 21.771702608666157,
+      "learning_rate": 6.92131398013751e-07,
+      "logits/chosen": -0.2303890883922577,
+      "logits/rejected": -0.18967962265014648,
+      "logps/chosen": -195.48226928710938,
+      "logps/rejected": -203.158447265625,
+      "loss": 0.6143,
+      "rewards/accuracies": 0.6703125238418579,
+      "rewards/chosen": -0.1789567768573761,
+      "rewards/margins": 0.3507557511329651,
+      "rewards/rejected": -0.5297124981880188,
+      "step": 550
+    },
+    {
+      "epoch": 0.3850947694159109,
+      "grad_norm": 22.729561095188803,
+      "learning_rate": 6.844919786096256e-07,
+      "logits/chosen": -0.20701324939727783,
+      "logits/rejected": -0.18544885516166687,
+      "logps/chosen": -198.18287658691406,
+      "logps/rejected": -206.41525268554688,
+      "loss": 0.6138,
+      "rewards/accuracies": 0.6750000715255737,
+      "rewards/chosen": -0.1394013613462448,
+      "rewards/margins": 0.3607535660266876,
+      "rewards/rejected": -0.500154972076416,
+      "step": 560
+    },
+    {
+      "epoch": 0.39197146172690933,
+      "grad_norm": 21.747354835708766,
+      "learning_rate": 6.768525592055004e-07,
+      "logits/chosen": -0.19353720545768738,
+      "logits/rejected": -0.17840342223644257,
+      "logps/chosen": -186.3765869140625,
+      "logps/rejected": -196.66709899902344,
+      "loss": 0.6166,
+      "rewards/accuracies": 0.667187511920929,
+      "rewards/chosen": -0.19582639634609222,
+      "rewards/margins": 0.3339621126651764,
+      "rewards/rejected": -0.5297885537147522,
+      "step": 570
+    },
+    {
+      "epoch": 0.39884815403790774,
+      "grad_norm": 20.847290517267425,
+      "learning_rate": 6.69213139801375e-07,
+      "logits/chosen": -0.20126751065254211,
+      "logits/rejected": -0.1916297972202301,
+      "logps/chosen": -195.2719268798828,
+      "logps/rejected": -197.80516052246094,
+      "loss": 0.5786,
+      "rewards/accuracies": 0.6968749761581421,
+      "rewards/chosen": -0.1558343470096588,
+      "rewards/margins": 0.4313123822212219,
+      "rewards/rejected": -0.5871467590332031,
+      "step": 580
+    },
+    {
+      "epoch": 0.40572484634890615,
+      "grad_norm": 25.220349314015735,
+      "learning_rate": 6.615737203972498e-07,
+      "logits/chosen": -0.21005675196647644,
+      "logits/rejected": -0.18306328356266022,
+      "logps/chosen": -201.1265869140625,
+      "logps/rejected": -206.52740478515625,
+      "loss": 0.6123,
+      "rewards/accuracies": 0.6640625,
+      "rewards/chosen": -0.14514455199241638,
+      "rewards/margins": 0.37125253677368164,
+      "rewards/rejected": -0.5163971185684204,
+      "step": 590
+    },
+    {
+      "epoch": 0.41260153865990457,
+      "grad_norm": 23.09878281707089,
+      "learning_rate": 6.539343009931245e-07,
+      "logits/chosen": -0.2232796549797058,
+      "logits/rejected": -0.20235514640808105,
+      "logps/chosen": -197.15594482421875,
+      "logps/rejected": -204.2799530029297,
+      "loss": 0.5818,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.10441678762435913,
+      "rewards/margins": 0.4412200152873993,
+      "rewards/rejected": -0.5456368327140808,
+      "step": 600
+    },
+    {
+      "epoch": 0.419478230970903,
+      "grad_norm": 21.299223036157755,
+      "learning_rate": 6.462948815889992e-07,
+      "logits/chosen": -0.19436593353748322,
+      "logits/rejected": -0.1735837459564209,
+      "logps/chosen": -192.80274963378906,
+      "logps/rejected": -206.69189453125,
+      "loss": 0.5839,
+      "rewards/accuracies": 0.7078125476837158,
+      "rewards/chosen": -0.16161832213401794,
+      "rewards/margins": 0.43346843123435974,
+      "rewards/rejected": -0.5950866937637329,
+      "step": 610
+    },
+    {
+      "epoch": 0.4263549232819014,
+      "grad_norm": 23.27788758526324,
+      "learning_rate": 6.386554621848739e-07,
+      "logits/chosen": -0.20898228883743286,
+      "logits/rejected": -0.18023236095905304,
+      "logps/chosen": -202.06637573242188,
+      "logps/rejected": -208.60118103027344,
+      "loss": 0.6254,
+      "rewards/accuracies": 0.6593750715255737,
+      "rewards/chosen": -0.18689092993736267,
+      "rewards/margins": 0.35333251953125,
+      "rewards/rejected": -0.5402234792709351,
+      "step": 620
+    },
+    {
+      "epoch": 0.4332316155928998,
+      "grad_norm": 19.046089044171406,
+      "learning_rate": 6.310160427807486e-07,
+      "logits/chosen": -0.2245250940322876,
+      "logits/rejected": -0.20658770203590393,
+      "logps/chosen": -193.53053283691406,
+      "logps/rejected": -202.41139221191406,
+      "loss": 0.6031,
+      "rewards/accuracies": 0.7062500715255737,
+      "rewards/chosen": -0.2109271138906479,
+      "rewards/margins": 0.42086154222488403,
+      "rewards/rejected": -0.6317886114120483,
+      "step": 630
+    },
+    {
+      "epoch": 0.4401083079038982,
+      "grad_norm": 22.096797282994814,
+      "learning_rate": 6.233766233766233e-07,
+      "logits/chosen": -0.2112444043159485,
+      "logits/rejected": -0.20102985203266144,
+      "logps/chosen": -198.9567413330078,
+      "logps/rejected": -202.45970153808594,
+      "loss": 0.5985,
+      "rewards/accuracies": 0.7140624523162842,
+      "rewards/chosen": -0.16410329937934875,
+      "rewards/margins": 0.40336376428604126,
+      "rewards/rejected": -0.5674670338630676,
+      "step": 640
+    },
+    {
+      "epoch": 0.4469850002148966,
+      "grad_norm": 24.894702297139187,
+      "learning_rate": 6.157372039724981e-07,
+      "logits/chosen": -0.24385106563568115,
+      "logits/rejected": -0.2102491557598114,
+      "logps/chosen": -204.98455810546875,
+      "logps/rejected": -211.8107147216797,
+      "loss": 0.599,
+      "rewards/accuracies": 0.6578125357627869,
+      "rewards/chosen": -0.2059740573167801,
+      "rewards/margins": 0.4995943307876587,
+      "rewards/rejected": -0.7055683732032776,
+      "step": 650
+    },
+    {
+      "epoch": 0.45386169252589503,
+      "grad_norm": 22.68581004612934,
+      "learning_rate": 6.080977845683728e-07,
+      "logits/chosen": -0.21157239377498627,
+      "logits/rejected": -0.1900298148393631,
+      "logps/chosen": -188.3769073486328,
