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_rmr1
+  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_rmr1
+
+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_rmr1 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: 5e-07
+- 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": 160669524688896.0,
+    "train_loss": 0.5754778021889021,
+    "train_runtime": 14476.1212,
+    "train_samples_per_second": 6.439,
+    "train_steps_per_second": 0.101
+}

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:a36bd4028c43bf626b6bad8d060d2812d234c7f075e71145c654531d5f89cd13
+size 4965841415

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77dddb5138e49224767e7fd15ae7988347d45f79e42d0b0704ac7757d68b991
+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": 160669524688896.0,
+    "train_loss": 0.5754778021889021,
+    "train_runtime": 14476.1212,
+    "train_samples_per_second": 6.439,
+    "train_steps_per_second": 0.101
+}

trainer_log.jsonl

@@ -0,0 +1,146 @@
+{"current_steps": 10, "total_steps": 1457, "loss": 0.6932, "accuracy": 0.4124999940395355, "lr": 3.082191780821918e-08, "epoch": 0.006866363402283066, "percentage": 0.69, "elapsed_time": "0:01:44", "remaining_time": "4:11:05"}
+{"current_steps": 20, "total_steps": 1457, "loss": 0.6937, "accuracy": 0.515625, "lr": 6.506849315068492e-08, "epoch": 0.013732726804566131, "percentage": 1.37, "elapsed_time": "0:03:27", "remaining_time": "4:08:38"}
+{"current_steps": 30, "total_steps": 1457, "loss": 0.6923, "accuracy": 0.534375011920929, "lr": 9.931506849315068e-08, "epoch": 0.020599090206849198, "percentage": 2.06, "elapsed_time": "0:05:04", "remaining_time": "4:01:46"}
+{"current_steps": 40, "total_steps": 1457, "loss": 0.6947, "accuracy": 0.48750001192092896, "lr": 1.3356164383561644e-07, "epoch": 0.027465453609132263, "percentage": 2.75, "elapsed_time": "0:06:43", "remaining_time": "3:57:56"}
+{"current_steps": 50, "total_steps": 1457, "loss": 0.6941, "accuracy": 0.5234375, "lr": 1.6780821917808218e-07, "epoch": 0.03433181701141533, "percentage": 3.43, "elapsed_time": "0:08:24", "remaining_time": "3:56:26"}
+{"current_steps": 60, "total_steps": 1457, "loss": 0.6959, "accuracy": 0.4906250238418579, "lr": 2.0205479452054795e-07, "epoch": 0.041198180413698396, "percentage": 4.12, "elapsed_time": "0:10:02", "remaining_time": "3:53:39"}
+{"current_steps": 70, "total_steps": 1457, "loss": 0.6928, "accuracy": 0.49375003576278687, "lr": 2.363013698630137e-07, "epoch": 0.048064543815981464, "percentage": 4.8, "elapsed_time": "0:11:38", "remaining_time": "3:50:34"}
+{"current_steps": 80, "total_steps": 1457, "loss": 0.6913, "accuracy": 0.5218750238418579, "lr": 2.7054794520547945e-07, "epoch": 0.054930907218264526, "percentage": 5.49, "elapsed_time": "0:13:20", "remaining_time": "3:49:44"}
+{"current_steps": 90, "total_steps": 1457, "loss": 0.6931, "accuracy": 0.5218749642372131, "lr": 3.047945205479452e-07, "epoch": 0.061797270620547594, "percentage": 6.18, "elapsed_time": "0:15:02", "remaining_time": "3:48:20"}
+{"current_steps": 100, "total_steps": 1457, "loss": 0.6899, "accuracy": 0.5281250476837158, "lr": 3.39041095890411e-07, "epoch": 0.06866363402283066, "percentage": 6.86, "elapsed_time": "0:16:39", "remaining_time": "3:46:02"}
+{"current_steps": 110, "total_steps": 1457, "loss": 0.689, "accuracy": 0.546875, "lr": 3.7328767123287667e-07, "epoch": 0.07552999742511372, "percentage": 7.55, "elapsed_time": "0:18:17", "remaining_time": "3:44:04"}
+{"current_steps": 120, "total_steps": 1457, "loss": 0.6885, "accuracy": 0.5750000476837158, "lr": 4.0753424657534246e-07, "epoch": 0.08239636082739679, "percentage": 8.24, "elapsed_time": "0:20:04", "remaining_time": "3:43:41"}
+{"current_steps": 130, "total_steps": 1457, "loss": 0.6842, "accuracy": 0.606249988079071, "lr": 4.417808219178082e-07, "epoch": 0.08926272422967986, "percentage": 8.92, "elapsed_time": "0:21:52", "remaining_time": "3:43:21"}
+{"current_steps": 140, "total_steps": 1457, "loss": 0.686, "accuracy": 0.5390625596046448, "lr": 4.7602739726027394e-07, "epoch": 0.09612908763196293, "percentage": 9.61, "elapsed_time": "0:23:33", "remaining_time": "3:41:37"}
+{"current_steps": 150, "total_steps": 1457, "loss": 0.6797, "accuracy": 0.6140625476837158, "lr": 4.988558352402745e-07, "epoch": 0.10299545103424598, "percentage": 10.3, "elapsed_time": "0:25:13", "remaining_time": "3:39:47"}
+{"current_steps": 160, "total_steps": 1457, "loss": 0.6782, "accuracy": 0.6109375357627869, "lr": 4.950419527078566e-07, "epoch": 0.10986181443652905, "percentage": 10.98, "elapsed_time": "0:26:51", "remaining_time": "3:37:45"}
+{"current_steps": 170, "total_steps": 1457, "loss": 0.6774, "accuracy": 0.604687511920929, "lr": 4.912280701754385e-07, "epoch": 0.11672817783881212, "percentage": 11.67, "elapsed_time": "0:28:35", "remaining_time": "3:36:29"}
+{"current_steps": 180, "total_steps": 1457, "loss": 0.67, "accuracy": 0.6343750357627869, "lr": 4.874141876430206e-07, "epoch": 0.12359454124109519, "percentage": 12.35, "elapsed_time": "0:30:13", "remaining_time": "3:34:27"}
+{"current_steps": 190, "total_steps": 1457, "loss": 0.6723, "accuracy": 0.573437511920929, "lr": 4.836003051106026e-07, "epoch": 0.13046090464337826, "percentage": 13.04, "elapsed_time": "0:31:51", "remaining_time": "3:32:26"}
+{"current_steps": 200, "total_steps": 1457, "loss": 0.6638, "accuracy": 0.6343750357627869, "lr": 4.797864225781846e-07, "epoch": 0.1373272680456613, "percentage": 13.73, "elapsed_time": "0:33:35", "remaining_time": "3:31:05"}
+{"current_steps": 210, "total_steps": 1457, "loss": 0.666, "accuracy": 0.6312500238418579, "lr": 4.759725400457666e-07, "epoch": 0.1441936314479444, "percentage": 14.41, "elapsed_time": "0:35:14", "remaining_time": "3:29:16"}
+{"current_steps": 220, "total_steps": 1457, "loss": 0.6633, "accuracy": 0.6296875476837158, "lr": 4.7215865751334857e-07, "epoch": 0.15105999485022745, "percentage": 15.1, "elapsed_time": "0:36:50", "remaining_time": "3:27:11"}
+{"current_steps": 230, "total_steps": 1457, "loss": 0.6537, "accuracy": 0.6484375, "lr": 4.6834477498093057e-07, "epoch": 0.1579263582525105, "percentage": 15.79, "elapsed_time": "0:38:27", "remaining_time": "3:25:09"}
+{"current_steps": 240, "total_steps": 1457, "loss": 0.6514, "accuracy": 0.6343750357627869, "lr": 4.6453089244851257e-07, "epoch": 0.16479272165479358, "percentage": 16.47, "elapsed_time": "0:40:08", "remaining_time": "3:23:32"}
+{"current_steps": 250, "total_steps": 1457, "loss": 0.6452, "accuracy": 0.6781250238418579, "lr": 4.607170099160946e-07, "epoch": 0.17165908505707664, "percentage": 17.16, "elapsed_time": "0:41:49", "remaining_time": "3:21:57"}
+{"current_steps": 260, "total_steps": 1457, "loss": 0.6508, "accuracy": 0.6421875357627869, "lr": 4.569031273836766e-07, "epoch": 0.17852544845935972, "percentage": 17.84, "elapsed_time": "0:43:50", "remaining_time": "3:21:50"}
+{"current_steps": 270, "total_steps": 1457, "loss": 0.6475, "accuracy": 0.6484375, "lr": 4.5308924485125853e-07, "epoch": 0.18539181186164277, "percentage": 18.53, "elapsed_time": "0:45:30", "remaining_time": "3:20:04"}
+{"current_steps": 280, "total_steps": 1457, "loss": 0.6457, "accuracy": 0.6656250357627869, "lr": 4.4927536231884053e-07, "epoch": 0.19225817526392586, "percentage": 19.22, "elapsed_time": "0:47:10", "remaining_time": "3:18:17"}
+{"current_steps": 290, "total_steps": 1457, "loss": 0.6373, "accuracy": 0.6484375596046448, "lr": 4.454614797864226e-07, "epoch": 0.1991245386662089, "percentage": 19.9, "elapsed_time": "0:48:46", "remaining_time": "3:16:18"}
+{"current_steps": 300, "total_steps": 1457, "loss": 0.629, "accuracy": 0.703125, "lr": 4.416475972540046e-07, "epoch": 0.20599090206849197, "percentage": 20.59, "elapsed_time": "0:50:26", "remaining_time": "3:14:31"}
+{"current_steps": 310, "total_steps": 1457, "loss": 0.6295, "accuracy": 0.6859375238418579, "lr": 4.3783371472158654e-07, "epoch": 0.21285726547077505, "percentage": 21.28, "elapsed_time": "0:52:06", "remaining_time": "3:12:46"}
+{"current_steps": 320, "total_steps": 1457, "loss": 0.6173, "accuracy": 0.671875, "lr": 4.3401983218916855e-07, "epoch": 0.2197236288730581, "percentage": 21.96, "elapsed_time": "0:53:47", "remaining_time": "3:11:09"}
+{"current_steps": 330, "total_steps": 1457, "loss": 0.6263, "accuracy": 0.6734375357627869, "lr": 4.3020594965675055e-07, "epoch": 0.22658999227534118, "percentage": 22.65, "elapsed_time": "0:55:25", "remaining_time": "3:09:16"}
+{"current_steps": 340, "total_steps": 1457, "loss": 0.6296, "accuracy": 0.6640625, "lr": 4.2639206712433255e-07, "epoch": 0.23345635567762424, "percentage": 23.34, "elapsed_time": "0:57:05", "remaining_time": "3:07:34"}
+{"current_steps": 350, "total_steps": 1457, "loss": 0.633, "accuracy": 0.6625000238418579, "lr": 4.2257818459191456e-07, "epoch": 0.2403227190799073, "percentage": 24.02, "elapsed_time": "0:58:45", "remaining_time": "3:05:50"}
+{"current_steps": 360, "total_steps": 1457, "loss": 0.6223, "accuracy": 0.690625011920929, "lr": 4.187643020594965e-07, "epoch": 0.24718908248219038, "percentage": 24.71, "elapsed_time": "1:00:24", "remaining_time": "3:04:04"}
+{"current_steps": 370, "total_steps": 1457, "loss": 0.6137, "accuracy": 0.6890624761581421, "lr": 4.1495041952707856e-07, "epoch": 0.25405544588447343, "percentage": 25.39, "elapsed_time": "1:02:01", "remaining_time": "3:02:13"}
+{"current_steps": 380, "total_steps": 1457, "loss": 0.6003, "accuracy": 0.7046874761581421, "lr": 4.1113653699466057e-07, "epoch": 0.2609218092867565, "percentage": 26.08, "elapsed_time": "1:03:42", "remaining_time": "3:00:32"}
+{"current_steps": 390, "total_steps": 1457, "loss": 0.613, "accuracy": 0.6781250238418579, "lr": 4.0732265446224257e-07, "epoch": 0.2677881726890396, "percentage": 26.77, "elapsed_time": "1:05:24", "remaining_time": "2:58:56"}
+{"current_steps": 400, "total_steps": 1457, "loss": 0.601, "accuracy": 0.7109375, "lr": 4.035087719298245e-07, "epoch": 0.2746545360913226, "percentage": 27.45, "elapsed_time": "1:07:06", "remaining_time": "2:57:19"}
+{"current_steps": 410, "total_steps": 1457, "loss": 0.5947, "accuracy": 0.703125, "lr": 3.996948893974065e-07, "epoch": 0.2815208994936057, "percentage": 28.14, "elapsed_time": "1:08:42", "remaining_time": "2:55:27"}
+{"current_steps": 420, "total_steps": 1457, "loss": 0.609, "accuracy": 0.6843750476837158, "lr": 3.9588100686498853e-07, "epoch": 0.2883872628958888, "percentage": 28.83, "elapsed_time": "1:10:22", "remaining_time": "2:53:45"}
+{"current_steps": 430, "total_steps": 1457, "loss": 0.6196, "accuracy": 0.671875, "lr": 3.9206712433257053e-07, "epoch": 0.2952536262981718, "percentage": 29.51, "elapsed_time": "1:12:06", "remaining_time": "2:52:12"}
+{"current_steps": 440, "total_steps": 1457, "loss": 0.5946, "accuracy": 0.6937500238418579, "lr": 3.882532418001526e-07, "epoch": 0.3021199897004549, "percentage": 30.2, "elapsed_time": "1:13:44", "remaining_time": "2:50:26"}
+{"current_steps": 450, "total_steps": 1457, "loss": 0.6148, "accuracy": 0.684374988079071, "lr": 3.8443935926773454e-07, "epoch": 0.308986353102738, "percentage": 30.89, "elapsed_time": "1:15:24", "remaining_time": "2:48:45"}
+{"current_steps": 460, "total_steps": 1457, "loss": 0.5991, "accuracy": 0.682812511920929, "lr": 3.8062547673531654e-07, "epoch": 0.315852716505021, "percentage": 31.57, "elapsed_time": "1:17:04", "remaining_time": "2:47:03"}
+{"current_steps": 470, "total_steps": 1457, "loss": 0.61, "accuracy": 0.6734375357627869, "lr": 3.7681159420289855e-07, "epoch": 0.3227190799073041, "percentage": 32.26, "elapsed_time": "1:18:40", "remaining_time": "2:45:13"}
+{"current_steps": 480, "total_steps": 1457, "loss": 0.5981, "accuracy": 0.6875000596046448, "lr": 3.7299771167048055e-07, "epoch": 0.32958544330958717, "percentage": 32.94, "elapsed_time": "1:20:13", "remaining_time": "2:43:18"}
+{"current_steps": 490, "total_steps": 1457, "loss": 0.5837, "accuracy": 0.7250000238418579, "lr": 3.691838291380625e-07, "epoch": 0.33645180671187025, "percentage": 33.63, "elapsed_time": "1:22:00", "remaining_time": "2:41:50"}
+{"current_steps": 500, "total_steps": 1457, "loss": 0.5909, "accuracy": 0.703125, "lr": 3.653699466056445e-07, "epoch": 0.3433181701141533, "percentage": 34.32, "elapsed_time": "1:23:34", "remaining_time": "2:39:57"}
+{"current_steps": 510, "total_steps": 1457, "loss": 0.584, "accuracy": 0.7109375, "lr": 3.615560640732265e-07, "epoch": 0.35018453351643636, "percentage": 35.0, "elapsed_time": "1:25:29", "remaining_time": "2:38:44"}
+{"current_steps": 520, "total_steps": 1457, "loss": 0.5673, "accuracy": 0.7250000238418579, "lr": 3.5774218154080856e-07, "epoch": 0.35705089691871944, "percentage": 35.69, "elapsed_time": "1:27:10", "remaining_time": "2:37:05"}
+{"current_steps": 530, "total_steps": 1457, "loss": 0.5954, "accuracy": 0.684374988079071, "lr": 3.5392829900839057e-07, "epoch": 0.36391726032100247, "percentage": 36.38, "elapsed_time": "1:28:49", "remaining_time": "2:35:22"}
+{"current_steps": 540, "total_steps": 1457, "loss": 0.5762, "accuracy": 0.7000000476837158, "lr": 3.501144164759725e-07, "epoch": 0.37078362372328555, "percentage": 37.06, "elapsed_time": "1:30:24", "remaining_time": "2:33:32"}
+{"current_steps": 550, "total_steps": 1457, "loss": 0.563, "accuracy": 0.7484375238418579, "lr": 3.463005339435545e-07, "epoch": 0.37764998712556863, "percentage": 37.75, "elapsed_time": "1:32:02", "remaining_time": "2:31:47"}
+{"current_steps": 560, "total_steps": 1457, "loss": 0.5741, "accuracy": 0.699999988079071, "lr": 3.424866514111365e-07, "epoch": 0.3845163505278517, "percentage": 38.44, "elapsed_time": "1:33:41", "remaining_time": "2:30:04"}
+{"current_steps": 570, "total_steps": 1457, "loss": 0.562, "accuracy": 0.714062511920929, "lr": 3.3867276887871853e-07, "epoch": 0.39138271393013474, "percentage": 39.12, "elapsed_time": "1:35:21", "remaining_time": "2:28:23"}
+{"current_steps": 580, "total_steps": 1457, "loss": 0.5746, "accuracy": 0.7046874761581421, "lr": 3.348588863463005e-07, "epoch": 0.3982490773324178, "percentage": 39.81, "elapsed_time": "1:36:59", "remaining_time": "2:26:40"}
