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: davidanugraha/Qwen3-4B-Concise-SimPO-StrategyB-Stage1
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: concise_phase2_short_qwen3_4b_config1_new
+  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. -->
+
+# concise_phase2_short_qwen3_4b_config1_new
+
+This model is a fine-tuned version of [davidanugraha/Qwen3-4B-Concise-SimPO-StrategyB-Stage1](https://huggingface.co/davidanugraha/Qwen3-4B-Concise-SimPO-StrategyB-Stage1) on the dpo_concise_phase2_short 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: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1
+- Datasets 3.6.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 44833908572160.0,
+    "train_loss": 0.9574610433157753,
+    "train_runtime": 3050.2608,
+    "train_samples_per_second": 2.849,
+    "train_steps_per_second": 0.045
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f9e02b6844e86d9bf2897f244cf0f7838636b5063ea03a9cd9221091211092
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fca0d52800ac075944f4858b6159a7f2852807778b0dd28de257b0b7c78b8b
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 44833908572160.0,
+    "train_loss": 0.9574610433157753,
+    "train_runtime": 3050.2608,
+    "train_samples_per_second": 2.849,
+    "train_steps_per_second": 0.045
+}

trainer_log.jsonl

@@ -0,0 +1,137 @@
+{"current_steps": 1, "total_steps": 136, "loss": 1.0051, "accuracy": 0.4375, "lr": 0.0, "epoch": 0.014719411223551058, "percentage": 0.74, "elapsed_time": "0:00:27", "remaining_time": "1:02:57"}
+{"current_steps": 2, "total_steps": 136, "loss": 1.0176, "accuracy": 0.359375, "lr": 7.142857142857142e-08, "epoch": 0.029438822447102116, "percentage": 1.47, "elapsed_time": "0:00:52", "remaining_time": "0:58:56"}
+{"current_steps": 3, "total_steps": 136, "loss": 0.9677, "accuracy": 0.4375, "lr": 1.4285714285714285e-07, "epoch": 0.04415823367065318, "percentage": 2.21, "elapsed_time": "0:01:15", "remaining_time": "0:55:49"}
+{"current_steps": 4, "total_steps": 136, "loss": 1.0147, "accuracy": 0.5, "lr": 2.1428571428571426e-07, "epoch": 0.05887764489420423, "percentage": 2.94, "elapsed_time": "0:01:37", "remaining_time": "0:53:43"}
+{"current_steps": 5, "total_steps": 136, "loss": 1.0084, "accuracy": 0.453125, "lr": 2.857142857142857e-07, "epoch": 0.07359705611775529, "percentage": 3.68, "elapsed_time": "0:01:59", "remaining_time": "0:52:19"}
+{"current_steps": 6, "total_steps": 136, "loss": 1.0025, "accuracy": 0.359375, "lr": 3.5714285714285716e-07, "epoch": 0.08831646734130635, "percentage": 4.41, "elapsed_time": "0:02:22", "remaining_time": "0:51:27"}
+{"current_steps": 7, "total_steps": 136, "loss": 1.0125, "accuracy": 0.453125, "lr": 4.285714285714285e-07, "epoch": 0.10303587856485741, "percentage": 5.15, "elapsed_time": "0:02:44", "remaining_time": "0:50:31"}
+{"current_steps": 8, "total_steps": 136, "loss": 0.9824, "accuracy": 0.421875, "lr": 5e-07, "epoch": 0.11775528978840846, "percentage": 5.88, "elapsed_time": "0:03:06", "remaining_time": "0:49:49"}
+{"current_steps": 9, "total_steps": 136, "loss": 0.9864, "accuracy": 0.40625, "lr": 5.714285714285714e-07, "epoch": 0.13247470101195952, "percentage": 6.62, "elapsed_time": "0:03:27", "remaining_time": "0:48:51"}
+{"current_steps": 10, "total_steps": 136, "loss": 0.9971, "accuracy": 0.46875, "lr": 6.428571428571429e-07, "epoch": 0.14719411223551057, "percentage": 7.35, "elapsed_time": "0:03:49", "remaining_time": "0:48:11"}
+{"current_steps": 11, "total_steps": 136, "loss": 1.0003, "accuracy": 0.453125, "lr": 7.142857142857143e-07, "epoch": 0.16191352345906163, "percentage": 8.09, "elapsed_time": "0:04:10", "remaining_time": "0:47:21"}
+{"current_steps": 12, "total_steps": 136, "loss": 1.0228, "accuracy": 0.390625, "lr": 7.857142857142856e-07, "epoch": 0.1766329346826127, "percentage": 8.82, "elapsed_time": "0:04:32", "remaining_time": "0:47:00"}
+{"current_steps": 13, "total_steps": 136, "loss": 1.0224, "accuracy": 0.4375, "lr": 8.57142857142857e-07, "epoch": 0.19135234590616376, "percentage": 9.56, "elapsed_time": "0:04:56", "remaining_time": "0:46:47"}
+{"current_steps": 14, "total_steps": 136, "loss": 1.0276, "accuracy": 0.28125, "lr": 9.285714285714285e-07, "epoch": 0.20607175712971482, "percentage": 10.29, "elapsed_time": "0:05:17", "remaining_time": "0:46:04"}
+{"current_steps": 15, "total_steps": 136, "loss": 1.0038, "accuracy": 0.375, "lr": 1e-06, "epoch": 0.22079116835326587, "percentage": 11.03, "elapsed_time": "0:05:38", "remaining_time": "0:45:31"}