+      "logps/rejected": -193.0936279296875,
+      "loss": 0.6192,
+      "rewards/accuracies": 0.6859375238418579,
+      "rewards/chosen": -0.22981426119804382,
+      "rewards/margins": 0.36119741201400757,
+      "rewards/rejected": -0.591011643409729,
+      "step": 660
+    },
+    {
+      "epoch": 0.46073838483689344,
+      "grad_norm": 20.403756461942695,
+      "learning_rate": 6.004583651642475e-07,
+      "logits/chosen": -0.21049100160598755,
+      "logits/rejected": -0.1666809320449829,
+      "logps/chosen": -197.26670837402344,
+      "logps/rejected": -201.7057342529297,
+      "loss": 0.5748,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.16547085344791412,
+      "rewards/margins": 0.5076817274093628,
+      "rewards/rejected": -0.6731526255607605,
+      "step": 670
+    },
+    {
+      "epoch": 0.46761507714789186,
+      "grad_norm": 21.094570180421684,
+      "learning_rate": 5.928189457601223e-07,
+      "logits/chosen": -0.21226650476455688,
+      "logits/rejected": -0.1999017894268036,
+      "logps/chosen": -199.63485717773438,
+      "logps/rejected": -206.0372314453125,
+      "loss": 0.5868,
+      "rewards/accuracies": 0.6843750476837158,
+      "rewards/chosen": -0.1587166041135788,
+      "rewards/margins": 0.4724137485027313,
+      "rewards/rejected": -0.6311303377151489,
+      "step": 680
+    },
+    {
+      "epoch": 0.47449176945889027,
+      "grad_norm": 19.759234266931482,
+      "learning_rate": 5.851795263559969e-07,
+      "logits/chosen": -0.21826893091201782,
+      "logits/rejected": -0.1906730979681015,
+      "logps/chosen": -192.1505126953125,
+      "logps/rejected": -197.7865447998047,
+      "loss": 0.5795,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.1622937172651291,
+      "rewards/margins": 0.4853915572166443,
+      "rewards/rejected": -0.6476852297782898,
+      "step": 690
+    },
+    {
+      "epoch": 0.4813684617698887,
+      "grad_norm": 23.644038409945107,
+      "learning_rate": 5.775401069518716e-07,
+      "logits/chosen": -0.22725778818130493,
+      "logits/rejected": -0.22313261032104492,
+      "logps/chosen": -197.45359802246094,
+      "logps/rejected": -204.32212829589844,
+      "loss": 0.6131,
+      "rewards/accuracies": 0.7015625238418579,
+      "rewards/chosen": -0.20547083020210266,
+      "rewards/margins": 0.406261146068573,
+      "rewards/rejected": -0.611732006072998,
+      "step": 700
+    },
+    {
+      "epoch": 0.4882451540808871,
+      "grad_norm": 24.828384695442697,
+      "learning_rate": 5.699006875477463e-07,
+      "logits/chosen": -0.26735788583755493,
+      "logits/rejected": -0.2615441083908081,
+      "logps/chosen": -194.3697052001953,
+      "logps/rejected": -199.2198486328125,
+      "loss": 0.5876,
+      "rewards/accuracies": 0.692187488079071,
+      "rewards/chosen": -0.15525513887405396,
+      "rewards/margins": 0.46965569257736206,
+      "rewards/rejected": -0.624910831451416,
+      "step": 710
+    },
+    {
+      "epoch": 0.4951218463918855,
+      "grad_norm": 25.35095914324955,
+      "learning_rate": 5.622612681436211e-07,
+      "logits/chosen": -0.28218579292297363,
+      "logits/rejected": -0.24854585528373718,
+      "logps/chosen": -194.7863006591797,
+      "logps/rejected": -206.6715087890625,
+      "loss": 0.5791,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.16084975004196167,
+      "rewards/margins": 0.49476325511932373,
+      "rewards/rejected": -0.6556130647659302,
+      "step": 720
+    },
+    {
+      "epoch": 0.5019985387028839,
+      "grad_norm": 22.80592965472249,
+      "learning_rate": 5.546218487394958e-07,
+      "logits/chosen": -0.2643795609474182,
+      "logits/rejected": -0.23982766270637512,
+      "logps/chosen": -207.25701904296875,
+      "logps/rejected": -213.31893920898438,
+      "loss": 0.7215,
+      "rewards/accuracies": 0.6953125,
+      "rewards/chosen": -0.31397566199302673,
+      "rewards/margins": 0.3858318328857422,
+      "rewards/rejected": -0.6998074650764465,
+      "step": 730
+    },
+    {
+      "epoch": 0.5088752310138823,
+      "grad_norm": 21.365270293353195,
+      "learning_rate": 5.469824293353705e-07,
+      "logits/chosen": -0.3060339391231537,
+      "logits/rejected": -0.27944815158843994,
+      "logps/chosen": -199.2218780517578,
+      "logps/rejected": -207.60980224609375,
+      "loss": 0.5916,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.21099844574928284,
+      "rewards/margins": 0.4499368667602539,
+      "rewards/rejected": -0.6609352827072144,
+      "step": 740
+    },
+    {
+      "epoch": 0.5157519233248807,
+      "grad_norm": 24.66364313570442,
+      "learning_rate": 5.393430099312452e-07,
+      "logits/chosen": -0.25179368257522583,
+      "logits/rejected": -0.2336534559726715,
+      "logps/chosen": -195.29815673828125,
+      "logps/rejected": -199.34864807128906,
+      "loss": 0.6025,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.22294992208480835,
+      "rewards/margins": 0.449633926153183,
+      "rewards/rejected": -0.6725838780403137,
+      "step": 750
+    },
+    {
+      "epoch": 0.5226286156358791,
+      "grad_norm": 21.696519274645965,
+      "learning_rate": 5.317035905271199e-07,
+      "logits/chosen": -0.23188501596450806,
+      "logits/rejected": -0.18740838766098022,
+      "logps/chosen": -194.13967895507812,
+      "logps/rejected": -205.78663635253906,
+      "loss": 0.5554,
+      "rewards/accuracies": 0.7125000357627869,
+      "rewards/chosen": -0.19764624536037445,
+      "rewards/margins": 0.5703191161155701,
+      "rewards/rejected": -0.7679654359817505,
+      "step": 760
+    },
+    {
+      "epoch": 0.5295053079468776,
+      "grad_norm": 19.823323655353022,
+      "learning_rate": 5.240641711229946e-07,
+      "logits/chosen": -0.22654050588607788,
+      "logits/rejected": -0.21553871035575867,
+      "logps/chosen": -195.4784698486328,
+      "logps/rejected": -201.73641967773438,
+      "loss": 0.6091,
+      "rewards/accuracies": 0.6609375476837158,
+      "rewards/chosen": -0.24171432852745056,
+      "rewards/margins": 0.4162150025367737,
+      "rewards/rejected": -0.6579293012619019,
+      "step": 770