+{"current_steps": 590, "total_steps": 1457, "loss": 0.574, "accuracy": 0.7124999761581421, "lr": 3.310450038138825e-07, "epoch": 0.4051154407347009, "percentage": 40.49, "elapsed_time": "1:38:36", "remaining_time": "2:24:54"}
+{"current_steps": 600, "total_steps": 1457, "loss": 0.5756, "accuracy": 0.7046875357627869, "lr": 3.2723112128146454e-07, "epoch": 0.41198180413698393, "percentage": 41.18, "elapsed_time": "1:40:17", "remaining_time": "2:23:14"}
+{"current_steps": 610, "total_steps": 1457, "loss": 0.5566, "accuracy": 0.7421875, "lr": 3.2341723874904654e-07, "epoch": 0.418848167539267, "percentage": 41.87, "elapsed_time": "1:41:54", "remaining_time": "2:21:30"}
+{"current_steps": 620, "total_steps": 1457, "loss": 0.5954, "accuracy": 0.667187511920929, "lr": 3.1960335621662854e-07, "epoch": 0.4257145309415501, "percentage": 42.55, "elapsed_time": "1:43:29", "remaining_time": "2:19:42"}
+{"current_steps": 630, "total_steps": 1457, "loss": 0.5581, "accuracy": 0.7390625476837158, "lr": 3.157894736842105e-07, "epoch": 0.4325808943438331, "percentage": 43.24, "elapsed_time": "1:45:08", "remaining_time": "2:18:01"}
+{"current_steps": 640, "total_steps": 1457, "loss": 0.547, "accuracy": 0.75, "lr": 3.119755911517925e-07, "epoch": 0.4394472577461162, "percentage": 43.93, "elapsed_time": "1:46:46", "remaining_time": "2:16:18"}
+{"current_steps": 650, "total_steps": 1457, "loss": 0.5785, "accuracy": 0.7093749642372131, "lr": 3.081617086193745e-07, "epoch": 0.4463136211483993, "percentage": 44.61, "elapsed_time": "1:48:24", "remaining_time": "2:14:35"}
+{"current_steps": 660, "total_steps": 1457, "loss": 0.5592, "accuracy": 0.7406249642372131, "lr": 3.043478260869565e-07, "epoch": 0.45317998455068237, "percentage": 45.3, "elapsed_time": "1:50:07", "remaining_time": "2:12:59"}
+{"current_steps": 670, "total_steps": 1457, "loss": 0.5636, "accuracy": 0.7359375357627869, "lr": 3.005339435545385e-07, "epoch": 0.4600463479529654, "percentage": 45.98, "elapsed_time": "1:51:43", "remaining_time": "2:11:14"}
+{"current_steps": 680, "total_steps": 1457, "loss": 0.5671, "accuracy": 0.7421875, "lr": 2.967200610221205e-07, "epoch": 0.4669127113552485, "percentage": 46.67, "elapsed_time": "1:53:21", "remaining_time": "2:09:31"}
+{"current_steps": 690, "total_steps": 1457, "loss": 0.5621, "accuracy": 0.7234375476837158, "lr": 2.929061784897025e-07, "epoch": 0.47377907475753156, "percentage": 47.36, "elapsed_time": "1:55:03", "remaining_time": "2:07:53"}
+{"current_steps": 700, "total_steps": 1457, "loss": 0.5599, "accuracy": 0.703125, "lr": 2.890922959572845e-07, "epoch": 0.4806454381598146, "percentage": 48.04, "elapsed_time": "1:56:43", "remaining_time": "2:06:13"}
+{"current_steps": 710, "total_steps": 1457, "loss": 0.5553, "accuracy": 0.7093750238418579, "lr": 2.852784134248665e-07, "epoch": 0.48751180156209767, "percentage": 48.73, "elapsed_time": "1:58:21", "remaining_time": "2:04:31"}
+{"current_steps": 720, "total_steps": 1457, "loss": 0.5597, "accuracy": 0.7156250476837158, "lr": 2.8146453089244847e-07, "epoch": 0.49437816496438075, "percentage": 49.42, "elapsed_time": "1:59:55", "remaining_time": "2:02:45"}
+{"current_steps": 730, "total_steps": 1457, "loss": 0.5693, "accuracy": 0.7124999761581421, "lr": 2.776506483600305e-07, "epoch": 0.5012445283666638, "percentage": 50.1, "elapsed_time": "2:01:32", "remaining_time": "2:01:02"}
+{"current_steps": 740, "total_steps": 1457, "loss": 0.5536, "accuracy": 0.7328125238418579, "lr": 2.738367658276125e-07, "epoch": 0.5081108917689469, "percentage": 50.79, "elapsed_time": "2:03:10", "remaining_time": "1:59:20"}
+{"current_steps": 750, "total_steps": 1457, "loss": 0.5538, "accuracy": 0.7281250357627869, "lr": 2.7002288329519454e-07, "epoch": 0.5149772551712299, "percentage": 51.48, "elapsed_time": "2:04:44", "remaining_time": "1:57:35"}
+{"current_steps": 760, "total_steps": 1457, "loss": 0.5472, "accuracy": 0.7265625, "lr": 2.662090007627765e-07, "epoch": 0.521843618573513, "percentage": 52.16, "elapsed_time": "2:06:42", "remaining_time": "1:56:12"}
+{"current_steps": 770, "total_steps": 1457, "loss": 0.5449, "accuracy": 0.731249988079071, "lr": 2.623951182303585e-07, "epoch": 0.5287099819757961, "percentage": 52.85, "elapsed_time": "2:08:23", "remaining_time": "1:54:33"}
+{"current_steps": 780, "total_steps": 1457, "loss": 0.5401, "accuracy": 0.7203124761581421, "lr": 2.585812356979405e-07, "epoch": 0.5355763453780792, "percentage": 53.53, "elapsed_time": "2:10:00", "remaining_time": "1:52:50"}
+{"current_steps": 790, "total_steps": 1457, "loss": 0.5675, "accuracy": 0.7015624642372131, "lr": 2.547673531655225e-07, "epoch": 0.5424427087803622, "percentage": 54.22, "elapsed_time": "2:11:39", "remaining_time": "1:51:09"}
+{"current_steps": 800, "total_steps": 1457, "loss": 0.5502, "accuracy": 0.7374999523162842, "lr": 2.509534706331045e-07, "epoch": 0.5493090721826452, "percentage": 54.91, "elapsed_time": "2:13:26", "remaining_time": "1:49:35"}
+{"current_steps": 810, "total_steps": 1457, "loss": 0.541, "accuracy": 0.7515624761581421, "lr": 2.471395881006865e-07, "epoch": 0.5561754355849283, "percentage": 55.59, "elapsed_time": "2:15:06", "remaining_time": "1:47:54"}
+{"current_steps": 820, "total_steps": 1457, "loss": 0.5414, "accuracy": 0.7390625476837158, "lr": 2.4332570556826846e-07, "epoch": 0.5630417989872114, "percentage": 56.28, "elapsed_time": "2:16:43", "remaining_time": "1:46:12"}
+{"current_steps": 830, "total_steps": 1457, "loss": 0.5367, "accuracy": 0.7578125, "lr": 2.395118230358505e-07, "epoch": 0.5699081623894945, "percentage": 56.97, "elapsed_time": "2:18:17", "remaining_time": "1:44:28"}
+{"current_steps": 840, "total_steps": 1457, "loss": 0.5326, "accuracy": 0.7593749761581421, "lr": 2.3569794050343246e-07, "epoch": 0.5767745257917776, "percentage": 57.65, "elapsed_time": "2:19:56", "remaining_time": "1:42:47"}
+{"current_steps": 850, "total_steps": 1457, "loss": 0.5613, "accuracy": 0.7171875238418579, "lr": 2.318840579710145e-07, "epoch": 0.5836408891940605, "percentage": 58.34, "elapsed_time": "2:21:31", "remaining_time": "1:41:03"}
+{"current_steps": 860, "total_steps": 1457, "loss": 0.5404, "accuracy": 0.7421875, "lr": 2.2807017543859647e-07, "epoch": 0.5905072525963436, "percentage": 59.03, "elapsed_time": "2:23:04", "remaining_time": "1:39:19"}
+{"current_steps": 870, "total_steps": 1457, "loss": 0.5283, "accuracy": 0.7718750238418579, "lr": 2.2425629290617847e-07, "epoch": 0.5973736159986267, "percentage": 59.71, "elapsed_time": "2:24:43", "remaining_time": "1:37:38"}
+{"current_steps": 880, "total_steps": 1457, "loss": 0.5364, "accuracy": 0.7265625596046448, "lr": 2.204424103737605e-07, "epoch": 0.6042399794009098, "percentage": 60.4, "elapsed_time": "2:26:20", "remaining_time": "1:35:57"}
+{"current_steps": 890, "total_steps": 1457, "loss": 0.5617, "accuracy": 0.7203125357627869, "lr": 2.1662852784134248e-07, "epoch": 0.6111063428031929, "percentage": 61.08, "elapsed_time": "2:27:55", "remaining_time": "1:34:14"}
+{"current_steps": 900, "total_steps": 1457, "loss": 0.5388, "accuracy": 0.753125011920929, "lr": 2.1281464530892448e-07, "epoch": 0.617972706205476, "percentage": 61.77, "elapsed_time": "2:29:35", "remaining_time": "1:32:34"}
+{"current_steps": 910, "total_steps": 1457, "loss": 0.538, "accuracy": 0.721875011920929, "lr": 2.0900076277650646e-07, "epoch": 0.624839069607759, "percentage": 62.46, "elapsed_time": "2:31:14", "remaining_time": "1:30:54"}
+{"current_steps": 920, "total_steps": 1457, "loss": 0.5427, "accuracy": 0.7312500476837158, "lr": 2.051868802440885e-07, "epoch": 0.631705433010042, "percentage": 63.14, "elapsed_time": "2:32:56", "remaining_time": "1:29:16"}
+{"current_steps": 930, "total_steps": 1457, "loss": 0.5025, "accuracy": 0.78125, "lr": 2.0137299771167047e-07, "epoch": 0.6385717964123251, "percentage": 63.83, "elapsed_time": "2:34:35", "remaining_time": "1:27:36"}
+{"current_steps": 940, "total_steps": 1457, "loss": 0.5416, "accuracy": 0.7156250476837158, "lr": 1.9755911517925247e-07, "epoch": 0.6454381598146082, "percentage": 64.52, "elapsed_time": "2:36:15", "remaining_time": "1:25:56"}
+{"current_steps": 950, "total_steps": 1457, "loss": 0.5358, "accuracy": 0.7281249761581421, "lr": 1.9374523264683445e-07, "epoch": 0.6523045232168913, "percentage": 65.2, "elapsed_time": "2:37:52", "remaining_time": "1:24:15"}
+{"current_steps": 960, "total_steps": 1457, "loss": 0.5448, "accuracy": 0.734375, "lr": 1.8993135011441648e-07, "epoch": 0.6591708866191743, "percentage": 65.89, "elapsed_time": "2:39:28", "remaining_time": "1:22:33"}
+{"current_steps": 970, "total_steps": 1457, "loss": 0.5278, "accuracy": 0.75, "lr": 1.8611746758199848e-07, "epoch": 0.6660372500214574, "percentage": 66.58, "elapsed_time": "2:41:01", "remaining_time": "1:20:50"}
+{"current_steps": 980, "total_steps": 1457, "loss": 0.5325, "accuracy": 0.7718750238418579, "lr": 1.8230358504958046e-07, "epoch": 0.6729036134237405, "percentage": 67.26, "elapsed_time": "2:42:41", "remaining_time": "1:19:11"}
+{"current_steps": 990, "total_steps": 1457, "loss": 0.5553, "accuracy": 0.746874988079071, "lr": 1.7848970251716246e-07, "epoch": 0.6797699768260235, "percentage": 67.95, "elapsed_time": "2:44:15", "remaining_time": "1:17:28"}
+{"current_steps": 1000, "total_steps": 1457, "loss": 0.5147, "accuracy": 0.760937511920929, "lr": 1.7467581998474446e-07, "epoch": 0.6866363402283066, "percentage": 68.63, "elapsed_time": "2:45:55", "remaining_time": "1:15:49"}
+{"current_steps": 1010, "total_steps": 1457, "loss": 0.5326, "accuracy": 0.7406250238418579, "lr": 1.7086193745232647e-07, "epoch": 0.6935027036305896, "percentage": 69.32, "elapsed_time": "2:47:51", "remaining_time": "1:14:17"}
+{"current_steps": 1020, "total_steps": 1457, "loss": 0.5303, "accuracy": 0.7578125596046448, "lr": 1.6704805491990844e-07, "epoch": 0.7003690670328727, "percentage": 70.01, "elapsed_time": "2:49:31", "remaining_time": "1:12:37"}
+{"current_steps": 1030, "total_steps": 1457, "loss": 0.5397, "accuracy": 0.7359375357627869, "lr": 1.6323417238749045e-07, "epoch": 0.7072354304351558, "percentage": 70.69, "elapsed_time": "2:51:07", "remaining_time": "1:10:56"}
+{"current_steps": 1040, "total_steps": 1457, "loss": 0.5401, "accuracy": 0.7515625357627869, "lr": 1.5942028985507245e-07, "epoch": 0.7141017938374389, "percentage": 71.38, "elapsed_time": "2:52:44", "remaining_time": "1:09:15"}
+{"current_steps": 1050, "total_steps": 1457, "loss": 0.5287, "accuracy": 0.7562500238418579, "lr": 1.5560640732265446e-07, "epoch": 0.720968157239722, "percentage": 72.07, "elapsed_time": "2:54:22", "remaining_time": "1:07:35"}
+{"current_steps": 1060, "total_steps": 1457, "loss": 0.5515, "accuracy": 0.7124999761581421, "lr": 1.5179252479023646e-07, "epoch": 0.7278345206420049, "percentage": 72.75, "elapsed_time": "2:55:59", "remaining_time": "1:05:54"}
+{"current_steps": 1070, "total_steps": 1457, "loss": 0.5169, "accuracy": 0.7484375238418579, "lr": 1.4797864225781844e-07, "epoch": 0.734700884044288, "percentage": 73.44, "elapsed_time": "2:57:37", "remaining_time": "1:04:14"}
+{"current_steps": 1080, "total_steps": 1457, "loss": 0.5423, "accuracy": 0.737500011920929, "lr": 1.4416475972540047e-07, "epoch": 0.7415672474465711, "percentage": 74.12, "elapsed_time": "2:59:14", "remaining_time": "1:02:34"}
+{"current_steps": 1090, "total_steps": 1457, "loss": 0.5251, "accuracy": 0.776562511920929, "lr": 1.4035087719298244e-07, "epoch": 0.7484336108488542, "percentage": 74.81, "elapsed_time": "3:00:50", "remaining_time": "1:00:53"}
+{"current_steps": 1100, "total_steps": 1457, "loss": 0.4939, "accuracy": 0.7640625238418579, "lr": 1.3653699466056445e-07, "epoch": 0.7552999742511373, "percentage": 75.5, "elapsed_time": "3:02:32", "remaining_time": "0:59:14"}
+{"current_steps": 1110, "total_steps": 1457, "loss": 0.5141, "accuracy": 0.7546875476837158, "lr": 1.3272311212814645e-07, "epoch": 0.7621663376534203, "percentage": 76.18, "elapsed_time": "3:04:06", "remaining_time": "0:57:33"}
+{"current_steps": 1120, "total_steps": 1457, "loss": 0.5309, "accuracy": 0.7312500476837158, "lr": 1.2890922959572845e-07, "epoch": 0.7690327010557034, "percentage": 76.87, "elapsed_time": "3:05:43", "remaining_time": "0:55:52"}
+{"current_steps": 1130, "total_steps": 1457, "loss": 0.5151, "accuracy": 0.7734375, "lr": 1.2509534706331046e-07, "epoch": 0.7758990644579864, "percentage": 77.56, "elapsed_time": "3:07:22", "remaining_time": "0:54:13"}
+{"current_steps": 1140, "total_steps": 1457, "loss": 0.5208, "accuracy": 0.7578125596046448, "lr": 1.2128146453089243e-07, "epoch": 0.7827654278602695, "percentage": 78.24, "elapsed_time": "3:08:54", "remaining_time": "0:52:31"}
+{"current_steps": 1150, "total_steps": 1457, "loss": 0.52, "accuracy": 0.7562500238418579, "lr": 1.1746758199847444e-07, "epoch": 0.7896317912625526, "percentage": 78.93, "elapsed_time": "3:10:36", "remaining_time": "0:50:52"}
+{"current_steps": 1160, "total_steps": 1457, "loss": 0.5272, "accuracy": 0.7500000596046448, "lr": 1.1365369946605644e-07, "epoch": 0.7964981546648356, "percentage": 79.62, "elapsed_time": "3:12:12", "remaining_time": "0:49:12"}
+{"current_steps": 1170, "total_steps": 1457, "loss": 0.5052, "accuracy": 0.760937511920929, "lr": 1.0983981693363843e-07, "epoch": 0.8033645180671187, "percentage": 80.3, "elapsed_time": "3:13:46", "remaining_time": "0:47:31"}
+{"current_steps": 1180, "total_steps": 1457, "loss": 0.5308, "accuracy": 0.7718750238418579, "lr": 1.0602593440122045e-07, "epoch": 0.8102308814694018, "percentage": 80.99, "elapsed_time": "3:15:24", "remaining_time": "0:45:52"}
+{"current_steps": 1190, "total_steps": 1457, "loss": 0.5198, "accuracy": 0.7578125, "lr": 1.0221205186880244e-07, "epoch": 0.8170972448716848, "percentage": 81.67, "elapsed_time": "3:16:59", "remaining_time": "0:44:12"}
+{"current_steps": 1200, "total_steps": 1457, "loss": 0.5135, "accuracy": 0.7640625238418579, "lr": 9.839816933638444e-08, "epoch": 0.8239636082739679, "percentage": 82.36, "elapsed_time": "3:18:35", "remaining_time": "0:42:31"}