+{"current_steps": 16, "total_steps": 136, "loss": 0.9802, "accuracy": 0.59375, "lr": 9.918032786885245e-07, "epoch": 0.23551057957681693, "percentage": 11.76, "elapsed_time": "0:06:00", "remaining_time": "0:45:03"}
+{"current_steps": 17, "total_steps": 136, "loss": 1.0029, "accuracy": 0.546875, "lr": 9.83606557377049e-07, "epoch": 0.250229990800368, "percentage": 12.5, "elapsed_time": "0:06:23", "remaining_time": "0:44:43"}
+{"current_steps": 18, "total_steps": 136, "loss": 1.0136, "accuracy": 0.453125, "lr": 9.754098360655736e-07, "epoch": 0.26494940202391903, "percentage": 13.24, "elapsed_time": "0:06:46", "remaining_time": "0:44:25"}
+{"current_steps": 19, "total_steps": 136, "loss": 0.9901, "accuracy": 0.40625, "lr": 9.672131147540984e-07, "epoch": 0.2796688132474701, "percentage": 13.97, "elapsed_time": "0:07:08", "remaining_time": "0:43:59"}
+{"current_steps": 20, "total_steps": 136, "loss": 0.9931, "accuracy": 0.484375, "lr": 9.59016393442623e-07, "epoch": 0.29438822447102114, "percentage": 14.71, "elapsed_time": "0:07:30", "remaining_time": "0:43:31"}
+{"current_steps": 21, "total_steps": 136, "loss": 0.9931, "accuracy": 0.453125, "lr": 9.508196721311474e-07, "epoch": 0.3091076356945722, "percentage": 15.44, "elapsed_time": "0:07:51", "remaining_time": "0:43:00"}
+{"current_steps": 22, "total_steps": 136, "loss": 1.0038, "accuracy": 0.421875, "lr": 9.426229508196721e-07, "epoch": 0.32382704691812325, "percentage": 16.18, "elapsed_time": "0:08:11", "remaining_time": "0:42:29"}
+{"current_steps": 23, "total_steps": 136, "loss": 0.9865, "accuracy": 0.484375, "lr": 9.344262295081968e-07, "epoch": 0.33854645814167433, "percentage": 16.91, "elapsed_time": "0:08:33", "remaining_time": "0:42:02"}
+{"current_steps": 24, "total_steps": 136, "loss": 0.9727, "accuracy": 0.53125, "lr": 9.262295081967213e-07, "epoch": 0.3532658693652254, "percentage": 17.65, "elapsed_time": "0:08:54", "remaining_time": "0:41:36"}
+{"current_steps": 25, "total_steps": 136, "loss": 1.0008, "accuracy": 0.4375, "lr": 9.180327868852458e-07, "epoch": 0.36798528058877644, "percentage": 18.38, "elapsed_time": "0:09:18", "remaining_time": "0:41:17"}
+{"current_steps": 26, "total_steps": 136, "loss": 0.9675, "accuracy": 0.421875, "lr": 9.098360655737705e-07, "epoch": 0.3827046918123275, "percentage": 19.12, "elapsed_time": "0:09:41", "remaining_time": "0:40:58"}
+{"current_steps": 27, "total_steps": 136, "loss": 0.9707, "accuracy": 0.515625, "lr": 9.01639344262295e-07, "epoch": 0.39742410303587855, "percentage": 19.85, "elapsed_time": "0:10:04", "remaining_time": "0:40:38"}
+{"current_steps": 28, "total_steps": 136, "loss": 0.9673, "accuracy": 0.5625, "lr": 8.934426229508196e-07, "epoch": 0.41214351425942963, "percentage": 20.59, "elapsed_time": "0:10:26", "remaining_time": "0:40:15"}
+{"current_steps": 29, "total_steps": 136, "loss": 0.9737, "accuracy": 0.53125, "lr": 8.852459016393443e-07, "epoch": 0.42686292548298066, "percentage": 21.32, "elapsed_time": "0:10:48", "remaining_time": "0:39:54"}
+{"current_steps": 30, "total_steps": 136, "loss": 0.9833, "accuracy": 0.515625, "lr": 8.770491803278688e-07, "epoch": 0.44158233670653174, "percentage": 22.06, "elapsed_time": "0:11:10", "remaining_time": "0:39:29"}
+{"current_steps": 31, "total_steps": 136, "loss": 0.9906, "accuracy": 0.46875, "lr": 8.688524590163933e-07, "epoch": 0.4563017479300828, "percentage": 22.79, "elapsed_time": "0:11:31", "remaining_time": "0:39:02"}
+{"current_steps": 32, "total_steps": 136, "loss": 0.9748, "accuracy": 0.453125, "lr": 8.60655737704918e-07, "epoch": 0.47102115915363385, "percentage": 23.53, "elapsed_time": "0:11:53", "remaining_time": "0:38:38"}
+{"current_steps": 33, "total_steps": 136, "loss": 0.9736, "accuracy": 0.53125, "lr": 8.524590163934425e-07, "epoch": 0.48574057037718493, "percentage": 24.26, "elapsed_time": "0:12:15", "remaining_time": "0:38:16"}
+{"current_steps": 34, "total_steps": 136, "loss": 0.9562, "accuracy": 0.5625, "lr": 8.442622950819672e-07, "epoch": 0.500459981600736, "percentage": 25.0, "elapsed_time": "0:12:38", "remaining_time": "0:37:54"}
+{"current_steps": 35, "total_steps": 136, "loss": 0.965, "accuracy": 0.625, "lr": 8.360655737704919e-07, "epoch": 0.515179392824287, "percentage": 25.74, "elapsed_time": "0:13:00", "remaining_time": "0:37:32"}
+{"current_steps": 36, "total_steps": 136, "loss": 0.9815, "accuracy": 0.453125, "lr": 8.278688524590164e-07, "epoch": 0.5298988040478381, "percentage": 26.47, "elapsed_time": "0:13:22", "remaining_time": "0:37:08"}