+    },
+    {
+      "epoch": 0.536382000257876,
+      "grad_norm": 27.677161536481233,
+      "learning_rate": 5.164247517188694e-07,
+      "logits/chosen": -0.25750795006752014,
+      "logits/rejected": -0.21803677082061768,
+      "logps/chosen": -189.33285522460938,
+      "logps/rejected": -200.5758056640625,
+      "loss": 0.5884,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": -0.2196999341249466,
+      "rewards/margins": 0.5162926316261292,
+      "rewards/rejected": -0.7359925508499146,
+      "step": 780
+    },
+    {
+      "epoch": 0.5432586925688744,
+      "grad_norm": 23.869787766709965,
+      "learning_rate": 5.08785332314744e-07,
+      "logits/chosen": -0.22552648186683655,
+      "logits/rejected": -0.2141103446483612,
+      "logps/chosen": -198.36676025390625,
+      "logps/rejected": -209.24111938476562,
+      "loss": 0.5752,
+      "rewards/accuracies": 0.715624988079071,
+      "rewards/chosen": -0.22112296521663666,
+      "rewards/margins": 0.5205415487289429,
+      "rewards/rejected": -0.7416645288467407,
+      "step": 790
+    },
+    {
+      "epoch": 0.5501353848798728,
+      "grad_norm": 21.442740342884818,
+      "learning_rate": 5.011459129106188e-07,
+      "logits/chosen": -0.24971872568130493,
+      "logits/rejected": -0.23532649874687195,
+      "logps/chosen": -195.80618286132812,
+      "logps/rejected": -204.13272094726562,
+      "loss": 0.5837,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": -0.21100682020187378,
+      "rewards/margins": 0.48472172021865845,
+      "rewards/rejected": -0.695728600025177,
+      "step": 800
+    },
+    {
+      "epoch": 0.5570120771908712,
+      "grad_norm": 23.649465420938917,
+      "learning_rate": 4.935064935064935e-07,
+      "logits/chosen": -0.20772293210029602,
+      "logits/rejected": -0.1990753710269928,
+      "logps/chosen": -190.77322387695312,
+      "logps/rejected": -201.27334594726562,
+      "loss": 0.5731,
+      "rewards/accuracies": 0.684374988079071,
+      "rewards/chosen": -0.26777908205986023,
+      "rewards/margins": 0.5119359493255615,
+      "rewards/rejected": -0.7797149419784546,
+      "step": 810
+    },
+    {
+      "epoch": 0.5638887695018696,
+      "grad_norm": 20.834632432860804,
+      "learning_rate": 4.858670741023682e-07,
+      "logits/chosen": -0.23629331588745117,
+      "logits/rejected": -0.21014532446861267,
+      "logps/chosen": -194.09735107421875,
+      "logps/rejected": -204.4751434326172,
+      "loss": 0.5683,
+      "rewards/accuracies": 0.7140624523162842,
+      "rewards/chosen": -0.2610727548599243,
+      "rewards/margins": 0.5246341824531555,
+      "rewards/rejected": -0.7857069373130798,
+      "step": 820
+    },
+    {
+      "epoch": 0.570765461812868,
+      "grad_norm": 21.895485023628986,
+      "learning_rate": 4.782276546982429e-07,
+      "logits/chosen": -0.21753302216529846,
+      "logits/rejected": -0.2036309391260147,
+      "logps/chosen": -202.1611328125,
+      "logps/rejected": -211.5482635498047,
+      "loss": 0.5698,
+      "rewards/accuracies": 0.698437511920929,
+      "rewards/chosen": -0.25107091665267944,
+      "rewards/margins": 0.5232045650482178,
+      "rewards/rejected": -0.774275541305542,
+      "step": 830
+    },
+    {
+      "epoch": 0.5776421541238664,
+      "grad_norm": 21.443223828952902,
+      "learning_rate": 4.705882352941176e-07,
+      "logits/chosen": -0.2529454529285431,
+      "logits/rejected": -0.2238178700208664,
+      "logps/chosen": -196.12887573242188,
+      "logps/rejected": -207.17364501953125,
+      "loss": 0.5546,
+      "rewards/accuracies": 0.729687511920929,
+      "rewards/chosen": -0.22495540976524353,
+      "rewards/margins": 0.6076815128326416,
+      "rewards/rejected": -0.8326369524002075,
+      "step": 840
+    },
+    {
+      "epoch": 0.5845188464348648,
+      "grad_norm": 21.225876530865918,
+      "learning_rate": 4.6294881588999233e-07,
+      "logits/chosen": -0.28026488423347473,
+      "logits/rejected": -0.266289621591568,
+      "logps/chosen": -201.97750854492188,
+      "logps/rejected": -212.987548828125,
+      "loss": 0.5735,
+      "rewards/accuracies": 0.7265625,
+      "rewards/chosen": -0.26331812143325806,
+      "rewards/margins": 0.582595705986023,
+      "rewards/rejected": -0.8459138870239258,
+      "step": 850
+    },
+    {
+      "epoch": 0.5913955387458633,
+      "grad_norm": 28.249065086967942,
+      "learning_rate": 4.553093964858671e-07,
+      "logits/chosen": -0.2620088458061218,
+      "logits/rejected": -0.23113124072551727,
+      "logps/chosen": -196.2758331298828,
+      "logps/rejected": -200.11190795898438,
+      "loss": 0.5697,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.2763211727142334,
+      "rewards/margins": 0.5339369177818298,
+      "rewards/rejected": -0.8102580904960632,
+      "step": 860
+    },
+    {
+      "epoch": 0.5982722310568617,
+      "grad_norm": 19.798351649647564,
+      "learning_rate": 4.4766997708174176e-07,
+      "logits/chosen": -0.29130977392196655,
+      "logits/rejected": -0.2608138918876648,
+      "logps/chosen": -205.44146728515625,
+      "logps/rejected": -213.7480926513672,
+      "loss": 0.5685,
+      "rewards/accuracies": 0.7234375476837158,
+      "rewards/chosen": -0.26992180943489075,
+      "rewards/margins": 0.5605109930038452,
+      "rewards/rejected": -0.8304328322410583,
+      "step": 870
+    },
+    {
+      "epoch": 0.6051489233678601,
+      "grad_norm": 20.78214558835817,
+      "learning_rate": 4.4003055767761647e-07,
+      "logits/chosen": -0.2577701508998871,
+      "logits/rejected": -0.23245316743850708,
+      "logps/chosen": -198.88690185546875,
+      "logps/rejected": -205.05946350097656,
+      "loss": 0.5899,
+      "rewards/accuracies": 0.6812500357627869,
+      "rewards/chosen": -0.27420300245285034,
+      "rewards/margins": 0.5197823643684387,
+      "rewards/rejected": -0.7939853668212891,
+      "step": 880
+    },
+    {
+      "epoch": 0.6120256156788585,
+      "grad_norm": 22.312291249160385,
+      "learning_rate": 4.3239113827349124e-07,
+      "logits/chosen": -0.2274932563304901,
+      "logits/rejected": -0.21958866715431213,
