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_en
+  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_en
+
+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_en 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": 159648317243392.0,
+    "train_loss": 0.5763244779045961,
+    "train_runtime": 14193.5309,
+    "train_samples_per_second": 6.548,
+    "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 sha256:927047f15317348b9a1ad41282049fa342ef06ebe767a27a48ba6d539969a719
+size 4965841415

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81e142d2b0767b3d7d889a700b33009e969dbac78a553630bb980fc561bb9107
+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": 159648317243392.0,
+    "train_loss": 0.5763244779045961,
+    "train_runtime": 14193.5309,
+    "train_samples_per_second": 6.548,
+    "train_steps_per_second": 0.102
+}

trainer_log.jsonl

@@ -0,0 +1,146 @@
+{"current_steps": 10, "total_steps": 1453, "loss": 0.694, "accuracy": 0.3843749761581421, "lr": 6.164383561643836e-08, "epoch": 0.006885866758478224, "percentage": 0.69, "elapsed_time": "0:01:43", "remaining_time": "4:08:12"}
+{"current_steps": 20, "total_steps": 1453, "loss": 0.6943, "accuracy": 0.5015624761581421, "lr": 1.3013698630136985e-07, "epoch": 0.013771733516956448, "percentage": 1.38, "elapsed_time": "0:03:20", "remaining_time": "3:59:19"}
+{"current_steps": 30, "total_steps": 1453, "loss": 0.6931, "accuracy": 0.4937500059604645, "lr": 1.9863013698630135e-07, "epoch": 0.02065760027543467, "percentage": 2.06, "elapsed_time": "0:05:00", "remaining_time": "3:57:47"}
+{"current_steps": 40, "total_steps": 1453, "loss": 0.6934, "accuracy": 0.53125, "lr": 2.671232876712329e-07, "epoch": 0.027543467033912895, "percentage": 2.75, "elapsed_time": "0:06:37", "remaining_time": "3:54:07"}
+{"current_steps": 50, "total_steps": 1453, "loss": 0.6927, "accuracy": 0.5265625715255737, "lr": 3.3561643835616436e-07, "epoch": 0.03442933379239112, "percentage": 3.44, "elapsed_time": "0:08:14", "remaining_time": "3:51:22"}
+{"current_steps": 60, "total_steps": 1453, "loss": 0.6917, "accuracy": 0.5062500238418579, "lr": 4.041095890410959e-07, "epoch": 0.04131520055086934, "percentage": 4.13, "elapsed_time": "0:09:53", "remaining_time": "3:49:32"}
+{"current_steps": 70, "total_steps": 1453, "loss": 0.6929, "accuracy": 0.503125011920929, "lr": 4.726027397260274e-07, "epoch": 0.04820106730934756, "percentage": 4.82, "elapsed_time": "0:11:33", "remaining_time": "3:48:28"}
+{"current_steps": 80, "total_steps": 1453, "loss": 0.6908, "accuracy": 0.5437500476837158, "lr": 5.410958904109589e-07, "epoch": 0.05508693406782579, "percentage": 5.51, "elapsed_time": "0:13:12", "remaining_time": "3:46:43"}
+{"current_steps": 90, "total_steps": 1453, "loss": 0.6894, "accuracy": 0.5625, "lr": 6.095890410958904e-07, "epoch": 0.06197280082630401, "percentage": 6.19, "elapsed_time": "0:14:50", "remaining_time": "3:44:44"}
+{"current_steps": 100, "total_steps": 1453, "loss": 0.6901, "accuracy": 0.5531250238418579, "lr": 6.78082191780822e-07, "epoch": 0.06885866758478223, "percentage": 6.88, "elapsed_time": "0:16:29", "remaining_time": "3:43:05"}
+{"current_steps": 110, "total_steps": 1453, "loss": 0.6856, "accuracy": 0.6171875, "lr": 7.465753424657533e-07, "epoch": 0.07574453434326046, "percentage": 7.57, "elapsed_time": "0:18:06", "remaining_time": "3:41:10"}
+{"current_steps": 120, "total_steps": 1453, "loss": 0.6837, "accuracy": 0.5953124761581421, "lr": 8.150684931506849e-07, "epoch": 0.08263040110173868, "percentage": 8.26, "elapsed_time": "0:19:45", "remaining_time": "3:39:28"}
+{"current_steps": 130, "total_steps": 1453, "loss": 0.682, "accuracy": 0.6031250357627869, "lr": 8.835616438356164e-07, "epoch": 0.08951626786021691, "percentage": 8.95, "elapsed_time": "0:21:24", "remaining_time": "3:37:47"}
+{"current_steps": 140, "total_steps": 1453, "loss": 0.6789, "accuracy": 0.6000000238418579, "lr": 9.520547945205479e-07, "epoch": 0.09640213461869512, "percentage": 9.64, "elapsed_time": "0:23:02", "remaining_time": "3:36:07"}
+{"current_steps": 150, "total_steps": 1453, "loss": 0.6775, "accuracy": 0.5906250476837158, "lr": 9.977046671767407e-07, "epoch": 0.10328800137717335, "percentage": 10.32, "elapsed_time": "0:24:41", "remaining_time": "3:34:33"}
+{"current_steps": 160, "total_steps": 1453, "loss": 0.6647, "accuracy": 0.6546875238418579, "lr": 9.90053557765876e-07, "epoch": 0.11017386813565158, "percentage": 11.01, "elapsed_time": "0:26:20", "remaining_time": "3:32:52"}
+{"current_steps": 170, "total_steps": 1453, "loss": 0.6698, "accuracy": 0.604687511920929, "lr": 9.824024483550113e-07, "epoch": 0.1170597348941298, "percentage": 11.7, "elapsed_time": "0:27:59", "remaining_time": "3:31:18"}
+{"current_steps": 180, "total_steps": 1453, "loss": 0.6713, "accuracy": 0.612500011920929, "lr": 9.747513389441468e-07, "epoch": 0.12394560165260803, "percentage": 12.39, "elapsed_time": "0:29:38", "remaining_time": "3:29:40"}
+{"current_steps": 190, "total_steps": 1453, "loss": 0.6543, "accuracy": 0.6296875476837158, "lr": 9.671002295332823e-07, "epoch": 0.13083146841108625, "percentage": 13.08, "elapsed_time": "0:31:16", "remaining_time": "3:27:55"}
+{"current_steps": 200, "total_steps": 1453, "loss": 0.6718, "accuracy": 0.609375, "lr": 9.594491201224178e-07, "epoch": 0.13771733516956447, "percentage": 13.76, "elapsed_time": "0:32:55", "remaining_time": "3:26:14"}
+{"current_steps": 210, "total_steps": 1453, "loss": 0.657, "accuracy": 0.6312500238418579, "lr": 9.517980107115531e-07, "epoch": 0.14460320192804269, "percentage": 14.45, "elapsed_time": "0:34:34", "remaining_time": "3:24:41"}
+{"current_steps": 220, "total_steps": 1453, "loss": 0.6495, "accuracy": 0.6375000476837158, "lr": 9.441469013006885e-07, "epoch": 0.15148906868652093, "percentage": 15.14, "elapsed_time": "0:36:12", "remaining_time": "3:22:57"}
+{"current_steps": 230, "total_steps": 1453, "loss": 0.6483, "accuracy": 0.6421874761581421, "lr": 9.364957918898239e-07, "epoch": 0.15837493544499914, "percentage": 15.83, "elapsed_time": "0:37:52", "remaining_time": "3:21:21"}
+{"current_steps": 240, "total_steps": 1453, "loss": 0.641, "accuracy": 0.643750011920929, "lr": 9.288446824789594e-07, "epoch": 0.16526080220347736, "percentage": 16.52, "elapsed_time": "0:39:29", "remaining_time": "3:19:38"}
+{"current_steps": 250, "total_steps": 1453, "loss": 0.6497, "accuracy": 0.6328125596046448, "lr": 9.211935730680948e-07, "epoch": 0.17214666896195557, "percentage": 17.21, "elapsed_time": "0:41:08", "remaining_time": "3:18:00"}
+{"current_steps": 260, "total_steps": 1453, "loss": 0.6466, "accuracy": 0.6296875476837158, "lr": 9.135424636572303e-07, "epoch": 0.17903253572043382, "percentage": 17.89, "elapsed_time": "0:42:47", "remaining_time": "3:16:21"}
+{"current_steps": 270, "total_steps": 1453, "loss": 0.6325, "accuracy": 0.6312500238418579, "lr": 9.058913542463656e-07, "epoch": 0.18591840247891203, "percentage": 18.58, "elapsed_time": "0:44:26", "remaining_time": "3:14:41"}
+{"current_steps": 280, "total_steps": 1453, "loss": 0.6299, "accuracy": 0.6625000238418579, "lr": 8.982402448355011e-07, "epoch": 0.19280426923739025, "percentage": 19.27, "elapsed_time": "0:46:03", "remaining_time": "3:12:57"}
+{"current_steps": 290, "total_steps": 1453, "loss": 0.6268, "accuracy": 0.6671875715255737, "lr": 8.905891354246365e-07, "epoch": 0.1996901359958685, "percentage": 19.96, "elapsed_time": "0:47:41", "remaining_time": "3:11:14"}
+{"current_steps": 300, "total_steps": 1453, "loss": 0.6151, "accuracy": 0.7046874761581421, "lr": 8.829380260137719e-07, "epoch": 0.2065760027543467, "percentage": 20.65, "elapsed_time": "0:49:20", "remaining_time": "3:09:38"}
+{"current_steps": 310, "total_steps": 1453, "loss": 0.6302, "accuracy": 0.6578125357627869, "lr": 8.752869166029074e-07, "epoch": 0.21346186951282492, "percentage": 21.34, "elapsed_time": "0:51:00", "remaining_time": "3:08:04"}
+{"current_steps": 320, "total_steps": 1453, "loss": 0.6266, "accuracy": 0.6656249761581421, "lr": 8.676358071920427e-07, "epoch": 0.22034773627130316, "percentage": 22.02, "elapsed_time": "0:52:36", "remaining_time": "3:06:17"}
+{"current_steps": 330, "total_steps": 1453, "loss": 0.612, "accuracy": 0.6796875, "lr": 8.599846977811782e-07, "epoch": 0.22723360302978138, "percentage": 22.71, "elapsed_time": "0:54:13", "remaining_time": "3:04:32"}
+{"current_steps": 340, "total_steps": 1453, "loss": 0.6088, "accuracy": 0.6796875596046448, "lr": 8.523335883703136e-07, "epoch": 0.2341194697882596, "percentage": 23.4, "elapsed_time": "0:55:52", "remaining_time": "3:02:56"}
+{"current_steps": 350, "total_steps": 1453, "loss": 0.6174, "accuracy": 0.667187511920929, "lr": 8.446824789594492e-07, "epoch": 0.2410053365467378, "percentage": 24.09, "elapsed_time": "0:57:29", "remaining_time": "3:01:11"}
+{"current_steps": 360, "total_steps": 1453, "loss": 0.6075, "accuracy": 0.6765625476837158, "lr": 8.370313695485846e-07, "epoch": 0.24789120330521605, "percentage": 24.78, "elapsed_time": "0:59:07", "remaining_time": "2:59:30"}
+{"current_steps": 370, "total_steps": 1453, "loss": 0.6099, "accuracy": 0.6812500357627869, "lr": 8.293802601377199e-07, "epoch": 0.25477707006369427, "percentage": 25.46, "elapsed_time": "1:00:45", "remaining_time": "2:57:49"}
+{"current_steps": 380, "total_steps": 1453, "loss": 0.612, "accuracy": 0.659375011920929, "lr": 8.217291507268554e-07, "epoch": 0.2616629368221725, "percentage": 26.15, "elapsed_time": "1:02:23", "remaining_time": "2:56:10"}
+{"current_steps": 390, "total_steps": 1453, "loss": 0.6082, "accuracy": 0.6796875, "lr": 8.140780413159908e-07, "epoch": 0.2685488035806507, "percentage": 26.84, "elapsed_time": "1:03:59", "remaining_time": "2:54:25"}
+{"current_steps": 400, "total_steps": 1453, "loss": 0.6055, "accuracy": 0.668749988079071, "lr": 8.064269319051263e-07, "epoch": 0.27543467033912894, "percentage": 27.53, "elapsed_time": "1:05:39", "remaining_time": "2:52:50"}
+{"current_steps": 410, "total_steps": 1453, "loss": 0.5995, "accuracy": 0.6812499761581421, "lr": 7.987758224942617e-07, "epoch": 0.2823205370976072, "percentage": 28.22, "elapsed_time": "1:07:19", "remaining_time": "2:51:15"}
+{"current_steps": 420, "total_steps": 1453, "loss": 0.6077, "accuracy": 0.6578124761581421, "lr": 7.91124713083397e-07, "epoch": 0.28920640385608537, "percentage": 28.91, "elapsed_time": "1:08:57", "remaining_time": "2:49:36"}
+{"current_steps": 430, "total_steps": 1453, "loss": 0.5838, "accuracy": 0.7093750238418579, "lr": 7.834736036725325e-07, "epoch": 0.2960922706145636, "percentage": 29.59, "elapsed_time": "1:10:36", "remaining_time": "2:47:58"}
+{"current_steps": 440, "total_steps": 1453, "loss": 0.5943, "accuracy": 0.7171875238418579, "lr": 7.758224942616679e-07, "epoch": 0.30297813737304186, "percentage": 30.28, "elapsed_time": "1:12:15", "remaining_time": "2:46:22"}
+{"current_steps": 450, "total_steps": 1453, "loss": 0.6007, "accuracy": 0.6968750357627869, "lr": 7.681713848508034e-07, "epoch": 0.30986400413152004, "percentage": 30.97, "elapsed_time": "1:13:53", "remaining_time": "2:44:42"}
+{"current_steps": 460, "total_steps": 1453, "loss": 0.5764, "accuracy": 0.6859375238418579, "lr": 7.605202754399388e-07, "epoch": 0.3167498708899983, "percentage": 31.66, "elapsed_time": "1:15:32", "remaining_time": "2:43:03"}
+{"current_steps": 470, "total_steps": 1453, "loss": 0.5815, "accuracy": 0.7015624642372131, "lr": 7.528691660290742e-07, "epoch": 0.32363573764847653, "percentage": 32.35, "elapsed_time": "1:17:10", "remaining_time": "2:41:24"}
+{"current_steps": 480, "total_steps": 1453, "loss": 0.601, "accuracy": 0.671875, "lr": 7.452180566182096e-07, "epoch": 0.3305216044069547, "percentage": 33.04, "elapsed_time": "1:18:50", "remaining_time": "2:39:48"}
+{"current_steps": 490, "total_steps": 1453, "loss": 0.5945, "accuracy": 0.6687500476837158, "lr": 7.37566947207345e-07, "epoch": 0.33740747116543296, "percentage": 33.72, "elapsed_time": "1:20:27", "remaining_time": "2:38:07"}
+{"current_steps": 500, "total_steps": 1453, "loss": 0.5829, "accuracy": 0.699999988079071, "lr": 7.299158377964805e-07, "epoch": 0.34429333792391115, "percentage": 34.41, "elapsed_time": "1:22:06", "remaining_time": "2:36:29"}
+{"current_steps": 510, "total_steps": 1453, "loss": 0.5725, "accuracy": 0.7312500476837158, "lr": 7.222647283856159e-07, "epoch": 0.3511792046823894, "percentage": 35.1, "elapsed_time": "1:24:07", "remaining_time": "2:35:32"}
+{"current_steps": 520, "total_steps": 1453, "loss": 0.577, "accuracy": 0.703125, "lr": 7.146136189747513e-07, "epoch": 0.35806507144086763, "percentage": 35.79, "elapsed_time": "1:25:43", "remaining_time": "2:33:47"}
+{"current_steps": 530, "total_steps": 1453, "loss": 0.5766, "accuracy": 0.707812488079071, "lr": 7.069625095638867e-07, "epoch": 0.3649509381993458, "percentage": 36.48, "elapsed_time": "1:27:21", "remaining_time": "2:32:07"}
+{"current_steps": 540, "total_steps": 1453, "loss": 0.5615, "accuracy": 0.7171875238418579, "lr": 6.993114001530222e-07, "epoch": 0.37183680495782406, "percentage": 37.16, "elapsed_time": "1:28:57", "remaining_time": "2:30:23"}
+{"current_steps": 550, "total_steps": 1453, "loss": 0.5994, "accuracy": 0.6890625357627869, "lr": 6.916602907421576e-07, "epoch": 0.3787226717163023, "percentage": 37.85, "elapsed_time": "1:30:34", "remaining_time": "2:28:42"}
+{"current_steps": 560, "total_steps": 1453, "loss": 0.6023, "accuracy": 0.6656250357627869, "lr": 6.84009181331293e-07, "epoch": 0.3856085384747805, "percentage": 38.54, "elapsed_time": "1:32:09", "remaining_time": "2:26:57"}
+{"current_steps": 570, "total_steps": 1453, "loss": 0.5773, "accuracy": 0.6812500357627869, "lr": 6.763580719204285e-07, "epoch": 0.39249440523325874, "percentage": 39.23, "elapsed_time": "1:33:47", "remaining_time": "2:25:18"}
+{"current_steps": 580, "total_steps": 1453, "loss": 0.5876, "accuracy": 0.7093750238418579, "lr": 6.687069625095638e-07, "epoch": 0.399380271991737, "percentage": 39.92, "elapsed_time": "1:35:24", "remaining_time": "2:23:36"}