+{"current_steps": 1210, "total_steps": 1457, "loss": 0.5341, "accuracy": 0.7359374761581421, "lr": 9.458428680396643e-08, "epoch": 0.830829971676251, "percentage": 83.05, "elapsed_time": "3:20:18", "remaining_time": "0:40:53"}
+{"current_steps": 1220, "total_steps": 1457, "loss": 0.51, "accuracy": 0.762499988079071, "lr": 9.077040427154843e-08, "epoch": 0.837696335078534, "percentage": 83.73, "elapsed_time": "3:21:57", "remaining_time": "0:39:14"}
+{"current_steps": 1230, "total_steps": 1457, "loss": 0.5175, "accuracy": 0.765625, "lr": 8.695652173913042e-08, "epoch": 0.8445626984808171, "percentage": 84.42, "elapsed_time": "3:23:35", "remaining_time": "0:37:34"}
+{"current_steps": 1240, "total_steps": 1457, "loss": 0.5419, "accuracy": 0.7515625357627869, "lr": 8.314263920671243e-08, "epoch": 0.8514290618831002, "percentage": 85.11, "elapsed_time": "3:25:11", "remaining_time": "0:35:54"}
+{"current_steps": 1250, "total_steps": 1457, "loss": 0.5386, "accuracy": 0.7484375238418579, "lr": 7.932875667429442e-08, "epoch": 0.8582954252853833, "percentage": 85.79, "elapsed_time": "3:26:53", "remaining_time": "0:34:15"}
+{"current_steps": 1260, "total_steps": 1457, "loss": 0.5072, "accuracy": 0.7562500238418579, "lr": 7.551487414187643e-08, "epoch": 0.8651617886876662, "percentage": 86.48, "elapsed_time": "3:28:55", "remaining_time": "0:32:39"}
+{"current_steps": 1270, "total_steps": 1457, "loss": 0.5378, "accuracy": 0.7171875238418579, "lr": 7.170099160945843e-08, "epoch": 0.8720281520899493, "percentage": 87.17, "elapsed_time": "3:30:35", "remaining_time": "0:31:00"}
+{"current_steps": 1280, "total_steps": 1457, "loss": 0.5169, "accuracy": 0.7468750476837158, "lr": 6.788710907704043e-08, "epoch": 0.8788945154922324, "percentage": 87.85, "elapsed_time": "3:32:15", "remaining_time": "0:29:21"}
+{"current_steps": 1290, "total_steps": 1457, "loss": 0.4972, "accuracy": 0.7906249761581421, "lr": 6.407322654462242e-08, "epoch": 0.8857608788945155, "percentage": 88.54, "elapsed_time": "3:33:54", "remaining_time": "0:27:41"}
+{"current_steps": 1300, "total_steps": 1457, "loss": 0.5156, "accuracy": 0.7640625238418579, "lr": 6.025934401220442e-08, "epoch": 0.8926272422967986, "percentage": 89.22, "elapsed_time": "3:35:33", "remaining_time": "0:26:01"}
+{"current_steps": 1310, "total_steps": 1457, "loss": 0.517, "accuracy": 0.760937511920929, "lr": 5.644546147978642e-08, "epoch": 0.8994936056990817, "percentage": 89.91, "elapsed_time": "3:37:07", "remaining_time": "0:24:21"}
+{"current_steps": 1320, "total_steps": 1457, "loss": 0.5129, "accuracy": 0.768750011920929, "lr": 5.2631578947368416e-08, "epoch": 0.9063599691013647, "percentage": 90.6, "elapsed_time": "3:38:44", "remaining_time": "0:22:42"}
+{"current_steps": 1330, "total_steps": 1457, "loss": 0.518, "accuracy": 0.7562500238418579, "lr": 4.881769641495042e-08, "epoch": 0.9132263325036477, "percentage": 91.28, "elapsed_time": "3:40:25", "remaining_time": "0:21:02"}
+{"current_steps": 1340, "total_steps": 1457, "loss": 0.5245, "accuracy": 0.754687488079071, "lr": 4.5003813882532416e-08, "epoch": 0.9200926959059308, "percentage": 91.97, "elapsed_time": "3:41:57", "remaining_time": "0:19:22"}
+{"current_steps": 1350, "total_steps": 1457, "loss": 0.5043, "accuracy": 0.7421875, "lr": 4.118993135011441e-08, "epoch": 0.9269590593082139, "percentage": 92.66, "elapsed_time": "3:43:34", "remaining_time": "0:17:43"}
+{"current_steps": 1360, "total_steps": 1457, "loss": 0.5196, "accuracy": 0.754687488079071, "lr": 3.737604881769641e-08, "epoch": 0.933825422710497, "percentage": 93.34, "elapsed_time": "3:45:12", "remaining_time": "0:16:03"}
+{"current_steps": 1370, "total_steps": 1457, "loss": 0.5305, "accuracy": 0.745312511920929, "lr": 3.356216628527841e-08, "epoch": 0.94069178611278, "percentage": 94.03, "elapsed_time": "3:46:51", "remaining_time": "0:14:24"}
+{"current_steps": 1380, "total_steps": 1457, "loss": 0.4831, "accuracy": 0.792187511920929, "lr": 2.9748283752860413e-08, "epoch": 0.9475581495150631, "percentage": 94.72, "elapsed_time": "3:48:29", "remaining_time": "0:12:44"}
+{"current_steps": 1390, "total_steps": 1457, "loss": 0.491, "accuracy": 0.776562511920929, "lr": 2.593440122044241e-08, "epoch": 0.9544245129173462, "percentage": 95.4, "elapsed_time": "3:50:08", "remaining_time": "0:11:05"}
+{"current_steps": 1400, "total_steps": 1457, "loss": 0.521, "accuracy": 0.7421875, "lr": 2.212051868802441e-08, "epoch": 0.9612908763196292, "percentage": 96.09, "elapsed_time": "3:51:44", "remaining_time": "0:09:26"}
+{"current_steps": 1410, "total_steps": 1457, "loss": 0.5076, "accuracy": 0.7562500238418579, "lr": 1.8306636155606407e-08, "epoch": 0.9681572397219123, "percentage": 96.77, "elapsed_time": "3:53:23", "remaining_time": "0:07:46"}
+{"current_steps": 1420, "total_steps": 1457, "loss": 0.5287, "accuracy": 0.7593750357627869, "lr": 1.4492753623188406e-08, "epoch": 0.9750236031241953, "percentage": 97.46, "elapsed_time": "3:54:59", "remaining_time": "0:06:07"}
+{"current_steps": 1430, "total_steps": 1457, "loss": 0.5281, "accuracy": 0.75, "lr": 1.0678871090770404e-08, "epoch": 0.9818899665264784, "percentage": 98.15, "elapsed_time": "3:56:40", "remaining_time": "0:04:28"}
+{"current_steps": 1440, "total_steps": 1457, "loss": 0.5302, "accuracy": 0.7250000238418579, "lr": 6.864988558352402e-09, "epoch": 0.9887563299287615, "percentage": 98.83, "elapsed_time": "3:58:16", "remaining_time": "0:02:48"}
+{"current_steps": 1450, "total_steps": 1457, "loss": 0.518, "accuracy": 0.7562500238418579, "lr": 3.0511060259344012e-09, "epoch": 0.9956226933310446, "percentage": 99.52, "elapsed_time": "3:59:53", "remaining_time": "0:01:09"}
+{"current_steps": 1457, "total_steps": 1457, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "4:01:16", "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": 1457,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006866363402283066,
+      "grad_norm": 40.24618346360798,
+      "learning_rate": 3.082191780821918e-08,
+      "logits/chosen": 0.42846742272377014,
+      "logits/rejected": 0.45268937945365906,
+      "logps/chosen": -183.30755615234375,
+      "logps/rejected": -195.22784423828125,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": 0.0004921938525512815,
+      "rewards/margins": 0.0011830208823084831,
+      "rewards/rejected": -0.0006908266805112362,
+      "step": 10
+    },
+    {
+      "epoch": 0.013732726804566131,
+      "grad_norm": 42.45940511830856,
+      "learning_rate": 6.506849315068492e-08,
+      "logits/chosen": 0.378580778837204,
+      "logits/rejected": 0.34625354409217834,
+      "logps/chosen": -184.8052978515625,
+      "logps/rejected": -188.45614624023438,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.00026374688604846597,
+      "rewards/margins": 0.0003242385573685169,
+      "rewards/rejected": -0.0005879853270016611,
+      "step": 20
+    },
+    {
+      "epoch": 0.020599090206849198,
+      "grad_norm": 41.66964168493646,
+      "learning_rate": 9.931506849315068e-08,
+      "logits/chosen": 0.35301661491394043,
+      "logits/rejected": 0.4009673595428467,
+      "logps/chosen": -192.31698608398438,
+      "logps/rejected": -194.3849639892578,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.534375011920929,
+      "rewards/chosen": -0.0016289607156068087,
+      "rewards/margins": 0.0033018598333001137,
+      "rewards/rejected": -0.004930821247398853,
+      "step": 30
+    },
+    {
+      "epoch": 0.027465453609132263,
+      "grad_norm": 39.249039173578126,
+      "learning_rate": 1.3356164383561644e-07,
+      "logits/chosen": 0.31915441155433655,
+      "logits/rejected": 0.3933267593383789,
+      "logps/chosen": -197.9785614013672,
+      "logps/rejected": -193.6060333251953,
+      "loss": 0.6947,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0002039932005573064,
+      "rewards/margins": -0.0016961463261395693,
+      "rewards/rejected": 0.0019001394975930452,
+      "step": 40
+    },
+    {
+      "epoch": 0.03433181701141533,
+      "grad_norm": 40.90604754389793,
+      "learning_rate": 1.6780821917808218e-07,
+      "logits/chosen": 0.35795748233795166,
+      "logits/rejected": 0.4378845691680908,
+      "logps/chosen": -187.54156494140625,
+      "logps/rejected": -189.99392700195312,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": 0.0017753265565261245,
+      "rewards/margins": -0.00030706170946359634,
+      "rewards/rejected": 0.0020823883824050426,
+      "step": 50
+    },
+    {
+      "epoch": 0.041198180413698396,
+      "grad_norm": 40.02800677179251,
+      "learning_rate": 2.0205479452054795e-07,
+      "logits/chosen": 0.34263893961906433,
+      "logits/rejected": 0.381570965051651,
+      "logps/chosen": -192.94613647460938,
+      "logps/rejected": -191.47396850585938,
+      "loss": 0.6959,
+      "rewards/accuracies": 0.4906250238418579,
+      "rewards/chosen": -0.0020632040686905384,
+      "rewards/margins": -0.00374617800116539,
+      "rewards/rejected": 0.0016829746309667826,
+      "step": 60
+    },
+    {
+      "epoch": 0.048064543815981464,
+      "grad_norm": 44.64464771956862,
+      "learning_rate": 2.363013698630137e-07,
+      "logits/chosen": 0.367872029542923,
+      "logits/rejected": 0.38009101152420044,
+      "logps/chosen": -191.12225341796875,
+      "logps/rejected": -192.7696990966797,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.49375003576278687,
+      "rewards/chosen": 0.00574580579996109,
+      "rewards/margins": 0.0022611478343605995,
+      "rewards/rejected": 0.0034846579656004906,
+      "step": 70
+    },
+    {
+      "epoch": 0.054930907218264526,
+      "grad_norm": 41.884882712897294,
+      "learning_rate": 2.7054794520547945e-07,
+      "logits/chosen": 0.3370077908039093,
+      "logits/rejected": 0.34699341654777527,
+      "logps/chosen": -188.7425537109375,
+      "logps/rejected": -190.76052856445312,
+      "loss": 0.6913,
+      "rewards/accuracies": 0.5218750238418579,
+      "rewards/chosen": 0.0027863490395247936,
+      "rewards/margins": 0.005139566957950592,
+      "rewards/rejected": -0.0023532179184257984,
+      "step": 80
+    },
+    {
+      "epoch": 0.061797270620547594,
+      "grad_norm": 44.4056603091038,
+      "learning_rate": 3.047945205479452e-07,
+      "logits/chosen": 0.3108683228492737,
+      "logits/rejected": 0.3609522581100464,
+      "logps/chosen": -195.35147094726562,
+      "logps/rejected": -193.3247833251953,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5218749642372131,
+      "rewards/chosen": 0.00044549518497660756,
+      "rewards/margins": 0.0018838731339201331,
+      "rewards/rejected": -0.0014383781235665083,
+      "step": 90
+    },
+    {
+      "epoch": 0.06866363402283066,
+      "grad_norm": 41.857792639398546,
+      "learning_rate": 3.39041095890411e-07,
+      "logits/chosen": 0.3763309121131897,
+      "logits/rejected": 0.3922409415245056,
+      "logps/chosen": -193.8089141845703,
+      "logps/rejected": -198.68551635742188,
+      "loss": 0.6899,
+      "rewards/accuracies": 0.5281250476837158,
+      "rewards/chosen": 0.005990107078105211,
+      "rewards/margins": 0.008157256990671158,
+      "rewards/rejected": -0.0021671501453965902,
+      "step": 100
+    },
+    {
+      "epoch": 0.07552999742511372,
+      "grad_norm": 41.62980958107549,
+      "learning_rate": 3.7328767123287667e-07,
+      "logits/chosen": 0.3591919541358948,
+      "logits/rejected": 0.39655131101608276,
+      "logps/chosen": -196.92422485351562,
+      "logps/rejected": -197.28872680664062,
+      "loss": 0.689,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": 0.004954576026648283,
+      "rewards/margins": 0.010082172229886055,
+      "rewards/rejected": -0.005127596668899059,
+      "step": 110
+    },
+    {
+      "epoch": 0.08239636082739679,
+      "grad_norm": 43.693807356131735,
+      "learning_rate": 4.0753424657534246e-07,
+      "logits/chosen": 0.3348645865917206,
+      "logits/rejected": 0.35767242312431335,
+      "logps/chosen": -198.3641357421875,
+      "logps/rejected": -203.7303009033203,
+      "loss": 0.6885,
+      "rewards/accuracies": 0.5750000476837158,
+      "rewards/chosen": 0.005779502913355827,
+      "rewards/margins": 0.01143658347427845,
+      "rewards/rejected": -0.005657079629600048,
+      "step": 120
+    },
+    {
+      "epoch": 0.08926272422967986,
+      "grad_norm": 40.57954536185725,
+      "learning_rate": 4.417808219178082e-07,
+      "logits/chosen": 0.336916983127594,
+      "logits/rejected": 0.3446354866027832,
+      "logps/chosen": -193.88165283203125,
+      "logps/rejected": -191.94683837890625,
+      "loss": 0.6842,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": 0.010509985499083996,
+      "rewards/margins": 0.020326683297753334,
+      "rewards/rejected": -0.009816695004701614,
+      "step": 130
+    },
+    {
+      "epoch": 0.09612908763196293,
+      "grad_norm": 41.15941757414013,
+      "learning_rate": 4.7602739726027394e-07,
+      "logits/chosen": 0.35713282227516174,
+      "logits/rejected": 0.3554469347000122,
+      "logps/chosen": -192.0938720703125,
+      "logps/rejected": -192.8302001953125,
+      "loss": 0.686,
+      "rewards/accuracies": 0.5390625596046448,
+      "rewards/chosen": -0.0002686302177608013,
+      "rewards/margins": 0.017483647912740707,
+      "rewards/rejected": -0.017752276733517647,
+      "step": 140
+    },
+    {
+      "epoch": 0.10299545103424598,
+      "grad_norm": 42.74829745936997,
+      "learning_rate": 4.988558352402745e-07,
+      "logits/chosen": 0.3553549349308014,
+      "logits/rejected": 0.36016494035720825,
+      "logps/chosen": -189.06460571289062,
+      "logps/rejected": -189.97903442382812,
+      "loss": 0.6797,
+      "rewards/accuracies": 0.6140625476837158,
+      "rewards/chosen": 0.008752593770623207,
+      "rewards/margins": 0.030557716265320778,
+      "rewards/rejected": -0.02180512063205242,
+      "step": 150
+    },
+    {
+      "epoch": 0.10986181443652905,
+      "grad_norm": 35.871465251274834,
+      "learning_rate": 4.950419527078566e-07,