+      "logps/chosen": -204.72377014160156,
+      "logps/rejected": -209.85736083984375,
+      "loss": 0.5723,
+      "rewards/accuracies": 0.715624988079071,
+      "rewards/chosen": -0.25001946091651917,
+      "rewards/margins": 0.5583000183105469,
+      "rewards/rejected": -0.8083194494247437,
+      "step": 890
+    },
+    {
+      "epoch": 0.6189023079898569,
+      "grad_norm": 25.49630333289921,
+      "learning_rate": 4.247517188693659e-07,
+      "logits/chosen": -0.24299953877925873,
+      "logits/rejected": -0.2256893813610077,
+      "logps/chosen": -208.52427673339844,
+      "logps/rejected": -210.1595001220703,
+      "loss": 0.5815,
+      "rewards/accuracies": 0.7140624523162842,
+      "rewards/chosen": -0.2674937844276428,
+      "rewards/margins": 0.528352677822113,
+      "rewards/rejected": -0.7958465218544006,
+      "step": 900
+    },
+    {
+      "epoch": 0.6257790003008553,
+      "grad_norm": 20.53779533869322,
+      "learning_rate": 4.171122994652406e-07,
+      "logits/chosen": -0.248798668384552,
+      "logits/rejected": -0.23299312591552734,
+      "logps/chosen": -202.05685424804688,
+      "logps/rejected": -212.53282165527344,
+      "loss": 0.5716,
+      "rewards/accuracies": 0.690625011920929,
+      "rewards/chosen": -0.23762881755828857,
+      "rewards/margins": 0.5192852020263672,
+      "rewards/rejected": -0.7569140195846558,
+      "step": 910
+    },
+    {
+      "epoch": 0.6326556926118537,
+      "grad_norm": 19.08129134756091,
+      "learning_rate": 4.094728800611154e-07,
+      "logits/chosen": -0.26804298162460327,
+      "logits/rejected": -0.2515054941177368,
+      "logps/chosen": -193.53302001953125,
+      "logps/rejected": -206.30044555664062,
+      "loss": 0.5365,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": -0.14372526109218597,
+      "rewards/margins": 0.630579948425293,
+      "rewards/rejected": -0.7743052244186401,
+      "step": 920
+    },
+    {
+      "epoch": 0.6395323849228521,
+      "grad_norm": 18.703547962812074,
+      "learning_rate": 4.0183346065699004e-07,
+      "logits/chosen": -0.28248900175094604,
+      "logits/rejected": -0.2462625950574875,
+      "logps/chosen": -198.85198974609375,
+      "logps/rejected": -207.67355346679688,
+      "loss": 0.532,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.16078238189220428,
+      "rewards/margins": 0.641302227973938,
+      "rewards/rejected": -0.8020846247673035,
+      "step": 930
+    },
+    {
+      "epoch": 0.6464090772338505,
+      "grad_norm": 20.41142350877169,
+      "learning_rate": 3.9419404125286475e-07,
+      "logits/chosen": -0.2985166907310486,
+      "logits/rejected": -0.24812492728233337,
+      "logps/chosen": -198.37818908691406,
+      "logps/rejected": -212.2599334716797,
+      "loss": 0.5656,
+      "rewards/accuracies": 0.7203125357627869,
+      "rewards/chosen": -0.16358602046966553,
+      "rewards/margins": 0.5863920450210571,
+      "rewards/rejected": -0.7499780058860779,
+      "step": 940
+    },
+    {
+      "epoch": 0.653285769544849,
+      "grad_norm": 21.785705703616344,
+      "learning_rate": 3.865546218487395e-07,
+      "logits/chosen": -0.2526381015777588,
+      "logits/rejected": -0.22008472681045532,
+      "logps/chosen": -204.68231201171875,
+      "logps/rejected": -218.895751953125,
+      "loss": 0.5528,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": -0.3044445514678955,
+      "rewards/margins": 0.6037268042564392,
+      "rewards/rejected": -0.9081714153289795,
+      "step": 950
+    },
+    {
+      "epoch": 0.6601624618558474,
+      "grad_norm": 22.594441167295546,
+      "learning_rate": 3.789152024446142e-07,
+      "logits/chosen": -0.29777246713638306,
+      "logits/rejected": -0.25746557116508484,
+      "logps/chosen": -195.57608032226562,
+      "logps/rejected": -209.7220001220703,
+      "loss": 0.5699,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.279017835855484,
+      "rewards/margins": 0.5582146644592285,
+      "rewards/rejected": -0.8372325301170349,
+      "step": 960
+    },
+    {
+      "epoch": 0.6670391541668458,
+      "grad_norm": 21.978835959015736,
+      "learning_rate": 3.712757830404889e-07,
+      "logits/chosen": -0.23148207366466522,
+      "logits/rejected": -0.21888744831085205,
+      "logps/chosen": -205.72726440429688,
+      "logps/rejected": -216.00201416015625,
+      "loss": 0.5486,
+      "rewards/accuracies": 0.7187500596046448,
+      "rewards/chosen": -0.26756638288497925,
+      "rewards/margins": 0.6475085616111755,
+      "rewards/rejected": -0.91507488489151,
+      "step": 970
+    },
+    {
+      "epoch": 0.6739158464778442,
+      "grad_norm": 22.873802825567996,
+      "learning_rate": 3.636363636363636e-07,
+      "logits/chosen": -0.27247849106788635,
+      "logits/rejected": -0.25619280338287354,
+      "logps/chosen": -194.8944091796875,
+      "logps/rejected": -203.31651306152344,
+      "loss": 0.575,
+      "rewards/accuracies": 0.7078125476837158,
+      "rewards/chosen": -0.3309789299964905,
+      "rewards/margins": 0.5653645396232605,
+      "rewards/rejected": -0.8963434100151062,
+      "step": 980
+    },
+    {
+      "epoch": 0.6807925387888426,
+      "grad_norm": 20.94553991910371,
+      "learning_rate": 3.5599694423223837e-07,
+      "logits/chosen": -0.25270241498947144,
+      "logits/rejected": -0.22576749324798584,
+      "logps/chosen": -193.91845703125,
+      "logps/rejected": -203.6450653076172,
+      "loss": 0.5489,
+      "rewards/accuracies": 0.714062511920929,
+      "rewards/chosen": -0.29697081446647644,
+      "rewards/margins": 0.5997652411460876,
+      "rewards/rejected": -0.8967360258102417,
+      "step": 990
+    },
+    {
+      "epoch": 0.687669231099841,
+      "grad_norm": 22.920934792482523,
+      "learning_rate": 3.4835752482811303e-07,
+      "logits/chosen": -0.32494282722473145,
+      "logits/rejected": -0.3064189851284027,
+      "logps/chosen": -200.22879028320312,
+      "logps/rejected": -213.04481506347656,
+      "loss": 0.5568,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.30442699790000916,
+      "rewards/margins": 0.6327985525131226,