+{"current_steps": 37, "total_steps": 136, "loss": 0.9836, "accuracy": 0.453125, "lr": 8.196721311475409e-07, "epoch": 0.5446182152713891, "percentage": 27.21, "elapsed_time": "0:13:45", "remaining_time": "0:36:47"}
+{"current_steps": 38, "total_steps": 136, "loss": 0.9685, "accuracy": 0.515625, "lr": 8.114754098360656e-07, "epoch": 0.5593376264949402, "percentage": 27.94, "elapsed_time": "0:14:06", "remaining_time": "0:36:22"}
+{"current_steps": 39, "total_steps": 136, "loss": 0.9656, "accuracy": 0.53125, "lr": 8.032786885245901e-07, "epoch": 0.5740570377184913, "percentage": 28.68, "elapsed_time": "0:14:28", "remaining_time": "0:36:00"}
+{"current_steps": 40, "total_steps": 136, "loss": 0.9814, "accuracy": 0.46875, "lr": 7.950819672131147e-07, "epoch": 0.5887764489420423, "percentage": 29.41, "elapsed_time": "0:14:49", "remaining_time": "0:35:33"}
+{"current_steps": 41, "total_steps": 136, "loss": 1.008, "accuracy": 0.40625, "lr": 7.868852459016393e-07, "epoch": 0.6034958601655934, "percentage": 30.15, "elapsed_time": "0:15:12", "remaining_time": "0:35:15"}
+{"current_steps": 42, "total_steps": 136, "loss": 0.9866, "accuracy": 0.484375, "lr": 7.786885245901639e-07, "epoch": 0.6182152713891444, "percentage": 30.88, "elapsed_time": "0:15:35", "remaining_time": "0:34:54"}
+{"current_steps": 43, "total_steps": 136, "loss": 0.9796, "accuracy": 0.484375, "lr": 7.704918032786884e-07, "epoch": 0.6329346826126955, "percentage": 31.62, "elapsed_time": "0:15:57", "remaining_time": "0:34:30"}
+{"current_steps": 44, "total_steps": 136, "loss": 1.001, "accuracy": 0.4375, "lr": 7.62295081967213e-07, "epoch": 0.6476540938362465, "percentage": 32.35, "elapsed_time": "0:16:19", "remaining_time": "0:34:07"}
+{"current_steps": 45, "total_steps": 136, "loss": 0.9713, "accuracy": 0.5, "lr": 7.540983606557376e-07, "epoch": 0.6623735050597976, "percentage": 33.09, "elapsed_time": "0:16:40", "remaining_time": "0:33:43"}
+{"current_steps": 46, "total_steps": 136, "loss": 0.9792, "accuracy": 0.546875, "lr": 7.459016393442623e-07, "epoch": 0.6770929162833487, "percentage": 33.82, "elapsed_time": "0:17:05", "remaining_time": "0:33:26"}
+{"current_steps": 47, "total_steps": 136, "loss": 0.9677, "accuracy": 0.59375, "lr": 7.377049180327869e-07, "epoch": 0.6918123275068997, "percentage": 34.56, "elapsed_time": "0:17:27", "remaining_time": "0:33:03"}
+{"current_steps": 48, "total_steps": 136, "loss": 0.9541, "accuracy": 0.640625, "lr": 7.295081967213115e-07, "epoch": 0.7065317387304508, "percentage": 35.29, "elapsed_time": "0:17:47", "remaining_time": "0:32:36"}
+{"current_steps": 49, "total_steps": 136, "loss": 0.9716, "accuracy": 0.53125, "lr": 7.21311475409836e-07, "epoch": 0.7212511499540019, "percentage": 36.03, "elapsed_time": "0:18:07", "remaining_time": "0:32:10"}
+{"current_steps": 50, "total_steps": 136, "loss": 0.9855, "accuracy": 0.484375, "lr": 7.131147540983606e-07, "epoch": 0.7359705611775529, "percentage": 36.76, "elapsed_time": "0:18:28", "remaining_time": "0:31:45"}
+{"current_steps": 51, "total_steps": 136, "loss": 0.9597, "accuracy": 0.5625, "lr": 7.049180327868852e-07, "epoch": 0.7506899724011039, "percentage": 37.5, "elapsed_time": "0:18:51", "remaining_time": "0:31:26"}
+{"current_steps": 52, "total_steps": 136, "loss": 0.9818, "accuracy": 0.59375, "lr": 6.967213114754098e-07, "epoch": 0.765409383624655, "percentage": 38.24, "elapsed_time": "0:19:12", "remaining_time": "0:31:01"}
+{"current_steps": 53, "total_steps": 136, "loss": 0.9674, "accuracy": 0.53125, "lr": 6.885245901639343e-07, "epoch": 0.7801287948482061, "percentage": 38.97, "elapsed_time": "0:19:33", "remaining_time": "0:30:38"}
+{"current_steps": 54, "total_steps": 136, "loss": 0.9664, "accuracy": 0.640625, "lr": 6.80327868852459e-07, "epoch": 0.7948482060717571, "percentage": 39.71, "elapsed_time": "0:19:55", "remaining_time": "0:30:15"}
+{"current_steps": 55, "total_steps": 136, "loss": 0.9809, "accuracy": 0.484375, "lr": 6.721311475409835e-07, "epoch": 0.8095676172953082, "percentage": 40.44, "elapsed_time": "0:20:17", "remaining_time": "0:29:52"}
+{"current_steps": 56, "total_steps": 136, "loss": 0.9797, "accuracy": 0.484375, "lr": 6.639344262295081e-07, "epoch": 0.8242870285188593, "percentage": 41.18, "elapsed_time": "0:20:40", "remaining_time": "0:29:31"}
+{"current_steps": 57, "total_steps": 136, "loss": 0.9571, "accuracy": 0.640625, "lr": 6.557377049180327e-07, "epoch": 0.8390064397424103, "percentage": 41.91, "elapsed_time": "0:21:01", "remaining_time": "0:29:07"}