+      "logits/chosen": 0.43320149183273315,
+      "logits/rejected": 0.41380226612091064,
+      "logps/chosen": -181.6295623779297,
+      "logps/rejected": -186.4168701171875,
+      "loss": 0.6782,
+      "rewards/accuracies": 0.6109375357627869,
+      "rewards/chosen": 0.0026512315962463617,
+      "rewards/margins": 0.03445584699511528,
+      "rewards/rejected": -0.03180461376905441,
+      "step": 160
+    },
+    {
+      "epoch": 0.11672817783881212,
+      "grad_norm": 43.14214265722976,
+      "learning_rate": 4.912280701754385e-07,
+      "logits/chosen": 0.3183770477771759,
+      "logits/rejected": 0.3852064311504364,
+      "logps/chosen": -198.97998046875,
+      "logps/rejected": -195.97885131835938,
+      "loss": 0.6774,
+      "rewards/accuracies": 0.604687511920929,
+      "rewards/chosen": -0.0013574912445619702,
+      "rewards/margins": 0.03735988214612007,
+      "rewards/rejected": -0.038717374205589294,
+      "step": 170
+    },
+    {
+      "epoch": 0.12359454124109519,
+      "grad_norm": 41.435109809126814,
+      "learning_rate": 4.874141876430206e-07,
+      "logits/chosen": 0.3532235324382782,
+      "logits/rejected": 0.37155628204345703,
+      "logps/chosen": -190.45042419433594,
+      "logps/rejected": -189.18121337890625,
+      "loss": 0.67,
+      "rewards/accuracies": 0.6343750357627869,
+      "rewards/chosen": 0.0023425191175192595,
+      "rewards/margins": 0.05440489947795868,
+      "rewards/rejected": -0.05206237733364105,
+      "step": 180
+    },
+    {
+      "epoch": 0.13046090464337826,
+      "grad_norm": 39.447517017039274,
+      "learning_rate": 4.836003051106026e-07,
+      "logits/chosen": 0.347377210855484,
+      "logits/rejected": 0.3284303843975067,
+      "logps/chosen": -194.7428741455078,
+      "logps/rejected": -194.8145294189453,
+      "loss": 0.6723,
+      "rewards/accuracies": 0.573437511920929,
+      "rewards/chosen": 0.0014576537068933249,
+      "rewards/margins": 0.051343731582164764,
+      "rewards/rejected": -0.049886077642440796,
+      "step": 190
+    },
+    {
+      "epoch": 0.1373272680456613,
+      "grad_norm": 38.847764648617996,
+      "learning_rate": 4.797864225781846e-07,
+      "logits/chosen": 0.3240855932235718,
+      "logits/rejected": 0.35028141736984253,
+      "logps/chosen": -195.90789794921875,
+      "logps/rejected": -196.3568878173828,
+      "loss": 0.6638,
+      "rewards/accuracies": 0.6343750357627869,
+      "rewards/chosen": -0.016327721998095512,
+      "rewards/margins": 0.07191106677055359,
+      "rewards/rejected": -0.08823878318071365,
+      "step": 200
+    },
+    {
+      "epoch": 0.1441936314479444,
+      "grad_norm": 40.58275358830573,
+      "learning_rate": 4.759725400457666e-07,
+      "logits/chosen": 0.3534795641899109,
+      "logits/rejected": 0.4051111340522766,
+      "logps/chosen": -189.0966796875,
+      "logps/rejected": -194.59945678710938,
+      "loss": 0.666,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -0.030735965818166733,
+      "rewards/margins": 0.06700534373521805,
+      "rewards/rejected": -0.09774130582809448,
+      "step": 210
+    },
+    {
+      "epoch": 0.15105999485022745,
+      "grad_norm": 45.10759256069824,
+      "learning_rate": 4.7215865751334857e-07,
+      "logits/chosen": 0.3427739143371582,
+      "logits/rejected": 0.3563682734966278,
+      "logps/chosen": -194.303955078125,
+      "logps/rejected": -196.68199157714844,
+      "loss": 0.6633,
+      "rewards/accuracies": 0.6296875476837158,
+      "rewards/chosen": -0.029208209365606308,
+      "rewards/margins": 0.0735444575548172,
+      "rewards/rejected": -0.1027526706457138,
+      "step": 220
+    },
+    {
+      "epoch": 0.1579263582525105,
+      "grad_norm": 37.81921037823293,
+      "learning_rate": 4.6834477498093057e-07,
+      "logits/chosen": 0.3555576801300049,
+      "logits/rejected": 0.36491692066192627,
+      "logps/chosen": -188.83424377441406,
+      "logps/rejected": -192.81069946289062,
+      "loss": 0.6537,
+      "rewards/accuracies": 0.6484375,
+      "rewards/chosen": -0.04094560444355011,
+      "rewards/margins": 0.0983317419886589,
+      "rewards/rejected": -0.1392773538827896,
+      "step": 230
+    },
+    {
+      "epoch": 0.16479272165479358,
+      "grad_norm": 41.32206557637078,
+      "learning_rate": 4.6453089244851257e-07,
+      "logits/chosen": 0.39804917573928833,
+      "logits/rejected": 0.36356666684150696,
+      "logps/chosen": -194.4440155029297,
+      "logps/rejected": -200.01412963867188,
+      "loss": 0.6514,
+      "rewards/accuracies": 0.6343750357627869,
+      "rewards/chosen": -0.04057128727436066,
+      "rewards/margins": 0.10563759505748749,
+      "rewards/rejected": -0.14620888233184814,
+      "step": 240
+    },
+    {
+      "epoch": 0.17165908505707664,
+      "grad_norm": 39.276473772360774,
+      "learning_rate": 4.607170099160946e-07,
+      "logits/chosen": 0.33169448375701904,
+      "logits/rejected": 0.3752690553665161,
+      "logps/chosen": -196.81478881835938,
+      "logps/rejected": -201.34481811523438,
+      "loss": 0.6452,
+      "rewards/accuracies": 0.6781250238418579,
+      "rewards/chosen": -0.03887462615966797,
+      "rewards/margins": 0.12037336826324463,
+      "rewards/rejected": -0.1592479944229126,
+      "step": 250
+    },
+    {
+      "epoch": 0.17852544845935972,
+      "grad_norm": 47.0610078724711,
+      "learning_rate": 4.569031273836766e-07,
+      "logits/chosen": 0.34487199783325195,
+      "logits/rejected": 0.3575427532196045,
+      "logps/chosen": -193.79837036132812,
+      "logps/rejected": -197.2197265625,
+      "loss": 0.6508,
+      "rewards/accuracies": 0.6421875357627869,
+      "rewards/chosen": -0.09015019237995148,
+      "rewards/margins": 0.11270132660865784,
+      "rewards/rejected": -0.20285151898860931,
+      "step": 260
+    },
+    {
+      "epoch": 0.18539181186164277,
+      "grad_norm": 38.626969264563606,
+      "learning_rate": 4.5308924485125853e-07,
+      "logits/chosen": 0.32855209708213806,
+      "logits/rejected": 0.3907463252544403,
+      "logps/chosen": -191.17459106445312,
+      "logps/rejected": -189.3603057861328,
+      "loss": 0.6475,
+      "rewards/accuracies": 0.6484375,
+      "rewards/chosen": -0.07459260523319244,
+      "rewards/margins": 0.11734659224748611,
+      "rewards/rejected": -0.19193920493125916,
+      "step": 270
+    },
+    {
+      "epoch": 0.19225817526392586,
+      "grad_norm": 40.103707367823155,
+      "learning_rate": 4.4927536231884053e-07,
+      "logits/chosen": 0.3284029960632324,
+      "logits/rejected": 0.3626914918422699,
+      "logps/chosen": -192.84405517578125,
+      "logps/rejected": -194.70567321777344,
+      "loss": 0.6457,
+      "rewards/accuracies": 0.6656250357627869,
+      "rewards/chosen": -0.07513514161109924,
+      "rewards/margins": 0.12614111602306366,
+      "rewards/rejected": -0.2012762576341629,
+      "step": 280
+    },
+    {
+      "epoch": 0.1991245386662089,
+      "grad_norm": 40.1951811593668,
+      "learning_rate": 4.454614797864226e-07,
+      "logits/chosen": 0.34982651472091675,
+      "logits/rejected": 0.3777983486652374,
+      "logps/chosen": -194.1185760498047,
+      "logps/rejected": -201.16836547851562,
+      "loss": 0.6373,
+      "rewards/accuracies": 0.6484375596046448,
+      "rewards/chosen": -0.062012314796447754,
+      "rewards/margins": 0.14990699291229248,
+      "rewards/rejected": -0.21191930770874023,
+      "step": 290
+    },
+    {
+      "epoch": 0.20599090206849197,
+      "grad_norm": 40.613600115901605,
+      "learning_rate": 4.416475972540046e-07,
+      "logits/chosen": 0.30782297253608704,
+      "logits/rejected": 0.3243838846683502,
+      "logps/chosen": -201.00067138671875,
+      "logps/rejected": -197.9466552734375,
+      "loss": 0.629,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.02788611315190792,
+      "rewards/margins": 0.17499074339866638,
+      "rewards/rejected": -0.20287683606147766,
+      "step": 300
+    },
+    {
+      "epoch": 0.21285726547077505,
+      "grad_norm": 38.45809132820782,
+      "learning_rate": 4.3783371472158654e-07,
+      "logits/chosen": 0.293393611907959,
+      "logits/rejected": 0.34445005655288696,
+      "logps/chosen": -190.18313598632812,
+      "logps/rejected": -192.75411987304688,
+      "loss": 0.6295,
+      "rewards/accuracies": 0.6859375238418579,
+      "rewards/chosen": -0.031520403921604156,
+      "rewards/margins": 0.16698937118053436,
+      "rewards/rejected": -0.19850978255271912,
+      "step": 310
+    },
+    {
+      "epoch": 0.2197236288730581,
+      "grad_norm": 38.34602578772718,
+      "learning_rate": 4.3401983218916855e-07,
+      "logits/chosen": 0.2906053066253662,
+      "logits/rejected": 0.34385767579078674,
+      "logps/chosen": -194.83795166015625,
+      "logps/rejected": -195.7698211669922,
+      "loss": 0.6173,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.01768593303859234,
+      "rewards/margins": 0.21204118430614471,
+      "rewards/rejected": -0.2297271192073822,
+      "step": 320
+    },
+    {
+      "epoch": 0.22658999227534118,
+      "grad_norm": 42.74391582277574,
+      "learning_rate": 4.3020594965675055e-07,
+      "logits/chosen": 0.30266571044921875,
+      "logits/rejected": 0.3389095067977905,
+      "logps/chosen": -198.25233459472656,
+      "logps/rejected": -200.7266082763672,
+      "loss": 0.6263,
+      "rewards/accuracies": 0.6734375357627869,
+      "rewards/chosen": -0.0333101749420166,
+      "rewards/margins": 0.19498664140701294,
+      "rewards/rejected": -0.22829681634902954,
+      "step": 330
+    },
+    {
+      "epoch": 0.23345635567762424,
+      "grad_norm": 43.615077922449544,
+      "learning_rate": 4.2639206712433255e-07,
+      "logits/chosen": 0.30118876695632935,
+      "logits/rejected": 0.34083983302116394,
+      "logps/chosen": -196.76663208007812,
+      "logps/rejected": -196.46299743652344,
+      "loss": 0.6296,
+      "rewards/accuracies": 0.6640625,
+      "rewards/chosen": -0.011256666854023933,
+      "rewards/margins": 0.1830688714981079,
+      "rewards/rejected": -0.1943255364894867,
+      "step": 340
+    },
+    {
+      "epoch": 0.2403227190799073,
+      "grad_norm": 37.24751529917733,
+      "learning_rate": 4.2257818459191456e-07,
+      "logits/chosen": 0.25924569368362427,
+      "logits/rejected": 0.283855676651001,
+      "logps/chosen": -183.45191955566406,
+      "logps/rejected": -187.04440307617188,
+      "loss": 0.633,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.015273300930857658,
+      "rewards/margins": 0.17985355854034424,
+      "rewards/rejected": -0.19512686133384705,
+      "step": 350
+    },
+    {
+      "epoch": 0.24718908248219038,
+      "grad_norm": 40.58954818497333,
+      "learning_rate": 4.187643020594965e-07,
+      "logits/chosen": 0.28448960185050964,
+      "logits/rejected": 0.33332377672195435,
+      "logps/chosen": -193.56716918945312,
+      "logps/rejected": -197.53184509277344,
+      "loss": 0.6223,
+      "rewards/accuracies": 0.690625011920929,
+      "rewards/chosen": -0.048774123191833496,
+      "rewards/margins": 0.20520111918449402,
+      "rewards/rejected": -0.2539752423763275,
+      "step": 360
+    },
+    {
+      "epoch": 0.25405544588447343,
+      "grad_norm": 36.17378532660478,
+      "learning_rate": 4.1495041952707856e-07,
+      "logits/chosen": 0.2762497067451477,
+      "logits/rejected": 0.2907570004463196,
+      "logps/chosen": -188.5650634765625,
+      "logps/rejected": -190.88734436035156,
+      "loss": 0.6137,
+      "rewards/accuracies": 0.6890624761581421,
+      "rewards/chosen": -0.05067811906337738,
+      "rewards/margins": 0.2351914346218109,
+      "rewards/rejected": -0.2858695387840271,
+      "step": 370
+    },
+    {
+      "epoch": 0.2609218092867565,
+      "grad_norm": 37.43784314884923,
+      "learning_rate": 4.1113653699466057e-07,
+      "logits/chosen": 0.31868118047714233,
+      "logits/rejected": 0.3551029562950134,
+      "logps/chosen": -194.93936157226562,
+      "logps/rejected": -198.65814208984375,
+      "loss": 0.6003,
+      "rewards/accuracies": 0.7046874761581421,
+      "rewards/chosen": -0.0772961899638176,
+      "rewards/margins": 0.2751655578613281,
+      "rewards/rejected": -0.35246172547340393,
+      "step": 380
+    },
+    {
+      "epoch": 0.2677881726890396,
+      "grad_norm": 35.91361143227307,
+      "learning_rate": 4.0732265446224257e-07,
+      "logits/chosen": 0.3169372081756592,
+      "logits/rejected": 0.36260250210762024,
+      "logps/chosen": -201.2320556640625,
+      "logps/rejected": -202.763427734375,
+      "loss": 0.613,
+      "rewards/accuracies": 0.6781250238418579,
+      "rewards/chosen": -0.09429500252008438,
+      "rewards/margins": 0.24527618288993835,
+      "rewards/rejected": -0.3395712077617645,
+      "step": 390
+    },
+    {
+      "epoch": 0.2746545360913226,
+      "grad_norm": 42.53335069773125,
+      "learning_rate": 4.035087719298245e-07,
+      "logits/chosen": 0.31207048892974854,
+      "logits/rejected": 0.3457629680633545,
+      "logps/chosen": -206.29269409179688,
+      "logps/rejected": -201.12423706054688,
+      "loss": 0.601,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": -0.08769121766090393,
+      "rewards/margins": 0.2706546187400818,
+      "rewards/rejected": -0.3583458364009857,
+      "step": 400
+    },
+    {
+      "epoch": 0.2815208994936057,
+      "grad_norm": 41.29813511944604,
+      "learning_rate": 3.996948893974065e-07,
+      "logits/chosen": 0.2636485993862152,
+      "logits/rejected": 0.31149038672447205,
+      "logps/chosen": -194.1279296875,
+      "logps/rejected": -194.5345001220703,
+      "loss": 0.5947,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.05628068745136261,
+      "rewards/margins": 0.2829420864582062,
+      "rewards/rejected": -0.33922278881073,
+      "step": 410
+    },
+    {
+      "epoch": 0.2883872628958888,
+      "grad_norm": 37.77093581368485,