+      "rewards/rejected": -0.9372255802154541,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6945459234108394,
+      "grad_norm": 23.631951442333467,
+      "learning_rate": 3.4071810542398775e-07,
+      "logits/chosen": -0.3100181221961975,
+      "logits/rejected": -0.286727637052536,
+      "logps/chosen": -202.29776000976562,
+      "logps/rejected": -211.05247497558594,
+      "loss": 0.5783,
+      "rewards/accuracies": 0.7125000357627869,
+      "rewards/chosen": -0.36704209446907043,
+      "rewards/margins": 0.5526846051216125,
+      "rewards/rejected": -0.9197267293930054,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7014226157218378,
+      "grad_norm": 18.747830881340672,
+      "learning_rate": 3.330786860198625e-07,
+      "logits/chosen": -0.27798181772232056,
+      "logits/rejected": -0.21886159479618073,
+      "logps/chosen": -201.37747192382812,
+      "logps/rejected": -218.2301025390625,
+      "loss": 0.515,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -0.24704203009605408,
+      "rewards/margins": 0.7255524396896362,
+      "rewards/rejected": -0.9725943803787231,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7082993080328363,
+      "grad_norm": 24.25409543649107,
+      "learning_rate": 3.2543926661573717e-07,
+      "logits/chosen": -0.3029528856277466,
+      "logits/rejected": -0.27629080414772034,
+      "logps/chosen": -193.83238220214844,
+      "logps/rejected": -203.4297332763672,
+      "loss": 0.5566,
+      "rewards/accuracies": 0.6984374523162842,
+      "rewards/chosen": -0.3451562523841858,
+      "rewards/margins": 0.6299095749855042,
+      "rewards/rejected": -0.9750658869743347,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7151760003438347,
+      "grad_norm": 26.97218970153312,
+      "learning_rate": 3.177998472116119e-07,
+      "logits/chosen": -0.29127955436706543,
+      "logits/rejected": -0.25185728073120117,
+      "logps/chosen": -204.32371520996094,
+      "logps/rejected": -221.5450439453125,
+      "loss": 0.5525,
+      "rewards/accuracies": 0.7218750715255737,
+      "rewards/chosen": -0.2525748312473297,
+      "rewards/margins": 0.608326256275177,
+      "rewards/rejected": -0.8609010577201843,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7220526926548331,
+      "grad_norm": 22.202001277198995,
+      "learning_rate": 3.1016042780748665e-07,
+      "logits/chosen": -0.27952516078948975,
+      "logits/rejected": -0.2715262174606323,
+      "logps/chosen": -195.66201782226562,
+      "logps/rejected": -200.53121948242188,
+      "loss": 0.5688,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.30520564317703247,
+      "rewards/margins": 0.5800539255142212,
+      "rewards/rejected": -0.8852595090866089,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7289293849658315,
+      "grad_norm": 23.68851239947594,
+      "learning_rate": 3.025210084033613e-07,
+      "logits/chosen": -0.3042244613170624,
+      "logits/rejected": -0.26939964294433594,
+      "logps/chosen": -205.25555419921875,
+      "logps/rejected": -215.33792114257812,
+      "loss": 0.5763,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.3437601327896118,
+      "rewards/margins": 0.648766815662384,
+      "rewards/rejected": -0.9925269484519958,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7358060772768299,
+      "grad_norm": 16.770485849221966,
+      "learning_rate": 2.9488158899923603e-07,
+      "logits/chosen": -0.29478147625923157,
+      "logits/rejected": -0.26331159472465515,
+      "logps/chosen": -191.68682861328125,
+      "logps/rejected": -205.52398681640625,
+      "loss": 0.5514,
+      "rewards/accuracies": 0.721875011920929,
+      "rewards/chosen": -0.22186440229415894,
+      "rewards/margins": 0.6213081479072571,
+      "rewards/rejected": -0.843172550201416,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7426827695878283,
+      "grad_norm": 21.974491833687136,
+      "learning_rate": 2.872421695951108e-07,
+      "logits/chosen": -0.25364449620246887,
+      "logits/rejected": -0.21501508355140686,
+      "logps/chosen": -185.8372802734375,
+      "logps/rejected": -200.8142547607422,
+      "loss": 0.57,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.24050012230873108,
+      "rewards/margins": 0.6280645728111267,
+      "rewards/rejected": -0.8685646653175354,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7495594618988267,
+      "grad_norm": 25.733854858297498,
+      "learning_rate": 2.7960275019098545e-07,
+      "logits/chosen": -0.23827332258224487,
+      "logits/rejected": -0.20885096490383148,
+      "logps/chosen": -203.6381072998047,
+      "logps/rejected": -218.4065704345703,
+      "loss": 0.5452,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.30213844776153564,
+      "rewards/margins": 0.638514518737793,
+      "rewards/rejected": -0.9406529664993286,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7564361542098251,
+      "grad_norm": 20.372146785031376,
+      "learning_rate": 2.7196333078686017e-07,
+      "logits/chosen": -0.2448071539402008,
+      "logits/rejected": -0.2028975635766983,
+      "logps/chosen": -200.01614379882812,
+      "logps/rejected": -211.32534790039062,
+      "loss": 0.545,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.30321523547172546,
+      "rewards/margins": 0.6893056631088257,
+      "rewards/rejected": -0.992520809173584,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7633128465208234,
+      "grad_norm": 20.430379953555082,
+      "learning_rate": 2.6432391138273493e-07,
+      "logits/chosen": -0.2551287114620209,
+      "logits/rejected": -0.23339179158210754,
+      "logps/chosen": -199.39683532714844,
+      "logps/rejected": -209.9544219970703,
+      "loss": 0.5584,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.3356574773788452,
+      "rewards/margins": 0.6131808161735535,
+      "rewards/rejected": -0.9488382339477539,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7701895388318218,
+      "grad_norm": 19.901880078755248,
+      "learning_rate": 2.5668449197860965e-07,
+      "logits/chosen": -0.22213828563690186,
+      "logits/rejected": -0.19397185742855072,
+      "logps/chosen": -199.30223083496094,
+      "logps/rejected": -207.69515991210938,