+{"current_steps": 58, "total_steps": 136, "loss": 0.9727, "accuracy": 0.59375, "lr": 6.475409836065574e-07, "epoch": 0.8537258509659613, "percentage": 42.65, "elapsed_time": "0:21:22", "remaining_time": "0:28:44"}
+{"current_steps": 59, "total_steps": 136, "loss": 0.9387, "accuracy": 0.703125, "lr": 6.393442622950819e-07, "epoch": 0.8684452621895125, "percentage": 43.38, "elapsed_time": "0:21:45", "remaining_time": "0:28:23"}
+{"current_steps": 60, "total_steps": 136, "loss": 0.9652, "accuracy": 0.59375, "lr": 6.311475409836066e-07, "epoch": 0.8831646734130635, "percentage": 44.12, "elapsed_time": "0:22:06", "remaining_time": "0:27:59"}
+{"current_steps": 61, "total_steps": 136, "loss": 0.9577, "accuracy": 0.546875, "lr": 6.229508196721311e-07, "epoch": 0.8978840846366145, "percentage": 44.85, "elapsed_time": "0:22:28", "remaining_time": "0:27:38"}
+{"current_steps": 62, "total_steps": 136, "loss": 0.9812, "accuracy": 0.5625, "lr": 6.147540983606557e-07, "epoch": 0.9126034958601656, "percentage": 45.59, "elapsed_time": "0:22:50", "remaining_time": "0:27:16"}
+{"current_steps": 63, "total_steps": 136, "loss": 0.9831, "accuracy": 0.484375, "lr": 6.065573770491803e-07, "epoch": 0.9273229070837167, "percentage": 46.32, "elapsed_time": "0:23:12", "remaining_time": "0:26:53"}
+{"current_steps": 64, "total_steps": 136, "loss": 0.9533, "accuracy": 0.609375, "lr": 5.983606557377049e-07, "epoch": 0.9420423183072677, "percentage": 47.06, "elapsed_time": "0:23:34", "remaining_time": "0:26:30"}
+{"current_steps": 65, "total_steps": 136, "loss": 0.9704, "accuracy": 0.546875, "lr": 5.901639344262294e-07, "epoch": 0.9567617295308187, "percentage": 47.79, "elapsed_time": "0:23:57", "remaining_time": "0:26:10"}
+{"current_steps": 66, "total_steps": 136, "loss": 0.9792, "accuracy": 0.546875, "lr": 5.819672131147541e-07, "epoch": 0.9714811407543699, "percentage": 48.53, "elapsed_time": "0:24:20", "remaining_time": "0:25:48"}
+{"current_steps": 67, "total_steps": 136, "loss": 0.9682, "accuracy": 0.5625, "lr": 5.737704918032786e-07, "epoch": 0.9862005519779209, "percentage": 49.26, "elapsed_time": "0:24:43", "remaining_time": "0:25:27"}
+{"current_steps": 68, "total_steps": 136, "loss": 0.9114, "accuracy": 0.5500000715255737, "lr": 5.655737704918032e-07, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:25:03", "remaining_time": "0:25:03"}
+{"current_steps": 69, "total_steps": 136, "loss": 0.9459, "accuracy": 0.671875, "lr": 5.573770491803278e-07, "epoch": 1.0147194112235511, "percentage": 50.74, "elapsed_time": "0:25:56", "remaining_time": "0:25:11"}
+{"current_steps": 70, "total_steps": 136, "loss": 0.9474, "accuracy": 0.671875, "lr": 5.491803278688525e-07, "epoch": 1.029438822447102, "percentage": 51.47, "elapsed_time": "0:26:21", "remaining_time": "0:24:50"}
+{"current_steps": 71, "total_steps": 136, "loss": 0.9301, "accuracy": 0.640625, "lr": 5.40983606557377e-07, "epoch": 1.0441582336706532, "percentage": 52.21, "elapsed_time": "0:26:42", "remaining_time": "0:24:27"}
+{"current_steps": 72, "total_steps": 136, "loss": 0.9439, "accuracy": 0.671875, "lr": 5.327868852459017e-07, "epoch": 1.0588776448942043, "percentage": 52.94, "elapsed_time": "0:27:04", "remaining_time": "0:24:03"}
+{"current_steps": 73, "total_steps": 136, "loss": 0.9606, "accuracy": 0.609375, "lr": 5.245901639344262e-07, "epoch": 1.0735970561177552, "percentage": 53.68, "elapsed_time": "0:27:25", "remaining_time": "0:23:40"}
+{"current_steps": 74, "total_steps": 136, "loss": 0.9235, "accuracy": 0.71875, "lr": 5.163934426229508e-07, "epoch": 1.0883164673413064, "percentage": 54.41, "elapsed_time": "0:27:48", "remaining_time": "0:23:17"}
+{"current_steps": 75, "total_steps": 136, "loss": 0.9365, "accuracy": 0.71875, "lr": 5.081967213114754e-07, "epoch": 1.1030358785648575, "percentage": 55.15, "elapsed_time": "0:28:11", "remaining_time": "0:22:55"}
+{"current_steps": 76, "total_steps": 136, "loss": 0.9397, "accuracy": 0.671875, "lr": 5e-07, "epoch": 1.1177552897884084, "percentage": 55.88, "elapsed_time": "0:28:32", "remaining_time": "0:22:31"}
+{"current_steps": 77, "total_steps": 136, "loss": 0.9284, "accuracy": 0.625, "lr": 4.918032786885245e-07, "epoch": 1.1324747010119596, "percentage": 56.62, "elapsed_time": "0:28:55", "remaining_time": "0:22:09"}
+{"current_steps": 78, "total_steps": 136, "loss": 0.9395, "accuracy": 0.671875, "lr": 4.836065573770492e-07, "epoch": 1.1471941122355105, "percentage": 57.35, "elapsed_time": "0:29:18", "remaining_time": "0:21:47"}