+      "learning_rate": 3.9588100686498853e-07,
+      "logits/chosen": 0.31741800904273987,
+      "logits/rejected": 0.32371169328689575,
+      "logps/chosen": -190.85951232910156,
+      "logps/rejected": -198.15396118164062,
+      "loss": 0.609,
+      "rewards/accuracies": 0.6843750476837158,
+      "rewards/chosen": -0.12272913008928299,
+      "rewards/margins": 0.2659768760204315,
+      "rewards/rejected": -0.3887060284614563,
+      "step": 420
+    },
+    {
+      "epoch": 0.2952536262981718,
+      "grad_norm": 42.18074374760277,
+      "learning_rate": 3.9206712433257053e-07,
+      "logits/chosen": 0.2479156255722046,
+      "logits/rejected": 0.2833534777164459,
+      "logps/chosen": -195.24853515625,
+      "logps/rejected": -199.1217498779297,
+      "loss": 0.6196,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.09873144328594208,
+      "rewards/margins": 0.23723819851875305,
+      "rewards/rejected": -0.3359696567058563,
+      "step": 430
+    },
+    {
+      "epoch": 0.3021199897004549,
+      "grad_norm": 40.84692701651787,
+      "learning_rate": 3.882532418001526e-07,
+      "logits/chosen": 0.26803913712501526,
+      "logits/rejected": 0.2534467577934265,
+      "logps/chosen": -198.0133056640625,
+      "logps/rejected": -203.25198364257812,
+      "loss": 0.5946,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.07623399049043655,
+      "rewards/margins": 0.3022476136684418,
+      "rewards/rejected": -0.3784816265106201,
+      "step": 440
+    },
+    {
+      "epoch": 0.308986353102738,
+      "grad_norm": 52.48738116894515,
+      "learning_rate": 3.8443935926773454e-07,
+      "logits/chosen": 0.2687249779701233,
+      "logits/rejected": 0.2839760184288025,
+      "logps/chosen": -190.901611328125,
+      "logps/rejected": -197.57106018066406,
+      "loss": 0.6148,
+      "rewards/accuracies": 0.684374988079071,
+      "rewards/chosen": -0.1082596629858017,
+      "rewards/margins": 0.2658810019493103,
+      "rewards/rejected": -0.3741406798362732,
+      "step": 450
+    },
+    {
+      "epoch": 0.315852716505021,
+      "grad_norm": 41.567018649209494,
+      "learning_rate": 3.8062547673531654e-07,
+      "logits/chosen": 0.2616228461265564,
+      "logits/rejected": 0.31667307019233704,
+      "logps/chosen": -190.47607421875,
+      "logps/rejected": -192.07882690429688,
+      "loss": 0.5991,
+      "rewards/accuracies": 0.682812511920929,
+      "rewards/chosen": -0.09240880608558655,
+      "rewards/margins": 0.2821645140647888,
+      "rewards/rejected": -0.37457332015037537,
+      "step": 460
+    },
+    {
+      "epoch": 0.3227190799073041,
+      "grad_norm": 35.499115046921446,
+      "learning_rate": 3.7681159420289855e-07,
+      "logits/chosen": 0.27905237674713135,
+      "logits/rejected": 0.31074196100234985,
+      "logps/chosen": -192.92088317871094,
+      "logps/rejected": -197.79124450683594,
+      "loss": 0.61,
+      "rewards/accuracies": 0.6734375357627869,
+      "rewards/chosen": -0.13386519253253937,
+      "rewards/margins": 0.27014487981796265,
+      "rewards/rejected": -0.4040100872516632,
+      "step": 470
+    },
+    {
+      "epoch": 0.32958544330958717,
+      "grad_norm": 41.86761698270693,
+      "learning_rate": 3.7299771167048055e-07,
+      "logits/chosen": 0.26603832840919495,
+      "logits/rejected": 0.26051998138427734,
+      "logps/chosen": -190.23660278320312,
+      "logps/rejected": -197.73736572265625,
+      "loss": 0.5981,
+      "rewards/accuracies": 0.6875000596046448,
+      "rewards/chosen": -0.1415073573589325,
+      "rewards/margins": 0.31012141704559326,
+      "rewards/rejected": -0.45162874460220337,
+      "step": 480
+    },
+    {
+      "epoch": 0.33645180671187025,
+      "grad_norm": 37.648693672476206,
+      "learning_rate": 3.691838291380625e-07,
+      "logits/chosen": 0.3558499813079834,
+      "logits/rejected": 0.3315980136394501,
+      "logps/chosen": -188.3795623779297,
+      "logps/rejected": -200.14048767089844,
+      "loss": 0.5837,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.1745017170906067,
+      "rewards/margins": 0.364481657743454,
+      "rewards/rejected": -0.5389833450317383,
+      "step": 490
+    },
+    {
+      "epoch": 0.3433181701141533,
+      "grad_norm": 40.65037054074536,
+      "learning_rate": 3.653699466056445e-07,
+      "logits/chosen": 0.2540973722934723,
+      "logits/rejected": 0.2895161509513855,
+      "logps/chosen": -187.24462890625,
+      "logps/rejected": -193.23289489746094,
+      "loss": 0.5909,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.1618882715702057,
+      "rewards/margins": 0.3192650377750397,
+      "rewards/rejected": -0.48115330934524536,
+      "step": 500
+    },
+    {
+      "epoch": 0.35018453351643636,
+      "grad_norm": 36.872109535629086,
+      "learning_rate": 3.615560640732265e-07,
+      "logits/chosen": 0.31113675236701965,
+      "logits/rejected": 0.3199848532676697,
+      "logps/chosen": -191.7982177734375,
+      "logps/rejected": -196.9516143798828,
+      "loss": 0.584,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": -0.18086068332195282,
+      "rewards/margins": 0.3591785430908203,
+      "rewards/rejected": -0.5400392413139343,
+      "step": 510
+    },
+    {
+      "epoch": 0.35705089691871944,
+      "grad_norm": 37.857597108335746,
+      "learning_rate": 3.5774218154080856e-07,
+      "logits/chosen": 0.27571016550064087,
+      "logits/rejected": 0.33552512526512146,
+      "logps/chosen": -199.4322509765625,
+      "logps/rejected": -199.8485870361328,
+      "loss": 0.5673,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.16350007057189941,
+      "rewards/margins": 0.4010578989982605,
+      "rewards/rejected": -0.5645579695701599,
+      "step": 520
+    },
+    {
+      "epoch": 0.36391726032100247,
+      "grad_norm": 37.54411288303357,
+      "learning_rate": 3.5392829900839057e-07,
+      "logits/chosen": 0.2737811803817749,
+      "logits/rejected": 0.30892500281333923,
+      "logps/chosen": -187.1866912841797,
+      "logps/rejected": -191.27017211914062,
+      "loss": 0.5954,
+      "rewards/accuracies": 0.684374988079071,
+      "rewards/chosen": -0.1845116764307022,
+      "rewards/margins": 0.33810287714004517,
+      "rewards/rejected": -0.5226145386695862,
+      "step": 530
+    },
+    {
+      "epoch": 0.37078362372328555,
+      "grad_norm": 36.379608658695076,
+      "learning_rate": 3.501144164759725e-07,
+      "logits/chosen": 0.3017553389072418,
+      "logits/rejected": 0.33447474241256714,
+      "logps/chosen": -186.4514923095703,
+      "logps/rejected": -192.16998291015625,
+      "loss": 0.5762,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.15427324175834656,
+      "rewards/margins": 0.3679887056350708,
+      "rewards/rejected": -0.5222619771957397,
+      "step": 540
+    },
+    {
+      "epoch": 0.37764998712556863,
+      "grad_norm": 34.175660697861545,
+      "learning_rate": 3.463005339435545e-07,
+      "logits/chosen": 0.27010437846183777,
+      "logits/rejected": 0.2763593792915344,
+      "logps/chosen": -195.02452087402344,
+      "logps/rejected": -202.46990966796875,
+      "loss": 0.563,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": -0.20031140744686127,
+      "rewards/margins": 0.4455968141555786,
+      "rewards/rejected": -0.6459081768989563,
+      "step": 550
+    },
+    {
+      "epoch": 0.3845163505278517,
+      "grad_norm": 42.17768587566113,
+      "learning_rate": 3.424866514111365e-07,
+      "logits/chosen": 0.2938051223754883,
+      "logits/rejected": 0.265284925699234,
+      "logps/chosen": -197.04212951660156,
+      "logps/rejected": -205.32717895507812,
+      "loss": 0.5741,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.20310233533382416,
+      "rewards/margins": 0.4046763479709625,
+      "rewards/rejected": -0.6077786684036255,
+      "step": 560
+    },
+    {
+      "epoch": 0.39138271393013474,
+      "grad_norm": 39.556354214822186,
+      "learning_rate": 3.3867276887871853e-07,
+      "logits/chosen": 0.31264281272888184,
+      "logits/rejected": 0.3123646676540375,
+      "logps/chosen": -189.451416015625,
+      "logps/rejected": -197.66497802734375,
+      "loss": 0.562,
+      "rewards/accuracies": 0.714062511920929,
+      "rewards/chosen": -0.17061220109462738,
+      "rewards/margins": 0.4390391707420349,
+      "rewards/rejected": -0.6096513867378235,
+      "step": 570
+    },
+    {
+      "epoch": 0.3982490773324178,
+      "grad_norm": 33.057101262111715,
+      "learning_rate": 3.348588863463005e-07,
+      "logits/chosen": 0.28659966588020325,
+      "logits/rejected": 0.3126603662967682,
+      "logps/chosen": -185.3994903564453,
+      "logps/rejected": -191.210693359375,
+      "loss": 0.5746,
+      "rewards/accuracies": 0.7046874761581421,
+      "rewards/chosen": -0.20723019540309906,
+      "rewards/margins": 0.42978933453559875,
+      "rewards/rejected": -0.6370195150375366,
+      "step": 580
+    },
+    {
+      "epoch": 0.4051154407347009,
+      "grad_norm": 40.67219189059665,
+      "learning_rate": 3.310450038138825e-07,
+      "logits/chosen": 0.34570857882499695,
+      "logits/rejected": 0.36093324422836304,
+      "logps/chosen": -191.6331787109375,
+      "logps/rejected": -195.85353088378906,
+      "loss": 0.574,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.24881573021411896,
+      "rewards/margins": 0.40310919284820557,
+      "rewards/rejected": -0.6519248485565186,
+      "step": 590
+    },
+    {
+      "epoch": 0.41198180413698393,
+      "grad_norm": 32.27412195705655,
+      "learning_rate": 3.2723112128146454e-07,
+      "logits/chosen": 0.28392359614372253,
+      "logits/rejected": 0.3210703730583191,
+      "logps/chosen": -193.51974487304688,
+      "logps/rejected": -204.85496520996094,
+      "loss": 0.5756,
+      "rewards/accuracies": 0.7046875357627869,
+      "rewards/chosen": -0.27069714665412903,
+      "rewards/margins": 0.39500606060028076,
+      "rewards/rejected": -0.6657031774520874,
+      "step": 600
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 40.11541316987076,
+      "learning_rate": 3.2341723874904654e-07,
+      "logits/chosen": 0.2726914882659912,
+      "logits/rejected": 0.3119577467441559,
+      "logps/chosen": -199.31056213378906,
+      "logps/rejected": -204.21376037597656,
+      "loss": 0.5566,
+      "rewards/accuracies": 0.7421875,
+      "rewards/chosen": -0.2292744219303131,
+      "rewards/margins": 0.47578680515289307,
+      "rewards/rejected": -0.7050611972808838,
+      "step": 610
+    },
+    {
+      "epoch": 0.4257145309415501,
+      "grad_norm": 38.57524526832705,
+      "learning_rate": 3.1960335621662854e-07,
+      "logits/chosen": 0.3519170880317688,
+      "logits/rejected": 0.32691216468811035,
+      "logps/chosen": -185.44210815429688,
+      "logps/rejected": -193.6503448486328,
+      "loss": 0.5954,
+      "rewards/accuracies": 0.667187511920929,
+      "rewards/chosen": -0.2960931956768036,
+      "rewards/margins": 0.3511514365673065,
+      "rewards/rejected": -0.6472446322441101,
+      "step": 620
+    },
+    {
+      "epoch": 0.4325808943438331,
+      "grad_norm": 37.69383619234179,
+      "learning_rate": 3.157894736842105e-07,
+      "logits/chosen": 0.29799604415893555,
+      "logits/rejected": 0.34074339270591736,
+      "logps/chosen": -195.78738403320312,
+      "logps/rejected": -199.2224578857422,
+      "loss": 0.5581,
+      "rewards/accuracies": 0.7390625476837158,
+      "rewards/chosen": -0.25615453720092773,
+      "rewards/margins": 0.450039267539978,
+      "rewards/rejected": -0.7061938047409058,
+      "step": 630
+    },
+    {
+      "epoch": 0.4394472577461162,
+      "grad_norm": 38.189321055235546,
+      "learning_rate": 3.119755911517925e-07,
+      "logits/chosen": 0.2873116135597229,
+      "logits/rejected": 0.3004646897315979,
+      "logps/chosen": -189.26136779785156,
+      "logps/rejected": -196.96090698242188,
+      "loss": 0.547,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.2134401500225067,
+      "rewards/margins": 0.49057334661483765,
+      "rewards/rejected": -0.704013466835022,
+      "step": 640
+    },
+    {
+      "epoch": 0.4463136211483993,
+      "grad_norm": 36.10179194685923,
+      "learning_rate": 3.081617086193745e-07,
+      "logits/chosen": 0.2833235263824463,
+      "logits/rejected": 0.29193115234375,
+      "logps/chosen": -192.39608764648438,
+      "logps/rejected": -196.04393005371094,
+      "loss": 0.5785,
+      "rewards/accuracies": 0.7093749642372131,
+      "rewards/chosen": -0.27462145686149597,
+      "rewards/margins": 0.42194679379463196,
+      "rewards/rejected": -0.6965682506561279,
+      "step": 650
+    },
+    {
+      "epoch": 0.45317998455068237,
+      "grad_norm": 40.70569476126112,
+      "learning_rate": 3.043478260869565e-07,
+      "logits/chosen": 0.2833031415939331,
+      "logits/rejected": 0.3039618134498596,
+      "logps/chosen": -194.68643188476562,
+      "logps/rejected": -201.3513641357422,
+      "loss": 0.5592,
+      "rewards/accuracies": 0.7406249642372131,
+      "rewards/chosen": -0.24034196138381958,
+      "rewards/margins": 0.47991621494293213,
+      "rewards/rejected": -0.7202582359313965,
+      "step": 660
+    },
+    {
+      "epoch": 0.4600463479529654,
+      "grad_norm": 39.47730074592621,
+      "learning_rate": 3.005339435545385e-07,
+      "logits/chosen": 0.24101117253303528,
+      "logits/rejected": 0.28705087304115295,
+      "logps/chosen": -193.5571746826172,
+      "logps/rejected": -200.22122192382812,
+      "loss": 0.5636,
+      "rewards/accuracies": 0.7359375357627869,
+      "rewards/chosen": -0.2813783586025238,
+      "rewards/margins": 0.4671448767185211,
+      "rewards/rejected": -0.7485232353210449,
+      "step": 670
+    },
+    {
+      "epoch": 0.4669127113552485,
+      "grad_norm": 39.65241691610216,
+      "learning_rate": 2.967200610221205e-07,
+      "logits/chosen": 0.3657754063606262,
