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_32b
+  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_32b
+
+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_32b dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0
+- Datasets 3.6.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 160003043033088.0,
+    "train_loss": 0.538088473287122,
+    "train_runtime": 14420.7196,
+    "train_samples_per_second": 6.434,
+    "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 sha256:0309e64337d8f8a49f67cfddec880339680eaf725d67b637ce9b075857d04f16
+size 4965841415

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9d25faf481e3e3edc7c01994753fd392765d6900ca4baeb68816a5c2728c8e
+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": 160003043033088.0,
+    "train_loss": 0.538088473287122,
+    "train_runtime": 14420.7196,
+    "train_samples_per_second": 6.434,
+    "train_steps_per_second": 0.101
+}

trainer_log.jsonl

@@ -0,0 +1,146 @@
+{"current_steps": 10, "total_steps": 1450, "loss": 0.694, "accuracy": 0.3765624761581421, "lr": 6.206896551724137e-08, "epoch": 0.006898038370338435, "percentage": 0.69, "elapsed_time": "0:01:41", "remaining_time": "4:03:23"}
+{"current_steps": 20, "total_steps": 1450, "loss": 0.6924, "accuracy": 0.518750011920929, "lr": 1.310344827586207e-07, "epoch": 0.01379607674067687, "percentage": 1.38, "elapsed_time": "0:03:20", "remaining_time": "3:59:03"}
+{"current_steps": 30, "total_steps": 1450, "loss": 0.6928, "accuracy": 0.4921875298023224, "lr": 2e-07, "epoch": 0.020694115111015304, "percentage": 2.07, "elapsed_time": "0:04:56", "remaining_time": "3:53:55"}
+{"current_steps": 40, "total_steps": 1450, "loss": 0.6927, "accuracy": 0.5140625238418579, "lr": 2.689655172413793e-07, "epoch": 0.02759215348135374, "percentage": 2.76, "elapsed_time": "0:06:31", "remaining_time": "3:50:07"}
+{"current_steps": 50, "total_steps": 1450, "loss": 0.6921, "accuracy": 0.535937488079071, "lr": 3.379310344827586e-07, "epoch": 0.03449019185169218, "percentage": 3.45, "elapsed_time": "0:08:10", "remaining_time": "3:48:50"}
+{"current_steps": 60, "total_steps": 1450, "loss": 0.6928, "accuracy": 0.48125001788139343, "lr": 4.068965517241379e-07, "epoch": 0.04138823022203061, "percentage": 4.14, "elapsed_time": "0:09:50", "remaining_time": "3:47:59"}
+{"current_steps": 70, "total_steps": 1450, "loss": 0.6914, "accuracy": 0.53125, "lr": 4.7586206896551725e-07, "epoch": 0.04828626859236904, "percentage": 4.83, "elapsed_time": "0:11:31", "remaining_time": "3:47:05"}
+{"current_steps": 80, "total_steps": 1450, "loss": 0.6903, "accuracy": 0.5453125238418579, "lr": 5.448275862068966e-07, "epoch": 0.05518430696270748, "percentage": 5.52, "elapsed_time": "0:13:09", "remaining_time": "3:45:13"}
+{"current_steps": 90, "total_steps": 1450, "loss": 0.6886, "accuracy": 0.574999988079071, "lr": 6.137931034482758e-07, "epoch": 0.062082345333045914, "percentage": 6.21, "elapsed_time": "0:14:47", "remaining_time": "3:43:31"}
+{"current_steps": 100, "total_steps": 1450, "loss": 0.6884, "accuracy": 0.590624988079071, "lr": 6.827586206896552e-07, "epoch": 0.06898038370338436, "percentage": 6.9, "elapsed_time": "0:16:29", "remaining_time": "3:42:41"}
+{"current_steps": 110, "total_steps": 1450, "loss": 0.6858, "accuracy": 0.582812488079071, "lr": 7.517241379310344e-07, "epoch": 0.07587842207372278, "percentage": 7.59, "elapsed_time": "0:18:09", "remaining_time": "3:41:06"}
+{"current_steps": 120, "total_steps": 1450, "loss": 0.6836, "accuracy": 0.590624988079071, "lr": 8.206896551724138e-07, "epoch": 0.08277646044406121, "percentage": 8.28, "elapsed_time": "0:19:47", "remaining_time": "3:39:25"}
+{"current_steps": 130, "total_steps": 1450, "loss": 0.683, "accuracy": 0.6000000238418579, "lr": 8.896551724137931e-07, "epoch": 0.08967449881439965, "percentage": 8.97, "elapsed_time": "0:21:26", "remaining_time": "3:37:47"}
+{"current_steps": 140, "total_steps": 1450, "loss": 0.6762, "accuracy": 0.6265625357627869, "lr": 9.586206896551724e-07, "epoch": 0.09657253718473809, "percentage": 9.66, "elapsed_time": "0:23:02", "remaining_time": "3:35:33"}
+{"current_steps": 150, "total_steps": 1450, "loss": 0.6703, "accuracy": 0.6578125357627869, "lr": 9.969348659003832e-07, "epoch": 0.10347057555507652, "percentage": 10.34, "elapsed_time": "0:24:38", "remaining_time": "3:33:34"}
+{"current_steps": 160, "total_steps": 1450, "loss": 0.6615, "accuracy": 0.6421875357627869, "lr": 9.89272030651341e-07, "epoch": 0.11036861392541496, "percentage": 11.03, "elapsed_time": "0:26:16", "remaining_time": "3:31:53"}
+{"current_steps": 170, "total_steps": 1450, "loss": 0.6544, "accuracy": 0.676562488079071, "lr": 9.816091954022988e-07, "epoch": 0.11726665229575339, "percentage": 11.72, "elapsed_time": "0:28:01", "remaining_time": "3:31:01"}
+{"current_steps": 180, "total_steps": 1450, "loss": 0.6512, "accuracy": 0.65625, "lr": 9.739463601532568e-07, "epoch": 0.12416469066609183, "percentage": 12.41, "elapsed_time": "0:29:39", "remaining_time": "3:29:16"}
+{"current_steps": 190, "total_steps": 1450, "loss": 0.655, "accuracy": 0.651562511920929, "lr": 9.662835249042146e-07, "epoch": 0.13106272903643026, "percentage": 13.1, "elapsed_time": "0:31:16", "remaining_time": "3:27:23"}
+{"current_steps": 200, "total_steps": 1450, "loss": 0.6477, "accuracy": 0.6390625238418579, "lr": 9.586206896551724e-07, "epoch": 0.13796076740676871, "percentage": 13.79, "elapsed_time": "0:32:59", "remaining_time": "3:26:09"}
+{"current_steps": 210, "total_steps": 1450, "loss": 0.6582, "accuracy": 0.6093750596046448, "lr": 9.509578544061302e-07, "epoch": 0.14485880577710714, "percentage": 14.48, "elapsed_time": "0:34:37", "remaining_time": "3:24:27"}
+{"current_steps": 220, "total_steps": 1450, "loss": 0.6466, "accuracy": 0.6843750476837158, "lr": 9.43295019157088e-07, "epoch": 0.15175684414744556, "percentage": 15.17, "elapsed_time": "0:36:15", "remaining_time": "3:22:45"}
+{"current_steps": 230, "total_steps": 1450, "loss": 0.6306, "accuracy": 0.651562511920929, "lr": 9.356321839080458e-07, "epoch": 0.158654882517784, "percentage": 15.86, "elapsed_time": "0:37:53", "remaining_time": "3:21:01"}
+{"current_steps": 240, "total_steps": 1450, "loss": 0.6324, "accuracy": 0.65625, "lr": 9.279693486590037e-07, "epoch": 0.16555292088812243, "percentage": 16.55, "elapsed_time": "0:39:36", "remaining_time": "3:19:39"}
+{"current_steps": 250, "total_steps": 1450, "loss": 0.6316, "accuracy": 0.6640625596046448, "lr": 9.203065134099616e-07, "epoch": 0.17245095925846088, "percentage": 17.24, "elapsed_time": "0:41:14", "remaining_time": "3:17:55"}
+{"current_steps": 260, "total_steps": 1450, "loss": 0.6387, "accuracy": 0.6484375, "lr": 9.126436781609194e-07, "epoch": 0.1793489976287993, "percentage": 17.93, "elapsed_time": "0:43:22", "remaining_time": "3:18:31"}
+{"current_steps": 270, "total_steps": 1450, "loss": 0.6228, "accuracy": 0.6796875, "lr": 9.049808429118773e-07, "epoch": 0.18624703599913775, "percentage": 18.62, "elapsed_time": "0:45:04", "remaining_time": "3:16:57"}
+{"current_steps": 280, "total_steps": 1450, "loss": 0.6144, "accuracy": 0.6843750476837158, "lr": 8.973180076628351e-07, "epoch": 0.19314507436947617, "percentage": 19.31, "elapsed_time": "0:46:50", "remaining_time": "3:15:43"}
+{"current_steps": 290, "total_steps": 1450, "loss": 0.6053, "accuracy": 0.6890625357627869, "lr": 8.896551724137931e-07, "epoch": 0.20004311273981462, "percentage": 20.0, "elapsed_time": "0:48:30", "remaining_time": "3:14:03"}
+{"current_steps": 300, "total_steps": 1450, "loss": 0.6032, "accuracy": 0.6812500357627869, "lr": 8.81992337164751e-07, "epoch": 0.20694115111015304, "percentage": 20.69, "elapsed_time": "0:50:11", "remaining_time": "3:12:25"}
+{"current_steps": 310, "total_steps": 1450, "loss": 0.6074, "accuracy": 0.6875, "lr": 8.743295019157088e-07, "epoch": 0.2138391894804915, "percentage": 21.38, "elapsed_time": "0:51:49", "remaining_time": "3:10:34"}
+{"current_steps": 320, "total_steps": 1450, "loss": 0.6047, "accuracy": 0.7000000476837158, "lr": 8.666666666666667e-07, "epoch": 0.22073722785082991, "percentage": 22.07, "elapsed_time": "0:53:28", "remaining_time": "3:08:50"}
+{"current_steps": 330, "total_steps": 1450, "loss": 0.6019, "accuracy": 0.6734375357627869, "lr": 8.590038314176245e-07, "epoch": 0.22763526622116836, "percentage": 22.76, "elapsed_time": "0:55:05", "remaining_time": "3:07:00"}
+{"current_steps": 340, "total_steps": 1450, "loss": 0.6038, "accuracy": 0.6765625476837158, "lr": 8.513409961685824e-07, "epoch": 0.23453330459150679, "percentage": 23.45, "elapsed_time": "0:56:43", "remaining_time": "3:05:10"}
+{"current_steps": 350, "total_steps": 1450, "loss": 0.5838, "accuracy": 0.7093750238418579, "lr": 8.436781609195402e-07, "epoch": 0.24143134296184524, "percentage": 24.14, "elapsed_time": "0:58:19", "remaining_time": "3:03:19"}
+{"current_steps": 360, "total_steps": 1450, "loss": 0.5962, "accuracy": 0.682812511920929, "lr": 8.360153256704981e-07, "epoch": 0.24832938133218366, "percentage": 24.83, "elapsed_time": "0:59:57", "remaining_time": "3:01:33"}
+{"current_steps": 370, "total_steps": 1450, "loss": 0.5912, "accuracy": 0.6859375238418579, "lr": 8.28352490421456e-07, "epoch": 0.2552274197025221, "percentage": 25.52, "elapsed_time": "1:01:36", "remaining_time": "2:59:49"}
+{"current_steps": 380, "total_steps": 1450, "loss": 0.5811, "accuracy": 0.7000000476837158, "lr": 8.206896551724138e-07, "epoch": 0.26212545807286053, "percentage": 26.21, "elapsed_time": "1:03:12", "remaining_time": "2:57:59"}
+{"current_steps": 390, "total_steps": 1450, "loss": 0.5902, "accuracy": 0.7000000476837158, "lr": 8.130268199233717e-07, "epoch": 0.26902349644319895, "percentage": 26.9, "elapsed_time": "1:04:53", "remaining_time": "2:56:23"}
+{"current_steps": 400, "total_steps": 1450, "loss": 0.5922, "accuracy": 0.699999988079071, "lr": 8.053639846743294e-07, "epoch": 0.27592153481353743, "percentage": 27.59, "elapsed_time": "1:06:35", "remaining_time": "2:54:47"}
+{"current_steps": 410, "total_steps": 1450, "loss": 0.5902, "accuracy": 0.6937500238418579, "lr": 7.977011494252873e-07, "epoch": 0.28281957318387585, "percentage": 28.28, "elapsed_time": "1:08:20", "remaining_time": "2:53:20"}
+{"current_steps": 420, "total_steps": 1450, "loss": 0.5791, "accuracy": 0.6843750476837158, "lr": 7.900383141762452e-07, "epoch": 0.28971761155421427, "percentage": 28.97, "elapsed_time": "1:09:55", "remaining_time": "2:51:27"}
+{"current_steps": 430, "total_steps": 1450, "loss": 0.5384, "accuracy": 0.7375000715255737, "lr": 7.82375478927203e-07, "epoch": 0.2966156499245527, "percentage": 29.66, "elapsed_time": "1:11:32", "remaining_time": "2:49:42"}
+{"current_steps": 440, "total_steps": 1450, "loss": 0.5753, "accuracy": 0.7046875357627869, "lr": 7.747126436781609e-07, "epoch": 0.3035136882948911, "percentage": 30.34, "elapsed_time": "1:13:10", "remaining_time": "2:47:57"}
+{"current_steps": 450, "total_steps": 1450, "loss": 0.5473, "accuracy": 0.7406250238418579, "lr": 7.670498084291187e-07, "epoch": 0.3104117266652296, "percentage": 31.03, "elapsed_time": "1:14:49", "remaining_time": "2:46:15"}
+{"current_steps": 460, "total_steps": 1450, "loss": 0.5984, "accuracy": 0.7140625715255737, "lr": 7.593869731800766e-07, "epoch": 0.317309765035568, "percentage": 31.72, "elapsed_time": "1:16:22", "remaining_time": "2:44:22"}
+{"current_steps": 470, "total_steps": 1450, "loss": 0.552, "accuracy": 0.7234375476837158, "lr": 7.517241379310344e-07, "epoch": 0.32420780340590644, "percentage": 32.41, "elapsed_time": "1:18:01", "remaining_time": "2:42:41"}
+{"current_steps": 480, "total_steps": 1450, "loss": 0.5457, "accuracy": 0.7156250476837158, "lr": 7.440613026819923e-07, "epoch": 0.33110584177624486, "percentage": 33.1, "elapsed_time": "1:19:38", "remaining_time": "2:40:55"}
+{"current_steps": 490, "total_steps": 1450, "loss": 0.5569, "accuracy": 0.7093750238418579, "lr": 7.363984674329502e-07, "epoch": 0.33800388014658334, "percentage": 33.79, "elapsed_time": "1:21:18", "remaining_time": "2:39:18"}
+{"current_steps": 500, "total_steps": 1450, "loss": 0.5488, "accuracy": 0.7265625, "lr": 7.28735632183908e-07, "epoch": 0.34490191851692176, "percentage": 34.48, "elapsed_time": "1:23:01", "remaining_time": "2:37:44"}
+{"current_steps": 510, "total_steps": 1450, "loss": 0.568, "accuracy": 0.6859375238418579, "lr": 7.210727969348659e-07, "epoch": 0.3517999568872602, "percentage": 35.17, "elapsed_time": "1:25:08", "remaining_time": "2:36:54"}
+{"current_steps": 520, "total_steps": 1450, "loss": 0.5676, "accuracy": 0.723437488079071, "lr": 7.134099616858237e-07, "epoch": 0.3586979952575986, "percentage": 35.86, "elapsed_time": "1:26:50", "remaining_time": "2:35:18"}
+{"current_steps": 530, "total_steps": 1450, "loss": 0.5301, "accuracy": 0.7234375476837158, "lr": 7.057471264367816e-07, "epoch": 0.3655960336279371, "percentage": 36.55, "elapsed_time": "1:28:29", "remaining_time": "2:33:36"}
+{"current_steps": 540, "total_steps": 1450, "loss": 0.5549, "accuracy": 0.737500011920929, "lr": 6.980842911877395e-07, "epoch": 0.3724940719982755, "percentage": 37.24, "elapsed_time": "1:30:11", "remaining_time": "2:31:58"}
+{"current_steps": 550, "total_steps": 1450, "loss": 0.5197, "accuracy": 0.734375, "lr": 6.904214559386973e-07, "epoch": 0.3793921103686139, "percentage": 37.93, "elapsed_time": "1:31:43", "remaining_time": "2:30:06"}
+{"current_steps": 560, "total_steps": 1450, "loss": 0.5603, "accuracy": 0.7312500476837158, "lr": 6.827586206896552e-07, "epoch": 0.38629014873895234, "percentage": 38.62, "elapsed_time": "1:33:19", "remaining_time": "2:28:18"}
+{"current_steps": 570, "total_steps": 1450, "loss": 0.5324, "accuracy": 0.7406250238418579, "lr": 6.750957854406129e-07, "epoch": 0.3931881871092908, "percentage": 39.31, "elapsed_time": "1:34:57", "remaining_time": "2:26:36"}
+{"current_steps": 580, "total_steps": 1450, "loss": 0.5603, "accuracy": 0.7265625, "lr": 6.674329501915708e-07, "epoch": 0.40008622547962924, "percentage": 40.0, "elapsed_time": "1:36:35", "remaining_time": "2:24:53"}