+{"current_steps": 590, "total_steps": 1453, "loss": 0.5925, "accuracy": 0.6734374761581421, "lr": 6.610558530986993e-07, "epoch": 0.40626613875021517, "percentage": 40.61, "elapsed_time": "1:37:00", "remaining_time": "2:21:53"}
+{"current_steps": 600, "total_steps": 1453, "loss": 0.5923, "accuracy": 0.6875, "lr": 6.534047436878347e-07, "epoch": 0.4131520055086934, "percentage": 41.29, "elapsed_time": "1:38:37", "remaining_time": "2:20:12"}
+{"current_steps": 610, "total_steps": 1453, "loss": 0.6058, "accuracy": 0.6890625357627869, "lr": 6.457536342769701e-07, "epoch": 0.42003787226717165, "percentage": 41.98, "elapsed_time": "1:40:12", "remaining_time": "2:18:29"}
+{"current_steps": 620, "total_steps": 1453, "loss": 0.5515, "accuracy": 0.7312500476837158, "lr": 6.381025248661056e-07, "epoch": 0.42692373902564984, "percentage": 42.67, "elapsed_time": "1:41:47", "remaining_time": "2:16:46"}
+{"current_steps": 630, "total_steps": 1453, "loss": 0.5643, "accuracy": 0.723437488079071, "lr": 6.304514154552409e-07, "epoch": 0.4338096057841281, "percentage": 43.36, "elapsed_time": "1:43:25", "remaining_time": "2:15:05"}
+{"current_steps": 640, "total_steps": 1453, "loss": 0.5342, "accuracy": 0.7531250715255737, "lr": 6.228003060443764e-07, "epoch": 0.4406954725426063, "percentage": 44.05, "elapsed_time": "1:44:59", "remaining_time": "2:13:21"}
+{"current_steps": 650, "total_steps": 1453, "loss": 0.5964, "accuracy": 0.6953125, "lr": 6.151491966335118e-07, "epoch": 0.4475813393010845, "percentage": 44.74, "elapsed_time": "1:46:35", "remaining_time": "2:11:41"}
+{"current_steps": 660, "total_steps": 1453, "loss": 0.593, "accuracy": 0.6875, "lr": 6.074980872226473e-07, "epoch": 0.45446720605956276, "percentage": 45.42, "elapsed_time": "1:48:11", "remaining_time": "2:10:00"}
+{"current_steps": 670, "total_steps": 1453, "loss": 0.5572, "accuracy": 0.7109375, "lr": 5.998469778117827e-07, "epoch": 0.46135307281804094, "percentage": 46.11, "elapsed_time": "1:49:47", "remaining_time": "2:08:18"}
+{"current_steps": 680, "total_steps": 1453, "loss": 0.574, "accuracy": 0.7000000476837158, "lr": 5.92195868400918e-07, "epoch": 0.4682389395765192, "percentage": 46.8, "elapsed_time": "1:51:24", "remaining_time": "2:06:39"}
+{"current_steps": 690, "total_steps": 1453, "loss": 0.5606, "accuracy": 0.7375000715255737, "lr": 5.845447589900535e-07, "epoch": 0.47512480633499743, "percentage": 47.49, "elapsed_time": "1:53:01", "remaining_time": "2:04:58"}
+{"current_steps": 700, "total_steps": 1453, "loss": 0.5816, "accuracy": 0.6968749761581421, "lr": 5.768936495791889e-07, "epoch": 0.4820106730934756, "percentage": 48.18, "elapsed_time": "1:54:38", "remaining_time": "2:03:19"}
+{"current_steps": 710, "total_steps": 1453, "loss": 0.5411, "accuracy": 0.7359374761581421, "lr": 5.692425401683244e-07, "epoch": 0.48889653985195386, "percentage": 48.86, "elapsed_time": "1:56:14", "remaining_time": "2:01:39"}
+{"current_steps": 720, "total_steps": 1453, "loss": 0.5499, "accuracy": 0.731249988079071, "lr": 5.615914307574598e-07, "epoch": 0.4957824066104321, "percentage": 49.55, "elapsed_time": "1:57:50", "remaining_time": "1:59:58"}
+{"current_steps": 730, "total_steps": 1453, "loss": 0.5664, "accuracy": 0.7312500476837158, "lr": 5.539403213465952e-07, "epoch": 0.5026682733689103, "percentage": 50.24, "elapsed_time": "1:59:27", "remaining_time": "1:58:19"}
+{"current_steps": 740, "total_steps": 1453, "loss": 0.6024, "accuracy": 0.6968750357627869, "lr": 5.462892119357306e-07, "epoch": 0.5095541401273885, "percentage": 50.93, "elapsed_time": "2:01:05", "remaining_time": "1:56:39"}
+{"current_steps": 750, "total_steps": 1453, "loss": 0.564, "accuracy": 0.71875, "lr": 5.38638102524866e-07, "epoch": 0.5164400068858668, "percentage": 51.62, "elapsed_time": "2:02:41", "remaining_time": "1:55:00"}
+{"current_steps": 760, "total_steps": 1453, "loss": 0.5744, "accuracy": 0.7109375, "lr": 5.309869931140015e-07, "epoch": 0.523325873644345, "percentage": 52.31, "elapsed_time": "2:04:17", "remaining_time": "1:53:19"}
+{"current_steps": 770, "total_steps": 1453, "loss": 0.5347, "accuracy": 0.7093750238418579, "lr": 5.233358837031369e-07, "epoch": 0.5302117404028232, "percentage": 52.99, "elapsed_time": "2:05:55", "remaining_time": "1:51:41"}
+{"current_steps": 780, "total_steps": 1453, "loss": 0.5347, "accuracy": 0.7312500476837158, "lr": 5.156847742922723e-07, "epoch": 0.5370976071613014, "percentage": 53.68, "elapsed_time": "2:07:32", "remaining_time": "1:50:02"}
+{"current_steps": 790, "total_steps": 1453, "loss": 0.5585, "accuracy": 0.7203124761581421, "lr": 5.080336648814077e-07, "epoch": 0.5439834739197796, "percentage": 54.37, "elapsed_time": "2:09:07", "remaining_time": "1:48:21"}
+{"current_steps": 800, "total_steps": 1453, "loss": 0.5629, "accuracy": 0.7328124642372131, "lr": 5.003825554705431e-07, "epoch": 0.5508693406782579, "percentage": 55.06, "elapsed_time": "2:10:43", "remaining_time": "1:46:42"}
+{"current_steps": 810, "total_steps": 1453, "loss": 0.5331, "accuracy": 0.7515624761581421, "lr": 4.927314460596787e-07, "epoch": 0.5577552074367361, "percentage": 55.75, "elapsed_time": "2:12:19", "remaining_time": "1:45:02"}
+{"current_steps": 820, "total_steps": 1453, "loss": 0.5524, "accuracy": 0.7250000238418579, "lr": 4.850803366488141e-07, "epoch": 0.5646410741952144, "percentage": 56.43, "elapsed_time": "2:13:56", "remaining_time": "1:43:24"}
+{"current_steps": 830, "total_steps": 1453, "loss": 0.5671, "accuracy": 0.7281249761581421, "lr": 4.774292272379495e-07, "epoch": 0.5715269409536925, "percentage": 57.12, "elapsed_time": "2:15:34", "remaining_time": "1:41:45"}
+{"current_steps": 840, "total_steps": 1453, "loss": 0.5342, "accuracy": 0.7359375357627869, "lr": 4.697781178270849e-07, "epoch": 0.5784128077121707, "percentage": 57.81, "elapsed_time": "2:17:10", "remaining_time": "1:40:06"}
+{"current_steps": 850, "total_steps": 1453, "loss": 0.5385, "accuracy": 0.753125011920929, "lr": 4.621270084162203e-07, "epoch": 0.585298674470649, "percentage": 58.5, "elapsed_time": "2:18:48", "remaining_time": "1:38:27"}
+{"current_steps": 860, "total_steps": 1453, "loss": 0.564, "accuracy": 0.7109375, "lr": 4.5447589900535577e-07, "epoch": 0.5921845412291272, "percentage": 59.19, "elapsed_time": "2:20:23", "remaining_time": "1:36:48"}
+{"current_steps": 870, "total_steps": 1453, "loss": 0.5551, "accuracy": 0.7406250238418579, "lr": 4.4682478959449117e-07, "epoch": 0.5990704079876055, "percentage": 59.88, "elapsed_time": "2:22:00", "remaining_time": "1:35:09"}
+{"current_steps": 880, "total_steps": 1453, "loss": 0.5571, "accuracy": 0.7046875357627869, "lr": 4.391736801836266e-07, "epoch": 0.6059562747460837, "percentage": 60.56, "elapsed_time": "2:23:36", "remaining_time": "1:33:30"}
+{"current_steps": 890, "total_steps": 1453, "loss": 0.5519, "accuracy": 0.75, "lr": 4.315225707727621e-07, "epoch": 0.6128421415045618, "percentage": 61.25, "elapsed_time": "2:25:15", "remaining_time": "1:31:53"}
+{"current_steps": 900, "total_steps": 1453, "loss": 0.5094, "accuracy": 0.7406250238418579, "lr": 4.238714613618974e-07, "epoch": 0.6197280082630401, "percentage": 61.94, "elapsed_time": "2:26:50", "remaining_time": "1:30:13"}
+{"current_steps": 910, "total_steps": 1453, "loss": 0.5408, "accuracy": 0.7265625, "lr": 4.162203519510329e-07, "epoch": 0.6266138750215183, "percentage": 62.63, "elapsed_time": "2:28:26", "remaining_time": "1:28:34"}
+{"current_steps": 920, "total_steps": 1453, "loss": 0.5653, "accuracy": 0.7312500476837158, "lr": 4.085692425401683e-07, "epoch": 0.6334997417799966, "percentage": 63.32, "elapsed_time": "2:30:04", "remaining_time": "1:26:56"}
+{"current_steps": 930, "total_steps": 1453, "loss": 0.5285, "accuracy": 0.729687511920929, "lr": 4.0091813312930373e-07, "epoch": 0.6403856085384748, "percentage": 64.01, "elapsed_time": "2:31:41", "remaining_time": "1:25:18"}
+{"current_steps": 940, "total_steps": 1453, "loss": 0.5237, "accuracy": 0.7437500357627869, "lr": 3.932670237184392e-07, "epoch": 0.6472714752969531, "percentage": 64.69, "elapsed_time": "2:33:19", "remaining_time": "1:23:40"}
+{"current_steps": 950, "total_steps": 1453, "loss": 0.5382, "accuracy": 0.745312511920929, "lr": 3.856159143075746e-07, "epoch": 0.6541573420554312, "percentage": 65.38, "elapsed_time": "2:34:55", "remaining_time": "1:22:01"}
+{"current_steps": 960, "total_steps": 1453, "loss": 0.5277, "accuracy": 0.7390625476837158, "lr": 3.7796480489671e-07, "epoch": 0.6610432088139094, "percentage": 66.07, "elapsed_time": "2:36:31", "remaining_time": "1:20:22"}
+{"current_steps": 970, "total_steps": 1453, "loss": 0.5169, "accuracy": 0.7546875476837158, "lr": 3.7031369548584544e-07, "epoch": 0.6679290755723877, "percentage": 66.76, "elapsed_time": "2:38:07", "remaining_time": "1:18:44"}
+{"current_steps": 980, "total_steps": 1453, "loss": 0.5366, "accuracy": 0.737500011920929, "lr": 3.6266258607498084e-07, "epoch": 0.6748149423308659, "percentage": 67.45, "elapsed_time": "2:39:44", "remaining_time": "1:17:06"}
+{"current_steps": 990, "total_steps": 1453, "loss": 0.5549, "accuracy": 0.7437500357627869, "lr": 3.550114766641163e-07, "epoch": 0.6817008090893442, "percentage": 68.13, "elapsed_time": "2:41:21", "remaining_time": "1:15:27"}
+{"current_steps": 1000, "total_steps": 1453, "loss": 0.5436, "accuracy": 0.721875011920929, "lr": 3.473603672532517e-07, "epoch": 0.6885866758478223, "percentage": 68.82, "elapsed_time": "2:42:56", "remaining_time": "1:13:48"}
+{"current_steps": 1010, "total_steps": 1453, "loss": 0.5122, "accuracy": 0.7468750476837158, "lr": 3.3970925784238715e-07, "epoch": 0.6954725426063005, "percentage": 69.51, "elapsed_time": "2:44:54", "remaining_time": "1:12:19"}
+{"current_steps": 1020, "total_steps": 1453, "loss": 0.5261, "accuracy": 0.7406250238418579, "lr": 3.3205814843152255e-07, "epoch": 0.7023584093647788, "percentage": 70.2, "elapsed_time": "2:46:30", "remaining_time": "1:10:41"}
+{"current_steps": 1030, "total_steps": 1453, "loss": 0.5143, "accuracy": 0.7562499642372131, "lr": 3.2440703902065795e-07, "epoch": 0.709244276123257, "percentage": 70.89, "elapsed_time": "2:48:07", "remaining_time": "1:09:02"}
+{"current_steps": 1040, "total_steps": 1453, "loss": 0.5347, "accuracy": 0.7484375238418579, "lr": 3.167559296097934e-07, "epoch": 0.7161301428817353, "percentage": 71.58, "elapsed_time": "2:49:44", "remaining_time": "1:07:24"}
+{"current_steps": 1050, "total_steps": 1453, "loss": 0.5281, "accuracy": 0.7437499761581421, "lr": 3.091048201989288e-07, "epoch": 0.7230160096402135, "percentage": 72.26, "elapsed_time": "2:51:21", "remaining_time": "1:05:46"}
+{"current_steps": 1060, "total_steps": 1453, "loss": 0.5556, "accuracy": 0.7328125238418579, "lr": 3.0145371078806426e-07, "epoch": 0.7299018763986916, "percentage": 72.95, "elapsed_time": "2:52:59", "remaining_time": "1:04:08"}
+{"current_steps": 1070, "total_steps": 1453, "loss": 0.518, "accuracy": 0.7437500357627869, "lr": 2.938026013771997e-07, "epoch": 0.7367877431571699, "percentage": 73.64, "elapsed_time": "2:54:35", "remaining_time": "1:02:29"}
+{"current_steps": 1080, "total_steps": 1453, "loss": 0.4957, "accuracy": 0.770312488079071, "lr": 2.861514919663351e-07, "epoch": 0.7436736099156481, "percentage": 74.33, "elapsed_time": "2:56:12", "remaining_time": "1:00:51"}
+{"current_steps": 1090, "total_steps": 1453, "loss": 0.5508, "accuracy": 0.7328125238418579, "lr": 2.785003825554705e-07, "epoch": 0.7505594766741264, "percentage": 75.02, "elapsed_time": "2:57:47", "remaining_time": "0:59:12"}
+{"current_steps": 1100, "total_steps": 1453, "loss": 0.5145, "accuracy": 0.753125011920929, "lr": 2.7084927314460597e-07, "epoch": 0.7574453434326046, "percentage": 75.71, "elapsed_time": "2:59:25", "remaining_time": "0:57:34"}
+{"current_steps": 1110, "total_steps": 1453, "loss": 0.5493, "accuracy": 0.7265625596046448, "lr": 2.6319816373374137e-07, "epoch": 0.7643312101910829, "percentage": 76.39, "elapsed_time": "3:01:01", "remaining_time": "0:55:56"}
+{"current_steps": 1120, "total_steps": 1453, "loss": 0.5556, "accuracy": 0.715624988079071, "lr": 2.555470543228768e-07, "epoch": 0.771217076949561, "percentage": 77.08, "elapsed_time": "3:02:37", "remaining_time": "0:54:17"}
+{"current_steps": 1130, "total_steps": 1453, "loss": 0.5247, "accuracy": 0.753125011920929, "lr": 2.4789594491201223e-07, "epoch": 0.7781029437080392, "percentage": 77.77, "elapsed_time": "3:04:14", "remaining_time": "0:52:39"}
+{"current_steps": 1140, "total_steps": 1453, "loss": 0.5388, "accuracy": 0.7437500357627869, "lr": 2.402448355011477e-07, "epoch": 0.7849888104665175, "percentage": 78.46, "elapsed_time": "3:05:51", "remaining_time": "0:51:01"}
+{"current_steps": 1150, "total_steps": 1453, "loss": 0.5362, "accuracy": 0.7515624761581421, "lr": 2.3259372609028308e-07, "epoch": 0.7918746772249957, "percentage": 79.15, "elapsed_time": "3:07:29", "remaining_time": "0:49:24"}
+{"current_steps": 1160, "total_steps": 1453, "loss": 0.5209, "accuracy": 0.7640625238418579, "lr": 2.2494261667941848e-07, "epoch": 0.798760543983474, "percentage": 79.83, "elapsed_time": "3:09:06", "remaining_time": "0:47:45"}
+{"current_steps": 1170, "total_steps": 1453, "loss": 0.5456, "accuracy": 0.7406250238418579, "lr": 2.1729150726855394e-07, "epoch": 0.8056464107419521, "percentage": 80.52, "elapsed_time": "3:10:41", "remaining_time": "0:46:07"}
+{"current_steps": 1180, "total_steps": 1453, "loss": 0.5012, "accuracy": 0.7406250238418579, "lr": 2.0964039785768936e-07, "epoch": 0.8125322775004303, "percentage": 81.21, "elapsed_time": "3:12:18", "remaining_time": "0:44:29"}
+{"current_steps": 1190, "total_steps": 1453, "loss": 0.5174, "accuracy": 0.7609375715255737, "lr": 2.019892884468248e-07, "epoch": 0.8194181442589086, "percentage": 81.9, "elapsed_time": "3:13:55", "remaining_time": "0:42:51"}
+{"current_steps": 1200, "total_steps": 1453, "loss": 0.5403, "accuracy": 0.714062511920929, "lr": 1.943381790359602e-07, "epoch": 0.8263040110173868, "percentage": 82.59, "elapsed_time": "3:15:33", "remaining_time": "0:41:13"}
+{"current_steps": 1210, "total_steps": 1453, "loss": 0.5334, "accuracy": 0.7484375238418579, "lr": 1.8668706962509562e-07, "epoch": 0.8331898777758651, "percentage": 83.28, "elapsed_time": "3:17:08", "remaining_time": "0:39:35"}