+      "logits/rejected": 0.37657299637794495,
+      "logps/chosen": -191.58316040039062,
+      "logps/rejected": -199.84127807617188,
+      "loss": 0.5671,
+      "rewards/accuracies": 0.7421875,
+      "rewards/chosen": -0.3193482756614685,
+      "rewards/margins": 0.4501326382160187,
+      "rewards/rejected": -0.7694809436798096,
+      "step": 680
+    },
+    {
+      "epoch": 0.47377907475753156,
+      "grad_norm": 38.57964300760157,
+      "learning_rate": 2.929061784897025e-07,
+      "logits/chosen": 0.23921574652194977,
+      "logits/rejected": 0.35300254821777344,
+      "logps/chosen": -201.5934295654297,
+      "logps/rejected": -198.59539794921875,
+      "loss": 0.5621,
+      "rewards/accuracies": 0.7234375476837158,
+      "rewards/chosen": -0.24311897158622742,
+      "rewards/margins": 0.4885551631450653,
+      "rewards/rejected": -0.7316741347312927,
+      "step": 690
+    },
+    {
+      "epoch": 0.4806454381598146,
+      "grad_norm": 37.6708105251052,
+      "learning_rate": 2.890922959572845e-07,
+      "logits/chosen": 0.35867607593536377,
+      "logits/rejected": 0.3570886254310608,
+      "logps/chosen": -196.69223022460938,
+      "logps/rejected": -203.36892700195312,
+      "loss": 0.5599,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.259895920753479,
+      "rewards/margins": 0.5065343379974365,
+      "rewards/rejected": -0.7664302587509155,
+      "step": 700
+    },
+    {
+      "epoch": 0.48751180156209767,
+      "grad_norm": 33.960668217462846,
+      "learning_rate": 2.852784134248665e-07,
+      "logits/chosen": 0.3202595114707947,
+      "logits/rejected": 0.34629160165786743,
+      "logps/chosen": -183.36761474609375,
+      "logps/rejected": -190.17095947265625,
+      "loss": 0.5553,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -0.29635459184646606,
+      "rewards/margins": 0.4687589406967163,
+      "rewards/rejected": -0.7651135921478271,
+      "step": 710
+    },
+    {
+      "epoch": 0.49437816496438075,
+      "grad_norm": 41.77915341763896,
+      "learning_rate": 2.8146453089244847e-07,
+      "logits/chosen": 0.3262189030647278,
+      "logits/rejected": 0.37001171708106995,
+      "logps/chosen": -197.56304931640625,
+      "logps/rejected": -208.429443359375,
+      "loss": 0.5597,
+      "rewards/accuracies": 0.7156250476837158,
+      "rewards/chosen": -0.3544178307056427,
+      "rewards/margins": 0.4729451835155487,
+      "rewards/rejected": -0.8273630142211914,
+      "step": 720
+    },
+    {
+      "epoch": 0.5012445283666638,
+      "grad_norm": 40.82775700536951,
+      "learning_rate": 2.776506483600305e-07,
+      "logits/chosen": 0.28899723291397095,
+      "logits/rejected": 0.35643595457077026,
+      "logps/chosen": -201.49356079101562,
+      "logps/rejected": -203.23558044433594,
+      "loss": 0.5693,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.3458954691886902,
+      "rewards/margins": 0.4600406587123871,
+      "rewards/rejected": -0.8059360980987549,
+      "step": 730
+    },
+    {
+      "epoch": 0.5081108917689469,
+      "grad_norm": 33.71404588891465,
+      "learning_rate": 2.738367658276125e-07,
+      "logits/chosen": 0.2703500986099243,
+      "logits/rejected": 0.3099355697631836,
+      "logps/chosen": -193.55145263671875,
+      "logps/rejected": -199.3096923828125,
+      "loss": 0.5536,
+      "rewards/accuracies": 0.7328125238418579,
+      "rewards/chosen": -0.26327142119407654,
+      "rewards/margins": 0.5031423568725586,
+      "rewards/rejected": -0.766413688659668,
+      "step": 740
+    },
+    {
+      "epoch": 0.5149772551712299,
+      "grad_norm": 33.075818317425,
+      "learning_rate": 2.7002288329519454e-07,
+      "logits/chosen": 0.2545013427734375,
+      "logits/rejected": 0.3025552034378052,
+      "logps/chosen": -193.26318359375,
+      "logps/rejected": -200.33660888671875,
+      "loss": 0.5538,
+      "rewards/accuracies": 0.7281250357627869,
+      "rewards/chosen": -0.27697205543518066,
+      "rewards/margins": 0.4808192849159241,
+      "rewards/rejected": -0.75779128074646,
+      "step": 750
+    },
+    {
+      "epoch": 0.521843618573513,
+      "grad_norm": 40.25992379877124,
+      "learning_rate": 2.662090007627765e-07,
+      "logits/chosen": 0.3036815822124481,
+      "logits/rejected": 0.3631848394870758,
+      "logps/chosen": -198.0908203125,
+      "logps/rejected": -206.98089599609375,
+      "loss": 0.5472,
+      "rewards/accuracies": 0.7265625,
+      "rewards/chosen": -0.2982957065105438,
+      "rewards/margins": 0.5238938927650452,
+      "rewards/rejected": -0.8221895694732666,
+      "step": 760
+    },
+    {
+      "epoch": 0.5287099819757961,
+      "grad_norm": 37.9070748761064,
+      "learning_rate": 2.623951182303585e-07,
+      "logits/chosen": 0.24659216403961182,
+      "logits/rejected": 0.3046765625476837,
+      "logps/chosen": -201.07363891601562,
+      "logps/rejected": -207.00537109375,
+      "loss": 0.5449,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.26615357398986816,
+      "rewards/margins": 0.5252472758293152,
+      "rewards/rejected": -0.7914008498191833,
+      "step": 770
+    },
+    {
+      "epoch": 0.5355763453780792,
+      "grad_norm": 37.80873404676217,
+      "learning_rate": 2.585812356979405e-07,
+      "logits/chosen": 0.25920283794403076,
+      "logits/rejected": 0.2916741371154785,
+      "logps/chosen": -185.62496948242188,
+      "logps/rejected": -192.09083557128906,
+      "loss": 0.5401,
+      "rewards/accuracies": 0.7203124761581421,
+      "rewards/chosen": -0.26164376735687256,
+      "rewards/margins": 0.5513469576835632,
+      "rewards/rejected": -0.8129907846450806,
+      "step": 780
+    },
+    {
+      "epoch": 0.5424427087803622,
+      "grad_norm": 42.53158233624783,
+      "learning_rate": 2.547673531655225e-07,
+      "logits/chosen": 0.2548454701900482,
+      "logits/rejected": 0.328127920627594,
+      "logps/chosen": -195.73593139648438,
+      "logps/rejected": -201.92825317382812,
+      "loss": 0.5675,
+      "rewards/accuracies": 0.7015624642372131,
+      "rewards/chosen": -0.33536800742149353,
+      "rewards/margins": 0.4790363907814026,
+      "rewards/rejected": -0.8144044280052185,
+      "step": 790
+    },
+    {
+      "epoch": 0.5493090721826452,
+      "grad_norm": 36.58925507564145,
+      "learning_rate": 2.509534706331045e-07,
+      "logits/chosen": 0.2698169946670532,
+      "logits/rejected": 0.3065064549446106,
+      "logps/chosen": -202.49847412109375,
+      "logps/rejected": -207.4984130859375,
+      "loss": 0.5502,
+      "rewards/accuracies": 0.7374999523162842,
+      "rewards/chosen": -0.30143699049949646,
+      "rewards/margins": 0.5463117957115173,
+      "rewards/rejected": -0.8477488160133362,
+      "step": 800
+    },
+    {
+      "epoch": 0.5561754355849283,
+      "grad_norm": 33.42536910745375,
+      "learning_rate": 2.471395881006865e-07,
+      "logits/chosen": 0.3269241154193878,
+      "logits/rejected": 0.33714747428894043,
+      "logps/chosen": -195.79061889648438,
+      "logps/rejected": -204.3171844482422,
+      "loss": 0.541,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": -0.2959471344947815,
+      "rewards/margins": 0.563454270362854,
+      "rewards/rejected": -0.8594014644622803,
+      "step": 810
+    },
+    {
+      "epoch": 0.5630417989872114,
+      "grad_norm": 38.40905751177336,
+      "learning_rate": 2.4332570556826846e-07,
+      "logits/chosen": 0.2773634195327759,
+      "logits/rejected": 0.3108067512512207,
+      "logps/chosen": -198.3325958251953,
+      "logps/rejected": -204.81982421875,
+      "loss": 0.5414,
+      "rewards/accuracies": 0.7390625476837158,
+      "rewards/chosen": -0.33161288499832153,
+      "rewards/margins": 0.5616108179092407,
+      "rewards/rejected": -0.8932236433029175,
+      "step": 820
+    },
+    {
+      "epoch": 0.5699081623894945,
+      "grad_norm": 43.36025952480035,
+      "learning_rate": 2.395118230358505e-07,
+      "logits/chosen": 0.3091006875038147,
+      "logits/rejected": 0.3100830018520355,
+      "logps/chosen": -194.6656036376953,
+      "logps/rejected": -204.10427856445312,
+      "loss": 0.5367,
+      "rewards/accuracies": 0.7578125,
+      "rewards/chosen": -0.3439427614212036,
+      "rewards/margins": 0.5804582238197327,
+      "rewards/rejected": -0.9244009256362915,
+      "step": 830
+    },
+    {
+      "epoch": 0.5767745257917776,
+      "grad_norm": 44.03658723941333,
+      "learning_rate": 2.3569794050343246e-07,
+      "logits/chosen": 0.23637430369853973,
+      "logits/rejected": 0.3134675920009613,
+      "logps/chosen": -194.6787109375,
+      "logps/rejected": -200.1925811767578,
+      "loss": 0.5326,
+      "rewards/accuracies": 0.7593749761581421,
+      "rewards/chosen": -0.30673253536224365,
+      "rewards/margins": 0.5752936005592346,
+      "rewards/rejected": -0.882026195526123,
+      "step": 840
+    },
+    {
+      "epoch": 0.5836408891940605,
+      "grad_norm": 35.08372363656115,
+      "learning_rate": 2.318840579710145e-07,
+      "logits/chosen": 0.29405680298805237,
+      "logits/rejected": 0.32297587394714355,
+      "logps/chosen": -199.6582794189453,
+      "logps/rejected": -201.277587890625,
+      "loss": 0.5613,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": -0.3533500134944916,
+      "rewards/margins": 0.4787251353263855,
+      "rewards/rejected": -0.8320751190185547,
+      "step": 850
+    },
+    {
+      "epoch": 0.5905072525963436,
+      "grad_norm": 37.57503746222717,
+      "learning_rate": 2.2807017543859647e-07,
+      "logits/chosen": 0.30716609954833984,
+      "logits/rejected": 0.3208872079849243,
+      "logps/chosen": -190.15570068359375,
+      "logps/rejected": -197.3380584716797,
+      "loss": 0.5404,
+      "rewards/accuracies": 0.7421875,
+      "rewards/chosen": -0.35594654083251953,
+      "rewards/margins": 0.5726853609085083,
+      "rewards/rejected": -0.9286319017410278,
+      "step": 860
+    },
+    {
+      "epoch": 0.5973736159986267,
+      "grad_norm": 38.24375810448517,
+      "learning_rate": 2.2425629290617847e-07,
+      "logits/chosen": 0.2411738932132721,
+      "logits/rejected": 0.32163745164871216,
+      "logps/chosen": -196.72198486328125,
+      "logps/rejected": -200.0342254638672,
+      "loss": 0.5283,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -0.26584312319755554,
+      "rewards/margins": 0.5993839502334595,
+      "rewards/rejected": -0.8652270436286926,
+      "step": 870
+    },
+    {
+      "epoch": 0.6042399794009098,
+      "grad_norm": 42.764478541441036,
+      "learning_rate": 2.204424103737605e-07,
+      "logits/chosen": 0.2489607334136963,
+      "logits/rejected": 0.32214033603668213,
+      "logps/chosen": -193.22962951660156,
+      "logps/rejected": -198.15139770507812,
+      "loss": 0.5364,
+      "rewards/accuracies": 0.7265625596046448,
+      "rewards/chosen": -0.2991304099559784,
+      "rewards/margins": 0.5733505487442017,
+      "rewards/rejected": -0.8724809885025024,
+      "step": 880
+    },
+    {
+      "epoch": 0.6111063428031929,
+      "grad_norm": 36.23455470329296,
+      "learning_rate": 2.1662852784134248e-07,
+      "logits/chosen": 0.2716100215911865,
+      "logits/rejected": 0.2950877547264099,
+      "logps/chosen": -200.77000427246094,
+      "logps/rejected": -207.59774780273438,
+      "loss": 0.5617,
+      "rewards/accuracies": 0.7203125357627869,
+      "rewards/chosen": -0.35562682151794434,
+      "rewards/margins": 0.5303334593772888,
+      "rewards/rejected": -0.8859602808952332,
+      "step": 890
+    },
+    {
+      "epoch": 0.617972706205476,
+      "grad_norm": 36.85079943729679,
+      "learning_rate": 2.1281464530892448e-07,
+      "logits/chosen": 0.2935597598552704,
+      "logits/rejected": 0.29276734590530396,
+      "logps/chosen": -199.0962371826172,
+      "logps/rejected": -208.84475708007812,
+      "loss": 0.5388,
+      "rewards/accuracies": 0.753125011920929,
+      "rewards/chosen": -0.3592212498188019,
+      "rewards/margins": 0.5828565955162048,
+      "rewards/rejected": -0.9420778751373291,
+      "step": 900
+    },
+    {
+      "epoch": 0.624839069607759,
+      "grad_norm": 38.47165659930442,
+      "learning_rate": 2.0900076277650646e-07,
+      "logits/chosen": 0.322465717792511,
+      "logits/rejected": 0.35115572810173035,
+      "logps/chosen": -197.81039428710938,
+      "logps/rejected": -203.60789489746094,
+      "loss": 0.538,
+      "rewards/accuracies": 0.721875011920929,
+      "rewards/chosen": -0.35633325576782227,
+      "rewards/margins": 0.5937191247940063,
+      "rewards/rejected": -0.9500523805618286,
+      "step": 910
+    },
+    {
+      "epoch": 0.631705433010042,
+      "grad_norm": 37.96068046141611,
+      "learning_rate": 2.051868802440885e-07,
+      "logits/chosen": 0.2791150212287903,
+      "logits/rejected": 0.31407302618026733,
+      "logps/chosen": -205.3975372314453,
+      "logps/rejected": -211.5294189453125,
+      "loss": 0.5427,
+      "rewards/accuracies": 0.7312500476837158,
+      "rewards/chosen": -0.3240187168121338,
+      "rewards/margins": 0.5994824767112732,
+      "rewards/rejected": -0.923501193523407,
+      "step": 920
+    },
+    {
+      "epoch": 0.6385717964123251,
+      "grad_norm": 36.87690959534342,
+      "learning_rate": 2.0137299771167047e-07,
+      "logits/chosen": 0.2880761921405792,
+      "logits/rejected": 0.30180174112319946,
+      "logps/chosen": -199.66058349609375,
+      "logps/rejected": -207.59580993652344,
+      "loss": 0.5025,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.3255097270011902,
+      "rewards/margins": 0.6759095191955566,
+      "rewards/rejected": -1.0014193058013916,
+      "step": 930
+    },
+    {
+      "epoch": 0.6454381598146082,
+      "grad_norm": 34.108839062919095,
+      "learning_rate": 1.9755911517925247e-07,
+      "logits/chosen": 0.23794284462928772,
+      "logits/rejected": 0.2611067295074463,
+      "logps/chosen": -195.78970336914062,