+      "loss": 0.5507,
+      "rewards/accuracies": 0.7468750476837158,
+      "rewards/chosen": -0.44687339663505554,
+      "rewards/margins": 0.6169517040252686,
+      "rewards/rejected": -1.0638251304626465,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7770662311428203,
+      "grad_norm": 20.24722363911535,
+      "learning_rate": 2.490450725744843e-07,
+      "logits/chosen": -0.2590638995170593,
+      "logits/rejected": -0.22945846617221832,
+      "logps/chosen": -200.342041015625,
+      "logps/rejected": -212.2578582763672,
+      "loss": 0.5454,
+      "rewards/accuracies": 0.7421875596046448,
+      "rewards/chosen": -0.33622223138809204,
+      "rewards/margins": 0.6579465270042419,
+      "rewards/rejected": -0.994168758392334,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7839429234538187,
+      "grad_norm": 21.086214479883942,
+      "learning_rate": 2.41405653170359e-07,
+      "logits/chosen": -0.25024640560150146,
+      "logits/rejected": -0.21352523565292358,
+      "logps/chosen": -200.02767944335938,
+      "logps/rejected": -210.52069091796875,
+      "loss": 0.5633,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.37010401487350464,
+      "rewards/margins": 0.6089712381362915,
+      "rewards/rejected": -0.9790753126144409,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7908196157648171,
+      "grad_norm": 19.875952183889193,
+      "learning_rate": 2.3376623376623376e-07,
+      "logits/chosen": -0.25371620059013367,
+      "logits/rejected": -0.2263481318950653,
+      "logps/chosen": -207.67349243164062,
+      "logps/rejected": -220.63577270507812,
+      "loss": 0.549,
+      "rewards/accuracies": 0.739062488079071,
+      "rewards/chosen": -0.3151938021183014,
+      "rewards/margins": 0.6516591310501099,
+      "rewards/rejected": -0.9668529033660889,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7976963080758155,
+      "grad_norm": 21.407536980595168,
+      "learning_rate": 2.2612681436210848e-07,
+      "logits/chosen": -0.2808507978916168,
+      "logits/rejected": -0.24474851787090302,
+      "logps/chosen": -198.8170166015625,
+      "logps/rejected": -210.86314392089844,
+      "loss": 0.5541,
+      "rewards/accuracies": 0.714062511920929,
+      "rewards/chosen": -0.32873424887657166,
+      "rewards/margins": 0.6663525700569153,
+      "rewards/rejected": -0.9950867891311646,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8045730003868139,
+      "grad_norm": 23.50770080300074,
+      "learning_rate": 2.184873949579832e-07,
+      "logits/chosen": -0.30061495304107666,
+      "logits/rejected": -0.26357635855674744,
+      "logps/chosen": -199.1419677734375,
+      "logps/rejected": -214.4768829345703,
+      "loss": 0.5306,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.282147616147995,
+      "rewards/margins": 0.6803615093231201,
+      "rewards/rejected": -0.9625092148780823,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8114496926978123,
+      "grad_norm": 24.155885332906,
+      "learning_rate": 2.1084797555385788e-07,
+      "logits/chosen": -0.24145373702049255,
+      "logits/rejected": -0.20655398070812225,
+      "logps/chosen": -206.26055908203125,
+      "logps/rejected": -213.5579833984375,
+      "loss": 0.5633,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": -0.38221338391304016,
+      "rewards/margins": 0.585527777671814,
+      "rewards/rejected": -0.967741072177887,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8183263850088107,
+      "grad_norm": 18.461701909835007,
+      "learning_rate": 2.0320855614973262e-07,
+      "logits/chosen": -0.29989033937454224,
+      "logits/rejected": -0.2700657546520233,
+      "logps/chosen": -191.77200317382812,
+      "logps/rejected": -204.35777282714844,
+      "loss": 0.5521,
+      "rewards/accuracies": 0.721875011920929,
+      "rewards/chosen": -0.32683059573173523,
+      "rewards/margins": 0.6650609970092773,
+      "rewards/rejected": -0.991891622543335,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8252030773198091,
+      "grad_norm": 22.37257340571811,
+      "learning_rate": 1.9556913674560733e-07,
+      "logits/chosen": -0.2594352662563324,
+      "logits/rejected": -0.23618939518928528,
+      "logps/chosen": -200.5668487548828,
+      "logps/rejected": -210.00950622558594,
+      "loss": 0.5702,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -0.31345993280410767,
+      "rewards/margins": 0.6197506785392761,
+      "rewards/rejected": -0.9332106113433838,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8320797696308075,
+      "grad_norm": 25.224789610569076,
+      "learning_rate": 1.8792971734148204e-07,
+      "logits/chosen": -0.2822037935256958,
+      "logits/rejected": -0.24582624435424805,
+      "logps/chosen": -198.5158233642578,
+      "logps/rejected": -210.27737426757812,
+      "loss": 0.543,
+      "rewards/accuracies": 0.7593749761581421,
+      "rewards/chosen": -0.37239497900009155,
+      "rewards/margins": 0.6797323822975159,
+      "rewards/rejected": -1.0521273612976074,
+      "step": 1210
+    },
+    {
+      "epoch": 0.838956461941806,
+      "grad_norm": 19.780304476647146,
+      "learning_rate": 1.8029029793735676e-07,
+      "logits/chosen": -0.26471930742263794,
+      "logits/rejected": -0.22956611216068268,
+      "logps/chosen": -197.03468322753906,
+      "logps/rejected": -215.57901000976562,
+      "loss": 0.5449,
+      "rewards/accuracies": 0.739062488079071,
+      "rewards/chosen": -0.34902551770210266,
+      "rewards/margins": 0.6907632350921631,
+      "rewards/rejected": -1.039788842201233,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8458331542528044,
+      "grad_norm": 16.98463514772764,
+      "learning_rate": 1.7265087853323147e-07,
+      "logits/chosen": -0.2907296419143677,
+      "logits/rejected": -0.26648983359336853,
+      "logps/chosen": -199.41156005859375,
+      "logps/rejected": -214.23023986816406,
+      "loss": 0.535,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": -0.3681446313858032,
+      "rewards/margins": 0.6866059899330139,
+      "rewards/rejected": -1.0547505617141724,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8527098465638028,