+{"current_steps": 590, "total_steps": 1450, "loss": 0.5281, "accuracy": 0.7437500357627869, "lr": 6.597701149425286e-07, "epoch": 0.40698426384996766, "percentage": 40.69, "elapsed_time": "1:38:10", "remaining_time": "2:23:06"}
+{"current_steps": 600, "total_steps": 1450, "loss": 0.5235, "accuracy": 0.729687511920929, "lr": 6.521072796934865e-07, "epoch": 0.4138823022203061, "percentage": 41.38, "elapsed_time": "1:39:49", "remaining_time": "2:21:25"}
+{"current_steps": 610, "total_steps": 1450, "loss": 0.5239, "accuracy": 0.7515624761581421, "lr": 6.444444444444444e-07, "epoch": 0.4207803405906445, "percentage": 42.07, "elapsed_time": "1:41:24", "remaining_time": "2:19:38"}
+{"current_steps": 620, "total_steps": 1450, "loss": 0.5296, "accuracy": 0.753125011920929, "lr": 6.367816091954022e-07, "epoch": 0.427678378960983, "percentage": 42.76, "elapsed_time": "1:43:01", "remaining_time": "2:17:55"}
+{"current_steps": 630, "total_steps": 1450, "loss": 0.5234, "accuracy": 0.7515624761581421, "lr": 6.291187739463601e-07, "epoch": 0.4345764173313214, "percentage": 43.45, "elapsed_time": "1:44:42", "remaining_time": "2:16:17"}
+{"current_steps": 640, "total_steps": 1450, "loss": 0.5165, "accuracy": 0.7406250238418579, "lr": 6.214559386973179e-07, "epoch": 0.44147445570165983, "percentage": 44.14, "elapsed_time": "1:46:26", "remaining_time": "2:14:42"}
+{"current_steps": 650, "total_steps": 1450, "loss": 0.5388, "accuracy": 0.7250000238418579, "lr": 6.137931034482758e-07, "epoch": 0.44837249407199825, "percentage": 44.83, "elapsed_time": "1:48:02", "remaining_time": "2:12:58"}
+{"current_steps": 660, "total_steps": 1450, "loss": 0.5558, "accuracy": 0.745312511920929, "lr": 6.061302681992337e-07, "epoch": 0.45527053244233673, "percentage": 45.52, "elapsed_time": "1:49:41", "remaining_time": "2:11:17"}
+{"current_steps": 670, "total_steps": 1450, "loss": 0.5195, "accuracy": 0.760937511920929, "lr": 5.984674329501915e-07, "epoch": 0.46216857081267515, "percentage": 46.21, "elapsed_time": "1:51:15", "remaining_time": "2:09:31"}
+{"current_steps": 680, "total_steps": 1450, "loss": 0.5034, "accuracy": 0.7640625238418579, "lr": 5.908045977011494e-07, "epoch": 0.46906660918301357, "percentage": 46.9, "elapsed_time": "1:52:49", "remaining_time": "2:07:45"}
+{"current_steps": 690, "total_steps": 1450, "loss": 0.5545, "accuracy": 0.71875, "lr": 5.831417624521072e-07, "epoch": 0.475964647553352, "percentage": 47.59, "elapsed_time": "1:54:30", "remaining_time": "2:06:07"}
+{"current_steps": 700, "total_steps": 1450, "loss": 0.5363, "accuracy": 0.739062488079071, "lr": 5.754789272030651e-07, "epoch": 0.48286268592369047, "percentage": 48.28, "elapsed_time": "1:56:06", "remaining_time": "2:04:24"}
+{"current_steps": 710, "total_steps": 1450, "loss": 0.5603, "accuracy": 0.6921875476837158, "lr": 5.678160919540229e-07, "epoch": 0.4897607242940289, "percentage": 48.97, "elapsed_time": "1:57:42", "remaining_time": "2:02:40"}
+{"current_steps": 720, "total_steps": 1450, "loss": 0.5005, "accuracy": 0.768750011920929, "lr": 5.601532567049809e-07, "epoch": 0.4966587626643673, "percentage": 49.66, "elapsed_time": "1:59:16", "remaining_time": "2:00:55"}
+{"current_steps": 730, "total_steps": 1450, "loss": 0.5219, "accuracy": 0.745312511920929, "lr": 5.524904214559388e-07, "epoch": 0.5035568010347058, "percentage": 50.34, "elapsed_time": "2:00:55", "remaining_time": "1:59:16"}
+{"current_steps": 740, "total_steps": 1450, "loss": 0.4984, "accuracy": 0.746874988079071, "lr": 5.448275862068966e-07, "epoch": 0.5104548394050442, "percentage": 51.03, "elapsed_time": "2:02:30", "remaining_time": "1:57:32"}
+{"current_steps": 750, "total_steps": 1450, "loss": 0.4902, "accuracy": 0.7843749523162842, "lr": 5.371647509578544e-07, "epoch": 0.5173528777753826, "percentage": 51.72, "elapsed_time": "2:04:09", "remaining_time": "1:55:53"}
+{"current_steps": 760, "total_steps": 1450, "loss": 0.511, "accuracy": 0.762499988079071, "lr": 5.295019157088122e-07, "epoch": 0.5242509161457211, "percentage": 52.41, "elapsed_time": "2:06:15", "remaining_time": "1:54:37"}
+{"current_steps": 770, "total_steps": 1450, "loss": 0.4868, "accuracy": 0.7749999761581421, "lr": 5.218390804597701e-07, "epoch": 0.5311489545160595, "percentage": 53.1, "elapsed_time": "2:07:55", "remaining_time": "1:52:58"}
+{"current_steps": 780, "total_steps": 1450, "loss": 0.5033, "accuracy": 0.745312511920929, "lr": 5.14176245210728e-07, "epoch": 0.5380469928863979, "percentage": 53.79, "elapsed_time": "2:09:34", "remaining_time": "1:51:17"}
+{"current_steps": 790, "total_steps": 1450, "loss": 0.4779, "accuracy": 0.768750011920929, "lr": 5.065134099616858e-07, "epoch": 0.5449450312567363, "percentage": 54.48, "elapsed_time": "2:11:08", "remaining_time": "1:49:33"}
+{"current_steps": 800, "total_steps": 1450, "loss": 0.5141, "accuracy": 0.746874988079071, "lr": 4.988505747126436e-07, "epoch": 0.5518430696270749, "percentage": 55.17, "elapsed_time": "2:12:42", "remaining_time": "1:47:49"}
+{"current_steps": 810, "total_steps": 1450, "loss": 0.5401, "accuracy": 0.7671875357627869, "lr": 4.911877394636015e-07, "epoch": 0.5587411079974133, "percentage": 55.86, "elapsed_time": "2:14:23", "remaining_time": "1:46:11"}
+{"current_steps": 820, "total_steps": 1450, "loss": 0.4873, "accuracy": 0.78125, "lr": 4.835249042145594e-07, "epoch": 0.5656391463677517, "percentage": 56.55, "elapsed_time": "2:15:59", "remaining_time": "1:44:28"}
+{"current_steps": 830, "total_steps": 1450, "loss": 0.503, "accuracy": 0.7593750357627869, "lr": 4.7586206896551725e-07, "epoch": 0.5725371847380901, "percentage": 57.24, "elapsed_time": "2:17:40", "remaining_time": "1:42:50"}
+{"current_steps": 840, "total_steps": 1450, "loss": 0.5211, "accuracy": 0.7500000596046448, "lr": 4.681992337164751e-07, "epoch": 0.5794352231084285, "percentage": 57.93, "elapsed_time": "2:19:20", "remaining_time": "1:41:11"}
+{"current_steps": 850, "total_steps": 1450, "loss": 0.481, "accuracy": 0.7749999761581421, "lr": 4.6053639846743294e-07, "epoch": 0.586333261478767, "percentage": 58.62, "elapsed_time": "2:20:59", "remaining_time": "1:39:31"}
+{"current_steps": 860, "total_steps": 1450, "loss": 0.4794, "accuracy": 0.778124988079071, "lr": 4.528735632183908e-07, "epoch": 0.5932312998491054, "percentage": 59.31, "elapsed_time": "2:22:31", "remaining_time": "1:37:46"}
+{"current_steps": 870, "total_steps": 1450, "loss": 0.4731, "accuracy": 0.776562511920929, "lr": 4.452107279693487e-07, "epoch": 0.6001293382194438, "percentage": 60.0, "elapsed_time": "2:24:13", "remaining_time": "1:36:09"}
+{"current_steps": 880, "total_steps": 1450, "loss": 0.5277, "accuracy": 0.7562499642372131, "lr": 4.375478927203065e-07, "epoch": 0.6070273765897822, "percentage": 60.69, "elapsed_time": "2:25:52", "remaining_time": "1:34:29"}
+{"current_steps": 890, "total_steps": 1450, "loss": 0.4904, "accuracy": 0.78125, "lr": 4.2988505747126437e-07, "epoch": 0.6139254149601208, "percentage": 61.38, "elapsed_time": "2:27:29", "remaining_time": "1:32:48"}
+{"current_steps": 900, "total_steps": 1450, "loss": 0.4955, "accuracy": 0.765625, "lr": 4.222222222222222e-07, "epoch": 0.6208234533304592, "percentage": 62.07, "elapsed_time": "2:29:11", "remaining_time": "1:31:10"}
+{"current_steps": 910, "total_steps": 1450, "loss": 0.4906, "accuracy": 0.7687499523162842, "lr": 4.1455938697318005e-07, "epoch": 0.6277214917007976, "percentage": 62.76, "elapsed_time": "2:30:47", "remaining_time": "1:29:28"}
+{"current_steps": 920, "total_steps": 1450, "loss": 0.4652, "accuracy": 0.8046875, "lr": 4.068965517241379e-07, "epoch": 0.634619530071136, "percentage": 63.45, "elapsed_time": "2:32:26", "remaining_time": "1:27:49"}
+{"current_steps": 930, "total_steps": 1450, "loss": 0.4609, "accuracy": 0.792187511920929, "lr": 3.992337164750958e-07, "epoch": 0.6415175684414745, "percentage": 64.14, "elapsed_time": "2:34:03", "remaining_time": "1:26:08"}
+{"current_steps": 940, "total_steps": 1450, "loss": 0.4956, "accuracy": 0.7671875357627869, "lr": 3.9157088122605364e-07, "epoch": 0.6484156068118129, "percentage": 64.83, "elapsed_time": "2:35:43", "remaining_time": "1:24:29"}
+{"current_steps": 950, "total_steps": 1450, "loss": 0.4729, "accuracy": 0.776562511920929, "lr": 3.839080459770115e-07, "epoch": 0.6553136451821513, "percentage": 65.52, "elapsed_time": "2:37:20", "remaining_time": "1:22:48"}
+{"current_steps": 960, "total_steps": 1450, "loss": 0.4797, "accuracy": 0.7734375, "lr": 3.762452107279693e-07, "epoch": 0.6622116835524897, "percentage": 66.21, "elapsed_time": "2:38:57", "remaining_time": "1:21:07"}
+{"current_steps": 970, "total_steps": 1450, "loss": 0.4687, "accuracy": 0.7875000238418579, "lr": 3.6858237547892717e-07, "epoch": 0.6691097219228282, "percentage": 66.9, "elapsed_time": "2:40:33", "remaining_time": "1:19:27"}
+{"current_steps": 980, "total_steps": 1450, "loss": 0.4689, "accuracy": 0.7890625596046448, "lr": 3.60919540229885e-07, "epoch": 0.6760077602931667, "percentage": 67.59, "elapsed_time": "2:42:10", "remaining_time": "1:17:46"}
+{"current_steps": 990, "total_steps": 1450, "loss": 0.4946, "accuracy": 0.776562511920929, "lr": 3.532567049808429e-07, "epoch": 0.6829057986635051, "percentage": 68.28, "elapsed_time": "2:43:50", "remaining_time": "1:16:07"}
+{"current_steps": 1000, "total_steps": 1450, "loss": 0.4856, "accuracy": 0.7718750238418579, "lr": 3.4559386973180075e-07, "epoch": 0.6898038370338435, "percentage": 68.97, "elapsed_time": "2:45:25", "remaining_time": "1:14:26"}
+{"current_steps": 1010, "total_steps": 1450, "loss": 0.4788, "accuracy": 0.785937488079071, "lr": 3.379310344827586e-07, "epoch": 0.6967018754041819, "percentage": 69.66, "elapsed_time": "2:47:35", "remaining_time": "1:13:00"}
+{"current_steps": 1020, "total_steps": 1450, "loss": 0.4723, "accuracy": 0.7656250596046448, "lr": 3.3026819923371644e-07, "epoch": 0.7035999137745204, "percentage": 70.34, "elapsed_time": "2:49:17", "remaining_time": "1:11:21"}
+{"current_steps": 1030, "total_steps": 1450, "loss": 0.4899, "accuracy": 0.784375011920929, "lr": 3.226053639846743e-07, "epoch": 0.7104979521448588, "percentage": 71.03, "elapsed_time": "2:50:49", "remaining_time": "1:09:39"}
+{"current_steps": 1040, "total_steps": 1450, "loss": 0.4572, "accuracy": 0.7859375476837158, "lr": 3.149425287356321e-07, "epoch": 0.7173959905151972, "percentage": 71.72, "elapsed_time": "2:52:27", "remaining_time": "1:07:59"}
+{"current_steps": 1050, "total_steps": 1450, "loss": 0.476, "accuracy": 0.7953125238418579, "lr": 3.0727969348659e-07, "epoch": 0.7242940288855356, "percentage": 72.41, "elapsed_time": "2:54:08", "remaining_time": "1:06:20"}
+{"current_steps": 1060, "total_steps": 1450, "loss": 0.4797, "accuracy": 0.7859375476837158, "lr": 2.996168582375479e-07, "epoch": 0.7311920672558742, "percentage": 73.1, "elapsed_time": "2:55:53", "remaining_time": "1:04:42"}
+{"current_steps": 1070, "total_steps": 1450, "loss": 0.4584, "accuracy": 0.8046875, "lr": 2.9195402298850576e-07, "epoch": 0.7380901056262126, "percentage": 73.79, "elapsed_time": "2:57:30", "remaining_time": "1:03:02"}
+{"current_steps": 1080, "total_steps": 1450, "loss": 0.4752, "accuracy": 0.7843750715255737, "lr": 2.842911877394636e-07, "epoch": 0.744988143996551, "percentage": 74.48, "elapsed_time": "2:59:10", "remaining_time": "1:01:23"}
+{"current_steps": 1090, "total_steps": 1450, "loss": 0.4815, "accuracy": 0.768750011920929, "lr": 2.7662835249042145e-07, "epoch": 0.7518861823668894, "percentage": 75.17, "elapsed_time": "3:00:46", "remaining_time": "0:59:42"}
+{"current_steps": 1100, "total_steps": 1450, "loss": 0.488, "accuracy": 0.7750000357627869, "lr": 2.689655172413793e-07, "epoch": 0.7587842207372278, "percentage": 75.86, "elapsed_time": "3:02:25", "remaining_time": "0:58:02"}
+{"current_steps": 1110, "total_steps": 1450, "loss": 0.4684, "accuracy": 0.8015625476837158, "lr": 2.6130268199233714e-07, "epoch": 0.7656822591075663, "percentage": 76.55, "elapsed_time": "3:04:00", "remaining_time": "0:56:21"}
+{"current_steps": 1120, "total_steps": 1450, "loss": 0.4579, "accuracy": 0.784375011920929, "lr": 2.5363984674329503e-07, "epoch": 0.7725802974779047, "percentage": 77.24, "elapsed_time": "3:05:37", "remaining_time": "0:54:41"}
+{"current_steps": 1130, "total_steps": 1450, "loss": 0.4743, "accuracy": 0.768750011920929, "lr": 2.459770114942529e-07, "epoch": 0.7794783358482431, "percentage": 77.93, "elapsed_time": "3:07:13", "remaining_time": "0:53:01"}
+{"current_steps": 1140, "total_steps": 1450, "loss": 0.4685, "accuracy": 0.7750000357627869, "lr": 2.3831417624521072e-07, "epoch": 0.7863763742185816, "percentage": 78.62, "elapsed_time": "3:08:50", "remaining_time": "0:51:21"}
+{"current_steps": 1150, "total_steps": 1450, "loss": 0.4579, "accuracy": 0.7984375357627869, "lr": 2.3065134099616856e-07, "epoch": 0.7932744125889201, "percentage": 79.31, "elapsed_time": "3:10:24", "remaining_time": "0:49:40"}
+{"current_steps": 1160, "total_steps": 1450, "loss": 0.4805, "accuracy": 0.7578125, "lr": 2.2298850574712643e-07, "epoch": 0.8001724509592585, "percentage": 80.0, "elapsed_time": "3:12:00", "remaining_time": "0:48:00"}
+{"current_steps": 1170, "total_steps": 1450, "loss": 0.4705, "accuracy": 0.778124988079071, "lr": 2.1532567049808428e-07, "epoch": 0.8070704893295969, "percentage": 80.69, "elapsed_time": "3:13:36", "remaining_time": "0:46:20"}
+{"current_steps": 1180, "total_steps": 1450, "loss": 0.4357, "accuracy": 0.7984375357627869, "lr": 2.0766283524904212e-07, "epoch": 0.8139685276999353, "percentage": 81.38, "elapsed_time": "3:15:14", "remaining_time": "0:44:40"}
+{"current_steps": 1190, "total_steps": 1450, "loss": 0.4544, "accuracy": 0.8109375238418579, "lr": 2e-07, "epoch": 0.8208665660702738, "percentage": 82.07, "elapsed_time": "3:16:52", "remaining_time": "0:43:00"}
+{"current_steps": 1200, "total_steps": 1450, "loss": 0.4769, "accuracy": 0.7718750238418579, "lr": 1.9233716475095783e-07, "epoch": 0.8277646044406122, "percentage": 82.76, "elapsed_time": "3:18:26", "remaining_time": "0:41:20"}
+{"current_steps": 1210, "total_steps": 1450, "loss": 0.4646, "accuracy": 0.7437500357627869, "lr": 1.846743295019157e-07, "epoch": 0.8346626428109506, "percentage": 83.45, "elapsed_time": "3:20:07", "remaining_time": "0:39:41"}