+      "logps/rejected": -200.48919677734375,
+      "loss": 0.5416,
+      "rewards/accuracies": 0.7156250476837158,
+      "rewards/chosen": -0.333574116230011,
+      "rewards/margins": 0.5876989364624023,
+      "rewards/rejected": -0.9212730526924133,
+      "step": 940
+    },
+    {
+      "epoch": 0.6523045232168913,
+      "grad_norm": 42.487643110620105,
+      "learning_rate": 1.9374523264683445e-07,
+      "logits/chosen": 0.21556894481182098,
+      "logits/rejected": 0.3087506890296936,
+      "logps/chosen": -203.08071899414062,
+      "logps/rejected": -204.42138671875,
+      "loss": 0.5358,
+      "rewards/accuracies": 0.7281249761581421,
+      "rewards/chosen": -0.3193817734718323,
+      "rewards/margins": 0.6358938813209534,
+      "rewards/rejected": -0.9552755951881409,
+      "step": 950
+    },
+    {
+      "epoch": 0.6591708866191743,
+      "grad_norm": 44.89635861946585,
+      "learning_rate": 1.8993135011441648e-07,
+      "logits/chosen": 0.292077898979187,
+      "logits/rejected": 0.3146917521953583,
+      "logps/chosen": -194.001220703125,
+      "logps/rejected": -202.2600860595703,
+      "loss": 0.5448,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": -0.3208439350128174,
+      "rewards/margins": 0.5795982480049133,
+      "rewards/rejected": -0.9004421830177307,
+      "step": 960
+    },
+    {
+      "epoch": 0.6660372500214574,
+      "grad_norm": 33.551478970398286,
+      "learning_rate": 1.8611746758199848e-07,
+      "logits/chosen": 0.2604063153266907,
+      "logits/rejected": 0.2851104736328125,
+      "logps/chosen": -192.01268005371094,
+      "logps/rejected": -199.5753631591797,
+      "loss": 0.5278,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.29537859559059143,
+      "rewards/margins": 0.5901771187782288,
+      "rewards/rejected": -0.8855556845664978,
+      "step": 970
+    },
+    {
+      "epoch": 0.6729036134237405,
+      "grad_norm": 35.66870501940745,
+      "learning_rate": 1.8230358504958046e-07,
+      "logits/chosen": 0.28516054153442383,
+      "logits/rejected": 0.30551978945732117,
+      "logps/chosen": -191.11451721191406,
+      "logps/rejected": -200.1798095703125,
+      "loss": 0.5325,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -0.2689625322818756,
+      "rewards/margins": 0.6204273104667664,
+      "rewards/rejected": -0.8893898129463196,
+      "step": 980
+    },
+    {
+      "epoch": 0.6797699768260235,
+      "grad_norm": 56.47041800124252,
+      "learning_rate": 1.7848970251716246e-07,
+      "logits/chosen": 0.3133455812931061,
+      "logits/rejected": 0.3184555470943451,
+      "logps/chosen": -191.03782653808594,
+      "logps/rejected": -200.31556701660156,
+      "loss": 0.5553,
+      "rewards/accuracies": 0.746874988079071,
+      "rewards/chosen": -0.3917931020259857,
+      "rewards/margins": 0.5545149445533752,
+      "rewards/rejected": -0.9463080763816833,
+      "step": 990
+    },
+    {
+      "epoch": 0.6866363402283066,
+      "grad_norm": 35.555828137231536,
+      "learning_rate": 1.7467581998474446e-07,
+      "logits/chosen": 0.2640990912914276,
+      "logits/rejected": 0.2870061993598938,
+      "logps/chosen": -200.83248901367188,
+      "logps/rejected": -213.00466918945312,
+      "loss": 0.5147,
+      "rewards/accuracies": 0.760937511920929,
+      "rewards/chosen": -0.3015330135822296,
+      "rewards/margins": 0.6684325933456421,
+      "rewards/rejected": -0.9699656367301941,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6935027036305896,
+      "grad_norm": 34.088214821820934,
+      "learning_rate": 1.7086193745232647e-07,
+      "logits/chosen": 0.2753002345561981,
+      "logits/rejected": 0.3184780478477478,
+      "logps/chosen": -185.6627960205078,
+      "logps/rejected": -191.78610229492188,
+      "loss": 0.5326,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.3113631010055542,
+      "rewards/margins": 0.584636390209198,
+      "rewards/rejected": -0.8959994912147522,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7003690670328727,
+      "grad_norm": 41.3910211936423,
+      "learning_rate": 1.6704805491990844e-07,
+      "logits/chosen": 0.21735849976539612,
+      "logits/rejected": 0.328865647315979,
+      "logps/chosen": -196.0897674560547,
+      "logps/rejected": -198.31881713867188,
+      "loss": 0.5303,
+      "rewards/accuracies": 0.7578125596046448,
+      "rewards/chosen": -0.3108276128768921,
+      "rewards/margins": 0.5797023773193359,
+      "rewards/rejected": -0.8905300498008728,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7072354304351558,
+      "grad_norm": 35.79945052953454,
+      "learning_rate": 1.6323417238749045e-07,
+      "logits/chosen": 0.21715006232261658,
+      "logits/rejected": 0.2603926956653595,
+      "logps/chosen": -191.06532287597656,
+      "logps/rejected": -196.79811096191406,
+      "loss": 0.5397,
+      "rewards/accuracies": 0.7359375357627869,
+      "rewards/chosen": -0.3505193889141083,
+      "rewards/margins": 0.5923134088516235,
+      "rewards/rejected": -0.9428327083587646,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7141017938374389,
+      "grad_norm": 38.89985342660555,
+      "learning_rate": 1.5942028985507245e-07,
+      "logits/chosen": 0.2547008693218231,
+      "logits/rejected": 0.27041909098625183,
+      "logps/chosen": -192.95919799804688,
+      "logps/rejected": -201.5959014892578,
+      "loss": 0.5401,
+      "rewards/accuracies": 0.7515625357627869,
+      "rewards/chosen": -0.31962740421295166,
+      "rewards/margins": 0.6006041765213013,
+      "rewards/rejected": -0.9202315211296082,
+      "step": 1040
+    },
+    {
+      "epoch": 0.720968157239722,
+      "grad_norm": 38.89083856333277,
+      "learning_rate": 1.5560640732265446e-07,
+      "logits/chosen": 0.22286555171012878,
+      "logits/rejected": 0.2649829685688019,
+      "logps/chosen": -195.25892639160156,
+      "logps/rejected": -201.61752319335938,
+      "loss": 0.5287,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -0.2955860495567322,
+      "rewards/margins": 0.6011725068092346,
+      "rewards/rejected": -0.8967585563659668,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7278345206420049,
+      "grad_norm": 38.82078220393796,
+      "learning_rate": 1.5179252479023646e-07,
+      "logits/chosen": 0.29512226581573486,
+      "logits/rejected": 0.2847123146057129,
+      "logps/chosen": -189.52247619628906,
+      "logps/rejected": -195.29598999023438,
+      "loss": 0.5515,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.2878785729408264,
+      "rewards/margins": 0.5302765965461731,
+      "rewards/rejected": -0.8181551694869995,
+      "step": 1060
+    },
+    {
+      "epoch": 0.734700884044288,
+      "grad_norm": 47.26245042175549,
+      "learning_rate": 1.4797864225781844e-07,
+      "logits/chosen": 0.2918851971626282,
+      "logits/rejected": 0.32630887627601624,
+      "logps/chosen": -195.94786071777344,
+      "logps/rejected": -203.26979064941406,
+      "loss": 0.5169,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": -0.3223276436328888,
+      "rewards/margins": 0.6719238758087158,
+      "rewards/rejected": -0.9942514896392822,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7415672474465711,
+      "grad_norm": 38.362363344324436,
+      "learning_rate": 1.4416475972540047e-07,
+      "logits/chosen": 0.2812820076942444,
+      "logits/rejected": 0.3306478261947632,
+      "logps/chosen": -195.67994689941406,
+      "logps/rejected": -203.43797302246094,
+      "loss": 0.5423,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.34005221724510193,
+      "rewards/margins": 0.5954278111457825,
+      "rewards/rejected": -0.9354800581932068,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7484336108488542,
+      "grad_norm": 33.005125056199134,
+      "learning_rate": 1.4035087719298244e-07,
+      "logits/chosen": 0.2390434741973877,
+      "logits/rejected": 0.33480697870254517,
+      "logps/chosen": -198.01687622070312,
+      "logps/rejected": -199.43064880371094,
+      "loss": 0.5251,
+      "rewards/accuracies": 0.776562511920929,
+      "rewards/chosen": -0.2991839051246643,
+      "rewards/margins": 0.6372097134590149,
+      "rewards/rejected": -0.9363937377929688,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7552999742511373,
+      "grad_norm": 33.828040981930215,
+      "learning_rate": 1.3653699466056445e-07,
+      "logits/chosen": 0.27923381328582764,
+      "logits/rejected": 0.29023945331573486,
+      "logps/chosen": -206.89694213867188,
+      "logps/rejected": -214.03880310058594,
+      "loss": 0.4939,
+      "rewards/accuracies": 0.7640625238418579,
+      "rewards/chosen": -0.30125996470451355,
+      "rewards/margins": 0.7326390147209167,
+      "rewards/rejected": -1.033898949623108,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7621663376534203,
+      "grad_norm": 31.87482658749529,
+      "learning_rate": 1.3272311212814645e-07,
+      "logits/chosen": 0.2957872152328491,
+      "logits/rejected": 0.3066104054450989,
+      "logps/chosen": -193.53025817871094,
+      "logps/rejected": -201.29710388183594,
+      "loss": 0.5141,
+      "rewards/accuracies": 0.7546875476837158,
+      "rewards/chosen": -0.2906218469142914,
+      "rewards/margins": 0.6594946980476379,
+      "rewards/rejected": -0.9501165151596069,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7690327010557034,
+      "grad_norm": 37.01925333474489,
+      "learning_rate": 1.2890922959572845e-07,
+      "logits/chosen": 0.23377490043640137,
+      "logits/rejected": 0.28193050622940063,
+      "logps/chosen": -203.5383758544922,
+      "logps/rejected": -210.682373046875,
+      "loss": 0.5309,
+      "rewards/accuracies": 0.7312500476837158,
+      "rewards/chosen": -0.3552318215370178,
+      "rewards/margins": 0.6278497576713562,
+      "rewards/rejected": -0.9830816388130188,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7758990644579864,
+      "grad_norm": 38.86521392049953,
+      "learning_rate": 1.2509534706331046e-07,
+      "logits/chosen": 0.25305452942848206,
+      "logits/rejected": 0.250664085149765,
+      "logps/chosen": -193.17884826660156,
+      "logps/rejected": -205.3461456298828,
+      "loss": 0.5151,
+      "rewards/accuracies": 0.7734375,
+      "rewards/chosen": -0.3200224041938782,
+      "rewards/margins": 0.7115429639816284,
+      "rewards/rejected": -1.0315654277801514,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7827654278602695,
+      "grad_norm": 41.16862629359382,
+      "learning_rate": 1.2128146453089243e-07,
+      "logits/chosen": 0.24563747644424438,
+      "logits/rejected": 0.2821294665336609,
+      "logps/chosen": -192.35116577148438,
+      "logps/rejected": -197.296630859375,
+      "loss": 0.5208,
+      "rewards/accuracies": 0.7578125596046448,
+      "rewards/chosen": -0.28378814458847046,
+      "rewards/margins": 0.667680025100708,
+      "rewards/rejected": -0.9514681696891785,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7896317912625526,
+      "grad_norm": 42.06746375990814,
+      "learning_rate": 1.1746758199847444e-07,
+      "logits/chosen": 0.22848859429359436,
+      "logits/rejected": 0.3029937744140625,
+      "logps/chosen": -193.92227172851562,
+      "logps/rejected": -200.07699584960938,
+      "loss": 0.52,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -0.3132557272911072,
+      "rewards/margins": 0.6495946049690247,
+      "rewards/rejected": -0.9628503322601318,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7964981546648356,
+      "grad_norm": 32.39256423163034,
+      "learning_rate": 1.1365369946605644e-07,
+      "logits/chosen": 0.29020410776138306,
+      "logits/rejected": 0.29822224378585815,
+      "logps/chosen": -189.2175750732422,
+      "logps/rejected": -198.12094116210938,
+      "loss": 0.5272,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -0.3057502508163452,
+      "rewards/margins": 0.6393308043479919,
+      "rewards/rejected": -0.9450810551643372,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8033645180671187,
+      "grad_norm": 34.13298433674702,
+      "learning_rate": 1.0983981693363843e-07,
+      "logits/chosen": 0.195723757147789,
+      "logits/rejected": 0.269298255443573,
+      "logps/chosen": -196.38954162597656,
+      "logps/rejected": -202.385986328125,
+      "loss": 0.5052,
+      "rewards/accuracies": 0.760937511920929,
+      "rewards/chosen": -0.29148977994918823,
+      "rewards/margins": 0.673367977142334,
+      "rewards/rejected": -0.9648576974868774,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8102308814694018,
+      "grad_norm": 41.904351029623406,
+      "learning_rate": 1.0602593440122045e-07,
+      "logits/chosen": 0.26145869493484497,
+      "logits/rejected": 0.304781049489975,
+      "logps/chosen": -196.5819091796875,
+      "logps/rejected": -206.65396118164062,
+      "loss": 0.5308,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -0.3446430563926697,
+      "rewards/margins": 0.6291292309761047,
+      "rewards/rejected": -0.973772406578064,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8170972448716848,
+      "grad_norm": 36.5024658205158,
+      "learning_rate": 1.0221205186880244e-07,
+      "logits/chosen": 0.22576144337654114,
+      "logits/rejected": 0.2602446973323822,
+      "logps/chosen": -188.89349365234375,
+      "logps/rejected": -195.39523315429688,
+      "loss": 0.5198,
+      "rewards/accuracies": 0.7578125,
+      "rewards/chosen": -0.23121029138565063,
+      "rewards/margins": 0.6549311876296997,
+      "rewards/rejected": -0.8861414790153503,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8239636082739679,
+      "grad_norm": 42.13359318077711,
+      "learning_rate": 9.839816933638444e-08,
+      "logits/chosen": 0.2552095055580139,
+      "logits/rejected": 0.3024769127368927,
+      "logps/chosen": -194.66673278808594,
+      "logps/rejected": -198.9243621826172,
+      "loss": 0.5135,
+      "rewards/accuracies": 0.7640625238418579,