+      "grad_norm": 32.69373101278549,
+      "learning_rate": 1.6501145912910618e-07,
+      "logits/chosen": -0.26771843433380127,
+      "logits/rejected": -0.2375665307044983,
+      "logps/chosen": -201.06895446777344,
+      "logps/rejected": -210.51840209960938,
+      "loss": 0.5723,
+      "rewards/accuracies": 0.7109375596046448,
+      "rewards/chosen": -0.38859817385673523,
+      "rewards/margins": 0.6455494165420532,
+      "rewards/rejected": -1.0341476202011108,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8595865388748012,
+      "grad_norm": 20.83949759552536,
+      "learning_rate": 1.573720397249809e-07,
+      "logits/chosen": -0.2752777934074402,
+      "logits/rejected": -0.24270716309547424,
+      "logps/chosen": -200.675537109375,
+      "logps/rejected": -212.04931640625,
+      "loss": 0.5395,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.3316209316253662,
+      "rewards/margins": 0.6646089553833008,
+      "rewards/rejected": -0.996229887008667,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8664632311857996,
+      "grad_norm": 24.573642614002804,
+      "learning_rate": 1.4973262032085558e-07,
+      "logits/chosen": -0.2565278112888336,
+      "logits/rejected": -0.21442291140556335,
+      "logps/chosen": -194.88111877441406,
+      "logps/rejected": -210.5688018798828,
+      "loss": 0.5582,
+      "rewards/accuracies": 0.7328125238418579,
+      "rewards/chosen": -0.44270479679107666,
+      "rewards/margins": 0.6293411254882812,
+      "rewards/rejected": -1.0720458030700684,
+      "step": 1260
+    },
+    {
+      "epoch": 0.873339923496798,
+      "grad_norm": 19.534250584569072,
+      "learning_rate": 1.4209320091673032e-07,
+      "logits/chosen": -0.2922959327697754,
+      "logits/rejected": -0.26131224632263184,
+      "logps/chosen": -194.8395538330078,
+      "logps/rejected": -209.4702911376953,
+      "loss": 0.5413,
+      "rewards/accuracies": 0.7421875,
+      "rewards/chosen": -0.33789727091789246,
+      "rewards/margins": 0.6527694463729858,
+      "rewards/rejected": -0.9906667470932007,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8802166158077964,
+      "grad_norm": 20.717698242318562,
+      "learning_rate": 1.3445378151260504e-07,
+      "logits/chosen": -0.2540634274482727,
+      "logits/rejected": -0.22778739035129547,
+      "logps/chosen": -203.4353790283203,
+      "logps/rejected": -211.83343505859375,
+      "loss": 0.5304,
+      "rewards/accuracies": 0.7390625476837158,
+      "rewards/chosen": -0.3961109519004822,
+      "rewards/margins": 0.6780579686164856,
+      "rewards/rejected": -1.0741689205169678,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8870933081187948,
+      "grad_norm": 23.96725955714651,
+      "learning_rate": 1.2681436210847975e-07,
+      "logits/chosen": -0.25593337416648865,
+      "logits/rejected": -0.21139128506183624,
+      "logps/chosen": -192.81637573242188,
+      "logps/rejected": -207.94528198242188,
+      "loss": 0.5305,
+      "rewards/accuracies": 0.7437500357627869,
+      "rewards/chosen": -0.3916109502315521,
+      "rewards/margins": 0.7024664878845215,
+      "rewards/rejected": -1.0940773487091064,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8939700004297932,
+      "grad_norm": 21.318918224883497,
+      "learning_rate": 1.1917494270435446e-07,
+      "logits/chosen": -0.2688959538936615,
+      "logits/rejected": -0.256546288728714,
+      "logps/chosen": -194.7349395751953,
+      "logps/rejected": -208.1248016357422,
+      "loss": 0.5503,
+      "rewards/accuracies": 0.7234375476837158,
+      "rewards/chosen": -0.41377341747283936,
+      "rewards/margins": 0.6503176689147949,
+      "rewards/rejected": -1.0640910863876343,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9008466927407917,
+      "grad_norm": 22.656364712253406,
+      "learning_rate": 1.1153552330022918e-07,
+      "logits/chosen": -0.27973228693008423,
+      "logits/rejected": -0.24073663353919983,
+      "logps/chosen": -197.87957763671875,
+      "logps/rejected": -209.244873046875,
+      "loss": 0.5439,
+      "rewards/accuracies": 0.721875011920929,
+      "rewards/chosen": -0.38405442237854004,
+      "rewards/margins": 0.6377519369125366,
+      "rewards/rejected": -1.0218064785003662,
+      "step": 1310
+    },
+    {
+      "epoch": 0.9077233850517901,
+      "grad_norm": 23.992301612667553,
+      "learning_rate": 1.038961038961039e-07,
+      "logits/chosen": -0.248391255736351,
+      "logits/rejected": -0.22697040438652039,
+      "logps/chosen": -200.25355529785156,
+      "logps/rejected": -216.67298889160156,
+      "loss": 0.5547,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -0.36668360233306885,
+      "rewards/margins": 0.6348526477813721,
+      "rewards/rejected": -1.001536250114441,
+      "step": 1320
+    },
+    {
+      "epoch": 0.9146000773627885,
+      "grad_norm": 23.080807444085426,
+      "learning_rate": 9.62566844919786e-08,
+      "logits/chosen": -0.23448041081428528,
+      "logits/rejected": -0.20045128464698792,
+      "logps/chosen": -200.07498168945312,
+      "logps/rejected": -213.40365600585938,
+      "loss": 0.5265,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": -0.41947588324546814,
+      "rewards/margins": 0.699980616569519,
+      "rewards/rejected": -1.1194565296173096,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9214767696737869,
+      "grad_norm": 27.13497379193061,
+      "learning_rate": 8.861726508785332e-08,
+      "logits/chosen": -0.21386350691318512,
+      "logits/rejected": -0.20405535399913788,
+      "logps/chosen": -207.48922729492188,
+      "logps/rejected": -213.19801330566406,
+      "loss": 0.5739,
+      "rewards/accuracies": 0.7109375596046448,
+      "rewards/chosen": -0.44666141271591187,
+      "rewards/margins": 0.6134124994277954,
+      "rewards/rejected": -1.060073971748352,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9283534619847853,
+      "grad_norm": 26.86309937846046,
+      "learning_rate": 8.097784568372803e-08,
+      "logits/chosen": -0.2825528681278229,
+      "logits/rejected": -0.2349400520324707,
+      "logps/chosen": -213.959716796875,