+{"current_steps": 1220, "total_steps": 1450, "loss": 0.4633, "accuracy": 0.7984375357627869, "lr": 1.7701149425287357e-07, "epoch": 0.841560681181289, "percentage": 84.14, "elapsed_time": "3:21:47", "remaining_time": "0:38:02"}
+{"current_steps": 1230, "total_steps": 1450, "loss": 0.4738, "accuracy": 0.7687499523162842, "lr": 1.6934865900383142e-07, "epoch": 0.8484587195516275, "percentage": 84.83, "elapsed_time": "3:23:28", "remaining_time": "0:36:23"}
+{"current_steps": 1240, "total_steps": 1450, "loss": 0.4701, "accuracy": 0.7750000357627869, "lr": 1.6168582375478926e-07, "epoch": 0.855356757921966, "percentage": 85.52, "elapsed_time": "3:25:06", "remaining_time": "0:34:44"}
+{"current_steps": 1250, "total_steps": 1450, "loss": 0.4404, "accuracy": 0.7859375476837158, "lr": 1.5402298850574713e-07, "epoch": 0.8622547962923044, "percentage": 86.21, "elapsed_time": "3:26:47", "remaining_time": "0:33:05"}
+{"current_steps": 1260, "total_steps": 1450, "loss": 0.4612, "accuracy": 0.768750011920929, "lr": 1.4636015325670498e-07, "epoch": 0.8691528346626428, "percentage": 86.9, "elapsed_time": "3:28:51", "remaining_time": "0:31:29"}
+{"current_steps": 1270, "total_steps": 1450, "loss": 0.4529, "accuracy": 0.796875, "lr": 1.3869731800766282e-07, "epoch": 0.8760508730329812, "percentage": 87.59, "elapsed_time": "3:30:27", "remaining_time": "0:29:49"}
+{"current_steps": 1280, "total_steps": 1450, "loss": 0.4947, "accuracy": 0.7828125357627869, "lr": 1.310344827586207e-07, "epoch": 0.8829489114033197, "percentage": 88.28, "elapsed_time": "3:32:07", "remaining_time": "0:28:10"}
+{"current_steps": 1290, "total_steps": 1450, "loss": 0.4644, "accuracy": 0.796875, "lr": 1.2337164750957853e-07, "epoch": 0.8898469497736581, "percentage": 88.97, "elapsed_time": "3:33:48", "remaining_time": "0:26:31"}
+{"current_steps": 1300, "total_steps": 1450, "loss": 0.4417, "accuracy": 0.792187511920929, "lr": 1.1570881226053639e-07, "epoch": 0.8967449881439965, "percentage": 89.66, "elapsed_time": "3:35:24", "remaining_time": "0:24:51"}
+{"current_steps": 1310, "total_steps": 1450, "loss": 0.4529, "accuracy": 0.7718750238418579, "lr": 1.0804597701149425e-07, "epoch": 0.903643026514335, "percentage": 90.34, "elapsed_time": "3:36:57", "remaining_time": "0:23:11"}
+{"current_steps": 1320, "total_steps": 1450, "loss": 0.4465, "accuracy": 0.7906249761581421, "lr": 1.003831417624521e-07, "epoch": 0.9105410648846735, "percentage": 91.03, "elapsed_time": "3:38:37", "remaining_time": "0:21:31"}
+{"current_steps": 1330, "total_steps": 1450, "loss": 0.5007, "accuracy": 0.7593750357627869, "lr": 9.272030651340995e-08, "epoch": 0.9174391032550119, "percentage": 91.72, "elapsed_time": "3:40:13", "remaining_time": "0:19:52"}
+{"current_steps": 1340, "total_steps": 1450, "loss": 0.4432, "accuracy": 0.7828124761581421, "lr": 8.505747126436782e-08, "epoch": 0.9243371416253503, "percentage": 92.41, "elapsed_time": "3:41:51", "remaining_time": "0:18:12"}
+{"current_steps": 1350, "total_steps": 1450, "loss": 0.496, "accuracy": 0.78125, "lr": 7.739463601532567e-08, "epoch": 0.9312351799956887, "percentage": 93.1, "elapsed_time": "3:43:31", "remaining_time": "0:16:33"}
+{"current_steps": 1360, "total_steps": 1450, "loss": 0.4914, "accuracy": 0.7593749761581421, "lr": 6.973180076628352e-08, "epoch": 0.9381332183660271, "percentage": 93.79, "elapsed_time": "3:45:18", "remaining_time": "0:14:54"}
+{"current_steps": 1370, "total_steps": 1450, "loss": 0.4409, "accuracy": 0.815625011920929, "lr": 6.206896551724137e-08, "epoch": 0.9450312567363656, "percentage": 94.48, "elapsed_time": "3:46:56", "remaining_time": "0:13:15"}
+{"current_steps": 1380, "total_steps": 1450, "loss": 0.4695, "accuracy": 0.7796875238418579, "lr": 5.440613026819923e-08, "epoch": 0.951929295106704, "percentage": 95.17, "elapsed_time": "3:48:35", "remaining_time": "0:11:35"}
+{"current_steps": 1390, "total_steps": 1450, "loss": 0.4592, "accuracy": 0.7999999523162842, "lr": 4.674329501915709e-08, "epoch": 0.9588273334770425, "percentage": 95.86, "elapsed_time": "3:50:14", "remaining_time": "0:09:56"}
+{"current_steps": 1400, "total_steps": 1450, "loss": 0.4819, "accuracy": 0.7718749642372131, "lr": 3.908045977011494e-08, "epoch": 0.9657253718473809, "percentage": 96.55, "elapsed_time": "3:51:52", "remaining_time": "0:08:16"}
+{"current_steps": 1410, "total_steps": 1450, "loss": 0.4469, "accuracy": 0.8203125, "lr": 3.1417624521072795e-08, "epoch": 0.9726234102177194, "percentage": 97.24, "elapsed_time": "3:53:26", "remaining_time": "0:06:37"}
+{"current_steps": 1420, "total_steps": 1450, "loss": 0.4339, "accuracy": 0.7921875715255737, "lr": 2.375478927203065e-08, "epoch": 0.9795214485880578, "percentage": 97.93, "elapsed_time": "3:55:01", "remaining_time": "0:04:57"}
+{"current_steps": 1430, "total_steps": 1450, "loss": 0.4703, "accuracy": 0.7953125238418579, "lr": 1.6091954022988505e-08, "epoch": 0.9864194869583962, "percentage": 98.62, "elapsed_time": "3:56:41", "remaining_time": "0:03:18"}
+{"current_steps": 1440, "total_steps": 1450, "loss": 0.4753, "accuracy": 0.7593750357627869, "lr": 8.429118773946359e-09, "epoch": 0.9933175253287346, "percentage": 99.31, "elapsed_time": "3:58:19", "remaining_time": "0:01:39"}
+{"current_steps": 1450, "total_steps": 1450, "loss": 0.4402, "accuracy": 0.7774193286895752, "lr": 7.662835249042145e-10, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:59:53", "remaining_time": "0:00:00"}
+{"current_steps": 1450, "total_steps": 1450, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "4:00:20", "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": 1450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006898038370338435,
+      "grad_norm": 19.705646458861423,
+      "learning_rate": 6.206896551724137e-08,
+      "logits/chosen": 0.36835142970085144,
+      "logits/rejected": 0.37963682413101196,
+      "logps/chosen": -187.7964324951172,
+      "logps/rejected": -188.8426971435547,
+      "loss": 0.694,
+      "rewards/accuracies": 0.3765624761581421,
+      "rewards/chosen": 0.00014640908921137452,
+      "rewards/margins": -0.0013930138666182756,
+      "rewards/rejected": 0.001539423130452633,
+      "step": 10
+    },
+    {
+      "epoch": 0.01379607674067687,
+      "grad_norm": 20.359376341203163,
+      "learning_rate": 1.310344827586207e-07,
+      "logits/chosen": 0.346253365278244,
+      "logits/rejected": 0.39457663893699646,
+      "logps/chosen": -198.4833526611328,
+      "logps/rejected": -201.30184936523438,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.518750011920929,
+      "rewards/chosen": 0.0007789735682308674,
+      "rewards/margins": 0.002007370116189122,
+      "rewards/rejected": -0.001228396431542933,
+      "step": 20
+    },
+    {
+      "epoch": 0.020694115111015304,
+      "grad_norm": 19.26655335814601,
+      "learning_rate": 2e-07,
+      "logits/chosen": 0.3383290767669678,
+      "logits/rejected": 0.3465532064437866,
+      "logps/chosen": -188.64797973632812,
+      "logps/rejected": -191.93255615234375,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.4921875298023224,
+      "rewards/chosen": 0.00016563231474719942,
+      "rewards/margins": 0.001079646055586636,
+      "rewards/rejected": -0.0009140136535279453,
+      "step": 30
+    },
+    {
+      "epoch": 0.02759215348135374,
+      "grad_norm": 19.461533122560674,
+      "learning_rate": 2.689655172413793e-07,
+      "logits/chosen": 0.3220195174217224,
+      "logits/rejected": 0.352189302444458,
+      "logps/chosen": -193.79917907714844,
+      "logps/rejected": -195.8463592529297,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5140625238418579,
+      "rewards/chosen": 0.0018630579579621553,
+      "rewards/margins": 0.0012647934490814805,
+      "rewards/rejected": 0.0005982647417113185,
+      "step": 40
+    },
+    {
+      "epoch": 0.03449019185169218,
+      "grad_norm": 18.709946510342135,
+      "learning_rate": 3.379310344827586e-07,
+      "logits/chosen": 0.3111805021762848,
+      "logits/rejected": 0.3789227604866028,
+      "logps/chosen": -193.026611328125,
+      "logps/rejected": -194.10079956054688,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.535937488079071,
+      "rewards/chosen": -4.348141374066472e-06,
+      "rewards/margins": 0.002440733602270484,
+      "rewards/rejected": -0.0024450814817100763,
+      "step": 50
+    },
+    {
+      "epoch": 0.04138823022203061,
+      "grad_norm": 20.819341516167324,
+      "learning_rate": 4.068965517241379e-07,
+      "logits/chosen": 0.2869677245616913,
+      "logits/rejected": 0.34675154089927673,
+      "logps/chosen": -193.4478759765625,
+      "logps/rejected": -193.21920776367188,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.48125001788139343,
+      "rewards/chosen": 0.002217940054833889,
+      "rewards/margins": 0.0011762925423681736,
+      "rewards/rejected": 0.001041647745296359,
+      "step": 60
+    },
+    {
+      "epoch": 0.04828626859236904,
+      "grad_norm": 20.28793702047738,
+      "learning_rate": 4.7586206896551725e-07,
+      "logits/chosen": 0.34730735421180725,
+      "logits/rejected": 0.3767208456993103,
+      "logps/chosen": -194.2237091064453,
+      "logps/rejected": -196.96975708007812,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.0017953569767996669,
+      "rewards/margins": 0.0039480566047132015,
+      "rewards/rejected": -0.002152699278667569,
+      "step": 70
+    },
+    {
+      "epoch": 0.05518430696270748,
+      "grad_norm": 22.20708731778355,
+      "learning_rate": 5.448275862068966e-07,
+      "logits/chosen": 0.3007983863353729,
+      "logits/rejected": 0.34858226776123047,
+      "logps/chosen": -196.1852569580078,
+      "logps/rejected": -200.59390258789062,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.5453125238418579,
+      "rewards/chosen": 0.0038398741744458675,
+      "rewards/margins": 0.006094089709222317,
+      "rewards/rejected": -0.0022542153019458055,
+      "step": 80
+    },
+    {
+      "epoch": 0.062082345333045914,
+      "grad_norm": 21.294776767220753,
+      "learning_rate": 6.137931034482758e-07,
+      "logits/chosen": 0.37359899282455444,
+      "logits/rejected": 0.42109134793281555,
+      "logps/chosen": -188.8787841796875,
+      "logps/rejected": -192.15109252929688,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.0028547337278723717,
+      "rewards/margins": 0.009716801345348358,
+      "rewards/rejected": -0.0068620676174759865,
+      "step": 90
+    },
+    {
+      "epoch": 0.06898038370338436,
+      "grad_norm": 20.217604268172767,
+      "learning_rate": 6.827586206896552e-07,
+      "logits/chosen": 0.3505266308784485,
+      "logits/rejected": 0.350009024143219,
+      "logps/chosen": -196.3862762451172,
+      "logps/rejected": -201.52877807617188,
+      "loss": 0.6884,
+      "rewards/accuracies": 0.590624988079071,
+      "rewards/chosen": -0.0006909169023856521,
+      "rewards/margins": 0.010285623371601105,
+      "rewards/rejected": -0.010976539924740791,
+      "step": 100
+    },
+    {
+      "epoch": 0.07587842207372278,
+      "grad_norm": 21.217963404784477,
+      "learning_rate": 7.517241379310344e-07,
+      "logits/chosen": 0.33910346031188965,
+      "logits/rejected": 0.36434462666511536,
+      "logps/chosen": -188.9788360595703,
+      "logps/rejected": -190.0298309326172,
+      "loss": 0.6858,
+      "rewards/accuracies": 0.582812488079071,
+      "rewards/chosen": -0.0009895700495690107,
+      "rewards/margins": 0.015926657244563103,
+      "rewards/rejected": -0.016916226595640182,
+      "step": 110
+    },
+    {
+      "epoch": 0.08277646044406121,
+      "grad_norm": 21.31628057119455,
+      "learning_rate": 8.206896551724138e-07,
+      "logits/chosen": 0.34675049781799316,
+      "logits/rejected": 0.3582940101623535,
+      "logps/chosen": -187.06553649902344,
+      "logps/rejected": -194.0469207763672,
+      "loss": 0.6836,
+      "rewards/accuracies": 0.590624988079071,
+      "rewards/chosen": -0.003323513315990567,
+      "rewards/margins": 0.020813049748539925,
+      "rewards/rejected": -0.024136561900377274,
+      "step": 120
+    },
+    {
+      "epoch": 0.08967449881439965,
+      "grad_norm": 18.756215965537713,
+      "learning_rate": 8.896551724137931e-07,
+      "logits/chosen": 0.34192919731140137,
+      "logits/rejected": 0.3638426661491394,
+      "logps/chosen": -186.26242065429688,
+      "logps/rejected": -192.37039184570312,
+      "loss": 0.683,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.019915325567126274,
+      "rewards/margins": 0.022372394800186157,
+      "rewards/rejected": -0.04228772222995758,
+      "step": 130
+    },
+    {
+      "epoch": 0.09657253718473809,
+      "grad_norm": 21.634404693009117,
+      "learning_rate": 9.586206896551724e-07,
+      "logits/chosen": 0.355460524559021,
+      "logits/rejected": 0.3625187277793884,
+      "logps/chosen": -195.02239990234375,
+      "logps/rejected": -198.76058959960938,
+      "loss": 0.6762,
+      "rewards/accuracies": 0.6265625357627869,
+      "rewards/chosen": -0.029798131436109543,
+      "rewards/margins": 0.03854268416762352,
+      "rewards/rejected": -0.06834081560373306,
+      "step": 140
+    },
+    {
+      "epoch": 0.10347057555507652,
+      "grad_norm": 21.48669810581556,
+      "learning_rate": 9.969348659003832e-07,
+      "logits/chosen": 0.374904990196228,
+      "logits/rejected": 0.361512690782547,
+      "logps/chosen": -193.9099884033203,
+      "logps/rejected": -205.7383270263672,
+      "loss": 0.6703,
+      "rewards/accuracies": 0.6578125357627869,
+      "rewards/chosen": -0.05483241379261017,
+      "rewards/margins": 0.051752641797065735,
+      "rewards/rejected": -0.1065850630402565,
+      "step": 150
+    },
+    {
+      "epoch": 0.11036861392541496,
+      "grad_norm": 22.595411287408094,
+      "learning_rate": 9.89272030651341e-07,
+      "logits/chosen": 0.37401390075683594,
+      "logits/rejected": 0.3333270847797394,