+{"current_steps": 79, "total_steps": 136, "loss": 0.9467, "accuracy": 0.734375, "lr": 4.754098360655737e-07, "epoch": 1.1619135234590616, "percentage": 58.09, "elapsed_time": "0:29:40", "remaining_time": "0:21:24"}
+{"current_steps": 80, "total_steps": 136, "loss": 0.9517, "accuracy": 0.640625, "lr": 4.672131147540984e-07, "epoch": 1.1766329346826128, "percentage": 58.82, "elapsed_time": "0:30:01", "remaining_time": "0:21:00"}
+{"current_steps": 81, "total_steps": 136, "loss": 0.9425, "accuracy": 0.65625, "lr": 4.590163934426229e-07, "epoch": 1.1913523459061637, "percentage": 59.56, "elapsed_time": "0:30:23", "remaining_time": "0:20:37"}
+{"current_steps": 82, "total_steps": 136, "loss": 0.9242, "accuracy": 0.703125, "lr": 4.508196721311475e-07, "epoch": 1.2060717571297148, "percentage": 60.29, "elapsed_time": "0:30:44", "remaining_time": "0:20:14"}
+{"current_steps": 83, "total_steps": 136, "loss": 0.9412, "accuracy": 0.671875, "lr": 4.426229508196721e-07, "epoch": 1.220791168353266, "percentage": 61.03, "elapsed_time": "0:31:06", "remaining_time": "0:19:51"}
+{"current_steps": 84, "total_steps": 136, "loss": 0.9396, "accuracy": 0.703125, "lr": 4.3442622950819667e-07, "epoch": 1.2355105795768169, "percentage": 61.76, "elapsed_time": "0:31:27", "remaining_time": "0:19:28"}
+{"current_steps": 85, "total_steps": 136, "loss": 0.9275, "accuracy": 0.734375, "lr": 4.2622950819672127e-07, "epoch": 1.250229990800368, "percentage": 62.5, "elapsed_time": "0:31:47", "remaining_time": "0:19:04"}
+{"current_steps": 86, "total_steps": 136, "loss": 0.9368, "accuracy": 0.671875, "lr": 4.180327868852459e-07, "epoch": 1.2649494020239191, "percentage": 63.24, "elapsed_time": "0:32:10", "remaining_time": "0:18:42"}
+{"current_steps": 87, "total_steps": 136, "loss": 0.9295, "accuracy": 0.6875, "lr": 4.0983606557377047e-07, "epoch": 1.27966881324747, "percentage": 63.97, "elapsed_time": "0:32:36", "remaining_time": "0:18:21"}
+{"current_steps": 88, "total_steps": 136, "loss": 0.9317, "accuracy": 0.75, "lr": 4.0163934426229507e-07, "epoch": 1.2943882244710212, "percentage": 64.71, "elapsed_time": "0:32:58", "remaining_time": "0:17:59"}
+{"current_steps": 89, "total_steps": 136, "loss": 0.9391, "accuracy": 0.609375, "lr": 3.9344262295081967e-07, "epoch": 1.3091076356945721, "percentage": 65.44, "elapsed_time": "0:33:19", "remaining_time": "0:17:35"}
+{"current_steps": 90, "total_steps": 136, "loss": 0.9191, "accuracy": 0.765625, "lr": 3.852459016393442e-07, "epoch": 1.3238270469181233, "percentage": 66.18, "elapsed_time": "0:33:41", "remaining_time": "0:17:13"}
+{"current_steps": 91, "total_steps": 136, "loss": 0.9424, "accuracy": 0.609375, "lr": 3.770491803278688e-07, "epoch": 1.3385464581416744, "percentage": 66.91, "elapsed_time": "0:34:02", "remaining_time": "0:16:50"}
+{"current_steps": 92, "total_steps": 136, "loss": 0.941, "accuracy": 0.640625, "lr": 3.6885245901639347e-07, "epoch": 1.3532658693652255, "percentage": 67.65, "elapsed_time": "0:34:23", "remaining_time": "0:16:26"}
+{"current_steps": 93, "total_steps": 136, "loss": 0.9469, "accuracy": 0.625, "lr": 3.60655737704918e-07, "epoch": 1.3679852805887764, "percentage": 68.38, "elapsed_time": "0:34:44", "remaining_time": "0:16:03"}
+{"current_steps": 94, "total_steps": 136, "loss": 0.9317, "accuracy": 0.6875, "lr": 3.524590163934426e-07, "epoch": 1.3827046918123276, "percentage": 69.12, "elapsed_time": "0:35:07", "remaining_time": "0:15:41"}
+{"current_steps": 95, "total_steps": 136, "loss": 0.9165, "accuracy": 0.78125, "lr": 3.4426229508196717e-07, "epoch": 1.3974241030358785, "percentage": 69.85, "elapsed_time": "0:35:28", "remaining_time": "0:15:18"}
+{"current_steps": 96, "total_steps": 136, "loss": 0.9495, "accuracy": 0.609375, "lr": 3.3606557377049177e-07, "epoch": 1.4121435142594296, "percentage": 70.59, "elapsed_time": "0:35:48", "remaining_time": "0:14:55"}
+{"current_steps": 97, "total_steps": 136, "loss": 0.9238, "accuracy": 0.71875, "lr": 3.2786885245901637e-07, "epoch": 1.4268629254829808, "percentage": 71.32, "elapsed_time": "0:36:10", "remaining_time": "0:14:32"}
+{"current_steps": 98, "total_steps": 136, "loss": 0.9244, "accuracy": 0.671875, "lr": 3.1967213114754097e-07, "epoch": 1.4415823367065317, "percentage": 72.06, "elapsed_time": "0:36:31", "remaining_time": "0:14:09"}
+{"current_steps": 99, "total_steps": 136, "loss": 0.9296, "accuracy": 0.734375, "lr": 3.1147540983606557e-07, "epoch": 1.4563017479300828, "percentage": 72.79, "elapsed_time": "0:36:51", "remaining_time": "0:13:46"}