+      "logps/rejected": -224.0325164794922,
+      "loss": 0.5575,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.4003857374191284,
+      "rewards/margins": 0.6982907056808472,
+      "rewards/rejected": -1.0986764430999756,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9352301542957837,
+      "grad_norm": 29.245122481397317,
+      "learning_rate": 7.333842627960276e-08,
+      "logits/chosen": -0.2761003375053406,
+      "logits/rejected": -0.24544045329093933,
+      "logps/chosen": -202.433349609375,
+      "logps/rejected": -217.29464721679688,
+      "loss": 0.5149,
+      "rewards/accuracies": 0.7828125357627869,
+      "rewards/chosen": -0.4048154354095459,
+      "rewards/margins": 0.7579847574234009,
+      "rewards/rejected": -1.1628003120422363,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9421068466067821,
+      "grad_norm": 25.075679763670674,
+      "learning_rate": 6.569900687547746e-08,
+      "logits/chosen": -0.2352394461631775,
+      "logits/rejected": -0.2183229774236679,
+      "logps/chosen": -204.6761474609375,
+      "logps/rejected": -213.91024780273438,
+      "loss": 0.5774,
+      "rewards/accuracies": 0.7015625238418579,
+      "rewards/chosen": -0.40830886363983154,
+      "rewards/margins": 0.6113278865814209,
+      "rewards/rejected": -1.0196367502212524,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9489835389177805,
+      "grad_norm": 20.1424199530658,
+      "learning_rate": 5.805958747135217e-08,
+      "logits/chosen": -0.23637357354164124,
+      "logits/rejected": -0.21443995833396912,
+      "logps/chosen": -196.8209991455078,
+      "logps/rejected": -207.15574645996094,
+      "loss": 0.5551,
+      "rewards/accuracies": 0.723437488079071,
+      "rewards/chosen": -0.4441874027252197,
+      "rewards/margins": 0.6192114353179932,
+      "rewards/rejected": -1.063398838043213,
+      "step": 1380
+    },
+    {
+      "epoch": 0.955860231228779,
+      "grad_norm": 24.76586280035536,
+      "learning_rate": 5.042016806722689e-08,
+      "logits/chosen": -0.3121819496154785,
+      "logits/rejected": -0.27099382877349854,
+      "logps/chosen": -211.52767944335938,
+      "logps/rejected": -222.99720764160156,
+      "loss": 0.5424,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": -0.30979296565055847,
+      "rewards/margins": 0.7096717953681946,
+      "rewards/rejected": -1.0194647312164307,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9627369235397774,
+      "grad_norm": 20.6202462278239,
+      "learning_rate": 4.27807486631016e-08,
+      "logits/chosen": -0.2805480659008026,
+      "logits/rejected": -0.2518741190433502,
+      "logps/chosen": -191.37855529785156,
+      "logps/rejected": -205.9793243408203,
+      "loss": 0.5252,
+      "rewards/accuracies": 0.753125011920929,
+      "rewards/chosen": -0.3638061285018921,
+      "rewards/margins": 0.6892703771591187,
+      "rewards/rejected": -1.0530765056610107,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9696136158507758,
+      "grad_norm": 19.926765783973885,
+      "learning_rate": 3.514132925897632e-08,
+      "logits/chosen": -0.26876330375671387,
+      "logits/rejected": -0.2324240803718567,
+      "logps/chosen": -198.6615447998047,
+      "logps/rejected": -215.54981994628906,
+      "loss": 0.4938,
+      "rewards/accuracies": 0.792187511920929,
+      "rewards/chosen": -0.3588196635246277,
+      "rewards/margins": 0.786273181438446,
+      "rewards/rejected": -1.1450928449630737,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9764903081617742,
+      "grad_norm": 21.09934832903724,
+      "learning_rate": 2.750190985485103e-08,
+      "logits/chosen": -0.21979323029518127,
+      "logits/rejected": -0.21775387227535248,
+      "logps/chosen": -195.7095489501953,
+      "logps/rejected": -205.0386505126953,
+      "loss": 0.5229,
+      "rewards/accuracies": 0.7468750476837158,
+      "rewards/chosen": -0.38191646337509155,
+      "rewards/margins": 0.7250487804412842,
+      "rewards/rejected": -1.1069653034210205,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9833670004727726,
+      "grad_norm": 19.940200333703277,
+      "learning_rate": 1.9862490450725743e-08,
+      "logits/chosen": -0.26562875509262085,
+      "logits/rejected": -0.25526827573776245,
+      "logps/chosen": -199.0478515625,
+      "logps/rejected": -207.9737548828125,
+      "loss": 0.5485,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.4320859909057617,
+      "rewards/margins": 0.6247124671936035,
+      "rewards/rejected": -1.0567984580993652,
+      "step": 1430
+    },
+    {
+      "epoch": 0.990243692783771,
+      "grad_norm": 21.44789284674788,
+      "learning_rate": 1.2223071046600458e-08,
+      "logits/chosen": -0.2715289294719696,
+      "logits/rejected": -0.23082685470581055,
+      "logps/chosen": -205.08152770996094,
+      "logps/rejected": -217.8182830810547,
+      "loss": 0.5481,
+      "rewards/accuracies": 0.715624988079071,
+      "rewards/chosen": -0.3798620104789734,
+      "rewards/margins": 0.667800784111023,
+      "rewards/rejected": -1.0476627349853516,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9971203850947694,
+      "grad_norm": 22.623803658983302,
+      "learning_rate": 4.583651642475172e-09,
+      "logits/chosen": -0.2716945707798004,
+      "logits/rejected": -0.24027717113494873,
+      "logps/chosen": -204.0220947265625,
+      "logps/rejected": -215.94126892089844,
+      "loss": 0.5363,
+      "rewards/accuracies": 0.7593749761581421,
+      "rewards/chosen": -0.4140065610408783,
+      "rewards/margins": 0.6608986258506775,
+      "rewards/rejected": -1.0749050378799438,
+      "step": 1450
+    },
+    {
+      "epoch": 1.0,
+      "step": 1455,
+      "total_flos": 160109785841664.0,
+      "train_loss": 0.5976956401903605,
+      "train_runtime": 14200.9584,
+      "train_samples_per_second": 6.554,
+      "train_steps_per_second": 0.102
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1455,
+  "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": 160109785841664.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed9008baf1493b0518247b719e6911a73a5a7de180055b9b171248354fd2d14
+size 7544