+      "logps/chosen": -201.05963134765625,
+      "logps/rejected": -208.31690979003906,
+      "loss": 0.6615,
+      "rewards/accuracies": 0.6421875357627869,
+      "rewards/chosen": -0.08352852612733841,
+      "rewards/margins": 0.07251986861228943,
+      "rewards/rejected": -0.15604838728904724,
+      "step": 160
+    },
+    {
+      "epoch": 0.11726665229575339,
+      "grad_norm": 21.048436327513958,
+      "learning_rate": 9.816091954022988e-07,
+      "logits/chosen": 0.3516397178173065,
+      "logits/rejected": 0.38395583629608154,
+      "logps/chosen": -195.45803833007812,
+      "logps/rejected": -202.01185607910156,
+      "loss": 0.6544,
+      "rewards/accuracies": 0.676562488079071,
+      "rewards/chosen": -0.1025937870144844,
+      "rewards/margins": 0.09426098316907883,
+      "rewards/rejected": -0.19685477018356323,
+      "step": 170
+    },
+    {
+      "epoch": 0.12416469066609183,
+      "grad_norm": 21.699149046811495,
+      "learning_rate": 9.739463601532568e-07,
+      "logits/chosen": 0.3513750731945038,
+      "logits/rejected": 0.3493267297744751,
+      "logps/chosen": -199.25662231445312,
+      "logps/rejected": -204.52728271484375,
+      "loss": 0.6512,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.12922349572181702,
+      "rewards/margins": 0.10247690975666046,
+      "rewards/rejected": -0.23170042037963867,
+      "step": 180
+    },
+    {
+      "epoch": 0.13106272903643026,
+      "grad_norm": 22.02241376896688,
+      "learning_rate": 9.662835249042146e-07,
+      "logits/chosen": 0.3174246847629547,
+      "logits/rejected": 0.3541577160358429,
+      "logps/chosen": -198.79998779296875,
+      "logps/rejected": -206.08731079101562,
+      "loss": 0.655,
+      "rewards/accuracies": 0.651562511920929,
+      "rewards/chosen": -0.15049652755260468,
+      "rewards/margins": 0.10282564908266068,
+      "rewards/rejected": -0.25332218408584595,
+      "step": 190
+    },
+    {
+      "epoch": 0.13796076740676871,
+      "grad_norm": 19.928303872875155,
+      "learning_rate": 9.586206896551724e-07,
+      "logits/chosen": 0.2792571485042572,
+      "logits/rejected": 0.3482253849506378,
+      "logps/chosen": -196.61712646484375,
+      "logps/rejected": -194.27162170410156,
+      "loss": 0.6477,
+      "rewards/accuracies": 0.6390625238418579,
+      "rewards/chosen": -0.16095106303691864,
+      "rewards/margins": 0.12415014207363129,
+      "rewards/rejected": -0.2851012051105499,
+      "step": 200
+    },
+    {
+      "epoch": 0.14485880577710714,
+      "grad_norm": 24.92460334180119,
+      "learning_rate": 9.509578544061302e-07,
+      "logits/chosen": 0.30972471833229065,
+      "logits/rejected": 0.3551430404186249,
+      "logps/chosen": -197.7263946533203,
+      "logps/rejected": -201.88555908203125,
+      "loss": 0.6582,
+      "rewards/accuracies": 0.6093750596046448,
+      "rewards/chosen": -0.18753336369991302,
+      "rewards/margins": 0.11249043047428131,
+      "rewards/rejected": -0.30002379417419434,
+      "step": 210
+    },
+    {
+      "epoch": 0.15175684414744556,
+      "grad_norm": 22.79442118870038,
+      "learning_rate": 9.43295019157088e-07,
+      "logits/chosen": 0.3017464578151703,
+      "logits/rejected": 0.352105975151062,
+      "logps/chosen": -189.9367218017578,
+      "logps/rejected": -192.67840576171875,
+      "loss": 0.6466,
+      "rewards/accuracies": 0.6843750476837158,
+      "rewards/chosen": -0.20621374249458313,
+      "rewards/margins": 0.1424286663532257,
+      "rewards/rejected": -0.34864240884780884,
+      "step": 220
+    },
+    {
+      "epoch": 0.158654882517784,
+      "grad_norm": 21.705464795180195,
+      "learning_rate": 9.356321839080458e-07,
+      "logits/chosen": 0.2900081276893616,
+      "logits/rejected": 0.3325185179710388,
+      "logps/chosen": -192.8509979248047,
+      "logps/rejected": -200.14572143554688,
+      "loss": 0.6306,
+      "rewards/accuracies": 0.651562511920929,
+      "rewards/chosen": -0.20791535079479218,
+      "rewards/margins": 0.17991559207439423,
+      "rewards/rejected": -0.3878309428691864,
+      "step": 230
+    },
+    {
+      "epoch": 0.16555292088812243,
+      "grad_norm": 20.441645860866057,
+      "learning_rate": 9.279693486590037e-07,
+      "logits/chosen": 0.2543826401233673,
+      "logits/rejected": 0.2842496633529663,
+      "logps/chosen": -199.53659057617188,
+      "logps/rejected": -206.34771728515625,
+      "loss": 0.6324,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.26963937282562256,
+      "rewards/margins": 0.18849027156829834,
+      "rewards/rejected": -0.4581296145915985,
+      "step": 240
+    },
+    {
+      "epoch": 0.17245095925846088,
+      "grad_norm": 22.57587749280274,
+      "learning_rate": 9.203065134099616e-07,
+      "logits/chosen": 0.26432597637176514,
+      "logits/rejected": 0.31688380241394043,
+      "logps/chosen": -199.59571838378906,
+      "logps/rejected": -207.96337890625,
+      "loss": 0.6316,
+      "rewards/accuracies": 0.6640625596046448,
+      "rewards/chosen": -0.2876093089580536,
+      "rewards/margins": 0.19110387563705444,
+      "rewards/rejected": -0.47871318459510803,
+      "step": 250
+    },
+    {
+      "epoch": 0.1793489976287993,
+      "grad_norm": 21.526505800441665,
+      "learning_rate": 9.126436781609194e-07,
+      "logits/chosen": 0.3052281141281128,
+      "logits/rejected": 0.31890809535980225,
+      "logps/chosen": -190.8103790283203,
+      "logps/rejected": -197.42758178710938,
+      "loss": 0.6387,
+      "rewards/accuracies": 0.6484375,
+      "rewards/chosen": -0.3205464780330658,
+      "rewards/margins": 0.189984530210495,
+      "rewards/rejected": -0.5105310082435608,
+      "step": 260
+    },
+    {
+      "epoch": 0.18624703599913775,
+      "grad_norm": 24.080067203690575,
+      "learning_rate": 9.049808429118773e-07,
+      "logits/chosen": 0.32106345891952515,
+      "logits/rejected": 0.3163641095161438,
+      "logps/chosen": -193.92506408691406,
+      "logps/rejected": -199.49679565429688,
+      "loss": 0.6228,
+      "rewards/accuracies": 0.6796875,
+      "rewards/chosen": -0.3592388927936554,
+      "rewards/margins": 0.21608832478523254,
+      "rewards/rejected": -0.5753272771835327,
+      "step": 270
+    },
+    {
+      "epoch": 0.19314507436947617,
+      "grad_norm": 22.934282465553025,
+      "learning_rate": 8.973180076628351e-07,
+      "logits/chosen": 0.29369789361953735,
+      "logits/rejected": 0.29175543785095215,
+      "logps/chosen": -202.85293579101562,
+      "logps/rejected": -212.9384765625,
+      "loss": 0.6144,
+      "rewards/accuracies": 0.6843750476837158,
+      "rewards/chosen": -0.37743711471557617,
+      "rewards/margins": 0.27061423659324646,
+      "rewards/rejected": -0.6480513215065002,
+      "step": 280
+    },
+    {
+      "epoch": 0.20004311273981462,
+      "grad_norm": 25.800311412575947,
+      "learning_rate": 8.896551724137931e-07,
+      "logits/chosen": 0.2707730233669281,
+      "logits/rejected": 0.3287985324859619,
+      "logps/chosen": -193.82411193847656,
+      "logps/rejected": -205.94606018066406,
+      "loss": 0.6053,
+      "rewards/accuracies": 0.6890625357627869,
+      "rewards/chosen": -0.40112268924713135,
+      "rewards/margins": 0.27477550506591797,
+      "rewards/rejected": -0.6758981943130493,
+      "step": 290
+    },
+    {
+      "epoch": 0.20694115111015304,
+      "grad_norm": 25.421379038162744,
+      "learning_rate": 8.81992337164751e-07,
+      "logits/chosen": 0.2867887020111084,
+      "logits/rejected": 0.2730118930339813,
+      "logps/chosen": -211.45458984375,
+      "logps/rejected": -224.3688507080078,
+      "loss": 0.6032,
+      "rewards/accuracies": 0.6812500357627869,
+      "rewards/chosen": -0.4323672950267792,
+      "rewards/margins": 0.311962366104126,
+      "rewards/rejected": -0.7443296909332275,
+      "step": 300
+    },
+    {
+      "epoch": 0.2138391894804915,
+      "grad_norm": 23.357935776008553,
+      "learning_rate": 8.743295019157088e-07,
+      "logits/chosen": 0.30384495854377747,
+      "logits/rejected": 0.31480729579925537,
+      "logps/chosen": -197.1667022705078,
+      "logps/rejected": -206.29144287109375,
+      "loss": 0.6074,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.49985194206237793,
+      "rewards/margins": 0.2933136820793152,
+      "rewards/rejected": -0.7931656241416931,
+      "step": 310
+    },
+    {
+      "epoch": 0.22073722785082991,
+      "grad_norm": 20.985500688578327,
+      "learning_rate": 8.666666666666667e-07,
+      "logits/chosen": 0.32146862149238586,
+      "logits/rejected": 0.38823962211608887,
+      "logps/chosen": -196.0064697265625,
+      "logps/rejected": -210.33905029296875,
+      "loss": 0.6047,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.5386682748794556,
+      "rewards/margins": 0.3213097155094147,
+      "rewards/rejected": -0.8599780201911926,
+      "step": 320
+    },
+    {
+      "epoch": 0.22763526622116836,
+      "grad_norm": 19.782650147196403,
+      "learning_rate": 8.590038314176245e-07,
+      "logits/chosen": 0.3865478038787842,
+      "logits/rejected": 0.4090644121170044,
+      "logps/chosen": -204.63607788085938,
+      "logps/rejected": -212.3304443359375,
+      "loss": 0.6019,
+      "rewards/accuracies": 0.6734375357627869,
+      "rewards/chosen": -0.6245216131210327,
+      "rewards/margins": 0.36608007550239563,
+      "rewards/rejected": -0.990601658821106,
+      "step": 330
+    },
+    {
+      "epoch": 0.23453330459150679,
+      "grad_norm": 22.660878566995944,
+      "learning_rate": 8.513409961685824e-07,
+      "logits/chosen": 0.33020085096359253,
+      "logits/rejected": 0.3953076899051666,
+      "logps/chosen": -198.2565460205078,
+      "logps/rejected": -208.3692169189453,
+      "loss": 0.6038,
+      "rewards/accuracies": 0.6765625476837158,
+      "rewards/chosen": -0.5995591878890991,
+      "rewards/margins": 0.3347458839416504,
+      "rewards/rejected": -0.9343050718307495,
+      "step": 340
+    },
+    {
+      "epoch": 0.24143134296184524,
+      "grad_norm": 23.697173711397785,
+      "learning_rate": 8.436781609195402e-07,
+      "logits/chosen": 0.2802509069442749,
+      "logits/rejected": 0.33361196517944336,
+      "logps/chosen": -199.09048461914062,
+      "logps/rejected": -209.76051330566406,
+      "loss": 0.5838,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -0.5859872102737427,
+      "rewards/margins": 0.37135303020477295,
+      "rewards/rejected": -0.9573402404785156,
+      "step": 350
+    },
+    {
+      "epoch": 0.24832938133218366,
+      "grad_norm": 21.021696982453527,
+      "learning_rate": 8.360153256704981e-07,
+      "logits/chosen": 0.3388012647628784,
+      "logits/rejected": 0.3767550587654114,
+      "logps/chosen": -197.89669799804688,
+      "logps/rejected": -207.66709899902344,
+      "loss": 0.5962,
+      "rewards/accuracies": 0.682812511920929,
+      "rewards/chosen": -0.5828956961631775,
+      "rewards/margins": 0.3945348858833313,
+      "rewards/rejected": -0.9774305820465088,
+      "step": 360
+    },
+    {
+      "epoch": 0.2552274197025221,
+      "grad_norm": 21.543666601248262,
+      "learning_rate": 8.28352490421456e-07,
+      "logits/chosen": 0.30326756834983826,
+      "logits/rejected": 0.3772284984588623,
+      "logps/chosen": -196.38209533691406,
+      "logps/rejected": -208.34056091308594,
+      "loss": 0.5912,
+      "rewards/accuracies": 0.6859375238418579,
+      "rewards/chosen": -0.5436594486236572,
+      "rewards/margins": 0.37626004219055176,
+      "rewards/rejected": -0.919919490814209,
+      "step": 370
+    },
+    {
+      "epoch": 0.26212545807286053,
+      "grad_norm": 21.02248262252068,
+      "learning_rate": 8.206896551724138e-07,
+      "logits/chosen": 0.3109130859375,
+      "logits/rejected": 0.28564298152923584,
+      "logps/chosen": -204.91912841796875,
+      "logps/rejected": -221.65782165527344,
+      "loss": 0.5811,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.5830342173576355,
+      "rewards/margins": 0.42591309547424316,
+      "rewards/rejected": -1.0089473724365234,
+      "step": 380
+    },
+    {
+      "epoch": 0.26902349644319895,
+      "grad_norm": 21.574655386442398,
+      "learning_rate": 8.130268199233717e-07,
+      "logits/chosen": 0.3019198477268219,
+      "logits/rejected": 0.321940153837204,
+      "logps/chosen": -207.87794494628906,
+      "logps/rejected": -218.37860107421875,
+      "loss": 0.5902,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -0.5571427345275879,
+      "rewards/margins": 0.3800555467605591,
+      "rewards/rejected": -0.937198281288147,
+      "step": 390
+    },
+    {
+      "epoch": 0.27592153481353743,
+      "grad_norm": 23.222399130782183,
+      "learning_rate": 8.053639846743294e-07,
+      "logits/chosen": 0.2715260088443756,
+      "logits/rejected": 0.28244683146476746,
+      "logps/chosen": -214.16189575195312,
+      "logps/rejected": -226.54576110839844,
+      "loss": 0.5922,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.6588503122329712,
+      "rewards/margins": 0.4110034704208374,
+      "rewards/rejected": -1.0698537826538086,
+      "step": 400
+    },
+    {
+      "epoch": 0.28281957318387585,
+      "grad_norm": 20.668994395434144,
+      "learning_rate": 7.977011494252873e-07,
+      "logits/chosen": 0.2664548456668854,
+      "logits/rejected": 0.29690778255462646,
+      "logps/chosen": -204.0004425048828,
+      "logps/rejected": -213.70797729492188,
+      "loss": 0.5902,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.6476739645004272,
+      "rewards/margins": 0.4224002957344055,
+      "rewards/rejected": -1.070074200630188,
+      "step": 410
+    },
+    {
+      "epoch": 0.28971761155421427,
+      "grad_norm": 23.387477174221438,
+      "learning_rate": 7.900383141762452e-07,
+      "logits/chosen": 0.26732271909713745,
+      "logits/rejected": 0.3153986930847168,
+      "logps/chosen": -196.22264099121094,