+      "rewards/chosen": -0.2669564187526703,
+      "rewards/margins": 0.6804448962211609,
+      "rewards/rejected": -0.9474013447761536,
+      "step": 1200
+    },
+    {
+      "epoch": 0.830829971676251,
+      "grad_norm": 39.317898860436635,
+      "learning_rate": 9.458428680396643e-08,
+      "logits/chosen": 0.20807792246341705,
+      "logits/rejected": 0.2506875991821289,
+      "logps/chosen": -194.7408905029297,
+      "logps/rejected": -202.78555297851562,
+      "loss": 0.5341,
+      "rewards/accuracies": 0.7359374761581421,
+      "rewards/chosen": -0.32548367977142334,
+      "rewards/margins": 0.6120297908782959,
+      "rewards/rejected": -0.9375134706497192,
+      "step": 1210
+    },
+    {
+      "epoch": 0.837696335078534,
+      "grad_norm": 39.302270375674155,
+      "learning_rate": 9.077040427154843e-08,
+      "logits/chosen": 0.2483367919921875,
+      "logits/rejected": 0.27390342950820923,
+      "logps/chosen": -197.6544647216797,
+      "logps/rejected": -204.05047607421875,
+      "loss": 0.51,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.2905549108982086,
+      "rewards/margins": 0.6854307651519775,
+      "rewards/rejected": -0.9759857058525085,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8445626984808171,
+      "grad_norm": 36.66056019529055,
+      "learning_rate": 8.695652173913042e-08,
+      "logits/chosen": 0.28719934821128845,
+      "logits/rejected": 0.3099461495876312,
+      "logps/chosen": -186.6349639892578,
+      "logps/rejected": -193.26979064941406,
+      "loss": 0.5175,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.388496994972229,
+      "rewards/margins": 0.6531878709793091,
+      "rewards/rejected": -1.041684865951538,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8514290618831002,
+      "grad_norm": 36.07042098698609,
+      "learning_rate": 8.314263920671243e-08,
+      "logits/chosen": 0.2238319218158722,
+      "logits/rejected": 0.2526761591434479,
+      "logps/chosen": -200.8705291748047,
+      "logps/rejected": -209.2767791748047,
+      "loss": 0.5419,
+      "rewards/accuracies": 0.7515625357627869,
+      "rewards/chosen": -0.359815776348114,
+      "rewards/margins": 0.5757598280906677,
+      "rewards/rejected": -0.9355756044387817,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8582954252853833,
+      "grad_norm": 37.98916737589895,
+      "learning_rate": 7.932875667429442e-08,
+      "logits/chosen": 0.2867482602596283,
+      "logits/rejected": 0.2855786979198456,
+      "logps/chosen": -200.7849578857422,
+      "logps/rejected": -209.64694213867188,
+      "loss": 0.5386,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": -0.3794117867946625,
+      "rewards/margins": 0.623035728931427,
+      "rewards/rejected": -1.002447485923767,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8651617886876662,
+      "grad_norm": 40.53269809980178,
+      "learning_rate": 7.551487414187643e-08,
+      "logits/chosen": 0.25138917565345764,
+      "logits/rejected": 0.2744777798652649,
+      "logps/chosen": -199.57286071777344,
+      "logps/rejected": -204.9058074951172,
+      "loss": 0.5072,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -0.28435054421424866,
+      "rewards/margins": 0.6674630641937256,
+      "rewards/rejected": -0.9518135786056519,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8720281520899493,
+      "grad_norm": 44.84817578049332,
+      "learning_rate": 7.170099160945843e-08,
+      "logits/chosen": 0.2759166359901428,
+      "logits/rejected": 0.32305389642715454,
+      "logps/chosen": -202.01171875,
+      "logps/rejected": -206.69354248046875,
+      "loss": 0.5378,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": -0.3561447262763977,
+      "rewards/margins": 0.609983503818512,
+      "rewards/rejected": -0.9661281704902649,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8788945154922324,
+      "grad_norm": 33.239181880901405,
+      "learning_rate": 6.788710907704043e-08,
+      "logits/chosen": 0.27904975414276123,
+      "logits/rejected": 0.3506329655647278,
+      "logps/chosen": -190.4373779296875,
+      "logps/rejected": -194.3594512939453,
+      "loss": 0.5169,
+      "rewards/accuracies": 0.7468750476837158,
+      "rewards/chosen": -0.33293962478637695,
+      "rewards/margins": 0.6674720048904419,
+      "rewards/rejected": -1.0004115104675293,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8857608788945155,
+      "grad_norm": 42.24278587548862,
+      "learning_rate": 6.407322654462242e-08,
+      "logits/chosen": 0.22125577926635742,
+      "logits/rejected": 0.23234713077545166,
+      "logps/chosen": -196.283935546875,
+      "logps/rejected": -206.2383270263672,
+      "loss": 0.4972,
+      "rewards/accuracies": 0.7906249761581421,
+      "rewards/chosen": -0.2478475719690323,
+      "rewards/margins": 0.7637631893157959,
+      "rewards/rejected": -1.011610746383667,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8926272422967986,
+      "grad_norm": 48.14687039805379,
+      "learning_rate": 6.025934401220442e-08,
+      "logits/chosen": 0.2196926772594452,
+      "logits/rejected": 0.26132142543792725,
+      "logps/chosen": -199.7481231689453,
+      "logps/rejected": -205.6083526611328,
+      "loss": 0.5156,
+      "rewards/accuracies": 0.7640625238418579,
+      "rewards/chosen": -0.32518845796585083,
+      "rewards/margins": 0.6625872850418091,
+      "rewards/rejected": -0.9877756834030151,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8994936056990817,
+      "grad_norm": 40.136271946129845,
+      "learning_rate": 5.644546147978642e-08,
+      "logits/chosen": 0.2690100073814392,
+      "logits/rejected": 0.3203776478767395,
+      "logps/chosen": -196.69924926757812,
+      "logps/rejected": -207.5710906982422,
+      "loss": 0.517,
+      "rewards/accuracies": 0.760937511920929,
+      "rewards/chosen": -0.3163500428199768,
+      "rewards/margins": 0.6733758449554443,
+      "rewards/rejected": -0.9897259473800659,
+      "step": 1310
+    },
+    {
+      "epoch": 0.9063599691013647,
+      "grad_norm": 38.232705361235354,
+      "learning_rate": 5.2631578947368416e-08,
+      "logits/chosen": 0.22911009192466736,
+      "logits/rejected": 0.2933771312236786,
+      "logps/chosen": -193.46011352539062,
+      "logps/rejected": -198.90769958496094,
+      "loss": 0.5129,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -0.31777265667915344,
+      "rewards/margins": 0.6428579688072205,
+      "rewards/rejected": -0.9606305956840515,
+      "step": 1320
+    },
+    {
+      "epoch": 0.9132263325036477,
+      "grad_norm": 32.32629597775676,
+      "learning_rate": 4.881769641495042e-08,
+      "logits/chosen": 0.2851574122905731,
+      "logits/rejected": 0.3311702311038971,
+      "logps/chosen": -190.674560546875,
+      "logps/rejected": -198.54489135742188,
+      "loss": 0.518,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -0.36391162872314453,
+      "rewards/margins": 0.6667385101318359,
+      "rewards/rejected": -1.0306501388549805,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9200926959059308,
+      "grad_norm": 34.564104656300344,
+      "learning_rate": 4.5003813882532416e-08,
+      "logits/chosen": 0.2709936499595642,
+      "logits/rejected": 0.29850390553474426,
+      "logps/chosen": -190.10250854492188,
+      "logps/rejected": -201.5867919921875,
+      "loss": 0.5245,
+      "rewards/accuracies": 0.754687488079071,
+      "rewards/chosen": -0.33972710371017456,
+      "rewards/margins": 0.6379141807556152,
+      "rewards/rejected": -0.9776412844657898,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9269590593082139,
+      "grad_norm": 40.20432402146685,
+      "learning_rate": 4.118993135011441e-08,
+      "logits/chosen": 0.31429168581962585,
+      "logits/rejected": 0.3014827370643616,
+      "logps/chosen": -193.68734741210938,
+      "logps/rejected": -206.73443603515625,
+      "loss": 0.5043,
+      "rewards/accuracies": 0.7421875,
+      "rewards/chosen": -0.33307623863220215,
+      "rewards/margins": 0.733502984046936,
+      "rewards/rejected": -1.0665792226791382,
+      "step": 1350
+    },
+    {
+      "epoch": 0.933825422710497,
+      "grad_norm": 42.378701373805164,
+      "learning_rate": 3.737604881769641e-08,
+      "logits/chosen": 0.26147449016571045,
+      "logits/rejected": 0.32908618450164795,
+      "logps/chosen": -202.1975860595703,
+      "logps/rejected": -206.84689331054688,
+      "loss": 0.5196,
+      "rewards/accuracies": 0.754687488079071,
+      "rewards/chosen": -0.30808600783348083,
+      "rewards/margins": 0.6519337296485901,
+      "rewards/rejected": -0.9600198268890381,
+      "step": 1360
+    },
+    {
+      "epoch": 0.94069178611278,
+      "grad_norm": 35.41777915691115,
+      "learning_rate": 3.356216628527841e-08,
+      "logits/chosen": 0.24308253824710846,
+      "logits/rejected": 0.28230151534080505,
+      "logps/chosen": -202.4017333984375,
+      "logps/rejected": -206.34548950195312,
+      "loss": 0.5305,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.364469051361084,
+      "rewards/margins": 0.6204385161399841,
+      "rewards/rejected": -0.9849075078964233,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9475581495150631,
+      "grad_norm": 31.86221090386857,
+      "learning_rate": 2.9748283752860413e-08,
+      "logits/chosen": 0.2843090295791626,
+      "logits/rejected": 0.316922128200531,
+      "logps/chosen": -189.54446411132812,
+      "logps/rejected": -199.91403198242188,
+      "loss": 0.4831,
+      "rewards/accuracies": 0.792187511920929,
+      "rewards/chosen": -0.2866865396499634,
+      "rewards/margins": 0.7708964347839355,
+      "rewards/rejected": -1.0575830936431885,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9544245129173462,
+      "grad_norm": 36.53519638891643,
+      "learning_rate": 2.593440122044241e-08,
+      "logits/chosen": 0.295163631439209,
+      "logits/rejected": 0.27683940529823303,
+      "logps/chosen": -198.69625854492188,
+      "logps/rejected": -206.66403198242188,
+      "loss": 0.491,
+      "rewards/accuracies": 0.776562511920929,
+      "rewards/chosen": -0.2761452794075012,
+      "rewards/margins": 0.7478234171867371,
+      "rewards/rejected": -1.0239686965942383,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9612908763196292,
+      "grad_norm": 35.87253035932275,
+      "learning_rate": 2.212051868802441e-08,
+      "logits/chosen": 0.2549622058868408,
+      "logits/rejected": 0.2964940071105957,
+      "logps/chosen": -191.95323181152344,
+      "logps/rejected": -199.76100158691406,
+      "loss": 0.521,
+      "rewards/accuracies": 0.7421875,
+      "rewards/chosen": -0.30250483751296997,
+      "rewards/margins": 0.6729665994644165,
+      "rewards/rejected": -0.9754714965820312,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9681572397219123,
+      "grad_norm": 36.42687734600846,
+      "learning_rate": 1.8306636155606407e-08,
+      "logits/chosen": 0.272115558385849,
+      "logits/rejected": 0.32787230610847473,
+      "logps/chosen": -199.0819091796875,
+      "logps/rejected": -205.5025177001953,
+      "loss": 0.5076,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -0.32656988501548767,
+      "rewards/margins": 0.6987006068229675,
+      "rewards/rejected": -1.0252704620361328,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9750236031241953,
+      "grad_norm": 32.32361768075354,
+      "learning_rate": 1.4492753623188406e-08,
+      "logits/chosen": 0.2514479458332062,
+      "logits/rejected": 0.29168808460235596,
+      "logps/chosen": -191.49757385253906,
+      "logps/rejected": -199.6735076904297,
+      "loss": 0.5287,
+      "rewards/accuracies": 0.7593750357627869,
+      "rewards/chosen": -0.34709036350250244,
+      "rewards/margins": 0.6339684724807739,
+      "rewards/rejected": -0.9810588955879211,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9818899665264784,
+      "grad_norm": 38.90237712846689,
+      "learning_rate": 1.0678871090770404e-08,
+      "logits/chosen": 0.2903396487236023,
+      "logits/rejected": 0.3211938142776489,
+      "logps/chosen": -199.82485961914062,
+      "logps/rejected": -210.410400390625,
+      "loss": 0.5281,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.28799813985824585,
+      "rewards/margins": 0.6520898342132568,
+      "rewards/rejected": -0.9400879740715027,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9887563299287615,
+      "grad_norm": 36.50225194256435,
+      "learning_rate": 6.864988558352402e-09,
+      "logits/chosen": 0.2802445888519287,
+      "logits/rejected": 0.32968616485595703,
+      "logps/chosen": -182.9055633544922,
+      "logps/rejected": -195.48397827148438,
+      "loss": 0.5302,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.3680599331855774,
+      "rewards/margins": 0.6278579831123352,
+      "rewards/rejected": -0.9959178566932678,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9956226933310446,
+      "grad_norm": 37.0877105218469,
+      "learning_rate": 3.0511060259344012e-09,
+      "logits/chosen": 0.23157478868961334,
+      "logits/rejected": 0.26915648579597473,
+      "logps/chosen": -202.55470275878906,
+      "logps/rejected": -210.82720947265625,
+      "loss": 0.518,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -0.3523581624031067,
+      "rewards/margins": 0.6836462616920471,
+      "rewards/rejected": -1.0360045433044434,
+      "step": 1450
+    },
+    {
+      "epoch": 1.0,
+      "step": 1457,
+      "total_flos": 160669524688896.0,
+      "train_loss": 0.5754778021889021,
+      "train_runtime": 14476.1212,
+      "train_samples_per_second": 6.439,
+      "train_steps_per_second": 0.101
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1457,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 160669524688896.0,
+  "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 sha256:931683ea9d56c1ca2e54f47ee04d8b5407fe8dac1f1220d8edb2e8aef0dfa4f0
+size 7544