+{"current_steps": 1220, "total_steps": 1453, "loss": 0.5213, "accuracy": 0.7359374761581421, "lr": 1.7903596021423107e-07, "epoch": 0.8400757445343433, "percentage": 83.96, "elapsed_time": "3:18:45", "remaining_time": "0:37:57"}
+{"current_steps": 1230, "total_steps": 1453, "loss": 0.493, "accuracy": 0.7718750238418579, "lr": 1.7138485080336647e-07, "epoch": 0.8469616112928214, "percentage": 84.65, "elapsed_time": "3:20:23", "remaining_time": "0:36:19"}
+{"current_steps": 1240, "total_steps": 1453, "loss": 0.4972, "accuracy": 0.7671875357627869, "lr": 1.637337413925019e-07, "epoch": 0.8538474780512997, "percentage": 85.34, "elapsed_time": "3:21:59", "remaining_time": "0:34:41"}
+{"current_steps": 1250, "total_steps": 1453, "loss": 0.5792, "accuracy": 0.7156250476837158, "lr": 1.5608263198163733e-07, "epoch": 0.8607333448097779, "percentage": 86.03, "elapsed_time": "3:23:36", "remaining_time": "0:33:04"}
+{"current_steps": 1260, "total_steps": 1453, "loss": 0.5382, "accuracy": 0.71875, "lr": 1.4843152257077276e-07, "epoch": 0.8676192115682562, "percentage": 86.72, "elapsed_time": "3:25:14", "remaining_time": "0:31:26"}
+{"current_steps": 1270, "total_steps": 1453, "loss": 0.5103, "accuracy": 0.7515625357627869, "lr": 1.4078041315990818e-07, "epoch": 0.8745050783267344, "percentage": 87.41, "elapsed_time": "3:26:50", "remaining_time": "0:29:48"}
+{"current_steps": 1280, "total_steps": 1453, "loss": 0.5217, "accuracy": 0.7484375238418579, "lr": 1.331293037490436e-07, "epoch": 0.8813909450852127, "percentage": 88.09, "elapsed_time": "3:28:26", "remaining_time": "0:28:10"}
+{"current_steps": 1290, "total_steps": 1453, "loss": 0.5456, "accuracy": 0.746874988079071, "lr": 1.25478194338179e-07, "epoch": 0.8882768118436908, "percentage": 88.78, "elapsed_time": "3:30:03", "remaining_time": "0:26:32"}
+{"current_steps": 1300, "total_steps": 1453, "loss": 0.525, "accuracy": 0.745312511920929, "lr": 1.1782708492731445e-07, "epoch": 0.895162678602169, "percentage": 89.47, "elapsed_time": "3:31:42", "remaining_time": "0:24:54"}
+{"current_steps": 1310, "total_steps": 1453, "loss": 0.521, "accuracy": 0.7250000238418579, "lr": 1.1017597551644987e-07, "epoch": 0.9020485453606473, "percentage": 90.16, "elapsed_time": "3:33:18", "remaining_time": "0:23:17"}
+{"current_steps": 1320, "total_steps": 1453, "loss": 0.5178, "accuracy": 0.745312511920929, "lr": 1.0252486610558531e-07, "epoch": 0.9089344121191255, "percentage": 90.85, "elapsed_time": "3:34:54", "remaining_time": "0:21:39"}
+{"current_steps": 1330, "total_steps": 1453, "loss": 0.5512, "accuracy": 0.721875011920929, "lr": 9.487375669472072e-08, "epoch": 0.9158202788776038, "percentage": 91.53, "elapsed_time": "3:36:32", "remaining_time": "0:20:01"}
+{"current_steps": 1340, "total_steps": 1453, "loss": 0.525, "accuracy": 0.7437500357627869, "lr": 8.722264728385616e-08, "epoch": 0.9227061456360819, "percentage": 92.22, "elapsed_time": "3:38:08", "remaining_time": "0:18:23"}
+{"current_steps": 1350, "total_steps": 1453, "loss": 0.529, "accuracy": 0.7265625, "lr": 7.957153787299158e-08, "epoch": 0.9295920123945601, "percentage": 92.91, "elapsed_time": "3:39:44", "remaining_time": "0:16:45"}
+{"current_steps": 1360, "total_steps": 1453, "loss": 0.4741, "accuracy": 0.770312488079071, "lr": 7.1920428462127e-08, "epoch": 0.9364778791530384, "percentage": 93.6, "elapsed_time": "3:41:20", "remaining_time": "0:15:08"}
+{"current_steps": 1370, "total_steps": 1453, "loss": 0.5188, "accuracy": 0.7515625357627869, "lr": 6.426931905126243e-08, "epoch": 0.9433637459115166, "percentage": 94.29, "elapsed_time": "3:42:55", "remaining_time": "0:13:30"}
+{"current_steps": 1380, "total_steps": 1453, "loss": 0.5022, "accuracy": 0.7671874761581421, "lr": 5.661820964039785e-08, "epoch": 0.9502496126699949, "percentage": 94.98, "elapsed_time": "3:44:31", "remaining_time": "0:11:52"}
+{"current_steps": 1390, "total_steps": 1453, "loss": 0.5119, "accuracy": 0.753125011920929, "lr": 4.896710022953328e-08, "epoch": 0.9571354794284731, "percentage": 95.66, "elapsed_time": "3:46:08", "remaining_time": "0:10:14"}
+{"current_steps": 1400, "total_steps": 1453, "loss": 0.5312, "accuracy": 0.745312511920929, "lr": 4.1315990818668707e-08, "epoch": 0.9640213461869512, "percentage": 96.35, "elapsed_time": "3:47:44", "remaining_time": "0:08:37"}
+{"current_steps": 1410, "total_steps": 1453, "loss": 0.4874, "accuracy": 0.7718750238418579, "lr": 3.366488140780413e-08, "epoch": 0.9709072129454295, "percentage": 97.04, "elapsed_time": "3:49:20", "remaining_time": "0:06:59"}
+{"current_steps": 1420, "total_steps": 1453, "loss": 0.5022, "accuracy": 0.7671874761581421, "lr": 2.6013771996939555e-08, "epoch": 0.9777930797039077, "percentage": 97.73, "elapsed_time": "3:50:59", "remaining_time": "0:05:22"}
+{"current_steps": 1430, "total_steps": 1453, "loss": 0.4884, "accuracy": 0.778124988079071, "lr": 1.8362662586074982e-08, "epoch": 0.984678946462386, "percentage": 98.42, "elapsed_time": "3:52:37", "remaining_time": "0:03:44"}
+{"current_steps": 1440, "total_steps": 1453, "loss": 0.5198, "accuracy": 0.734375, "lr": 1.0711553175210405e-08, "epoch": 0.9915648132208642, "percentage": 99.11, "elapsed_time": "3:54:14", "remaining_time": "0:02:06"}
+{"current_steps": 1450, "total_steps": 1453, "loss": 0.4988, "accuracy": 0.7734375, "lr": 3.06044376434583e-09, "epoch": 0.9984506799793424, "percentage": 99.79, "elapsed_time": "3:55:51", "remaining_time": "0:00:29"}
+{"current_steps": 1453, "total_steps": 1453, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:56:33", "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": 1453,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006885866758478224,
+      "grad_norm": 21.357118272730254,
+      "learning_rate": 6.164383561643836e-08,
+      "logits/chosen": 0.028968211263418198,
+      "logits/rejected": 0.01612178608775139,
+      "logps/chosen": -197.14283752441406,
+      "logps/rejected": -195.18118286132812,
+      "loss": 0.694,
+      "rewards/accuracies": 0.3843749761581421,
+      "rewards/chosen": -0.0008211384410969913,
+      "rewards/margins": -0.0012691060546785593,
+      "rewards/rejected": 0.00044796784641221166,
+      "step": 10
+    },
+    {
+      "epoch": 0.013771733516956448,
+      "grad_norm": 22.78927104925093,
+      "learning_rate": 1.3013698630136985e-07,
+      "logits/chosen": 0.05674262344837189,
+      "logits/rejected": 0.0543050691485405,
+      "logps/chosen": -196.9640655517578,
+      "logps/rejected": -198.33688354492188,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.5015624761581421,
+      "rewards/chosen": 0.0005912931519560516,
+      "rewards/margins": -0.0018875878304243088,
+      "rewards/rejected": 0.0024788810405880213,
+      "step": 20
+    },
+    {
+      "epoch": 0.02065760027543467,
+      "grad_norm": 20.1623734420225,
+      "learning_rate": 1.9863013698630135e-07,
+      "logits/chosen": 0.030807409435510635,
+      "logits/rejected": 0.015413804911077023,
+      "logps/chosen": -200.63473510742188,
+      "logps/rejected": -193.79344177246094,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": -0.00030722294468432665,
+      "rewards/margins": 0.0004742158344015479,
+      "rewards/rejected": -0.0007814386044628918,
+      "step": 30
+    },
+    {
+      "epoch": 0.027543467033912895,
+      "grad_norm": 19.302715968951826,
+      "learning_rate": 2.671232876712329e-07,
+      "logits/chosen": 0.019373048096895218,
+      "logits/rejected": 0.015362609177827835,
+      "logps/chosen": -193.3689422607422,
+      "logps/rejected": -193.8937530517578,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.00165457627736032,
+      "rewards/margins": -0.00010138965444639325,
+      "rewards/rejected": 0.001755966106429696,
+      "step": 40
+    },
+    {
+      "epoch": 0.03442933379239112,
+      "grad_norm": 19.28639543966955,
+      "learning_rate": 3.3561643835616436e-07,
+      "logits/chosen": 0.02099643275141716,
+      "logits/rejected": 0.017172984778881073,
+      "logps/chosen": -195.41319274902344,
+      "logps/rejected": -192.13592529296875,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5265625715255737,
+      "rewards/chosen": 0.003476072335615754,
+      "rewards/margins": 0.0012514767004176974,
+      "rewards/rejected": 0.0022245957516133785,
+      "step": 50
+    },
+    {
+      "epoch": 0.04131520055086934,
+      "grad_norm": 18.35177129376054,
+      "learning_rate": 4.041095890410959e-07,
+      "logits/chosen": 0.028478674590587616,
+      "logits/rejected": 0.045705921947956085,
+      "logps/chosen": -193.37350463867188,
+      "logps/rejected": -193.1693115234375,
+      "loss": 0.6917,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": 0.007831841707229614,
+      "rewards/margins": 0.0032318192534148693,
+      "rewards/rejected": 0.004600022919476032,
+      "step": 60
+    },
+    {
+      "epoch": 0.04820106730934756,
+      "grad_norm": 20.04933062392871,
+      "learning_rate": 4.726027397260274e-07,
+      "logits/chosen": 0.030644051730632782,
+      "logits/rejected": 0.010686805471777916,
+      "logps/chosen": -195.0802459716797,
+      "logps/rejected": -192.6405792236328,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.503125011920929,
+      "rewards/chosen": 0.011022167280316353,
+      "rewards/margins": 0.0009471712401136756,
+      "rewards/rejected": 0.010074996389448643,
+      "step": 70
+    },
+    {
+      "epoch": 0.05508693406782579,
+      "grad_norm": 20.668505160828992,
+      "learning_rate": 5.410958904109589e-07,
+      "logits/chosen": 0.026326147839426994,
+      "logits/rejected": 0.04052453488111496,
+      "logps/chosen": -197.54429626464844,
+      "logps/rejected": -190.3190155029297,
+      "loss": 0.6908,
+      "rewards/accuracies": 0.5437500476837158,
+      "rewards/chosen": 0.01964644528925419,
+      "rewards/margins": 0.005270515568554401,
+      "rewards/rejected": 0.014375930652022362,
+      "step": 80
+    },
+    {
+      "epoch": 0.06197280082630401,
+      "grad_norm": 21.121196165929355,
+      "learning_rate": 6.095890410958904e-07,
+      "logits/chosen": -0.019326386973261833,
+      "logits/rejected": -0.022055240347981453,
+      "logps/chosen": -186.5928955078125,
+      "logps/rejected": -186.8990478515625,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.024418987333774567,
+      "rewards/margins": 0.00805748626589775,
+      "rewards/rejected": 0.016361497342586517,
+      "step": 90
+    },
+    {
+      "epoch": 0.06885866758478223,
+      "grad_norm": 21.91548535538128,
+      "learning_rate": 6.78082191780822e-07,
+      "logits/chosen": 0.011051855981349945,
+      "logits/rejected": 0.012394784018397331,
+      "logps/chosen": -195.57264709472656,
+      "logps/rejected": -193.32449340820312,
+      "loss": 0.6901,
+      "rewards/accuracies": 0.5531250238418579,
+      "rewards/chosen": 0.03320036083459854,
+      "rewards/margins": 0.006988395471125841,
+      "rewards/rejected": 0.026211963966488838,
+      "step": 100
+    },
+    {
+      "epoch": 0.07574453434326046,
+      "grad_norm": 21.717264270490062,
+      "learning_rate": 7.465753424657533e-07,
+      "logits/chosen": 0.012640159577131271,
+      "logits/rejected": 0.010473139584064484,
+      "logps/chosen": -186.4929962158203,
+      "logps/rejected": -187.80308532714844,
+      "loss": 0.6856,
+      "rewards/accuracies": 0.6171875,
+      "rewards/chosen": 0.04811429604887962,
+      "rewards/margins": 0.016630370169878006,
+      "rewards/rejected": 0.03148392587900162,
+      "step": 110
+    },
+    {
+      "epoch": 0.08263040110173868,
+      "grad_norm": 19.33792551477739,
+      "learning_rate": 8.150684931506849e-07,
+      "logits/chosen": 0.025827227160334587,
+      "logits/rejected": 0.02327391505241394,
+      "logps/chosen": -190.1212921142578,
+      "logps/rejected": -187.36219787597656,
+      "loss": 0.6837,
+      "rewards/accuracies": 0.5953124761581421,
+      "rewards/chosen": 0.06050765886902809,
+      "rewards/margins": 0.020764853805303574,
+      "rewards/rejected": 0.039742808789014816,
+      "step": 120
+    },
+    {
+      "epoch": 0.08951626786021691,
+      "grad_norm": 20.381956172548726,
+      "learning_rate": 8.835616438356164e-07,
+      "logits/chosen": -0.005789112765341997,
+      "logits/rejected": -0.013411665335297585,
+      "logps/chosen": -192.898681640625,
+      "logps/rejected": -190.70518493652344,
+      "loss": 0.682,
+      "rewards/accuracies": 0.6031250357627869,
+      "rewards/chosen": 0.08533641695976257,
+      "rewards/margins": 0.025243345648050308,
+      "rewards/rejected": 0.060093071311712265,
+      "step": 130
+    },
+    {
+      "epoch": 0.09640213461869512,
+      "grad_norm": 20.606801959315014,
+      "learning_rate": 9.520547945205479e-07,
+      "logits/chosen": -0.016342442482709885,
+      "logits/rejected": -0.025571543723344803,
+      "logps/chosen": -192.14207458496094,
+      "logps/rejected": -187.4148712158203,
+      "loss": 0.6789,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.10957922041416168,
+      "rewards/margins": 0.033595748245716095,
+      "rewards/rejected": 0.07598347216844559,
+      "step": 140
+    },
+    {
+      "epoch": 0.10328800137717335,
+      "grad_norm": 23.262305629362952,
+      "learning_rate": 9.977046671767407e-07,
+      "logits/chosen": -0.0596565343439579,
+      "logits/rejected": -0.07673357427120209,
+      "logps/chosen": -188.7398223876953,
+      "logps/rejected": -188.24871826171875,
+      "loss": 0.6775,
+      "rewards/accuracies": 0.5906250476837158,
+      "rewards/chosen": 0.12745949625968933,
+      "rewards/margins": 0.03920283168554306,
+      "rewards/rejected": 0.08825664967298508,
+      "step": 150
+    },
+    {
+      "epoch": 0.11017386813565158,
+      "grad_norm": 19.7846291123117,
+      "learning_rate": 9.90053557765876e-07,
+      "logits/chosen": -0.047244228422641754,
+      "logits/rejected": -0.04694109782576561,
+      "logps/chosen": -181.18203735351562,
+      "logps/rejected": -178.70843505859375,