+      "logps/rejected": -206.97850036621094,
+      "loss": 0.5791,
+      "rewards/accuracies": 0.6843750476837158,
+      "rewards/chosen": -0.5797644853591919,
+      "rewards/margins": 0.4164075255393982,
+      "rewards/rejected": -0.9961719512939453,
+      "step": 420
+    },
+    {
+      "epoch": 0.2966156499245527,
+      "grad_norm": 21.18326793123928,
+      "learning_rate": 7.82375478927203e-07,
+      "logits/chosen": 0.21811504662036896,
+      "logits/rejected": 0.2583531439304352,
+      "logps/chosen": -207.00149536132812,
+      "logps/rejected": -219.3418731689453,
+      "loss": 0.5384,
+      "rewards/accuracies": 0.7375000715255737,
+      "rewards/chosen": -0.5487433671951294,
+      "rewards/margins": 0.535973072052002,
+      "rewards/rejected": -1.0847163200378418,
+      "step": 430
+    },
+    {
+      "epoch": 0.3035136882948911,
+      "grad_norm": 26.940070706652882,
+      "learning_rate": 7.747126436781609e-07,
+      "logits/chosen": 0.21293707191944122,
+      "logits/rejected": 0.22856633365154266,
+      "logps/chosen": -208.216796875,
+      "logps/rejected": -220.22528076171875,
+      "loss": 0.5753,
+      "rewards/accuracies": 0.7046875357627869,
+      "rewards/chosen": -0.6004849076271057,
+      "rewards/margins": 0.4932917356491089,
+      "rewards/rejected": -1.0937767028808594,
+      "step": 440
+    },
+    {
+      "epoch": 0.3104117266652296,
+      "grad_norm": 17.108456205097973,
+      "learning_rate": 7.670498084291187e-07,
+      "logits/chosen": 0.21750858426094055,
+      "logits/rejected": 0.27465111017227173,
+      "logps/chosen": -200.55621337890625,
+      "logps/rejected": -210.05360412597656,
+      "loss": 0.5473,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.588002622127533,
+      "rewards/margins": 0.5616728067398071,
+      "rewards/rejected": -1.1496754884719849,
+      "step": 450
+    },
+    {
+      "epoch": 0.317309765035568,
+      "grad_norm": 25.016877550394028,
+      "learning_rate": 7.593869731800766e-07,
+      "logits/chosen": 0.15050889551639557,
+      "logits/rejected": 0.24773681163787842,
+      "logps/chosen": -201.76043701171875,
+      "logps/rejected": -215.86187744140625,
+      "loss": 0.5984,
+      "rewards/accuracies": 0.7140625715255737,
+      "rewards/chosen": -0.6779018044471741,
+      "rewards/margins": 0.470897912979126,
+      "rewards/rejected": -1.1487996578216553,
+      "step": 460
+    },
+    {
+      "epoch": 0.32420780340590644,
+      "grad_norm": 20.958071725485514,
+      "learning_rate": 7.517241379310344e-07,
+      "logits/chosen": 0.1510736346244812,
+      "logits/rejected": 0.24761702120304108,
+      "logps/chosen": -208.5487060546875,
+      "logps/rejected": -216.71127319335938,
+      "loss": 0.552,
+      "rewards/accuracies": 0.7234375476837158,
+      "rewards/chosen": -0.6728602647781372,
+      "rewards/margins": 0.5733956098556519,
+      "rewards/rejected": -1.246255874633789,
+      "step": 470
+    },
+    {
+      "epoch": 0.33110584177624486,
+      "grad_norm": 21.914142386799554,
+      "learning_rate": 7.440613026819923e-07,
+      "logits/chosen": 0.2657942473888397,
+      "logits/rejected": 0.28262150287628174,
+      "logps/chosen": -200.79815673828125,
+      "logps/rejected": -213.93600463867188,
+      "loss": 0.5457,
+      "rewards/accuracies": 0.7156250476837158,
+      "rewards/chosen": -0.7010958790779114,
+      "rewards/margins": 0.5760525465011597,
+      "rewards/rejected": -1.2771484851837158,
+      "step": 480
+    },
+    {
+      "epoch": 0.33800388014658334,
+      "grad_norm": 20.691760332158143,
+      "learning_rate": 7.363984674329502e-07,
+      "logits/chosen": 0.1785193532705307,
+      "logits/rejected": 0.2651832401752472,
+      "logps/chosen": -207.3889617919922,
+      "logps/rejected": -216.79388427734375,
+      "loss": 0.5569,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -0.7134870886802673,
+      "rewards/margins": 0.542286217212677,
+      "rewards/rejected": -1.2557734251022339,
+      "step": 490
+    },
+    {
+      "epoch": 0.34490191851692176,
+      "grad_norm": 23.474962325162984,
+      "learning_rate": 7.28735632183908e-07,
+      "logits/chosen": 0.1998932659626007,
+      "logits/rejected": 0.24436387419700623,
+      "logps/chosen": -207.51589965820312,
+      "logps/rejected": -217.1973419189453,
+      "loss": 0.5488,
+      "rewards/accuracies": 0.7265625,
+      "rewards/chosen": -0.7165147066116333,
+      "rewards/margins": 0.6149377226829529,
+      "rewards/rejected": -1.3314523696899414,
+      "step": 500
+    },
+    {
+      "epoch": 0.3517999568872602,
+      "grad_norm": 22.888075753667685,
+      "learning_rate": 7.210727969348659e-07,
+      "logits/chosen": 0.17916660010814667,
+      "logits/rejected": 0.2139005810022354,
+      "logps/chosen": -206.5091094970703,
+      "logps/rejected": -218.1505584716797,
+      "loss": 0.568,
+      "rewards/accuracies": 0.6859375238418579,
+      "rewards/chosen": -0.7650787830352783,
+      "rewards/margins": 0.5644460916519165,
+      "rewards/rejected": -1.3295247554779053,
+      "step": 510
+    },
+    {
+      "epoch": 0.3586979952575986,
+      "grad_norm": 26.102732396040366,
+      "learning_rate": 7.134099616858237e-07,
+      "logits/chosen": 0.19337040185928345,
+      "logits/rejected": 0.17022080719470978,
+      "logps/chosen": -210.6927947998047,
+      "logps/rejected": -223.4407501220703,
+      "loss": 0.5676,
+      "rewards/accuracies": 0.723437488079071,
+      "rewards/chosen": -0.754781186580658,
+      "rewards/margins": 0.596481442451477,
+      "rewards/rejected": -1.3512626886367798,
+      "step": 520
+    },
+    {
+      "epoch": 0.3655960336279371,
+      "grad_norm": 22.211123954654255,
+      "learning_rate": 7.057471264367816e-07,
+      "logits/chosen": 0.17498114705085754,
+      "logits/rejected": 0.21647687256336212,
+      "logps/chosen": -204.9669647216797,
+      "logps/rejected": -220.52435302734375,
+      "loss": 0.5301,
+      "rewards/accuracies": 0.7234375476837158,
+      "rewards/chosen": -0.6388720273971558,
+      "rewards/margins": 0.6742045879364014,
+      "rewards/rejected": -1.3130766153335571,
+      "step": 530
+    },
+    {
+      "epoch": 0.3724940719982755,
+      "grad_norm": 19.802648080199884,
+      "learning_rate": 6.980842911877395e-07,
+      "logits/chosen": 0.19523748755455017,
+      "logits/rejected": 0.21661296486854553,
+      "logps/chosen": -204.8290557861328,
+      "logps/rejected": -221.68118286132812,
+      "loss": 0.5549,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.6770638227462769,
+      "rewards/margins": 0.6107801198959351,
+      "rewards/rejected": -1.287843942642212,
+      "step": 540
+    },
+    {
+      "epoch": 0.3793921103686139,
+      "grad_norm": 21.39010759759459,
+      "learning_rate": 6.904214559386973e-07,
+      "logits/chosen": 0.20838454365730286,
+      "logits/rejected": 0.21981817483901978,
+      "logps/chosen": -206.594482421875,
+      "logps/rejected": -226.77719116210938,
+      "loss": 0.5197,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": -0.6928226351737976,
+      "rewards/margins": 0.7122121453285217,
+      "rewards/rejected": -1.4050347805023193,
+      "step": 550
+    },
+    {
+      "epoch": 0.38629014873895234,
+      "grad_norm": 24.388542970501526,
+      "learning_rate": 6.827586206896552e-07,
+      "logits/chosen": 0.21371379494667053,
+      "logits/rejected": 0.2217874974012375,
+      "logps/chosen": -203.6668701171875,
+      "logps/rejected": -220.09390258789062,
+      "loss": 0.5603,
+      "rewards/accuracies": 0.7312500476837158,
+      "rewards/chosen": -0.7243704199790955,
+      "rewards/margins": 0.5787999629974365,
+      "rewards/rejected": -1.3031704425811768,
+      "step": 560
+    },
+    {
+      "epoch": 0.3931881871092908,
+      "grad_norm": 18.31272079122668,
+      "learning_rate": 6.750957854406129e-07,
+      "logits/chosen": 0.19194141030311584,
+      "logits/rejected": 0.23956988751888275,
+      "logps/chosen": -200.03921508789062,
+      "logps/rejected": -220.68844604492188,
+      "loss": 0.5324,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.6924073696136475,
+      "rewards/margins": 0.7310079336166382,
+      "rewards/rejected": -1.4234153032302856,
+      "step": 570
+    },
+    {
+      "epoch": 0.40008622547962924,
+      "grad_norm": 23.278396001880992,
+      "learning_rate": 6.674329501915708e-07,
+      "logits/chosen": 0.18476101756095886,
+      "logits/rejected": 0.3003040552139282,
+      "logps/chosen": -212.16586303710938,
+      "logps/rejected": -221.8807830810547,
+      "loss": 0.5603,
+      "rewards/accuracies": 0.7265625,
+      "rewards/chosen": -0.7272917032241821,
+      "rewards/margins": 0.594864010810852,
+      "rewards/rejected": -1.3221557140350342,
+      "step": 580
+    },
+    {
+      "epoch": 0.40698426384996766,
+      "grad_norm": 22.774833668061657,
+      "learning_rate": 6.597701149425286e-07,
+      "logits/chosen": 0.27348437905311584,
+      "logits/rejected": 0.29119783639907837,
+      "logps/chosen": -208.50161743164062,
+      "logps/rejected": -223.21377563476562,
+      "loss": 0.5281,
+      "rewards/accuracies": 0.7437500357627869,
+      "rewards/chosen": -0.7116725444793701,
+      "rewards/margins": 0.6606653332710266,
+      "rewards/rejected": -1.3723379373550415,
+      "step": 590
+    },
+    {
+      "epoch": 0.4138823022203061,
+      "grad_norm": 24.57400616632902,
+      "learning_rate": 6.521072796934865e-07,
+      "logits/chosen": 0.20140346884727478,
+      "logits/rejected": 0.233355313539505,
+      "logps/chosen": -197.4592742919922,
+      "logps/rejected": -212.82032775878906,
+      "loss": 0.5235,
+      "rewards/accuracies": 0.729687511920929,
+      "rewards/chosen": -0.6597610712051392,
+      "rewards/margins": 0.7397715449333191,
+      "rewards/rejected": -1.3995325565338135,
+      "step": 600
+    },
+    {
+      "epoch": 0.4207803405906445,
+      "grad_norm": 21.41678620311021,
+      "learning_rate": 6.444444444444444e-07,
+      "logits/chosen": 0.2271338552236557,
+      "logits/rejected": 0.2577861547470093,
+      "logps/chosen": -210.82029724121094,
+      "logps/rejected": -230.77545166015625,
+      "loss": 0.5239,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": -0.7849064469337463,
+      "rewards/margins": 0.7753893136978149,
+      "rewards/rejected": -1.560295820236206,
+      "step": 610
+    },
+    {
+      "epoch": 0.427678378960983,
+      "grad_norm": 27.454507207142147,
+      "learning_rate": 6.367816091954022e-07,
+      "logits/chosen": 0.2676536440849304,
+      "logits/rejected": 0.2785859704017639,
+      "logps/chosen": -200.918701171875,
+      "logps/rejected": -218.0684814453125,
+      "loss": 0.5296,
+      "rewards/accuracies": 0.753125011920929,
+      "rewards/chosen": -0.7359431982040405,
+      "rewards/margins": 0.7085081338882446,
+      "rewards/rejected": -1.4444513320922852,
+      "step": 620
+    },
+    {
+      "epoch": 0.4345764173313214,
+      "grad_norm": 23.055409383831122,
+      "learning_rate": 6.291187739463601e-07,
+      "logits/chosen": 0.22078415751457214,
+      "logits/rejected": 0.286234587430954,
+      "logps/chosen": -209.9963836669922,
+      "logps/rejected": -228.6524658203125,
+      "loss": 0.5234,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": -0.7776533961296082,
+      "rewards/margins": 0.7566480040550232,
+      "rewards/rejected": -1.5343014001846313,
+      "step": 630
+    },
+    {
+      "epoch": 0.44147445570165983,
+      "grad_norm": 20.425933679340293,
+      "learning_rate": 6.214559386973179e-07,
+      "logits/chosen": 0.2468743622303009,
+      "logits/rejected": 0.27129438519477844,
+      "logps/chosen": -207.75270080566406,
+      "logps/rejected": -220.77560424804688,
+      "loss": 0.5165,
+      "rewards/accuracies": 0.7406250238418579,
+      "rewards/chosen": -0.8151954412460327,
+      "rewards/margins": 0.7754901647567749,
+      "rewards/rejected": -1.5906856060028076,
+      "step": 640
+    },
+    {
+      "epoch": 0.44837249407199825,
+      "grad_norm": 23.41797315632108,
+      "learning_rate": 6.137931034482758e-07,
+      "logits/chosen": 0.15889199078083038,
+      "logits/rejected": 0.2550981938838959,
+      "logps/chosen": -209.88893127441406,
+      "logps/rejected": -223.1925506591797,
+      "loss": 0.5388,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.8657385110855103,
+      "rewards/margins": 0.6958652138710022,
+      "rewards/rejected": -1.5616039037704468,
+      "step": 650
+    },
+    {
+      "epoch": 0.45527053244233673,
+      "grad_norm": 26.006440186662328,
+      "learning_rate": 6.061302681992337e-07,
+      "logits/chosen": 0.2198886126279831,
+      "logits/rejected": 0.24105188250541687,
+      "logps/chosen": -211.81887817382812,
+      "logps/rejected": -229.9445037841797,
+      "loss": 0.5558,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.9279370903968811,
+      "rewards/margins": 0.6996958255767822,
+      "rewards/rejected": -1.627632737159729,
+      "step": 660
+    },
+    {
+      "epoch": 0.46216857081267515,
+      "grad_norm": 24.986970918973174,
+      "learning_rate": 5.984674329501915e-07,
+      "logits/chosen": 0.21261385083198547,
+      "logits/rejected": 0.23078909516334534,
+      "logps/chosen": -197.61631774902344,
+      "logps/rejected": -221.3162384033203,
+      "loss": 0.5195,
+      "rewards/accuracies": 0.760937511920929,
+      "rewards/chosen": -0.8430317640304565,
+      "rewards/margins": 0.8105250597000122,
+      "rewards/rejected": -1.6535569429397583,
+      "step": 670
+    },
+    {
+      "epoch": 0.46906660918301357,
+      "grad_norm": 18.699804314432686,
+      "learning_rate": 5.908045977011494e-07,
+      "logits/chosen": 0.2194710671901703,
+      "logits/rejected": 0.2245461493730545,
+      "logps/chosen": -206.41171264648438,
+      "logps/rejected": -225.4470977783203,
+      "loss": 0.5034,