+{"current_steps": 100, "total_steps": 136, "loss": 0.9216, "accuracy": 0.703125, "lr": 3.0327868852459017e-07, "epoch": 1.4710211591536337, "percentage": 73.53, "elapsed_time": "0:37:13", "remaining_time": "0:13:23"}
+{"current_steps": 101, "total_steps": 136, "loss": 0.9231, "accuracy": 0.6875, "lr": 2.950819672131147e-07, "epoch": 1.4857405703771849, "percentage": 74.26, "elapsed_time": "0:37:32", "remaining_time": "0:13:00"}
+{"current_steps": 102, "total_steps": 136, "loss": 0.929, "accuracy": 0.65625, "lr": 2.868852459016393e-07, "epoch": 1.500459981600736, "percentage": 75.0, "elapsed_time": "0:37:55", "remaining_time": "0:12:38"}
+{"current_steps": 103, "total_steps": 136, "loss": 0.9235, "accuracy": 0.640625, "lr": 2.786885245901639e-07, "epoch": 1.5151793928242872, "percentage": 75.74, "elapsed_time": "0:38:16", "remaining_time": "0:12:15"}
+{"current_steps": 104, "total_steps": 136, "loss": 0.9457, "accuracy": 0.703125, "lr": 2.704918032786885e-07, "epoch": 1.529898804047838, "percentage": 76.47, "elapsed_time": "0:38:39", "remaining_time": "0:11:53"}
+{"current_steps": 105, "total_steps": 136, "loss": 0.9303, "accuracy": 0.71875, "lr": 2.622950819672131e-07, "epoch": 1.544618215271389, "percentage": 77.21, "elapsed_time": "0:39:02", "remaining_time": "0:11:31"}
+{"current_steps": 106, "total_steps": 136, "loss": 0.9302, "accuracy": 0.765625, "lr": 2.540983606557377e-07, "epoch": 1.5593376264949401, "percentage": 77.94, "elapsed_time": "0:39:25", "remaining_time": "0:11:09"}
+{"current_steps": 107, "total_steps": 136, "loss": 0.9072, "accuracy": 0.765625, "lr": 2.4590163934426226e-07, "epoch": 1.5740570377184913, "percentage": 78.68, "elapsed_time": "0:39:48", "remaining_time": "0:10:47"}
+{"current_steps": 108, "total_steps": 136, "loss": 0.938, "accuracy": 0.640625, "lr": 2.3770491803278686e-07, "epoch": 1.5887764489420424, "percentage": 79.41, "elapsed_time": "0:40:10", "remaining_time": "0:10:25"}
+{"current_steps": 109, "total_steps": 136, "loss": 0.9233, "accuracy": 0.671875, "lr": 2.2950819672131146e-07, "epoch": 1.6034958601655935, "percentage": 80.15, "elapsed_time": "0:40:33", "remaining_time": "0:10:02"}
+{"current_steps": 110, "total_steps": 136, "loss": 0.9516, "accuracy": 0.625, "lr": 2.2131147540983606e-07, "epoch": 1.6182152713891444, "percentage": 80.88, "elapsed_time": "0:40:56", "remaining_time": "0:09:40"}
+{"current_steps": 111, "total_steps": 136, "loss": 0.944, "accuracy": 0.609375, "lr": 2.1311475409836064e-07, "epoch": 1.6329346826126954, "percentage": 81.62, "elapsed_time": "0:41:18", "remaining_time": "0:09:18"}
+{"current_steps": 112, "total_steps": 136, "loss": 0.9439, "accuracy": 0.59375, "lr": 2.0491803278688524e-07, "epoch": 1.6476540938362465, "percentage": 82.35, "elapsed_time": "0:41:39", "remaining_time": "0:08:55"}
+{"current_steps": 113, "total_steps": 136, "loss": 0.9404, "accuracy": 0.5625, "lr": 1.9672131147540984e-07, "epoch": 1.6623735050597976, "percentage": 83.09, "elapsed_time": "0:42:00", "remaining_time": "0:08:33"}
+{"current_steps": 114, "total_steps": 136, "loss": 0.9139, "accuracy": 0.6875, "lr": 1.885245901639344e-07, "epoch": 1.6770929162833488, "percentage": 83.82, "elapsed_time": "0:42:21", "remaining_time": "0:08:10"}
+{"current_steps": 115, "total_steps": 136, "loss": 0.9206, "accuracy": 0.671875, "lr": 1.80327868852459e-07, "epoch": 1.6918123275068997, "percentage": 84.56, "elapsed_time": "0:42:44", "remaining_time": "0:07:48"}
+{"current_steps": 116, "total_steps": 136, "loss": 0.9386, "accuracy": 0.609375, "lr": 1.7213114754098358e-07, "epoch": 1.7065317387304508, "percentage": 85.29, "elapsed_time": "0:43:05", "remaining_time": "0:07:25"}
+{"current_steps": 117, "total_steps": 136, "loss": 0.9326, "accuracy": 0.765625, "lr": 1.6393442622950818e-07, "epoch": 1.7212511499540017, "percentage": 86.03, "elapsed_time": "0:43:27", "remaining_time": "0:07:03"}
+{"current_steps": 118, "total_steps": 136, "loss": 0.9374, "accuracy": 0.640625, "lr": 1.5573770491803278e-07, "epoch": 1.7359705611775529, "percentage": 86.76, "elapsed_time": "0:43:48", "remaining_time": "0:06:40"}
+{"current_steps": 119, "total_steps": 136, "loss": 0.9186, "accuracy": 0.6875, "lr": 1.4754098360655736e-07, "epoch": 1.750689972401104, "percentage": 87.5, "elapsed_time": "0:44:11", "remaining_time": "0:06:18"}
+{"current_steps": 120, "total_steps": 136, "loss": 0.9394, "accuracy": 0.734375, "lr": 1.3934426229508196e-07, "epoch": 1.7654093836246552, "percentage": 88.24, "elapsed_time": "0:44:34", "remaining_time": "0:05:56"}