+      "loss": 0.6647,
+      "rewards/accuracies": 0.6546875238418579,
+      "rewards/chosen": 0.15349924564361572,
+      "rewards/margins": 0.06813298165798187,
+      "rewards/rejected": 0.08536626398563385,
+      "step": 160
+    },
+    {
+      "epoch": 0.1170597348941298,
+      "grad_norm": 21.472880138840512,
+      "learning_rate": 9.824024483550113e-07,
+      "logits/chosen": -0.14841578900814056,
+      "logits/rejected": -0.12123996764421463,
+      "logps/chosen": -190.9058837890625,
+      "logps/rejected": -187.15444946289062,
+      "loss": 0.6698,
+      "rewards/accuracies": 0.604687511920929,
+      "rewards/chosen": 0.16753645241260529,
+      "rewards/margins": 0.06376808881759644,
+      "rewards/rejected": 0.10376835614442825,
+      "step": 170
+    },
+    {
+      "epoch": 0.12394560165260803,
+      "grad_norm": 23.964636488520863,
+      "learning_rate": 9.747513389441468e-07,
+      "logits/chosen": -0.13839945197105408,
+      "logits/rejected": -0.1292952597141266,
+      "logps/chosen": -188.83291625976562,
+      "logps/rejected": -189.17947387695312,
+      "loss": 0.6713,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": 0.15886150300502777,
+      "rewards/margins": 0.06130904704332352,
+      "rewards/rejected": 0.09755245596170425,
+      "step": 180
+    },
+    {
+      "epoch": 0.13083146841108625,
+      "grad_norm": 21.014923075997917,
+      "learning_rate": 9.671002295332823e-07,
+      "logits/chosen": -0.17998671531677246,
+      "logits/rejected": -0.16726107895374298,
+      "logps/chosen": -186.77247619628906,
+      "logps/rejected": -183.4087371826172,
+      "loss": 0.6543,
+      "rewards/accuracies": 0.6296875476837158,
+      "rewards/chosen": 0.2054910957813263,
+      "rewards/margins": 0.11184875667095184,
+      "rewards/rejected": 0.09364232420921326,
+      "step": 190
+    },
+    {
+      "epoch": 0.13771733516956447,
+      "grad_norm": 20.66388348945257,
+      "learning_rate": 9.594491201224178e-07,
+      "logits/chosen": -0.14593414962291718,
+      "logits/rejected": -0.13679011166095734,
+      "logps/chosen": -190.45223999023438,
+      "logps/rejected": -191.02951049804688,
+      "loss": 0.6718,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": 0.16157108545303345,
+      "rewards/margins": 0.07207615673542023,
+      "rewards/rejected": 0.08949493616819382,
+      "step": 200
+    },
+    {
+      "epoch": 0.14460320192804269,
+      "grad_norm": 29.99539925690682,
+      "learning_rate": 9.517980107115531e-07,
+      "logits/chosen": -0.15793928503990173,
+      "logits/rejected": -0.15555617213249207,
+      "logps/chosen": -196.1856231689453,
+      "logps/rejected": -190.77688598632812,
+      "loss": 0.657,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": 0.15518102049827576,
+      "rewards/margins": 0.10747373104095459,
+      "rewards/rejected": 0.04770728200674057,
+      "step": 210
+    },
+    {
+      "epoch": 0.15148906868652093,
+      "grad_norm": 22.484571855499286,
+      "learning_rate": 9.441469013006885e-07,
+      "logits/chosen": -0.09849053621292114,
+      "logits/rejected": -0.10602966696023941,
+      "logps/chosen": -188.15655517578125,
+      "logps/rejected": -189.34217834472656,
+      "loss": 0.6495,
+      "rewards/accuracies": 0.6375000476837158,
+      "rewards/chosen": 0.14013966917991638,
+      "rewards/margins": 0.12994103133678436,
+      "rewards/rejected": 0.010198642499744892,
+      "step": 220
+    },
+    {
+      "epoch": 0.15837493544499914,
+      "grad_norm": 23.14684419321817,
+      "learning_rate": 9.364957918898239e-07,
+      "logits/chosen": -0.12771211564540863,
+      "logits/rejected": -0.12738053500652313,
+      "logps/chosen": -188.27279663085938,
+      "logps/rejected": -189.2296142578125,
+      "loss": 0.6483,
+      "rewards/accuracies": 0.6421874761581421,
+      "rewards/chosen": 0.12199673056602478,
+      "rewards/margins": 0.13607241213321686,
+      "rewards/rejected": -0.014075696468353271,
+      "step": 230
+    },
+    {
+      "epoch": 0.16526080220347736,
+      "grad_norm": 21.14311199895393,
+      "learning_rate": 9.288446824789594e-07,
+      "logits/chosen": -0.1267087310552597,
+      "logits/rejected": -0.11214447021484375,
+      "logps/chosen": -183.26416015625,
+      "logps/rejected": -186.4851837158203,
+      "loss": 0.641,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.10954004526138306,
+      "rewards/margins": 0.14909771084785461,
+      "rewards/rejected": -0.03955767676234245,
+      "step": 240
+    },
+    {
+      "epoch": 0.17214666896195557,
+      "grad_norm": 25.009711908956962,
+      "learning_rate": 9.211935730680948e-07,
+      "logits/chosen": -0.14686468243598938,
+      "logits/rejected": -0.12413311004638672,
+      "logps/chosen": -193.5541229248047,
+      "logps/rejected": -197.37326049804688,
+      "loss": 0.6497,
+      "rewards/accuracies": 0.6328125596046448,
+      "rewards/chosen": 0.06355239450931549,
+      "rewards/margins": 0.1444573700428009,
+      "rewards/rejected": -0.08090498298406601,
+      "step": 250
+    },
+    {
+      "epoch": 0.17903253572043382,
+      "grad_norm": 21.375848926501856,
+      "learning_rate": 9.135424636572303e-07,
+      "logits/chosen": -0.12750156223773956,
+      "logits/rejected": -0.11904246360063553,
+      "logps/chosen": -194.12649536132812,
+      "logps/rejected": -188.32383728027344,
+      "loss": 0.6466,
+      "rewards/accuracies": 0.6296875476837158,
+      "rewards/chosen": 0.060907114297151566,
+      "rewards/margins": 0.14842237532138824,
+      "rewards/rejected": -0.08751524984836578,
+      "step": 260
+    },
+    {
+      "epoch": 0.18591840247891203,
+      "grad_norm": 23.09705200083216,
+      "learning_rate": 9.058913542463656e-07,
+      "logits/chosen": -0.20926274359226227,
+      "logits/rejected": -0.19603878259658813,
+      "logps/chosen": -193.5789337158203,
+      "logps/rejected": -190.8974609375,
+      "loss": 0.6325,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": 0.08186967670917511,
+      "rewards/margins": 0.190498948097229,
+      "rewards/rejected": -0.1086292639374733,
+      "step": 270
+    },
+    {
+      "epoch": 0.19280426923739025,
+      "grad_norm": 21.037835718471506,
+      "learning_rate": 8.982402448355011e-07,
+      "logits/chosen": -0.17319074273109436,
+      "logits/rejected": -0.17468921840190887,
+      "logps/chosen": -192.30039978027344,
+      "logps/rejected": -192.83987426757812,
+      "loss": 0.6299,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.08289219439029694,
+      "rewards/margins": 0.21142172813415527,
+      "rewards/rejected": -0.12852953374385834,
+      "step": 280
+    },
+    {
+      "epoch": 0.1996901359958685,
+      "grad_norm": 21.56149675955503,
+      "learning_rate": 8.905891354246365e-07,
+      "logits/chosen": -0.12733662128448486,
+      "logits/rejected": -0.15374454855918884,
+      "logps/chosen": -191.71080017089844,
+      "logps/rejected": -192.95883178710938,
+      "loss": 0.6268,
+      "rewards/accuracies": 0.6671875715255737,
+      "rewards/chosen": 0.02507857419550419,
+      "rewards/margins": 0.211945578455925,
+      "rewards/rejected": -0.18686699867248535,
+      "step": 290
+    },
+    {
+      "epoch": 0.2065760027543467,
+      "grad_norm": 21.105833082853255,
+      "learning_rate": 8.829380260137719e-07,
+      "logits/chosen": -0.14651824533939362,
+      "logits/rejected": -0.12377053499221802,
+      "logps/chosen": -195.86325073242188,
+      "logps/rejected": -201.83001708984375,
+      "loss": 0.6151,
+      "rewards/accuracies": 0.7046874761581421,
+      "rewards/chosen": 0.008288959972560406,
+      "rewards/margins": 0.25510185956954956,
+      "rewards/rejected": -0.2468128800392151,
+      "step": 300
+    },
+    {
+      "epoch": 0.21346186951282492,
+      "grad_norm": 21.239404607014603,
+      "learning_rate": 8.752869166029074e-07,
+      "logits/chosen": -0.13711729645729065,
+      "logits/rejected": -0.11297348141670227,
+      "logps/chosen": -197.0601043701172,
+      "logps/rejected": -203.13510131835938,
+      "loss": 0.6302,
+      "rewards/accuracies": 0.6578125357627869,
+      "rewards/chosen": -0.033613648265600204,
+      "rewards/margins": 0.23345637321472168,
+      "rewards/rejected": -0.2670700252056122,
+      "step": 310
+    },
+    {
+      "epoch": 0.22034773627130316,
+      "grad_norm": 28.358576456872942,
+      "learning_rate": 8.676358071920427e-07,
+      "logits/chosen": -0.15952648222446442,
+      "logits/rejected": -0.13048917055130005,
+      "logps/chosen": -191.40574645996094,
+      "logps/rejected": -194.6696319580078,
+      "loss": 0.6266,
+      "rewards/accuracies": 0.6656249761581421,
+      "rewards/chosen": -0.06403035670518875,
+      "rewards/margins": 0.23444205522537231,
+      "rewards/rejected": -0.29847240447998047,
+      "step": 320
+    },
+    {
+      "epoch": 0.22723360302978138,
+      "grad_norm": 21.824170653831928,
+      "learning_rate": 8.599846977811782e-07,
+      "logits/chosen": -0.1640833169221878,
+      "logits/rejected": -0.1528327465057373,
+      "logps/chosen": -187.84799194335938,
+      "logps/rejected": -201.14830017089844,
+      "loss": 0.612,
+      "rewards/accuracies": 0.6796875,
+      "rewards/chosen": -0.07599131762981415,
+      "rewards/margins": 0.2906650900840759,
+      "rewards/rejected": -0.36665642261505127,
+      "step": 330
+    },
+    {
+      "epoch": 0.2341194697882596,
+      "grad_norm": 21.074085075809414,
+      "learning_rate": 8.523335883703136e-07,
+      "logits/chosen": -0.1743679940700531,
+      "logits/rejected": -0.16399502754211426,
+      "logps/chosen": -202.89622497558594,
+      "logps/rejected": -212.13699340820312,
+      "loss": 0.6088,
+      "rewards/accuracies": 0.6796875596046448,
+      "rewards/chosen": -0.055201247334480286,
+      "rewards/margins": 0.30173224210739136,
+      "rewards/rejected": -0.35693347454071045,
+      "step": 340
+    },
+    {
+      "epoch": 0.2410053365467378,
+      "grad_norm": 23.097522066642618,
+      "learning_rate": 8.446824789594492e-07,
+      "logits/chosen": -0.17943890392780304,
+      "logits/rejected": -0.16794875264167786,
+      "logps/chosen": -194.87747192382812,
+      "logps/rejected": -194.46771240234375,
+      "loss": 0.6174,
+      "rewards/accuracies": 0.667187511920929,
+      "rewards/chosen": -0.12930315732955933,
+      "rewards/margins": 0.2889351546764374,
+      "rewards/rejected": -0.4182383418083191,
+      "step": 350
+    },
+    {
+      "epoch": 0.24789120330521605,
+      "grad_norm": 22.706444342156583,
+      "learning_rate": 8.370313695485846e-07,
+      "logits/chosen": -0.19892311096191406,
+      "logits/rejected": -0.18966780602931976,
+      "logps/chosen": -190.1072998046875,
+      "logps/rejected": -193.8407745361328,
+      "loss": 0.6075,
+      "rewards/accuracies": 0.6765625476837158,
+      "rewards/chosen": -0.08109837025403976,
+      "rewards/margins": 0.31933993101119995,
+      "rewards/rejected": -0.4004383087158203,
+      "step": 360
+    },
+    {
+      "epoch": 0.25477707006369427,
+      "grad_norm": 22.66877601351879,
+      "learning_rate": 8.293802601377199e-07,
+      "logits/chosen": -0.20010100305080414,
+      "logits/rejected": -0.17780742049217224,
+      "logps/chosen": -194.33409118652344,
+      "logps/rejected": -196.40740966796875,
+      "loss": 0.6099,
+      "rewards/accuracies": 0.6812500357627869,
+      "rewards/chosen": -0.10439629852771759,
+      "rewards/margins": 0.31406161189079285,
+      "rewards/rejected": -0.41845792531967163,
+      "step": 370
+    },
+    {
+      "epoch": 0.2616629368221725,
+      "grad_norm": 23.861244423965402,
+      "learning_rate": 8.217291507268554e-07,
+      "logits/chosen": -0.2074911892414093,
+      "logits/rejected": -0.2102966606616974,
+      "logps/chosen": -204.8916015625,
+      "logps/rejected": -206.48434448242188,
+      "loss": 0.612,
+      "rewards/accuracies": 0.659375011920929,
+      "rewards/chosen": -0.12396355718374252,
+      "rewards/margins": 0.32503077387809753,
+      "rewards/rejected": -0.44899433851242065,
+      "step": 380
+    },
+    {
+      "epoch": 0.2685488035806507,
+      "grad_norm": 18.426704146792513,
+      "learning_rate": 8.140780413159908e-07,
+      "logits/chosen": -0.1731143593788147,
+      "logits/rejected": -0.1533968597650528,
+      "logps/chosen": -189.8383331298828,
+      "logps/rejected": -195.228515625,
+      "loss": 0.6082,
+      "rewards/accuracies": 0.6796875,
+      "rewards/chosen": -0.16357733309268951,
+      "rewards/margins": 0.3212567865848541,
+      "rewards/rejected": -0.48483413457870483,
+      "step": 390
+    },
+    {
+      "epoch": 0.27543467033912894,
+      "grad_norm": 22.10185350841625,
+      "learning_rate": 8.064269319051263e-07,
+      "logits/chosen": -0.19260063767433167,
+      "logits/rejected": -0.18926046788692474,
+      "logps/chosen": -203.06272888183594,
+      "logps/rejected": -201.2696533203125,
+      "loss": 0.6055,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -0.19341671466827393,
+      "rewards/margins": 0.3326266407966614,
+      "rewards/rejected": -0.5260434150695801,
+      "step": 400
+    },
+    {
+      "epoch": 0.2823205370976072,
+      "grad_norm": 19.998016249738562,
+      "learning_rate": 7.987758224942617e-07,
+      "logits/chosen": -0.21146024763584137,
+      "logits/rejected": -0.17835554480552673,
+      "logps/chosen": -195.14520263671875,
+      "logps/rejected": -204.84442138671875,
+      "loss": 0.5995,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.16101008653640747,
+      "rewards/margins": 0.37827068567276,
+      "rewards/rejected": -0.5392807722091675,
+      "step": 410
+    },
+    {
+      "epoch": 0.28920640385608537,
+      "grad_norm": 23.467770681704234,
+      "learning_rate": 7.91124713083397e-07,
+      "logits/chosen": -0.21747922897338867,
+      "logits/rejected": -0.18482878804206848,