+      "rewards/accuracies": 0.7640625238418579,
+      "rewards/chosen": -0.8391079902648926,
+      "rewards/margins": 0.8192622065544128,
+      "rewards/rejected": -1.6583701372146606,
+      "step": 680
+    },
+    {
+      "epoch": 0.475964647553352,
+      "grad_norm": 27.943474512199224,
+      "learning_rate": 5.831417624521072e-07,
+      "logits/chosen": 0.17129182815551758,
+      "logits/rejected": 0.26508453488349915,
+      "logps/chosen": -197.73431396484375,
+      "logps/rejected": -210.53427124023438,
+      "loss": 0.5545,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.7708035707473755,
+      "rewards/margins": 0.7140544056892395,
+      "rewards/rejected": -1.4848580360412598,
+      "step": 690
+    },
+    {
+      "epoch": 0.48286268592369047,
+      "grad_norm": 18.799210721144906,
+      "learning_rate": 5.754789272030651e-07,
+      "logits/chosen": 0.20475523173809052,
+      "logits/rejected": 0.3040182292461395,
+      "logps/chosen": -213.24290466308594,
+      "logps/rejected": -230.26467895507812,
+      "loss": 0.5363,
+      "rewards/accuracies": 0.739062488079071,
+      "rewards/chosen": -0.8690279722213745,
+      "rewards/margins": 0.7869499325752258,
+      "rewards/rejected": -1.6559779644012451,
+      "step": 700
+    },
+    {
+      "epoch": 0.4897607242940289,
+      "grad_norm": 25.644011365351712,
+      "learning_rate": 5.678160919540229e-07,
+      "logits/chosen": 0.16487537324428558,
+      "logits/rejected": 0.2230132669210434,
+      "logps/chosen": -205.01168823242188,
+      "logps/rejected": -218.5323486328125,
+      "loss": 0.5603,
+      "rewards/accuracies": 0.6921875476837158,
+      "rewards/chosen": -0.9361888766288757,
+      "rewards/margins": 0.6677310466766357,
+      "rewards/rejected": -1.6039198637008667,
+      "step": 710
+    },
+    {
+      "epoch": 0.4966587626643673,
+      "grad_norm": 22.153532795458556,
+      "learning_rate": 5.601532567049809e-07,
+      "logits/chosen": 0.19576019048690796,
+      "logits/rejected": 0.27333715558052063,
+      "logps/chosen": -200.7130889892578,
+      "logps/rejected": -219.6556854248047,
+      "loss": 0.5005,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -0.8190287947654724,
+      "rewards/margins": 0.8135865330696106,
+      "rewards/rejected": -1.632615327835083,
+      "step": 720
+    },
+    {
+      "epoch": 0.5035568010347058,
+      "grad_norm": 21.512930303082918,
+      "learning_rate": 5.524904214559388e-07,
+      "logits/chosen": 0.1499469131231308,
+      "logits/rejected": 0.20389853417873383,
+      "logps/chosen": -206.646484375,
+      "logps/rejected": -228.37503051757812,
+      "loss": 0.5219,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -0.88575679063797,
+      "rewards/margins": 0.7930079698562622,
+      "rewards/rejected": -1.6787649393081665,
+      "step": 730
+    },
+    {
+      "epoch": 0.5104548394050442,
+      "grad_norm": 24.61147206437457,
+      "learning_rate": 5.448275862068966e-07,
+      "logits/chosen": 0.18222621083259583,
+      "logits/rejected": 0.22593136131763458,
+      "logps/chosen": -216.77786254882812,
+      "logps/rejected": -238.52584838867188,
+      "loss": 0.4984,
+      "rewards/accuracies": 0.746874988079071,
+      "rewards/chosen": -0.9311150312423706,
+      "rewards/margins": 0.8666337132453918,
+      "rewards/rejected": -1.7977488040924072,
+      "step": 740
+    },
+    {
+      "epoch": 0.5173528777753826,
+      "grad_norm": 24.318520131273452,
+      "learning_rate": 5.371647509578544e-07,
+      "logits/chosen": 0.18827559053897858,
+      "logits/rejected": 0.24765178561210632,
+      "logps/chosen": -201.89991760253906,
+      "logps/rejected": -226.2533416748047,
+      "loss": 0.4902,
+      "rewards/accuracies": 0.7843749523162842,
+      "rewards/chosen": -0.8815733790397644,
+      "rewards/margins": 0.9414010047912598,
+      "rewards/rejected": -1.822974443435669,
+      "step": 750
+    },
+    {
+      "epoch": 0.5242509161457211,
+      "grad_norm": 38.718538073738564,
+      "learning_rate": 5.295019157088122e-07,
+      "logits/chosen": 0.17381815612316132,
+      "logits/rejected": 0.2428828477859497,
+      "logps/chosen": -206.8114013671875,
+      "logps/rejected": -225.81219482421875,
+      "loss": 0.511,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.0074797868728638,
+      "rewards/margins": 0.8152840733528137,
+      "rewards/rejected": -1.8227639198303223,
+      "step": 760
+    },
+    {
+      "epoch": 0.5311489545160595,
+      "grad_norm": 20.957009249774774,
+      "learning_rate": 5.218390804597701e-07,
+      "logits/chosen": 0.11571212112903595,
+      "logits/rejected": 0.18467916548252106,
+      "logps/chosen": -216.8351287841797,
+      "logps/rejected": -235.50743103027344,
+      "loss": 0.4868,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.9625260233879089,
+      "rewards/margins": 0.9064898490905762,
+      "rewards/rejected": -1.8690159320831299,
+      "step": 770
+    },
+    {
+      "epoch": 0.5380469928863979,
+      "grad_norm": 25.56373586600605,
+      "learning_rate": 5.14176245210728e-07,
+      "logits/chosen": 0.20467066764831543,
+      "logits/rejected": 0.1702248752117157,
+      "logps/chosen": -211.35308837890625,
+      "logps/rejected": -236.63363647460938,
+      "loss": 0.5033,
+      "rewards/accuracies": 0.745312511920929,
+      "rewards/chosen": -1.0503700971603394,
+      "rewards/margins": 0.8642019033432007,
+      "rewards/rejected": -1.91457200050354,
+      "step": 780
+    },
+    {
+      "epoch": 0.5449450312567363,
+      "grad_norm": 24.493933489793076,
+      "learning_rate": 5.065134099616858e-07,
+      "logits/chosen": 0.13319827616214752,
+      "logits/rejected": 0.18873748183250427,
+      "logps/chosen": -205.13214111328125,
+      "logps/rejected": -226.38357543945312,
+      "loss": 0.4779,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.0021754503250122,
+      "rewards/margins": 0.9200892448425293,
+      "rewards/rejected": -1.9222646951675415,
+      "step": 790
+    },
+    {
+      "epoch": 0.5518430696270749,
+      "grad_norm": 23.309860892057635,
+      "learning_rate": 4.988505747126436e-07,
+      "logits/chosen": 0.12849828600883484,
+      "logits/rejected": 0.22922158241271973,
+      "logps/chosen": -219.03140258789062,
+      "logps/rejected": -238.4054412841797,
+      "loss": 0.5141,
+      "rewards/accuracies": 0.746874988079071,
+      "rewards/chosen": -1.1349990367889404,
+      "rewards/margins": 0.8661084771156311,
+      "rewards/rejected": -2.0011074542999268,
+      "step": 800
+    },
+    {
+      "epoch": 0.5587411079974133,
+      "grad_norm": 23.833527951692258,
+      "learning_rate": 4.911877394636015e-07,
+      "logits/chosen": 0.15572428703308105,
+      "logits/rejected": 0.2141249179840088,
+      "logps/chosen": -214.1897430419922,
+      "logps/rejected": -235.65524291992188,
+      "loss": 0.5401,
+      "rewards/accuracies": 0.7671875357627869,
+      "rewards/chosen": -1.1772220134735107,
+      "rewards/margins": 0.9108952879905701,
+      "rewards/rejected": -2.0881171226501465,
+      "step": 810
+    },
+    {
+      "epoch": 0.5656391463677517,
+      "grad_norm": 22.362990514361123,
+      "learning_rate": 4.835249042145594e-07,
+      "logits/chosen": 0.13951486349105835,
+      "logits/rejected": 0.19652993977069855,
+      "logps/chosen": -212.92039489746094,
+      "logps/rejected": -235.84652709960938,
+      "loss": 0.4873,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -1.0033161640167236,
+      "rewards/margins": 0.9333437085151672,
+      "rewards/rejected": -1.936659812927246,
+      "step": 820
+    },
+    {
+      "epoch": 0.5725371847380901,
+      "grad_norm": 22.124457707735143,
+      "learning_rate": 4.7586206896551725e-07,
+      "logits/chosen": 0.1511804461479187,
+      "logits/rejected": 0.16028037667274475,
+      "logps/chosen": -221.8773193359375,
+      "logps/rejected": -240.11473083496094,
+      "loss": 0.503,
+      "rewards/accuracies": 0.7593750357627869,
+      "rewards/chosen": -1.0800548791885376,
+      "rewards/margins": 0.8837151527404785,
+      "rewards/rejected": -1.9637700319290161,
+      "step": 830
+    },
+    {
+      "epoch": 0.5794352231084285,
+      "grad_norm": 23.474946170740125,
+      "learning_rate": 4.681992337164751e-07,
+      "logits/chosen": 0.16761063039302826,
+      "logits/rejected": 0.24748662114143372,
+      "logps/chosen": -215.3556365966797,
+      "logps/rejected": -237.9365692138672,
+      "loss": 0.5211,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -1.1380001306533813,
+      "rewards/margins": 0.9258146286010742,
+      "rewards/rejected": -2.063814878463745,
+      "step": 840
+    },
+    {
+      "epoch": 0.586333261478767,
+      "grad_norm": 22.631103668833546,
+      "learning_rate": 4.6053639846743294e-07,
+      "logits/chosen": 0.1405535489320755,
+      "logits/rejected": 0.2345820665359497,
+      "logps/chosen": -217.42453002929688,
+      "logps/rejected": -235.82891845703125,
+      "loss": 0.481,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.9171855449676514,
+      "rewards/margins": 0.9807693362236023,
+      "rewards/rejected": -1.8979549407958984,
+      "step": 850
+    },
+    {
+      "epoch": 0.5932312998491054,
+      "grad_norm": 22.177230826478425,
+      "learning_rate": 4.528735632183908e-07,
+      "logits/chosen": 0.12721370160579681,
+      "logits/rejected": 0.17560192942619324,
+      "logps/chosen": -210.74789428710938,
+      "logps/rejected": -235.66932678222656,
+      "loss": 0.4794,
+      "rewards/accuracies": 0.778124988079071,
+      "rewards/chosen": -1.1062588691711426,
+      "rewards/margins": 1.0230000019073486,
+      "rewards/rejected": -2.1292591094970703,
+      "step": 860
+    },
+    {
+      "epoch": 0.6001293382194438,
+      "grad_norm": 23.02504819124567,
+      "learning_rate": 4.452107279693487e-07,
+      "logits/chosen": 0.10594005882740021,
+      "logits/rejected": 0.163488507270813,
+      "logps/chosen": -225.18484497070312,
+      "logps/rejected": -245.45799255371094,
+      "loss": 0.4731,
+      "rewards/accuracies": 0.776562511920929,
+      "rewards/chosen": -1.194356083869934,
+      "rewards/margins": 1.0393599271774292,
+      "rewards/rejected": -2.2337160110473633,
+      "step": 870
+    },
+    {
+      "epoch": 0.6070273765897822,
+      "grad_norm": 25.061402331091273,
+      "learning_rate": 4.375478927203065e-07,
+      "logits/chosen": 0.10525962710380554,
+      "logits/rejected": 0.16414019465446472,
+      "logps/chosen": -223.8541259765625,
+      "logps/rejected": -242.67599487304688,
+      "loss": 0.5277,
+      "rewards/accuracies": 0.7562499642372131,
+      "rewards/chosen": -1.145894169807434,
+      "rewards/margins": 0.9744288921356201,
+      "rewards/rejected": -2.1203231811523438,
+      "step": 880
+    },
+    {
+      "epoch": 0.6139254149601208,
+      "grad_norm": 31.327283409677584,
+      "learning_rate": 4.2988505747126437e-07,
+      "logits/chosen": 0.11804062128067017,
+      "logits/rejected": 0.19818758964538574,
+      "logps/chosen": -217.53366088867188,
+      "logps/rejected": -236.1646270751953,
+      "loss": 0.4904,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -1.151870846748352,
+      "rewards/margins": 0.9757134914398193,
+      "rewards/rejected": -2.127584457397461,
+      "step": 890
+    },
+    {
+      "epoch": 0.6208234533304592,
+      "grad_norm": 24.285377972042877,
+      "learning_rate": 4.222222222222222e-07,
+      "logits/chosen": 0.1879817396402359,
+      "logits/rejected": 0.1984453946352005,
+      "logps/chosen": -219.58839416503906,
+      "logps/rejected": -239.14683532714844,
+      "loss": 0.4955,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -1.072831630706787,
+      "rewards/margins": 0.972345232963562,
+      "rewards/rejected": -2.0451767444610596,
+      "step": 900
+    },
+    {
+      "epoch": 0.6277214917007976,
+      "grad_norm": 21.37218624566544,
+      "learning_rate": 4.1455938697318005e-07,
+      "logits/chosen": 0.11960437893867493,
+      "logits/rejected": 0.18714536726474762,
+      "logps/chosen": -208.94317626953125,
+      "logps/rejected": -227.9283447265625,
+      "loss": 0.4906,
+      "rewards/accuracies": 0.7687499523162842,
+      "rewards/chosen": -1.0316712856292725,
+      "rewards/margins": 0.9537010192871094,
+      "rewards/rejected": -1.9853723049163818,
+      "step": 910
+    },
+    {
+      "epoch": 0.634619530071136,
+      "grad_norm": 23.23303919337177,
+      "learning_rate": 4.068965517241379e-07,
+      "logits/chosen": 0.16769134998321533,
+      "logits/rejected": 0.23668895661830902,
+      "logps/chosen": -215.3607635498047,
+      "logps/rejected": -242.46231079101562,
+      "loss": 0.4652,
+      "rewards/accuracies": 0.8046875,
+      "rewards/chosen": -1.0188840627670288,
+      "rewards/margins": 1.050809621810913,
+      "rewards/rejected": -2.0696938037872314,
+      "step": 920
+    },
+    {
+      "epoch": 0.6415175684414745,
+      "grad_norm": 22.586673634781295,
+      "learning_rate": 3.992337164750958e-07,
+      "logits/chosen": 0.16347406804561615,
+      "logits/rejected": 0.22088101506233215,
+      "logps/chosen": -219.6250457763672,
+      "logps/rejected": -243.36587524414062,
+      "loss": 0.4609,
+      "rewards/accuracies": 0.792187511920929,
+      "rewards/chosen": -1.0500195026397705,
+      "rewards/margins": 1.0837587118148804,
+      "rewards/rejected": -2.1337780952453613,
+      "step": 930
+    },
+    {
+      "epoch": 0.6484156068118129,
+      "grad_norm": 22.98002801655956,
+      "learning_rate": 3.9157088122605364e-07,
+      "logits/chosen": 0.18367891013622284,
+      "logits/rejected": 0.17907743155956268,
+      "logps/chosen": -214.0507354736328,
+      "logps/rejected": -238.12570190429688,
+      "loss": 0.4956,
+      "rewards/accuracies": 0.7671875357627869,
+      "rewards/chosen": -1.1288217306137085,
+      "rewards/margins": 0.9605937004089355,