+{"current_steps": 121, "total_steps": 136, "loss": 0.9452, "accuracy": 0.484375, "lr": 1.3114754098360656e-07, "epoch": 1.780128794848206, "percentage": 88.97, "elapsed_time": "0:44:56", "remaining_time": "0:05:34"}
+{"current_steps": 122, "total_steps": 136, "loss": 0.9323, "accuracy": 0.671875, "lr": 1.2295081967213113e-07, "epoch": 1.794848206071757, "percentage": 89.71, "elapsed_time": "0:45:17", "remaining_time": "0:05:11"}
+{"current_steps": 123, "total_steps": 136, "loss": 0.9348, "accuracy": 0.703125, "lr": 1.1475409836065573e-07, "epoch": 1.8095676172953081, "percentage": 90.44, "elapsed_time": "0:45:38", "remaining_time": "0:04:49"}
+{"current_steps": 124, "total_steps": 136, "loss": 0.9163, "accuracy": 0.65625, "lr": 1.0655737704918032e-07, "epoch": 1.8242870285188593, "percentage": 91.18, "elapsed_time": "0:46:00", "remaining_time": "0:04:27"}
+{"current_steps": 125, "total_steps": 136, "loss": 0.941, "accuracy": 0.703125, "lr": 9.836065573770492e-08, "epoch": 1.8390064397424104, "percentage": 91.91, "elapsed_time": "0:46:22", "remaining_time": "0:04:04"}
+{"current_steps": 126, "total_steps": 136, "loss": 0.9525, "accuracy": 0.59375, "lr": 9.01639344262295e-08, "epoch": 1.8537258509659613, "percentage": 92.65, "elapsed_time": "0:46:44", "remaining_time": "0:03:42"}
+{"current_steps": 127, "total_steps": 136, "loss": 0.9356, "accuracy": 0.65625, "lr": 8.196721311475409e-08, "epoch": 1.8684452621895125, "percentage": 93.38, "elapsed_time": "0:47:06", "remaining_time": "0:03:20"}
+{"current_steps": 128, "total_steps": 136, "loss": 0.9164, "accuracy": 0.71875, "lr": 7.377049180327868e-08, "epoch": 1.8831646734130634, "percentage": 94.12, "elapsed_time": "0:47:26", "remaining_time": "0:02:57"}
+{"current_steps": 129, "total_steps": 136, "loss": 0.9298, "accuracy": 0.6875, "lr": 6.557377049180328e-08, "epoch": 1.8978840846366145, "percentage": 94.85, "elapsed_time": "0:47:47", "remaining_time": "0:02:35"}
+{"current_steps": 130, "total_steps": 136, "loss": 0.9354, "accuracy": 0.59375, "lr": 5.7377049180327866e-08, "epoch": 1.9126034958601656, "percentage": 95.59, "elapsed_time": "0:48:08", "remaining_time": "0:02:13"}
+{"current_steps": 131, "total_steps": 136, "loss": 0.9359, "accuracy": 0.703125, "lr": 4.918032786885246e-08, "epoch": 1.9273229070837168, "percentage": 96.32, "elapsed_time": "0:48:30", "remaining_time": "0:01:51"}
+{"current_steps": 132, "total_steps": 136, "loss": 0.9253, "accuracy": 0.65625, "lr": 4.0983606557377046e-08, "epoch": 1.9420423183072677, "percentage": 97.06, "elapsed_time": "0:48:52", "remaining_time": "0:01:28"}
+{"current_steps": 133, "total_steps": 136, "loss": 0.9188, "accuracy": 0.765625, "lr": 3.278688524590164e-08, "epoch": 1.9567617295308186, "percentage": 97.79, "elapsed_time": "0:49:14", "remaining_time": "0:01:06"}
+{"current_steps": 134, "total_steps": 136, "loss": 0.9204, "accuracy": 0.765625, "lr": 2.459016393442623e-08, "epoch": 1.9714811407543698, "percentage": 98.53, "elapsed_time": "0:49:38", "remaining_time": "0:00:44"}
+{"current_steps": 135, "total_steps": 136, "loss": 0.9194, "accuracy": 0.765625, "lr": 1.639344262295082e-08, "epoch": 1.986200551977921, "percentage": 99.26, "elapsed_time": "0:50:00", "remaining_time": "0:00:22"}
+{"current_steps": 136, "total_steps": 136, "loss": 0.8813, "accuracy": 0.6166666746139526, "lr": 8.19672131147541e-09, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:50:20", "remaining_time": "0:00:00"}
+{"current_steps": 136, "total_steps": 136, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:50:50", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2083 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 136,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014719411223551058,
+      "grad_norm": 10.21645450592041,
+      "learning_rate": 0.0,
+      "logits/chosen": -3.0194568634033203,
+      "logits/rejected": -2.950680732727051,
+      "logps/chosen": -0.45742279291152954,
+      "logps/rejected": -0.4388114809989929,
+      "loss": 1.0051,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.9148455858230591,
+      "rewards/margins": -0.03722264617681503,
+      "rewards/rejected": -0.8776229619979858,
+      "step": 1
+    },
+    {
+      "epoch": 0.029438822447102116,
+      "grad_norm": 9.920907020568848,
+      "learning_rate": 7.142857142857142e-08,
+      "logits/chosen": -3.3881869316101074,
+      "logits/rejected": -3.4658308029174805,
+      "logps/chosen": -0.4393010139465332,
+      "logps/rejected": -0.40908509492874146,