+      "logps/chosen": -196.29568481445312,
+      "logps/rejected": -203.74679565429688,
+      "loss": 0.6077,
+      "rewards/accuracies": 0.6578124761581421,
+      "rewards/chosen": -0.231543630361557,
+      "rewards/margins": 0.3246532380580902,
+      "rewards/rejected": -0.5561968684196472,
+      "step": 420
+    },
+    {
+      "epoch": 0.2960922706145636,
+      "grad_norm": 23.246622169062537,
+      "learning_rate": 7.834736036725325e-07,
+      "logits/chosen": -0.22648438811302185,
+      "logits/rejected": -0.19521580636501312,
+      "logps/chosen": -199.969970703125,
+      "logps/rejected": -207.82162475585938,
+      "loss": 0.5838,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -0.21634486317634583,
+      "rewards/margins": 0.43085139989852905,
+      "rewards/rejected": -0.6471962928771973,
+      "step": 430
+    },
+    {
+      "epoch": 0.30297813737304186,
+      "grad_norm": 21.048208882279503,
+      "learning_rate": 7.758224942616679e-07,
+      "logits/chosen": -0.25602301955223083,
+      "logits/rejected": -0.216285839676857,
+      "logps/chosen": -209.1434326171875,
+      "logps/rejected": -216.78334045410156,
+      "loss": 0.5943,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": -0.26122772693634033,
+      "rewards/margins": 0.4267864227294922,
+      "rewards/rejected": -0.6880142092704773,
+      "step": 440
+    },
+    {
+      "epoch": 0.30986400413152004,
+      "grad_norm": 22.59925573646321,
+      "learning_rate": 7.681713848508034e-07,
+      "logits/chosen": -0.18633471429347992,
+      "logits/rejected": -0.1828474998474121,
+      "logps/chosen": -193.50070190429688,
+      "logps/rejected": -200.55421447753906,
+      "loss": 0.6007,
+      "rewards/accuracies": 0.6968750357627869,
+      "rewards/chosen": -0.2820444107055664,
+      "rewards/margins": 0.3879047632217407,
+      "rewards/rejected": -0.6699492335319519,
+      "step": 450
+    },
+    {
+      "epoch": 0.3167498708899983,
+      "grad_norm": 21.64590415072203,
+      "learning_rate": 7.605202754399388e-07,
+      "logits/chosen": -0.2189503312110901,
+      "logits/rejected": -0.2030341923236847,
+      "logps/chosen": -201.5972900390625,
+      "logps/rejected": -206.25152587890625,
+      "loss": 0.5764,
+      "rewards/accuracies": 0.6859375238418579,
+      "rewards/chosen": -0.22065776586532593,
+      "rewards/margins": 0.47276243567466736,
+      "rewards/rejected": -0.6934202313423157,
+      "step": 460
+    },
+    {
+      "epoch": 0.32363573764847653,
+      "grad_norm": 23.7581974437075,
+      "learning_rate": 7.528691660290742e-07,
+      "logits/chosen": -0.22047793865203857,
+      "logits/rejected": -0.19113516807556152,
+      "logps/chosen": -199.07958984375,
+      "logps/rejected": -199.7004852294922,
+      "loss": 0.5815,
+      "rewards/accuracies": 0.7015624642372131,
+      "rewards/chosen": -0.24612434208393097,
+      "rewards/margins": 0.4380369186401367,
+      "rewards/rejected": -0.6841613054275513,
+      "step": 470
+    },
+    {
+      "epoch": 0.3305216044069547,
+      "grad_norm": 19.206769763517677,
+      "learning_rate": 7.452180566182096e-07,
+      "logits/chosen": -0.2202739715576172,
+      "logits/rejected": -0.19977977871894836,
+      "logps/chosen": -193.5897216796875,
+      "logps/rejected": -202.0029754638672,
+      "loss": 0.601,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.31127315759658813,
+      "rewards/margins": 0.4242890477180481,
+      "rewards/rejected": -0.7355621457099915,
+      "step": 480
+    },
+    {
+      "epoch": 0.33740747116543296,
+      "grad_norm": 24.0864716650183,
+      "learning_rate": 7.37566947207345e-07,
+      "logits/chosen": -0.2397327870130539,
+      "logits/rejected": -0.21453964710235596,
+      "logps/chosen": -203.811279296875,
+      "logps/rejected": -207.71994018554688,
+      "loss": 0.5945,
+      "rewards/accuracies": 0.6687500476837158,
+      "rewards/chosen": -0.1965150386095047,
+      "rewards/margins": 0.4662647843360901,
+      "rewards/rejected": -0.6627798080444336,
+      "step": 490
+    },
+    {
+      "epoch": 0.34429333792391115,
+      "grad_norm": 23.441407049395554,
+      "learning_rate": 7.299158377964805e-07,
+      "logits/chosen": -0.2867848873138428,
+      "logits/rejected": -0.26185181736946106,
+      "logps/chosen": -197.30357360839844,
+      "logps/rejected": -202.0620574951172,
+      "loss": 0.5829,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.22782030701637268,
+      "rewards/margins": 0.4941255450248718,
+      "rewards/rejected": -0.7219458222389221,
+      "step": 500
+    },
+    {
+      "epoch": 0.3511792046823894,
+      "grad_norm": 24.24165547819113,
+      "learning_rate": 7.222647283856159e-07,
+      "logits/chosen": -0.322261780500412,
+      "logits/rejected": -0.29276198148727417,
+      "logps/chosen": -208.84205627441406,
+      "logps/rejected": -212.8937530517578,
+      "loss": 0.5725,
+      "rewards/accuracies": 0.7312500476837158,
+      "rewards/chosen": -0.17469552159309387,
+      "rewards/margins": 0.5125805139541626,
+      "rewards/rejected": -0.6872760057449341,
+      "step": 510
+    },
+    {
+      "epoch": 0.35806507144086763,
+      "grad_norm": 20.872269830269385,
+      "learning_rate": 7.146136189747513e-07,
+      "logits/chosen": -0.3218885660171509,
+      "logits/rejected": -0.29816335439682007,
+      "logps/chosen": -193.01654052734375,
+      "logps/rejected": -196.80349731445312,
+      "loss": 0.577,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.24363525211811066,
+      "rewards/margins": 0.4531596302986145,
+      "rewards/rejected": -0.696794867515564,
+      "step": 520
+    },
+    {
+      "epoch": 0.3649509381993458,
+      "grad_norm": 28.4673161426841,
+      "learning_rate": 7.069625095638867e-07,
+      "logits/chosen": -0.34582602977752686,
+      "logits/rejected": -0.31747424602508545,
+      "logps/chosen": -196.18231201171875,
+      "logps/rejected": -201.42234802246094,
+      "loss": 0.5766,
+      "rewards/accuracies": 0.707812488079071,
+      "rewards/chosen": -0.24639394879341125,
+      "rewards/margins": 0.5019959211349487,
+      "rewards/rejected": -0.7483898997306824,
+      "step": 530
+    },
+    {
+      "epoch": 0.37183680495782406,
+      "grad_norm": 24.919532919405224,
+      "learning_rate": 6.993114001530222e-07,
+      "logits/chosen": -0.3100280165672302,
+      "logits/rejected": -0.29064637422561646,
+      "logps/chosen": -198.67388916015625,
+      "logps/rejected": -202.16505432128906,
+      "loss": 0.5615,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": -0.1877853274345398,
+      "rewards/margins": 0.5081425905227661,
+      "rewards/rejected": -0.6959279179573059,
+      "step": 540
+    },
+    {
+      "epoch": 0.3787226717163023,
+      "grad_norm": 22.60350537919111,
+      "learning_rate": 6.916602907421576e-07,
+      "logits/chosen": -0.29818981885910034,
+      "logits/rejected": -0.26806640625,
+      "logps/chosen": -191.7179412841797,
+      "logps/rejected": -201.2666015625,
+      "loss": 0.5994,
+      "rewards/accuracies": 0.6890625357627869,
+      "rewards/chosen": -0.2534283399581909,
+      "rewards/margins": 0.48638302087783813,
+      "rewards/rejected": -0.739811360836029,
+      "step": 550
+    },
+    {
+      "epoch": 0.3856085384747805,
+      "grad_norm": 25.67908922423141,
+      "learning_rate": 6.84009181331293e-07,
+      "logits/chosen": -0.2803298830986023,
+      "logits/rejected": -0.2273053675889969,
+      "logps/chosen": -193.68869018554688,
+      "logps/rejected": -201.9783935546875,
+      "loss": 0.6023,
+      "rewards/accuracies": 0.6656250357627869,
+      "rewards/chosen": -0.23008039593696594,
+      "rewards/margins": 0.43934205174446106,
+      "rewards/rejected": -0.6694223880767822,
+      "step": 560
+    },
+    {
+      "epoch": 0.39249440523325874,
+      "grad_norm": 23.790727771917158,
+      "learning_rate": 6.763580719204285e-07,
+      "logits/chosen": -0.2388366162776947,
+      "logits/rejected": -0.20770037174224854,
+      "logps/chosen": -195.17596435546875,
+      "logps/rejected": -203.053466796875,
+      "loss": 0.5773,
+      "rewards/accuracies": 0.6812500357627869,
+      "rewards/chosen": -0.26547545194625854,
+      "rewards/margins": 0.4970327615737915,
+      "rewards/rejected": -0.7625082731246948,
+      "step": 570
+    },
+    {
+      "epoch": 0.399380271991737,
+      "grad_norm": 22.2692853997441,
+      "learning_rate": 6.687069625095638e-07,
+      "logits/chosen": -0.25696471333503723,
+      "logits/rejected": -0.2511045038700104,
+      "logps/chosen": -201.10848999023438,
+      "logps/rejected": -210.22183227539062,
+      "loss": 0.5876,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -0.2806377708911896,
+      "rewards/margins": 0.48363256454467773,
+      "rewards/rejected": -0.7642703056335449,
+      "step": 580
+    },
+    {
+      "epoch": 0.40626613875021517,
+      "grad_norm": 20.563254457184485,
+      "learning_rate": 6.610558530986993e-07,
+      "logits/chosen": -0.2363700568675995,
+      "logits/rejected": -0.2016097605228424,
+      "logps/chosen": -192.15310668945312,
+      "logps/rejected": -198.71865844726562,
+      "loss": 0.5925,
+      "rewards/accuracies": 0.6734374761581421,
+      "rewards/chosen": -0.2997559607028961,
+      "rewards/margins": 0.4971032738685608,
+      "rewards/rejected": -0.7968591451644897,
+      "step": 590
+    },
+    {
+      "epoch": 0.4131520055086934,
+      "grad_norm": 27.42297939022822,
+      "learning_rate": 6.534047436878347e-07,
+      "logits/chosen": -0.25612396001815796,
+      "logits/rejected": -0.24113687872886658,
+      "logps/chosen": -202.80996704101562,
+      "logps/rejected": -206.5990753173828,
+      "loss": 0.5923,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.2972622215747833,
+      "rewards/margins": 0.44471475481987,
+      "rewards/rejected": -0.7419769763946533,
+      "step": 600
+    },
+    {
+      "epoch": 0.42003787226717165,
+      "grad_norm": 21.920676991754373,
+      "learning_rate": 6.457536342769701e-07,
+      "logits/chosen": -0.298888236284256,
+      "logits/rejected": -0.2644284665584564,
+      "logps/chosen": -196.77108764648438,
+      "logps/rejected": -203.39205932617188,
+      "loss": 0.6058,
+      "rewards/accuracies": 0.6890625357627869,
+      "rewards/chosen": -0.3232823312282562,
+      "rewards/margins": 0.45335179567337036,
+      "rewards/rejected": -0.7766340970993042,
+      "step": 610
+    },
+    {
+      "epoch": 0.42692373902564984,
+      "grad_norm": 22.64266147842626,
+      "learning_rate": 6.381025248661056e-07,
+      "logits/chosen": -0.28491443395614624,
+      "logits/rejected": -0.25603392720222473,
+      "logps/chosen": -196.12831115722656,
+      "logps/rejected": -210.8316192626953,
+      "loss": 0.5515,
+      "rewards/accuracies": 0.7312500476837158,
+      "rewards/chosen": -0.22433951497077942,
+      "rewards/margins": 0.564956545829773,
+      "rewards/rejected": -0.7892960906028748,
+      "step": 620
+    },
+    {
+      "epoch": 0.4338096057841281,
+      "grad_norm": 22.374449198558654,
+      "learning_rate": 6.304514154552409e-07,
+      "logits/chosen": -0.2371789813041687,
+      "logits/rejected": -0.21084988117218018,
+      "logps/chosen": -196.3636932373047,
+      "logps/rejected": -205.9162139892578,
+      "loss": 0.5643,
+      "rewards/accuracies": 0.723437488079071,
+      "rewards/chosen": -0.22664019465446472,
+      "rewards/margins": 0.5722544193267822,
+      "rewards/rejected": -0.7988946437835693,
+      "step": 630
+    },
+    {
+      "epoch": 0.4406954725426063,
+      "grad_norm": 23.27173099331,
+      "learning_rate": 6.228003060443764e-07,
+      "logits/chosen": -0.22489549219608307,
+      "logits/rejected": -0.20038262009620667,
+      "logps/chosen": -186.9170684814453,
+      "logps/rejected": -196.61355590820312,
+      "loss": 0.5342,
+      "rewards/accuracies": 0.7531250715255737,
+      "rewards/chosen": -0.1936413049697876,
+      "rewards/margins": 0.6107944250106812,
+      "rewards/rejected": -0.8044357299804688,
+      "step": 640
+    },
+    {
+      "epoch": 0.4475813393010845,
+      "grad_norm": 23.12513848271565,
+      "learning_rate": 6.151491966335118e-07,
+      "logits/chosen": -0.2062905728816986,
+      "logits/rejected": -0.1937059462070465,
+      "logps/chosen": -207.9930877685547,
+      "logps/rejected": -216.9258575439453,
+      "loss": 0.5964,
+      "rewards/accuracies": 0.6953125,
+      "rewards/chosen": -0.3074573278427124,
+      "rewards/margins": 0.5258516669273376,
+      "rewards/rejected": -0.8333090543746948,
+      "step": 650
+    },
+    {
+      "epoch": 0.45446720605956276,
+      "grad_norm": 23.623328160601158,
+      "learning_rate": 6.074980872226473e-07,
+      "logits/chosen": -0.2363741099834442,
+      "logits/rejected": -0.19654276967048645,
+      "logps/chosen": -201.72991943359375,
+      "logps/rejected": -210.9528045654297,
+      "loss": 0.593,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.3014895021915436,
+      "rewards/margins": 0.4921172559261322,
+      "rewards/rejected": -0.7936067581176758,
+      "step": 660
+    },
+    {
+      "epoch": 0.46135307281804094,
+      "grad_norm": 22.738540567341648,
+      "learning_rate": 5.998469778117827e-07,
+      "logits/chosen": -0.25270819664001465,
+      "logits/rejected": -0.22932419180870056,
+      "logps/chosen": -199.99636840820312,
+      "logps/rejected": -211.69168090820312,
+      "loss": 0.5572,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": -0.25672680139541626,
+      "rewards/margins": 0.5584204792976379,
+      "rewards/rejected": -0.8151472806930542,
+      "step": 670
+    },
+    {
+      "epoch": 0.4682389395765192,
+      "grad_norm": 25.684422832815645,
+      "learning_rate": 5.92195868400918e-07,
+      "logits/chosen": -0.19682064652442932,
+      "logits/rejected": -0.1747521609067917,
+      "logps/chosen": -207.11001586914062,
+      "logps/rejected": -213.78707885742188,