+      "rewards/rejected": -2.0894155502319336,
+      "step": 940
+    },
+    {
+      "epoch": 0.6553136451821513,
+      "grad_norm": 17.84640106890724,
+      "learning_rate": 3.839080459770115e-07,
+      "logits/chosen": 0.18814033269882202,
+      "logits/rejected": 0.26034802198410034,
+      "logps/chosen": -216.52496337890625,
+      "logps/rejected": -243.90826416015625,
+      "loss": 0.4729,
+      "rewards/accuracies": 0.776562511920929,
+      "rewards/chosen": -1.0930984020233154,
+      "rewards/margins": 1.0433658361434937,
+      "rewards/rejected": -2.1364643573760986,
+      "step": 950
+    },
+    {
+      "epoch": 0.6622116835524897,
+      "grad_norm": 22.315274563938523,
+      "learning_rate": 3.762452107279693e-07,
+      "logits/chosen": 0.13583947718143463,
+      "logits/rejected": 0.1586841642856598,
+      "logps/chosen": -210.781982421875,
+      "logps/rejected": -234.8236083984375,
+      "loss": 0.4797,
+      "rewards/accuracies": 0.7734375,
+      "rewards/chosen": -1.0251853466033936,
+      "rewards/margins": 1.022051215171814,
+      "rewards/rejected": -2.047236442565918,
+      "step": 960
+    },
+    {
+      "epoch": 0.6691097219228282,
+      "grad_norm": 21.660020820117154,
+      "learning_rate": 3.6858237547892717e-07,
+      "logits/chosen": 0.13990166783332825,
+      "logits/rejected": 0.19136521220207214,
+      "logps/chosen": -210.8424072265625,
+      "logps/rejected": -236.0836181640625,
+      "loss": 0.4687,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.101256251335144,
+      "rewards/margins": 1.099085807800293,
+      "rewards/rejected": -2.2003421783447266,
+      "step": 970
+    },
+    {
+      "epoch": 0.6760077602931667,
+      "grad_norm": 21.295429551155927,
+      "learning_rate": 3.60919540229885e-07,
+      "logits/chosen": 0.13500508666038513,
+      "logits/rejected": 0.1818273663520813,
+      "logps/chosen": -215.73947143554688,
+      "logps/rejected": -237.76312255859375,
+      "loss": 0.4689,
+      "rewards/accuracies": 0.7890625596046448,
+      "rewards/chosen": -1.0879331827163696,
+      "rewards/margins": 1.0524659156799316,
+      "rewards/rejected": -2.1403989791870117,
+      "step": 980
+    },
+    {
+      "epoch": 0.6829057986635051,
+      "grad_norm": 24.350539790328526,
+      "learning_rate": 3.532567049808429e-07,
+      "logits/chosen": 0.18764442205429077,
+      "logits/rejected": 0.14521312713623047,
+      "logps/chosen": -210.7366943359375,
+      "logps/rejected": -237.19691467285156,
+      "loss": 0.4946,
+      "rewards/accuracies": 0.776562511920929,
+      "rewards/chosen": -1.1615097522735596,
+      "rewards/margins": 1.009273886680603,
+      "rewards/rejected": -2.170783758163452,
+      "step": 990
+    },
+    {
+      "epoch": 0.6898038370338435,
+      "grad_norm": 24.430527768004612,
+      "learning_rate": 3.4559386973180075e-07,
+      "logits/chosen": 0.1154608502984047,
+      "logits/rejected": 0.14394116401672363,
+      "logps/chosen": -211.67010498046875,
+      "logps/rejected": -235.22601318359375,
+      "loss": 0.4856,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -1.1421856880187988,
+      "rewards/margins": 1.003755807876587,
+      "rewards/rejected": -2.1459412574768066,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6967018754041819,
+      "grad_norm": 25.333257716089456,
+      "learning_rate": 3.379310344827586e-07,
+      "logits/chosen": 0.05758751928806305,
+      "logits/rejected": 0.23519480228424072,
+      "logps/chosen": -220.646484375,
+      "logps/rejected": -239.65780639648438,
+      "loss": 0.4788,
+      "rewards/accuracies": 0.785937488079071,
+      "rewards/chosen": -1.2021660804748535,
+      "rewards/margins": 1.0922119617462158,
+      "rewards/rejected": -2.2943780422210693,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7035999137745204,
+      "grad_norm": 23.831188739778135,
+      "learning_rate": 3.3026819923371644e-07,
+      "logits/chosen": 0.1304895281791687,
+      "logits/rejected": 0.19071732461452484,
+      "logps/chosen": -210.5736083984375,
+      "logps/rejected": -232.50901794433594,
+      "loss": 0.4723,
+      "rewards/accuracies": 0.7656250596046448,
+      "rewards/chosen": -1.054470181465149,
+      "rewards/margins": 1.0092376470565796,
+      "rewards/rejected": -2.0637075901031494,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7104979521448588,
+      "grad_norm": 21.71715110582083,
+      "learning_rate": 3.226053639846743e-07,
+      "logits/chosen": 0.0674755871295929,
+      "logits/rejected": 0.1555739939212799,
+      "logps/chosen": -208.80389404296875,
+      "logps/rejected": -228.76556396484375,
+      "loss": 0.4899,
+      "rewards/accuracies": 0.784375011920929,
+      "rewards/chosen": -1.0720574855804443,
+      "rewards/margins": 0.988200306892395,
+      "rewards/rejected": -2.060257911682129,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7173959905151972,
+      "grad_norm": 19.885607800102576,
+      "learning_rate": 3.149425287356321e-07,
+      "logits/chosen": 0.11615429818630219,
+      "logits/rejected": 0.13085736334323883,
+      "logps/chosen": -223.4676513671875,
+      "logps/rejected": -245.81130981445312,
+      "loss": 0.4572,
+      "rewards/accuracies": 0.7859375476837158,
+      "rewards/chosen": -1.104932188987732,
+      "rewards/margins": 1.1073505878448486,
+      "rewards/rejected": -2.212282657623291,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7242940288855356,
+      "grad_norm": 22.633180774780207,
+      "learning_rate": 3.0727969348659e-07,
+      "logits/chosen": 0.11931788921356201,
+      "logits/rejected": 0.1989806443452835,
+      "logps/chosen": -223.46701049804688,
+      "logps/rejected": -245.942626953125,
+      "loss": 0.476,
+      "rewards/accuracies": 0.7953125238418579,
+      "rewards/chosen": -1.1209880113601685,
+      "rewards/margins": 1.1126110553741455,
+      "rewards/rejected": -2.2335991859436035,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7311920672558742,
+      "grad_norm": 22.607339620969345,
+      "learning_rate": 2.996168582375479e-07,
+      "logits/chosen": 0.15352767705917358,
+      "logits/rejected": 0.22844256460666656,
+      "logps/chosen": -208.1845703125,
+      "logps/rejected": -230.12515258789062,
+      "loss": 0.4797,
+      "rewards/accuracies": 0.7859375476837158,
+      "rewards/chosen": -1.1647709608078003,
+      "rewards/margins": 1.111741542816162,
+      "rewards/rejected": -2.276512622833252,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7380901056262126,
+      "grad_norm": 22.10853554321452,
+      "learning_rate": 2.9195402298850576e-07,
+      "logits/chosen": 0.14773155748844147,
+      "logits/rejected": 0.1732293963432312,
+      "logps/chosen": -209.5767059326172,
+      "logps/rejected": -239.27427673339844,
+      "loss": 0.4584,
+      "rewards/accuracies": 0.8046875,
+      "rewards/chosen": -1.1018071174621582,
+      "rewards/margins": 1.0996737480163574,
+      "rewards/rejected": -2.2014808654785156,
+      "step": 1070
+    },
+    {
+      "epoch": 0.744988143996551,
+      "grad_norm": 24.492427020207415,
+      "learning_rate": 2.842911877394636e-07,
+      "logits/chosen": 0.1176578477025032,
+      "logits/rejected": 0.18459954857826233,
+      "logps/chosen": -208.61622619628906,
+      "logps/rejected": -232.27537536621094,
+      "loss": 0.4752,
+      "rewards/accuracies": 0.7843750715255737,
+      "rewards/chosen": -1.079516053199768,
+      "rewards/margins": 1.0623971223831177,
+      "rewards/rejected": -2.141913414001465,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7518861823668894,
+      "grad_norm": 40.036510583262064,
+      "learning_rate": 2.7662835249042145e-07,
+      "logits/chosen": 0.15787634253501892,
+      "logits/rejected": 0.1683928668498993,
+      "logps/chosen": -218.29855346679688,
+      "logps/rejected": -239.5789794921875,
+      "loss": 0.4815,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.1719642877578735,
+      "rewards/margins": 1.0352319478988647,
+      "rewards/rejected": -2.2071962356567383,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7587842207372278,
+      "grad_norm": 21.374240830481533,
+      "learning_rate": 2.689655172413793e-07,
+      "logits/chosen": 0.17153756320476532,
+      "logits/rejected": 0.17747098207473755,
+      "logps/chosen": -210.64163208007812,
+      "logps/rejected": -234.2825927734375,
+      "loss": 0.488,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -1.1999056339263916,
+      "rewards/margins": 0.9716651439666748,
+      "rewards/rejected": -2.1715710163116455,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7656822591075663,
+      "grad_norm": 23.23316889911473,
+      "learning_rate": 2.6130268199233714e-07,
+      "logits/chosen": 0.15322671830654144,
+      "logits/rejected": 0.18879210948944092,
+      "logps/chosen": -214.78797912597656,
+      "logps/rejected": -239.0963897705078,
+      "loss": 0.4684,
+      "rewards/accuracies": 0.8015625476837158,
+      "rewards/chosen": -1.113561749458313,
+      "rewards/margins": 1.0662989616394043,
+      "rewards/rejected": -2.1798605918884277,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7725802974779047,
+      "grad_norm": 21.606963571039277,
+      "learning_rate": 2.5363984674329503e-07,
+      "logits/chosen": 0.18151381611824036,
+      "logits/rejected": 0.19774743914604187,
+      "logps/chosen": -213.07774353027344,
+      "logps/rejected": -236.7171173095703,
+      "loss": 0.4579,
+      "rewards/accuracies": 0.784375011920929,
+      "rewards/chosen": -1.1090879440307617,
+      "rewards/margins": 1.1060962677001953,
+      "rewards/rejected": -2.215184450149536,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7794783358482431,
+      "grad_norm": 31.597389723510716,
+      "learning_rate": 2.459770114942529e-07,
+      "logits/chosen": 0.12418875098228455,
+      "logits/rejected": 0.25851666927337646,
+      "logps/chosen": -207.92999267578125,
+      "logps/rejected": -228.67929077148438,
+      "loss": 0.4743,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.1108900308609009,
+      "rewards/margins": 1.0005470514297485,
+      "rewards/rejected": -2.1114370822906494,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7863763742185816,
+      "grad_norm": 22.767345565284042,
+      "learning_rate": 2.3831417624521072e-07,
+      "logits/chosen": 0.14228317141532898,
+      "logits/rejected": 0.21690289676189423,
+      "logps/chosen": -224.71209716796875,
+      "logps/rejected": -243.876953125,
+      "loss": 0.4685,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -1.2229084968566895,
+      "rewards/margins": 1.051608920097351,
+      "rewards/rejected": -2.27451753616333,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7932744125889201,
+      "grad_norm": 27.34667176932844,
+      "learning_rate": 2.3065134099616856e-07,
+      "logits/chosen": 0.07832491397857666,
+      "logits/rejected": 0.1705821305513382,
+      "logps/chosen": -221.5072784423828,
+      "logps/rejected": -246.1153564453125,
+      "loss": 0.4579,
+      "rewards/accuracies": 0.7984375357627869,
+      "rewards/chosen": -1.1345467567443848,
+      "rewards/margins": 1.146794319152832,
+      "rewards/rejected": -2.281341075897217,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8001724509592585,
+      "grad_norm": 23.770336500523456,
+      "learning_rate": 2.2298850574712643e-07,
+      "logits/chosen": 0.14851118624210358,
+      "logits/rejected": 0.18459179997444153,
+      "logps/chosen": -216.7705535888672,
+      "logps/rejected": -236.89364624023438,
+      "loss": 0.4805,
+      "rewards/accuracies": 0.7578125,
+      "rewards/chosen": -1.1201305389404297,
+      "rewards/margins": 1.0015616416931152,
+      "rewards/rejected": -2.121692180633545,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8070704893295969,
+      "grad_norm": 30.260951075153393,
+      "learning_rate": 2.1532567049808428e-07,
+      "logits/chosen": 0.2019878774881363,
+      "logits/rejected": 0.1767769604921341,
+      "logps/chosen": -209.51361083984375,
+      "logps/rejected": -239.5547332763672,
+      "loss": 0.4705,
+      "rewards/accuracies": 0.778124988079071,
+      "rewards/chosen": -1.2167738676071167,
+      "rewards/margins": 1.0992836952209473,
+      "rewards/rejected": -2.3160576820373535,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8139685276999353,
+      "grad_norm": 27.377397146898016,
+      "learning_rate": 2.0766283524904212e-07,
+      "logits/chosen": 0.1637146770954132,
+      "logits/rejected": 0.18806767463684082,
+      "logps/chosen": -216.56570434570312,
+      "logps/rejected": -240.6849822998047,
+      "loss": 0.4357,
+      "rewards/accuracies": 0.7984375357627869,
+      "rewards/chosen": -1.123631238937378,
+      "rewards/margins": 1.1824723482131958,
+      "rewards/rejected": -2.3061037063598633,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8208665660702738,
+      "grad_norm": 25.354240699491303,
+      "learning_rate": 2e-07,
+      "logits/chosen": 0.14868010580539703,
+      "logits/rejected": 0.14347989857196808,
+      "logps/chosen": -225.78515625,
+      "logps/rejected": -256.4184875488281,
+      "loss": 0.4544,
+      "rewards/accuracies": 0.8109375238418579,
+      "rewards/chosen": -1.2112679481506348,
+      "rewards/margins": 1.1206707954406738,
+      "rewards/rejected": -2.3319387435913086,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8277646044406122,
+      "grad_norm": 20.190249426572805,
+      "learning_rate": 1.9233716475095783e-07,
+      "logits/chosen": 0.17432813346385956,
+      "logits/rejected": 0.19997775554656982,
+      "logps/chosen": -214.68603515625,
+      "logps/rejected": -242.19955444335938,
+      "loss": 0.4769,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -1.2452560663223267,
+      "rewards/margins": 1.1149595975875854,
+      "rewards/rejected": -2.360215663909912,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8346626428109506,