+      "loss": 0.574,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.34769681096076965,
+      "rewards/margins": 0.5807652473449707,
+      "rewards/rejected": -0.928462028503418,
+      "step": 680
+    },
+    {
+      "epoch": 0.47512480633499743,
+      "grad_norm": 20.71126021785729,
+      "learning_rate": 5.845447589900535e-07,
+      "logits/chosen": -0.24822764098644257,
+      "logits/rejected": -0.22624938189983368,
+      "logps/chosen": -204.87779235839844,
+      "logps/rejected": -210.4464569091797,
+      "loss": 0.5606,
+      "rewards/accuracies": 0.7375000715255737,
+      "rewards/chosen": -0.28525784611701965,
+      "rewards/margins": 0.5286524891853333,
+      "rewards/rejected": -0.8139103651046753,
+      "step": 690
+    },
+    {
+      "epoch": 0.4820106730934756,
+      "grad_norm": 26.349944755934768,
+      "learning_rate": 5.768936495791889e-07,
+      "logits/chosen": -0.21356113255023956,
+      "logits/rejected": -0.1965031921863556,
+      "logps/chosen": -199.73861694335938,
+      "logps/rejected": -204.8638153076172,
+      "loss": 0.5816,
+      "rewards/accuracies": 0.6968749761581421,
+      "rewards/chosen": -0.3604661524295807,
+      "rewards/margins": 0.5489579439163208,
+      "rewards/rejected": -0.9094240665435791,
+      "step": 700
+    },
+    {
+      "epoch": 0.48889653985195386,
+      "grad_norm": 23.535098442619628,
+      "learning_rate": 5.692425401683244e-07,
+      "logits/chosen": -0.22684970498085022,
+      "logits/rejected": -0.1970938742160797,
+      "logps/chosen": -197.89776611328125,
+      "logps/rejected": -206.56236267089844,
+      "loss": 0.5411,
+      "rewards/accuracies": 0.7359374761581421,
+      "rewards/chosen": -0.3052551746368408,
+      "rewards/margins": 0.689602255821228,
+      "rewards/rejected": -0.9948574304580688,
+      "step": 710
+    },
+    {
+      "epoch": 0.4957824066104321,
+      "grad_norm": 22.76862056281205,
+      "learning_rate": 5.615914307574598e-07,
+      "logits/chosen": -0.2701479494571686,
+      "logits/rejected": -0.2529926002025604,
+      "logps/chosen": -205.52587890625,
+      "logps/rejected": -217.68336486816406,
+      "loss": 0.5499,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.3150857090950012,
+      "rewards/margins": 0.6676312685012817,
+      "rewards/rejected": -0.9827169179916382,
+      "step": 720
+    },
+    {
+      "epoch": 0.5026682733689103,
+      "grad_norm": 24.11490022902473,
+      "learning_rate": 5.539403213465952e-07,
+      "logits/chosen": -0.26072609424591064,
+      "logits/rejected": -0.24569085240364075,
+      "logps/chosen": -206.5780792236328,
+      "logps/rejected": -214.70892333984375,
+      "loss": 0.5664,
+      "rewards/accuracies": 0.7312500476837158,
+      "rewards/chosen": -0.34358713030815125,
+      "rewards/margins": 0.5998888611793518,
+      "rewards/rejected": -0.9434760212898254,
+      "step": 730
+    },
+    {
+      "epoch": 0.5095541401273885,
+      "grad_norm": 24.667914885216494,
+      "learning_rate": 5.462892119357306e-07,
+      "logits/chosen": -0.2955350875854492,
+      "logits/rejected": -0.267596960067749,
+      "logps/chosen": -204.7119140625,
+      "logps/rejected": -219.7845916748047,
+      "loss": 0.6024,
+      "rewards/accuracies": 0.6968750357627869,
+      "rewards/chosen": -0.35112637281417847,
+      "rewards/margins": 0.5716503262519836,
+      "rewards/rejected": -0.9227766394615173,
+      "step": 740
+    },
+    {
+      "epoch": 0.5164400068858668,
+      "grad_norm": 26.70861098025808,
+      "learning_rate": 5.38638102524866e-07,
+      "logits/chosen": -0.27651071548461914,
+      "logits/rejected": -0.2475259155035019,
+      "logps/chosen": -197.40142822265625,
+      "logps/rejected": -209.98281860351562,
+      "loss": 0.564,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.2942546308040619,
+      "rewards/margins": 0.5781306028366089,
+      "rewards/rejected": -0.8723852038383484,
+      "step": 750
+    },
+    {
+      "epoch": 0.523325873644345,
+      "grad_norm": 22.606570297594942,
+      "learning_rate": 5.309869931140015e-07,
+      "logits/chosen": -0.3192262053489685,
+      "logits/rejected": -0.2856769859790802,
+      "logps/chosen": -198.66526794433594,
+      "logps/rejected": -209.6296844482422,
+      "loss": 0.5744,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": -0.33672210574150085,
+      "rewards/margins": 0.5660472512245178,
+      "rewards/rejected": -0.9027693271636963,
+      "step": 760
+    },
+    {
+      "epoch": 0.5302117404028232,
+      "grad_norm": 20.35249313890797,
+      "learning_rate": 5.233358837031369e-07,
+      "logits/chosen": -0.28755855560302734,
+      "logits/rejected": -0.23860663175582886,
+      "logps/chosen": -206.0916290283203,
+      "logps/rejected": -218.12562561035156,
+      "loss": 0.5347,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -0.39329051971435547,
+      "rewards/margins": 0.6772298216819763,
+      "rewards/rejected": -1.0705204010009766,
+      "step": 770
+    },
+    {
+      "epoch": 0.5370976071613014,
+      "grad_norm": 23.98875613027924,
+      "learning_rate": 5.156847742922723e-07,
+      "logits/chosen": -0.29115819931030273,
+      "logits/rejected": -0.2669009566307068,
+      "logps/chosen": -195.95689392089844,
+      "logps/rejected": -204.91221618652344,
+      "loss": 0.5347,
+      "rewards/accuracies": 0.7312500476837158,
+      "rewards/chosen": -0.3034020662307739,
+      "rewards/margins": 0.6618468165397644,
+      "rewards/rejected": -0.9652489423751831,
+      "step": 780
+    },
+    {
+      "epoch": 0.5439834739197796,
+      "grad_norm": 21.889026312300274,
+      "learning_rate": 5.080336648814077e-07,
+      "logits/chosen": -0.2898753881454468,
+      "logits/rejected": -0.26701635122299194,
+      "logps/chosen": -197.73936462402344,
+      "logps/rejected": -207.7303924560547,
+      "loss": 0.5585,
+      "rewards/accuracies": 0.7203124761581421,
+      "rewards/chosen": -0.37752565741539,
+      "rewards/margins": 0.6297482252120972,
+      "rewards/rejected": -1.0072739124298096,
+      "step": 790
+    },
+    {
+      "epoch": 0.5508693406782579,
+      "grad_norm": 22.78320300180032,
+      "learning_rate": 5.003825554705431e-07,
+      "logits/chosen": -0.25664806365966797,
+      "logits/rejected": -0.2466067373752594,
+      "logps/chosen": -203.13661193847656,
+      "logps/rejected": -211.3241424560547,
+      "loss": 0.5629,
+      "rewards/accuracies": 0.7328124642372131,
+      "rewards/chosen": -0.3754059672355652,
+      "rewards/margins": 0.6045074462890625,
+      "rewards/rejected": -0.9799134731292725,
+      "step": 800
+    },
+    {
+      "epoch": 0.5577552074367361,
+      "grad_norm": 20.845027944826946,
+      "learning_rate": 4.927314460596787e-07,
+      "logits/chosen": -0.24083290994167328,
+      "logits/rejected": -0.20561712980270386,
+      "logps/chosen": -199.92298889160156,
+      "logps/rejected": -212.12783813476562,
+      "loss": 0.5331,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": -0.33173495531082153,
+      "rewards/margins": 0.7252557873725891,
+      "rewards/rejected": -1.0569908618927002,
+      "step": 810
+    },
+    {
+      "epoch": 0.5646410741952144,
+      "grad_norm": 23.03440686836388,
+      "learning_rate": 4.850803366488141e-07,
+      "logits/chosen": -0.27781039476394653,
+      "logits/rejected": -0.25066977739334106,
+      "logps/chosen": -205.1341552734375,
+      "logps/rejected": -215.48867797851562,
+      "loss": 0.5524,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.4363483190536499,
+      "rewards/margins": 0.6705613732337952,
+      "rewards/rejected": -1.1069096326828003,
+      "step": 820
+    },
+    {
+      "epoch": 0.5715269409536925,
+      "grad_norm": 25.880904118103416,
+      "learning_rate": 4.774292272379495e-07,
+      "logits/chosen": -0.26057904958724976,
+      "logits/rejected": -0.25437307357788086,
+      "logps/chosen": -199.4198455810547,
+      "logps/rejected": -206.81875610351562,
+      "loss": 0.5671,
+      "rewards/accuracies": 0.7281249761581421,
+      "rewards/chosen": -0.4462214708328247,
+      "rewards/margins": 0.6281691193580627,
+      "rewards/rejected": -1.0743906497955322,
+      "step": 830
+    },
+    {
+      "epoch": 0.5784128077121707,
+      "grad_norm": 22.29449401198685,
+      "learning_rate": 4.697781178270849e-07,
+      "logits/chosen": -0.22187501192092896,
+      "logits/rejected": -0.1855536848306656,
+      "logps/chosen": -194.93341064453125,
+      "logps/rejected": -207.49209594726562,
+      "loss": 0.5342,
+      "rewards/accuracies": 0.7359375357627869,
+      "rewards/chosen": -0.32722094655036926,
+      "rewards/margins": 0.69352787733078,
+      "rewards/rejected": -1.0207487344741821,
+      "step": 840
+    },
+    {
+      "epoch": 0.585298674470649,
+      "grad_norm": 23.681302591674456,
+      "learning_rate": 4.621270084162203e-07,
+      "logits/chosen": -0.26163047552108765,
+      "logits/rejected": -0.2241986244916916,
+      "logps/chosen": -202.11473083496094,
+      "logps/rejected": -211.72190856933594,
+      "loss": 0.5385,
+      "rewards/accuracies": 0.753125011920929,
+      "rewards/chosen": -0.35107535123825073,
+      "rewards/margins": 0.6962921023368835,
+      "rewards/rejected": -1.0473673343658447,
+      "step": 850
+    },
+    {
+      "epoch": 0.5921845412291272,
+      "grad_norm": 24.089626973464824,
+      "learning_rate": 4.5447589900535577e-07,
+      "logits/chosen": -0.2115095555782318,
+      "logits/rejected": -0.1764950454235077,
+      "logps/chosen": -202.98338317871094,
+      "logps/rejected": -214.40467834472656,
+      "loss": 0.564,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": -0.4069036841392517,
+      "rewards/margins": 0.6364681720733643,
+      "rewards/rejected": -1.0433719158172607,
+      "step": 860
+    },
+    {
+      "epoch": 0.5990704079876055,
+      "grad_norm": 19.882045733809733,
+      "learning_rate": 4.4682478959449117e-07,
+      "logits/chosen": -0.259220689535141,
+      "logits/rejected": -0.23780278861522675,
+      "logps/chosen": -198.67410278320312,
+      "logps/rejected": -212.25843811035156,
+      "loss": 0.5551,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.3562455475330353,
+      "rewards/margins": 0.6455320119857788,
+      "rewards/rejected": -1.0017775297164917,
+      "step": 870
+    },
+    {
+      "epoch": 0.6059562747460837,
+      "grad_norm": 22.848542792283176,
+      "learning_rate": 4.391736801836266e-07,
+      "logits/chosen": -0.22383271157741547,
+      "logits/rejected": -0.1870381087064743,
+      "logps/chosen": -195.6481170654297,
+      "logps/rejected": -214.82052612304688,
+      "loss": 0.5571,
+      "rewards/accuracies": 0.7046875357627869,
+      "rewards/chosen": -0.3412778675556183,
+      "rewards/margins": 0.667373538017273,
+      "rewards/rejected": -1.0086513757705688,
+      "step": 880
+    },
+    {
+      "epoch": 0.6128421415045618,
+      "grad_norm": 22.07328478798222,
+      "learning_rate": 4.315225707727621e-07,
+      "logits/chosen": -0.2479555606842041,
+      "logits/rejected": -0.23453199863433838,
+      "logps/chosen": -207.93699645996094,
+      "logps/rejected": -213.48202514648438,
+      "loss": 0.5519,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.41722822189331055,
+      "rewards/margins": 0.6200730800628662,
+      "rewards/rejected": -1.0373013019561768,
+      "step": 890
+    },
+    {
+      "epoch": 0.6197280082630401,
+      "grad_norm": 23.698155914649785,
+      "learning_rate": 4.238714613618974e-07,
+      "logits/chosen": -0.2827821969985962,
+      "logits/rejected": -0.2659350335597992,
+      "logps/chosen": -194.46591186523438,
+      "logps/rejected": -204.5747528076172,
+      "loss": 0.5094,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.34797102212905884,
+      "rewards/margins": 0.7520918846130371,
+      "rewards/rejected": -1.1000628471374512,
+      "step": 900
+    },
+    {
+      "epoch": 0.6266138750215183,
+      "grad_norm": 23.820275610745107,
+      "learning_rate": 4.162203519510329e-07,
+      "logits/chosen": -0.30107322335243225,
+      "logits/rejected": -0.2755378484725952,
+      "logps/chosen": -193.82180786132812,
+      "logps/rejected": -201.58070373535156,
+      "loss": 0.5408,
+      "rewards/accuracies": 0.7265625,
+      "rewards/chosen": -0.36847078800201416,
+      "rewards/margins": 0.6643326878547668,
+      "rewards/rejected": -1.0328035354614258,
+      "step": 910
+    },
+    {
+      "epoch": 0.6334997417799966,
+      "grad_norm": 25.18137423151907,
+      "learning_rate": 4.085692425401683e-07,
+      "logits/chosen": -0.2921736240386963,
+      "logits/rejected": -0.27882224321365356,
+      "logps/chosen": -205.14035034179688,
+      "logps/rejected": -218.99960327148438,
+      "loss": 0.5653,
+      "rewards/accuracies": 0.7312500476837158,
+      "rewards/chosen": -0.35154396295547485,
+      "rewards/margins": 0.6647427678108215,
+      "rewards/rejected": -1.0162867307662964,
+      "step": 920
+    },
+    {
+      "epoch": 0.6403856085384748,
+      "grad_norm": 21.770256912198327,
+      "learning_rate": 4.0091813312930373e-07,
+      "logits/chosen": -0.2791680693626404,
+      "logits/rejected": -0.26233184337615967,
+      "logps/chosen": -197.62933349609375,
+      "logps/rejected": -208.18617248535156,
+      "loss": 0.5285,
+      "rewards/accuracies": 0.729687511920929,
+      "rewards/chosen": -0.320173054933548,
+      "rewards/margins": 0.7681188583374023,
+      "rewards/rejected": -1.088291883468628,
+      "step": 930
+    },
+    {
+      "epoch": 0.6472714752969531,
+      "grad_norm": 20.768362506243623,
+      "learning_rate": 3.932670237184392e-07,
+      "logits/chosen": -0.3179224729537964,
+      "logits/rejected": -0.28427645564079285,
+      "logps/chosen": -205.0663299560547,
+      "logps/rejected": -213.0223388671875,
+      "loss": 0.5237,
+      "rewards/accuracies": 0.7437500357627869,