+      "grad_norm": 22.228370921152507,
+      "learning_rate": 1.846743295019157e-07,
+      "logits/chosen": 0.12424763292074203,
+      "logits/rejected": 0.19307748973369598,
+      "logps/chosen": -219.47999572753906,
+      "logps/rejected": -244.67124938964844,
+      "loss": 0.4646,
+      "rewards/accuracies": 0.7437500357627869,
+      "rewards/chosen": -1.2520346641540527,
+      "rewards/margins": 1.1548492908477783,
+      "rewards/rejected": -2.406883955001831,
+      "step": 1210
+    },
+    {
+      "epoch": 0.841560681181289,
+      "grad_norm": 25.41931454357561,
+      "learning_rate": 1.7701149425287357e-07,
+      "logits/chosen": 0.12825195491313934,
+      "logits/rejected": 0.17117546498775482,
+      "logps/chosen": -213.5985870361328,
+      "logps/rejected": -235.36941528320312,
+      "loss": 0.4633,
+      "rewards/accuracies": 0.7984375357627869,
+      "rewards/chosen": -1.148476243019104,
+      "rewards/margins": 1.119852066040039,
+      "rewards/rejected": -2.2683281898498535,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8484587195516275,
+      "grad_norm": 30.167829998794836,
+      "learning_rate": 1.6934865900383142e-07,
+      "logits/chosen": 0.19128039479255676,
+      "logits/rejected": 0.2100141942501068,
+      "logps/chosen": -222.0583953857422,
+      "logps/rejected": -245.87979125976562,
+      "loss": 0.4738,
+      "rewards/accuracies": 0.7687499523162842,
+      "rewards/chosen": -1.3405332565307617,
+      "rewards/margins": 1.0950267314910889,
+      "rewards/rejected": -2.4355597496032715,
+      "step": 1230
+    },
+    {
+      "epoch": 0.855356757921966,
+      "grad_norm": 26.728879899623912,
+      "learning_rate": 1.6168582375478926e-07,
+      "logits/chosen": 0.12200842052698135,
+      "logits/rejected": 0.17066144943237305,
+      "logps/chosen": -214.36114501953125,
+      "logps/rejected": -235.70079040527344,
+      "loss": 0.4701,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -1.2356151342391968,
+      "rewards/margins": 1.0795714855194092,
+      "rewards/rejected": -2.3151865005493164,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8622547962923044,
+      "grad_norm": 25.162229685459597,
+      "learning_rate": 1.5402298850574713e-07,
+      "logits/chosen": 0.13873139023780823,
+      "logits/rejected": 0.19574517011642456,
+      "logps/chosen": -217.75022888183594,
+      "logps/rejected": -240.75650024414062,
+      "loss": 0.4404,
+      "rewards/accuracies": 0.7859375476837158,
+      "rewards/chosen": -1.2010749578475952,
+      "rewards/margins": 1.2063066959381104,
+      "rewards/rejected": -2.407381534576416,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8691528346626428,
+      "grad_norm": 23.666288426380707,
+      "learning_rate": 1.4636015325670498e-07,
+      "logits/chosen": 0.11364492774009705,
+      "logits/rejected": 0.1443002074956894,
+      "logps/chosen": -219.42230224609375,
+      "logps/rejected": -244.23477172851562,
+      "loss": 0.4612,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.271179437637329,
+      "rewards/margins": 1.1596243381500244,
+      "rewards/rejected": -2.4308037757873535,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8760508730329812,
+      "grad_norm": 21.869263002803784,
+      "learning_rate": 1.3869731800766282e-07,
+      "logits/chosen": 0.14046192169189453,
+      "logits/rejected": 0.17701970040798187,
+      "logps/chosen": -217.38250732421875,
+      "logps/rejected": -240.967529296875,
+      "loss": 0.4529,
+      "rewards/accuracies": 0.796875,
+      "rewards/chosen": -1.199389934539795,
+      "rewards/margins": 1.158388376235962,
+      "rewards/rejected": -2.357778549194336,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8829489114033197,
+      "grad_norm": 23.643447697873064,
+      "learning_rate": 1.310344827586207e-07,
+      "logits/chosen": 0.12723781168460846,
+      "logits/rejected": 0.19653302431106567,
+      "logps/chosen": -215.25897216796875,
+      "logps/rejected": -236.8069305419922,
+      "loss": 0.4947,
+      "rewards/accuracies": 0.7828125357627869,
+      "rewards/chosen": -1.253035306930542,
+      "rewards/margins": 1.1224628686904907,
+      "rewards/rejected": -2.3754982948303223,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8898469497736581,
+      "grad_norm": 25.274424651570303,
+      "learning_rate": 1.2337164750957853e-07,
+      "logits/chosen": 0.18923957645893097,
+      "logits/rejected": 0.18438169360160828,
+      "logps/chosen": -214.2564239501953,
+      "logps/rejected": -239.39871215820312,
+      "loss": 0.4644,
+      "rewards/accuracies": 0.796875,
+      "rewards/chosen": -1.2227095365524292,
+      "rewards/margins": 1.1552302837371826,
+      "rewards/rejected": -2.3779397010803223,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8967449881439965,
+      "grad_norm": 22.069123537359786,
+      "learning_rate": 1.1570881226053639e-07,
+      "logits/chosen": 0.08069028705358505,
+      "logits/rejected": 0.2447403222322464,
+      "logps/chosen": -219.84442138671875,
+      "logps/rejected": -241.29461669921875,
+      "loss": 0.4417,
+      "rewards/accuracies": 0.792187511920929,
+      "rewards/chosen": -1.110395908355713,
+      "rewards/margins": 1.2345901727676392,
+      "rewards/rejected": -2.3449859619140625,
+      "step": 1300
+    },
+    {
+      "epoch": 0.903643026514335,
+      "grad_norm": 21.99285086423841,
+      "learning_rate": 1.0804597701149425e-07,
+      "logits/chosen": 0.12903529405593872,
+      "logits/rejected": 0.15087783336639404,
+      "logps/chosen": -215.73480224609375,
+      "logps/rejected": -239.2603759765625,
+      "loss": 0.4529,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -1.2006369829177856,
+      "rewards/margins": 1.1153340339660645,
+      "rewards/rejected": -2.3159708976745605,
+      "step": 1310
+    },
+    {
+      "epoch": 0.9105410648846735,
+      "grad_norm": 20.312748964979473,
+      "learning_rate": 1.003831417624521e-07,
+      "logits/chosen": 0.11999164521694183,
+      "logits/rejected": 0.1974225789308548,
+      "logps/chosen": -216.77389526367188,
+      "logps/rejected": -237.3870391845703,
+      "loss": 0.4465,
+      "rewards/accuracies": 0.7906249761581421,
+      "rewards/chosen": -1.1557135581970215,
+      "rewards/margins": 1.1768665313720703,
+      "rewards/rejected": -2.332580089569092,
+      "step": 1320
+    },
+    {
+      "epoch": 0.9174391032550119,
+      "grad_norm": 25.30850934446684,
+      "learning_rate": 9.272030651340995e-08,
+      "logits/chosen": 0.14219430088996887,
+      "logits/rejected": 0.18175333738327026,
+      "logps/chosen": -215.50270080566406,
+      "logps/rejected": -235.79623413085938,
+      "loss": 0.5007,
+      "rewards/accuracies": 0.7593750357627869,
+      "rewards/chosen": -1.278659701347351,
+      "rewards/margins": 0.9686375260353088,
+      "rewards/rejected": -2.2472972869873047,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9243371416253503,
+      "grad_norm": 23.186087599735348,
+      "learning_rate": 8.505747126436782e-08,
+      "logits/chosen": 0.11075228452682495,
+      "logits/rejected": 0.20603428781032562,
+      "logps/chosen": -210.88516235351562,
+      "logps/rejected": -240.35678100585938,
+      "loss": 0.4432,
+      "rewards/accuracies": 0.7828124761581421,
+      "rewards/chosen": -1.1982022523880005,
+      "rewards/margins": 1.176865577697754,
+      "rewards/rejected": -2.375067949295044,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9312351799956887,
+      "grad_norm": 26.236430191442004,
+      "learning_rate": 7.739463601532567e-08,
+      "logits/chosen": 0.14156416058540344,
+      "logits/rejected": 0.2178121656179428,
+      "logps/chosen": -214.24050903320312,
+      "logps/rejected": -235.45953369140625,
+      "loss": 0.496,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -1.298641562461853,
+      "rewards/margins": 1.0931938886642456,
+      "rewards/rejected": -2.3918354511260986,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9381332183660271,
+      "grad_norm": 26.761777481619593,
+      "learning_rate": 6.973180076628352e-08,
+      "logits/chosen": 0.09703594446182251,
+      "logits/rejected": 0.19476377964019775,
+      "logps/chosen": -221.1289520263672,
+      "logps/rejected": -242.93923950195312,
+      "loss": 0.4914,
+      "rewards/accuracies": 0.7593749761581421,
+      "rewards/chosen": -1.2596949338912964,
+      "rewards/margins": 1.0118179321289062,
+      "rewards/rejected": -2.271512985229492,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9450312567363656,
+      "grad_norm": 23.607901076870643,
+      "learning_rate": 6.206896551724137e-08,
+      "logits/chosen": 0.05706113576889038,
+      "logits/rejected": 0.20017537474632263,
+      "logps/chosen": -214.57180786132812,
+      "logps/rejected": -240.35067749023438,
+      "loss": 0.4409,
+      "rewards/accuracies": 0.815625011920929,
+      "rewards/chosen": -1.1195130348205566,
+      "rewards/margins": 1.2302576303482056,
+      "rewards/rejected": -2.3497705459594727,
+      "step": 1370
+    },
+    {
+      "epoch": 0.951929295106704,
+      "grad_norm": 20.38307949461832,
+      "learning_rate": 5.440613026819923e-08,
+      "logits/chosen": 0.09781169891357422,
+      "logits/rejected": 0.11969345808029175,
+      "logps/chosen": -221.07252502441406,
+      "logps/rejected": -245.23606872558594,
+      "loss": 0.4695,
+      "rewards/accuracies": 0.7796875238418579,
+      "rewards/chosen": -1.2874337434768677,
+      "rewards/margins": 1.1202243566513062,
+      "rewards/rejected": -2.407658100128174,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9588273334770425,
+      "grad_norm": 25.47882209795097,
+      "learning_rate": 4.674329501915709e-08,
+      "logits/chosen": 0.08676274120807648,
+      "logits/rejected": 0.19397087395191193,
+      "logps/chosen": -214.9215087890625,
+      "logps/rejected": -236.62606811523438,
+      "loss": 0.4592,
+      "rewards/accuracies": 0.7999999523162842,
+      "rewards/chosen": -1.2205379009246826,
+      "rewards/margins": 1.0657426118850708,
+      "rewards/rejected": -2.286280632019043,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9657253718473809,
+      "grad_norm": 22.952653079541584,
+      "learning_rate": 3.908045977011494e-08,
+      "logits/chosen": 0.1025160402059555,
+      "logits/rejected": 0.142715722322464,
+      "logps/chosen": -218.51333618164062,
+      "logps/rejected": -243.1075439453125,
+      "loss": 0.4819,
+      "rewards/accuracies": 0.7718749642372131,
+      "rewards/chosen": -1.2564886808395386,
+      "rewards/margins": 1.0429816246032715,
+      "rewards/rejected": -2.2994704246520996,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9726234102177194,
+      "grad_norm": 20.867881946381864,
+      "learning_rate": 3.1417624521072795e-08,
+      "logits/chosen": 0.05843396484851837,
+      "logits/rejected": 0.12826119363307953,
+      "logps/chosen": -217.50735473632812,
+      "logps/rejected": -244.44912719726562,
+      "loss": 0.4469,
+      "rewards/accuracies": 0.8203125,
+      "rewards/chosen": -1.1856391429901123,
+      "rewards/margins": 1.1579524278640747,
+      "rewards/rejected": -2.3435914516448975,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9795214485880578,
+      "grad_norm": 23.82920991184487,
+      "learning_rate": 2.375478927203065e-08,
+      "logits/chosen": 0.1010110154747963,
+      "logits/rejected": 0.09921743720769882,
+      "logps/chosen": -219.37962341308594,
+      "logps/rejected": -246.5306396484375,
+      "loss": 0.4339,
+      "rewards/accuracies": 0.7921875715255737,
+      "rewards/chosen": -1.140840768814087,
+      "rewards/margins": 1.2549952268600464,
+      "rewards/rejected": -2.395836353302002,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9864194869583962,
+      "grad_norm": 24.317865057607765,
+      "learning_rate": 1.6091954022988505e-08,
+      "logits/chosen": 0.11954033374786377,
+      "logits/rejected": 0.16331204771995544,
+      "logps/chosen": -205.85574340820312,
+      "logps/rejected": -231.82656860351562,
+      "loss": 0.4703,
+      "rewards/accuracies": 0.7953125238418579,
+      "rewards/chosen": -1.1854947805404663,
+      "rewards/margins": 1.10270094871521,
+      "rewards/rejected": -2.2881956100463867,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9933175253287346,
+      "grad_norm": 31.018823587254435,
+      "learning_rate": 8.429118773946359e-09,
+      "logits/chosen": 0.10009612143039703,
+      "logits/rejected": 0.17402292788028717,
+      "logps/chosen": -214.16224670410156,
+      "logps/rejected": -239.9188232421875,
+      "loss": 0.4753,
+      "rewards/accuracies": 0.7593750357627869,
+      "rewards/chosen": -1.2428853511810303,
+      "rewards/margins": 1.140334129333496,
+      "rewards/rejected": -2.3832194805145264,
+      "step": 1440
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 23.50715246309972,
+      "learning_rate": 7.662835249042145e-10,
+      "logits/chosen": 0.0691741406917572,
+      "logits/rejected": 0.1229172945022583,
+      "logps/chosen": -216.78927612304688,
+      "logps/rejected": -239.19741821289062,
+      "loss": 0.4402,
+      "rewards/accuracies": 0.7774193286895752,
+      "rewards/chosen": -1.1669424772262573,
+      "rewards/margins": 1.1343679428100586,
+      "rewards/rejected": -2.3013103008270264,
+      "step": 1450
+    },
+    {
+      "epoch": 1.0,
+      "step": 1450,
+      "total_flos": 160003043033088.0,
+      "train_loss": 0.538088473287122,
+      "train_runtime": 14420.7196,
+      "train_samples_per_second": 6.434,
+      "train_steps_per_second": 0.101
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1450,
+  "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": 160003043033088.0,
+  "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 sha256:40241b1160d2ec9ecf5d9f38878b1cd32b946c2a2d458c4571941761fbc2ff78
+size 7544