+      "rewards/chosen": -0.3529094159603119,
+      "rewards/margins": 0.7018887996673584,
+      "rewards/rejected": -1.0547982454299927,
+      "step": 940
+    },
+    {
+      "epoch": 0.6541573420554312,
+      "grad_norm": 24.168246031231085,
+      "learning_rate": 3.856159143075746e-07,
+      "logits/chosen": -0.2807343602180481,
+      "logits/rejected": -0.260441392660141,
+      "logps/chosen": -204.5944366455078,
+      "logps/rejected": -217.90736389160156,
+      "loss": 0.5382,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.33213984966278076,
+      "rewards/margins": 0.7174164056777954,
+      "rewards/rejected": -1.0495562553405762,
+      "step": 950
+    },
+    {
+      "epoch": 0.6610432088139094,
+      "grad_norm": 20.29598172536042,
+      "learning_rate": 3.7796480489671e-07,
+      "logits/chosen": -0.28455644845962524,
+      "logits/rejected": -0.25150707364082336,
+      "logps/chosen": -199.77969360351562,
+      "logps/rejected": -209.3079833984375,
+      "loss": 0.5277,
+      "rewards/accuracies": 0.7390625476837158,
+      "rewards/chosen": -0.3357803523540497,
+      "rewards/margins": 0.6916924715042114,
+      "rewards/rejected": -1.0274728536605835,
+      "step": 960
+    },
+    {
+      "epoch": 0.6679290755723877,
+      "grad_norm": 23.263000578519865,
+      "learning_rate": 3.7031369548584544e-07,
+      "logits/chosen": -0.3258031904697418,
+      "logits/rejected": -0.3066006600856781,
+      "logps/chosen": -198.5902099609375,
+      "logps/rejected": -211.4296875,
+      "loss": 0.5169,
+      "rewards/accuracies": 0.7546875476837158,
+      "rewards/chosen": -0.2921166718006134,
+      "rewards/margins": 0.7654004693031311,
+      "rewards/rejected": -1.057517170906067,
+      "step": 970
+    },
+    {
+      "epoch": 0.6748149423308659,
+      "grad_norm": 27.58985651394188,
+      "learning_rate": 3.6266258607498084e-07,
+      "logits/chosen": -0.32159218192100525,
+      "logits/rejected": -0.3140263557434082,
+      "logps/chosen": -202.26385498046875,
+      "logps/rejected": -217.04469299316406,
+      "loss": 0.5366,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.3014247417449951,
+      "rewards/margins": 0.7427166700363159,
+      "rewards/rejected": -1.044141411781311,
+      "step": 980
+    },
+    {
+      "epoch": 0.6817008090893442,
+      "grad_norm": 23.116860359749147,
+      "learning_rate": 3.550114766641163e-07,
+      "logits/chosen": -0.2947474420070648,
+      "logits/rejected": -0.26782095432281494,
+      "logps/chosen": -205.06268310546875,
+      "logps/rejected": -221.36981201171875,
+      "loss": 0.5549,
+      "rewards/accuracies": 0.7437500357627869,
+      "rewards/chosen": -0.3489997684955597,
+      "rewards/margins": 0.7195862531661987,
+      "rewards/rejected": -1.0685861110687256,
+      "step": 990
+    },
+    {
+      "epoch": 0.6885866758478223,
+      "grad_norm": 23.978575280673038,
+      "learning_rate": 3.473603672532517e-07,
+      "logits/chosen": -0.3905680477619171,
+      "logits/rejected": -0.3640524446964264,
+      "logps/chosen": -198.04745483398438,
+      "logps/rejected": -208.67324829101562,
+      "loss": 0.5436,
+      "rewards/accuracies": 0.721875011920929,
+      "rewards/chosen": -0.34358733892440796,
+      "rewards/margins": 0.6835037469863892,
+      "rewards/rejected": -1.0270910263061523,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6954725426063005,
+      "grad_norm": 20.189411791862387,
+      "learning_rate": 3.3970925784238715e-07,
+      "logits/chosen": -0.29821571707725525,
+      "logits/rejected": -0.2687515318393707,
+      "logps/chosen": -200.1770782470703,
+      "logps/rejected": -216.76576232910156,
+      "loss": 0.5122,
+      "rewards/accuracies": 0.7468750476837158,
+      "rewards/chosen": -0.3284381031990051,
+      "rewards/margins": 0.7797881364822388,
+      "rewards/rejected": -1.1082262992858887,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7023584093647788,
+      "grad_norm": 24.729161803473662,
+      "learning_rate": 3.3205814843152255e-07,
+      "logits/chosen": -0.35373279452323914,
+      "logits/rejected": -0.30401962995529175,
+      "logps/chosen": -199.4246826171875,
+      "logps/rejected": -211.8179168701172,
+      "loss": 0.5261,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.349697470664978,
+      "rewards/margins": 0.7501545548439026,
+      "rewards/rejected": -1.0998519659042358,
+      "step": 1020
+    },
+    {
+      "epoch": 0.709244276123257,
+      "grad_norm": 19.89999565338996,
+      "learning_rate": 3.2440703902065795e-07,
+      "logits/chosen": -0.3316059112548828,
+      "logits/rejected": -0.2792198657989502,
+      "logps/chosen": -204.58319091796875,
+      "logps/rejected": -224.2587127685547,
+      "loss": 0.5143,
+      "rewards/accuracies": 0.7562499642372131,
+      "rewards/chosen": -0.3548116385936737,
+      "rewards/margins": 0.8157339096069336,
+      "rewards/rejected": -1.1705455780029297,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7161301428817353,
+      "grad_norm": 21.29752204371925,
+      "learning_rate": 3.167559296097934e-07,
+      "logits/chosen": -0.3314603567123413,
+      "logits/rejected": -0.30693235993385315,
+      "logps/chosen": -203.65330505371094,
+      "logps/rejected": -214.09750366210938,
+      "loss": 0.5347,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": -0.37685102224349976,
+      "rewards/margins": 0.7335286736488342,
+      "rewards/rejected": -1.110379695892334,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7230160096402135,
+      "grad_norm": 25.358261156803007,
+      "learning_rate": 3.091048201989288e-07,
+      "logits/chosen": -0.3865748643875122,
+      "logits/rejected": -0.3486027121543884,
+      "logps/chosen": -204.2187957763672,
+      "logps/rejected": -213.5407257080078,
+      "loss": 0.5281,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -0.39082208275794983,
+      "rewards/margins": 0.7356584668159485,
+      "rewards/rejected": -1.1264805793762207,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7299018763986916,
+      "grad_norm": 26.050502019430347,
+      "learning_rate": 3.0145371078806426e-07,
+      "logits/chosen": -0.31970304250717163,
+      "logits/rejected": -0.2877205014228821,
+      "logps/chosen": -199.24700927734375,
+      "logps/rejected": -211.90777587890625,
+      "loss": 0.5556,
+      "rewards/accuracies": 0.7328125238418579,
+      "rewards/chosen": -0.36632290482521057,
+      "rewards/margins": 0.7173328399658203,
+      "rewards/rejected": -1.083655834197998,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7367877431571699,
+      "grad_norm": 26.846914766196015,
+      "learning_rate": 2.938026013771997e-07,
+      "logits/chosen": -0.3748086392879486,
+      "logits/rejected": -0.32532060146331787,
+      "logps/chosen": -204.9930419921875,
+      "logps/rejected": -217.00918579101562,
+      "loss": 0.518,
+      "rewards/accuracies": 0.7437500357627869,
+      "rewards/chosen": -0.32681968808174133,
+      "rewards/margins": 0.7986001968383789,
+      "rewards/rejected": -1.1254198551177979,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7436736099156481,
+      "grad_norm": 19.81791648317305,
+      "learning_rate": 2.861514919663351e-07,
+      "logits/chosen": -0.35734954476356506,
+      "logits/rejected": -0.3137910068035126,
+      "logps/chosen": -190.3447265625,
+      "logps/rejected": -205.507568359375,
+      "loss": 0.4957,
+      "rewards/accuracies": 0.770312488079071,
+      "rewards/chosen": -0.301634281873703,
+      "rewards/margins": 0.8440784215927124,
+      "rewards/rejected": -1.1457128524780273,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7505594766741264,
+      "grad_norm": 21.610848655147894,
+      "learning_rate": 2.785003825554705e-07,
+      "logits/chosen": -0.3268454074859619,
+      "logits/rejected": -0.31099632382392883,
+      "logps/chosen": -206.75418090820312,
+      "logps/rejected": -215.38848876953125,
+      "loss": 0.5508,
+      "rewards/accuracies": 0.7328125238418579,
+      "rewards/chosen": -0.4365284740924835,
+      "rewards/margins": 0.7196505665779114,
+      "rewards/rejected": -1.1561790704727173,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7574453434326046,
+      "grad_norm": 21.30323322387434,
+      "learning_rate": 2.7084927314460597e-07,
+      "logits/chosen": -0.3255113959312439,
+      "logits/rejected": -0.2992578446865082,
+      "logps/chosen": -192.91909790039062,
+      "logps/rejected": -208.11151123046875,
+      "loss": 0.5145,
+      "rewards/accuracies": 0.753125011920929,
+      "rewards/chosen": -0.3881222903728485,
+      "rewards/margins": 0.8132278919219971,
+      "rewards/rejected": -1.201350212097168,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 20.135623041976924,
+      "learning_rate": 2.6319816373374137e-07,
+      "logits/chosen": -0.3734041750431061,
+      "logits/rejected": -0.3278706967830658,
+      "logps/chosen": -202.39517211914062,
+      "logps/rejected": -215.2314910888672,
+      "loss": 0.5493,
+      "rewards/accuracies": 0.7265625596046448,
+      "rewards/chosen": -0.3905448317527771,
+      "rewards/margins": 0.7275549173355103,
+      "rewards/rejected": -1.1180996894836426,
+      "step": 1110
+    },
+    {
+      "epoch": 0.771217076949561,
+      "grad_norm": 22.016629785130043,
+      "learning_rate": 2.555470543228768e-07,
+      "logits/chosen": -0.4030528664588928,
+      "logits/rejected": -0.3748015761375427,
+      "logps/chosen": -199.6988983154297,
+      "logps/rejected": -211.9576416015625,
+      "loss": 0.5556,
+      "rewards/accuracies": 0.715624988079071,
+      "rewards/chosen": -0.3250424861907959,
+      "rewards/margins": 0.724652111530304,
+      "rewards/rejected": -1.0496946573257446,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7781029437080392,
+      "grad_norm": 23.41840157614551,
+      "learning_rate": 2.4789594491201223e-07,
+      "logits/chosen": -0.36145588755607605,
+      "logits/rejected": -0.2941068410873413,
+      "logps/chosen": -197.30921936035156,
+      "logps/rejected": -212.53648376464844,
+      "loss": 0.5247,
+      "rewards/accuracies": 0.753125011920929,
+      "rewards/chosen": -0.3182806372642517,
+      "rewards/margins": 0.7811294794082642,
+      "rewards/rejected": -1.099410057067871,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7849888104665175,
+      "grad_norm": 21.06304161826817,
+      "learning_rate": 2.402448355011477e-07,
+      "logits/chosen": -0.32696184515953064,
+      "logits/rejected": -0.2999955117702484,
+      "logps/chosen": -193.55752563476562,
+      "logps/rejected": -213.47972106933594,
+      "loss": 0.5388,
+      "rewards/accuracies": 0.7437500357627869,
+      "rewards/chosen": -0.3747640550136566,
+      "rewards/margins": 0.7560409307479858,
+      "rewards/rejected": -1.1308048963546753,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7918746772249957,
+      "grad_norm": 20.793097909497455,
+      "learning_rate": 2.3259372609028308e-07,
+      "logits/chosen": -0.36112964153289795,
+      "logits/rejected": -0.3267067074775696,
+      "logps/chosen": -203.5668182373047,
+      "logps/rejected": -212.1382598876953,
+      "loss": 0.5362,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": -0.3771086037158966,
+      "rewards/margins": 0.7114807367324829,
+      "rewards/rejected": -1.0885894298553467,
+      "step": 1150
+    },
+    {
+      "epoch": 0.798760543983474,
+      "grad_norm": 24.909405192079628,
+      "learning_rate": 2.2494261667941848e-07,
+      "logits/chosen": -0.34521499276161194,
+      "logits/rejected": -0.32405370473861694,
+      "logps/chosen": -194.30148315429688,
+      "logps/rejected": -208.0577392578125,
+      "loss": 0.5209,
+      "rewards/accuracies": 0.7640625238418579,
+      "rewards/chosen": -0.3107369542121887,
+      "rewards/margins": 0.7539686560630798,
+      "rewards/rejected": -1.0647056102752686,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8056464107419521,
+      "grad_norm": 25.5580619560939,
+      "learning_rate": 2.1729150726855394e-07,
+      "logits/chosen": -0.3413427770137787,
+      "logits/rejected": -0.30263420939445496,
+      "logps/chosen": -192.62452697753906,
+      "logps/rejected": -201.20782470703125,
+      "loss": 0.5456,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.3429095149040222,
+      "rewards/margins": 0.7008405327796936,
+      "rewards/rejected": -1.0437501668930054,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8125322775004303,
+      "grad_norm": 20.40074379527458,
+      "learning_rate": 2.0964039785768936e-07,
+      "logits/chosen": -0.3403051495552063,
+      "logits/rejected": -0.3150518536567688,
+      "logps/chosen": -202.23458862304688,
+      "logps/rejected": -218.47067260742188,
+      "loss": 0.5012,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.3068324327468872,
+      "rewards/margins": 0.8549840450286865,
+      "rewards/rejected": -1.1618163585662842,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8194181442589086,
+      "grad_norm": 24.7780771443421,
+      "learning_rate": 2.019892884468248e-07,
+      "logits/chosen": -0.3548561930656433,
+      "logits/rejected": -0.33061498403549194,
+      "logps/chosen": -198.79690551757812,
+      "logps/rejected": -216.0151824951172,
+      "loss": 0.5174,
+      "rewards/accuracies": 0.7609375715255737,
+      "rewards/chosen": -0.3230586349964142,
+      "rewards/margins": 0.8606723546981812,
+      "rewards/rejected": -1.1837310791015625,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8263040110173868,
+      "grad_norm": 26.180779145376622,
+      "learning_rate": 1.943381790359602e-07,
+      "logits/chosen": -0.3222372233867645,
+      "logits/rejected": -0.29423391819000244,
+      "logps/chosen": -205.35232543945312,
+      "logps/rejected": -218.5619659423828,
+      "loss": 0.5403,
+      "rewards/accuracies": 0.714062511920929,
+      "rewards/chosen": -0.4436132311820984,
+      "rewards/margins": 0.730433464050293,
+      "rewards/rejected": -1.1740467548370361,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8331898777758651,
+      "grad_norm": 24.835512380545932,
+      "learning_rate": 1.8668706962509562e-07,
+      "logits/chosen": -0.3160286545753479,
+      "logits/rejected": -0.289877712726593,
+      "logps/chosen": -198.57736206054688,
+      "logps/rejected": -208.46429443359375,
+      "loss": 0.5334,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": -0.3664984703063965,
+      "rewards/margins": 0.7671695947647095,
+      "rewards/rejected": -1.133668065071106,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8400757445343433,
+      "grad_norm": 24.491015676047468,
+      "learning_rate": 1.7903596021423107e-07,
+      "logits/chosen": -0.31306660175323486,
+      "logits/rejected": -0.2788822650909424,
+      "logps/chosen": -202.64613342285156,
+      "logps/rejected": -214.78054809570312,
+      "loss": 0.5213,
+      "rewards/accuracies": 0.7359374761581421,
+      "rewards/chosen": -0.42141586542129517,
+      "rewards/margins": 0.7737562656402588,
+      "rewards/rejected": -1.1951720714569092,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8469616112928214,
+      "grad_norm": 24.059372649386674,
+      "learning_rate": 1.7138485080336647e-07,
+      "logits/chosen": -0.3656036853790283,
+      "logits/rejected": -0.3244956135749817,
+      "logps/chosen": -199.56884765625,
+      "logps/rejected": -217.80772399902344,
+      "loss": 0.493,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -0.325540691614151,
+      "rewards/margins": 0.8619417548179626,
+      "rewards/rejected": -1.187482476234436,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8538474780512997,
+      "grad_norm": 18.27717476339513,
+      "learning_rate": 1.637337413925019e-07,
+      "logits/chosen": -0.4079727828502655,
+      "logits/rejected": -0.35690948367118835,
+      "logps/chosen": -200.95855712890625,
+      "logps/rejected": -218.0155029296875,
+      "loss": 0.4972,
+      "rewards/accuracies": 0.7671875357627869,
+      "rewards/chosen": -0.36264702677726746,
+      "rewards/margins": 0.8437535166740417,
+      "rewards/rejected": -1.2064005136489868,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8607333448097779,
+      "grad_norm": 23.065530605405485,
+      "learning_rate": 1.5608263198163733e-07,
+      "logits/chosen": -0.33324557542800903,
+      "logits/rejected": -0.3149731755256653,
+      "logps/chosen": -197.61123657226562,
+      "logps/rejected": -204.68450927734375,
+      "loss": 0.5792,
+      "rewards/accuracies": 0.7156250476837158,
+      "rewards/chosen": -0.44249990582466125,
+      "rewards/margins": 0.6359133720397949,
+      "rewards/rejected": -1.0784132480621338,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8676192115682562,
+      "grad_norm": 20.73050366973397,
+      "learning_rate": 1.4843152257077276e-07,
+      "logits/chosen": -0.3171376883983612,
+      "logits/rejected": -0.28074705600738525,
+      "logps/chosen": -209.62078857421875,
+      "logps/rejected": -221.52203369140625,
+      "loss": 0.5382,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.41873699426651,
+      "rewards/margins": 0.7794735431671143,
+      "rewards/rejected": -1.198210597038269,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8745050783267344,
+      "grad_norm": 21.760277541218,
+      "learning_rate": 1.4078041315990818e-07,
+      "logits/chosen": -0.3449145257472992,
+      "logits/rejected": -0.30704426765441895,
+      "logps/chosen": -197.60946655273438,
+      "logps/rejected": -218.5653076171875,
+      "loss": 0.5103,
+      "rewards/accuracies": 0.7515625357627869,
+      "rewards/chosen": -0.3605595529079437,
+      "rewards/margins": 0.8724721670150757,
+      "rewards/rejected": -1.2330316305160522,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8813909450852127,
+      "grad_norm": 21.675216189688292,
+      "learning_rate": 1.331293037490436e-07,
+      "logits/chosen": -0.37944453954696655,
+      "logits/rejected": -0.3386183977127075,
+      "logps/chosen": -198.25186157226562,
+      "logps/rejected": -213.14938354492188,
+      "loss": 0.5217,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": -0.3340380787849426,
+      "rewards/margins": 0.793717086315155,
+      "rewards/rejected": -1.127755045890808,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8882768118436908,
+      "grad_norm": 26.560486484637135,
+      "learning_rate": 1.25478194338179e-07,
+      "logits/chosen": -0.3314391076564789,
+      "logits/rejected": -0.29684922099113464,
+      "logps/chosen": -204.3308563232422,
+      "logps/rejected": -218.03488159179688,
+      "loss": 0.5456,
+      "rewards/accuracies": 0.746874988079071,
+      "rewards/chosen": -0.3798133134841919,
+      "rewards/margins": 0.7324703335762024,
+      "rewards/rejected": -1.112283706665039,
+      "step": 1290
+    },
+    {
+      "epoch": 0.895162678602169,
+      "grad_norm": 21.343267028495998,
+      "learning_rate": 1.1782708492731445e-07,
+      "logits/chosen": -0.35801607370376587,
+      "logits/rejected": -0.33859655261039734,
+      "logps/chosen": -193.88063049316406,
+      "logps/rejected": -212.57852172851562,
+      "loss": 0.525,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.402618944644928,
+      "rewards/margins": 0.7918345928192139,
+      "rewards/rejected": -1.1944535970687866,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9020485453606473,
+      "grad_norm": 23.511393076340966,
+      "learning_rate": 1.1017597551644987e-07,
+      "logits/chosen": -0.3655666708946228,
+      "logits/rejected": -0.327680379152298,
+      "logps/chosen": -200.72186279296875,
+      "logps/rejected": -212.2158203125,
+      "loss": 0.521,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.38576409220695496,
+      "rewards/margins": 0.760851263999939,
+      "rewards/rejected": -1.1466155052185059,
+      "step": 1310
+    },
+    {
+      "epoch": 0.9089344121191255,
+      "grad_norm": 22.97590079047081,
+      "learning_rate": 1.0252486610558531e-07,
+      "logits/chosen": -0.34880805015563965,
+      "logits/rejected": -0.3193954825401306,
+      "logps/chosen": -204.40707397460938,
+      "logps/rejected": -218.28848266601562,
+      "loss": 0.5178,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.38576388359069824,
+      "rewards/margins": 0.8154311180114746,
+      "rewards/rejected": -1.2011948823928833,
+      "step": 1320
+    },
+    {
+      "epoch": 0.9158202788776038,
+      "grad_norm": 20.603754969383694,
+      "learning_rate": 9.487375669472072e-08,
+      "logits/chosen": -0.33260923624038696,
+      "logits/rejected": -0.30312278866767883,
+      "logps/chosen": -203.37368774414062,
+      "logps/rejected": -215.08058166503906,
+      "loss": 0.5512,
+      "rewards/accuracies": 0.721875011920929,
+      "rewards/chosen": -0.42205169796943665,
+      "rewards/margins": 0.725147008895874,
+      "rewards/rejected": -1.1471986770629883,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9227061456360819,
+      "grad_norm": 21.191512286508,
+      "learning_rate": 8.722264728385616e-08,
+      "logits/chosen": -0.317133367061615,
+      "logits/rejected": -0.2866368293762207,
+      "logps/chosen": -199.86302185058594,
+      "logps/rejected": -214.34527587890625,
+      "loss": 0.525,
+      "rewards/accuracies": 0.7437500357627869,
+      "rewards/chosen": -0.4098660349845886,
+      "rewards/margins": 0.795417845249176,
+      "rewards/rejected": -1.2052838802337646,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9295920123945601,
+      "grad_norm": 23.130990012985187,
+      "learning_rate": 7.957153787299158e-08,
+      "logits/chosen": -0.3709363043308258,
+      "logits/rejected": -0.33735787868499756,
+      "logps/chosen": -200.1358184814453,
+      "logps/rejected": -213.65025329589844,
+      "loss": 0.529,
+      "rewards/accuracies": 0.7265625,
+      "rewards/chosen": -0.35897552967071533,
+      "rewards/margins": 0.7571591734886169,
+      "rewards/rejected": -1.1161346435546875,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9364778791530384,
+      "grad_norm": 18.120466166668564,
+      "learning_rate": 7.1920428462127e-08,
+      "logits/chosen": -0.329379141330719,
+      "logits/rejected": -0.27726149559020996,
+      "logps/chosen": -199.76431274414062,
+      "logps/rejected": -208.10348510742188,
+      "loss": 0.4741,
+      "rewards/accuracies": 0.770312488079071,
+      "rewards/chosen": -0.3599850535392761,
+      "rewards/margins": 0.8584945797920227,
+      "rewards/rejected": -1.2184796333312988,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9433637459115166,
+      "grad_norm": 22.98023018579539,
+      "learning_rate": 6.426931905126243e-08,
+      "logits/chosen": -0.35116755962371826,
+      "logits/rejected": -0.3177265524864197,
+      "logps/chosen": -194.65065002441406,
+      "logps/rejected": -209.42718505859375,
+      "loss": 0.5188,
+      "rewards/accuracies": 0.7515625357627869,
+      "rewards/chosen": -0.3557957410812378,
+      "rewards/margins": 0.79322749376297,
+      "rewards/rejected": -1.1490232944488525,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9502496126699949,
+      "grad_norm": 20.3222208875411,
+      "learning_rate": 5.661820964039785e-08,
+      "logits/chosen": -0.28668609261512756,
+      "logits/rejected": -0.2664375901222229,
+      "logps/chosen": -202.85134887695312,
+      "logps/rejected": -215.53598022460938,
+      "loss": 0.5022,
+      "rewards/accuracies": 0.7671874761581421,
+      "rewards/chosen": -0.3684632480144501,
+      "rewards/margins": 0.8430503010749817,
+      "rewards/rejected": -1.2115135192871094,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9571354794284731,
+      "grad_norm": 24.983901569618467,
+      "learning_rate": 4.896710022953328e-08,
+      "logits/chosen": -0.32899972796440125,
+      "logits/rejected": -0.27919813990592957,
+      "logps/chosen": -199.9358367919922,
+      "logps/rejected": -213.5103759765625,
+      "loss": 0.5119,
+      "rewards/accuracies": 0.753125011920929,
+      "rewards/chosen": -0.364630788564682,
+      "rewards/margins": 0.8253352642059326,
+      "rewards/rejected": -1.1899659633636475,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9640213461869512,
+      "grad_norm": 18.554502970350672,
+      "learning_rate": 4.1315990818668707e-08,
+      "logits/chosen": -0.3384089469909668,
+      "logits/rejected": -0.3053920269012451,
+      "logps/chosen": -198.3701934814453,
+      "logps/rejected": -205.8408203125,
+      "loss": 0.5312,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.3812635540962219,
+      "rewards/margins": 0.7723795175552368,
+      "rewards/rejected": -1.1536431312561035,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9709072129454295,
+      "grad_norm": 18.01675823590483,
+      "learning_rate": 3.366488140780413e-08,
+      "logits/chosen": -0.32437849044799805,
+      "logits/rejected": -0.2919423580169678,
+      "logps/chosen": -201.2761688232422,
+      "logps/rejected": -218.30552673339844,
+      "loss": 0.4874,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -0.37892454862594604,
+      "rewards/margins": 0.9029428958892822,
+      "rewards/rejected": -1.2818673849105835,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9777930797039077,
+      "grad_norm": 29.39318412255784,
+      "learning_rate": 2.6013771996939555e-08,
+      "logits/chosen": -0.3163904845714569,
+      "logits/rejected": -0.29091766476631165,
+      "logps/chosen": -204.334228515625,
+      "logps/rejected": -215.79502868652344,
+      "loss": 0.5022,
+      "rewards/accuracies": 0.7671874761581421,
+      "rewards/chosen": -0.38413873314857483,
+      "rewards/margins": 0.827136754989624,
+      "rewards/rejected": -1.2112754583358765,
+      "step": 1420
+    },
+    {
+      "epoch": 0.984678946462386,
+      "grad_norm": 19.461173491088918,
+      "learning_rate": 1.8362662586074982e-08,
+      "logits/chosen": -0.3308340609073639,
+      "logits/rejected": -0.30718377232551575,
+      "logps/chosen": -198.67318725585938,
+      "logps/rejected": -216.25709533691406,
+      "loss": 0.4884,
+      "rewards/accuracies": 0.778124988079071,
+      "rewards/chosen": -0.3805069327354431,
+      "rewards/margins": 0.8595027327537537,
+      "rewards/rejected": -1.2400096654891968,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9915648132208642,
+      "grad_norm": 24.14268800406746,
+      "learning_rate": 1.0711553175210405e-08,
+      "logits/chosen": -0.321536123752594,
+      "logits/rejected": -0.2926163375377655,
+      "logps/chosen": -197.82186889648438,
+      "logps/rejected": -209.32135009765625,
+      "loss": 0.5198,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": -0.3956286907196045,
+      "rewards/margins": 0.800367534160614,
+      "rewards/rejected": -1.1959962844848633,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9984506799793424,
+      "grad_norm": 19.57722185128953,
+      "learning_rate": 3.06044376434583e-09,
+      "logits/chosen": -0.36749356985092163,
+      "logits/rejected": -0.3329501450061798,
+      "logps/chosen": -197.41607666015625,
+      "logps/rejected": -212.35079956054688,
+      "loss": 0.4988,
+      "rewards/accuracies": 0.7734375,
+      "rewards/chosen": -0.3526759147644043,
+      "rewards/margins": 0.8231874108314514,
+      "rewards/rejected": -1.175863265991211,
+      "step": 1450
+    },
+    {
+      "epoch": 1.0,
+      "step": 1453,
+      "total_flos": 159648317243392.0,
+      "train_loss": 0.5763244779045961,
+      "train_runtime": 14193.5309,
+      "train_samples_per_second": 6.548,
+      "train_steps_per_second": 0.102
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1453,
+  "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": 159648317243392.0,
+  "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:a2563263dce28d47cd685ad855ed3282ac27a6982b6180e6ce41b1a30b345336
+size 7544