+      "loss": 1.0176,
+      "rewards/accuracies": 0.359375,
+      "rewards/chosen": -0.8786020278930664,
+      "rewards/margins": -0.06043180450797081,
+      "rewards/rejected": -0.8181700706481934,
+      "step": 2
+    },
+    {
+      "epoch": 0.04415823367065318,
+      "grad_norm": 9.453459739685059,
+      "learning_rate": 1.4285714285714285e-07,
+      "logits/chosen": -3.019883155822754,
+      "logits/rejected": -3.200739860534668,
+      "logps/chosen": -0.41646909713745117,
+      "logps/rejected": -0.4280118942260742,
+      "loss": 0.9677,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.8329381942749023,
+      "rewards/margins": 0.0230855755507946,
+      "rewards/rejected": -0.8560237884521484,
+      "step": 3
+    },
+    {
+      "epoch": 0.05887764489420423,
+      "grad_norm": 10.635061264038086,
+      "learning_rate": 2.1428571428571426e-07,
+      "logits/chosen": -2.7175631523132324,
+      "logits/rejected": -2.886113166809082,
+      "logps/chosen": -0.4779108166694641,
+      "logps/rejected": -0.45090264081954956,
+      "loss": 1.0147,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.9558216333389282,
+      "rewards/margins": -0.054016292095184326,
+      "rewards/rejected": -0.9018052816390991,
+      "step": 4
+    },
+    {
+      "epoch": 0.07359705611775529,
+      "grad_norm": 10.923693656921387,
+      "learning_rate": 2.857142857142857e-07,
+      "logits/chosen": -2.7420175075531006,
+      "logits/rejected": -2.9430060386657715,
+      "logps/chosen": -0.4806134104728699,
+      "logps/rejected": -0.4588547945022583,
+      "loss": 1.0084,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.9612268209457397,
+      "rewards/margins": -0.04351712763309479,
+      "rewards/rejected": -0.9177095890045166,
+      "step": 5
+    },
+    {
+      "epoch": 0.08831646734130635,
+      "grad_norm": 10.25864028930664,
+      "learning_rate": 3.5714285714285716e-07,
+      "logits/chosen": -2.754415273666382,
+      "logits/rejected": -3.0695841312408447,
+      "logps/chosen": -0.46477335691452026,
+      "logps/rejected": -0.44464749097824097,
+      "loss": 1.0025,
+      "rewards/accuracies": 0.359375,
+      "rewards/chosen": -0.9295467138290405,
+      "rewards/margins": -0.04025167599320412,
+      "rewards/rejected": -0.8892950415611267,
+      "step": 6
+    },
+    {
+      "epoch": 0.10303587856485741,
+      "grad_norm": 11.24145793914795,
+      "learning_rate": 4.285714285714285e-07,
+      "logits/chosen": -2.9528307914733887,
+      "logits/rejected": -3.126439094543457,
+      "logps/chosen": -0.4697887897491455,
+      "logps/rejected": -0.4457703232765198,
+      "loss": 1.0125,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.9395775198936462,
+      "rewards/margins": -0.048036910593509674,
+      "rewards/rejected": -0.8915406465530396,
+      "step": 7
+    },
+    {
+      "epoch": 0.11775528978840846,
+      "grad_norm": 9.375962257385254,
+      "learning_rate": 5e-07,
+      "logits/chosen": -3.262545585632324,
+      "logits/rejected": -3.296149969100952,
+      "logps/chosen": -0.43063342571258545,
+      "logps/rejected": -0.4382564425468445,
+      "loss": 0.9824,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.8612668514251709,
+      "rewards/margins": 0.015246011316776276,
+      "rewards/rejected": -0.876512885093689,
+      "step": 8
+    },
+    {
+      "epoch": 0.13247470101195952,
+      "grad_norm": 10.173127174377441,
+      "learning_rate": 5.714285714285714e-07,
+      "logits/chosen": -2.697115898132324,
+      "logits/rejected": -3.103816509246826,
+      "logps/chosen": -0.4361271262168884,
+      "logps/rejected": -0.43252134323120117,
+      "loss": 0.9864,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.8722542524337769,
+      "rewards/margins": -0.007211566902697086,
+      "rewards/rejected": -0.8650426864624023,
+      "step": 9
+    },
+    {
+      "epoch": 0.14719411223551057,
+      "grad_norm": 9.083308219909668,
+      "learning_rate": 6.428571428571429e-07,
+      "logits/chosen": -3.46915864944458,
+      "logits/rejected": -3.5064210891723633,
+      "logps/chosen": -0.41334497928619385,
+      "logps/rejected": -0.4007585346698761,
+      "loss": 0.9971,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.8266898393630981,
+      "rewards/margins": -0.02517283335328102,
+      "rewards/rejected": -0.8015170097351074,
+      "step": 10
+    },
+    {
+      "epoch": 0.16191352345906163,
+      "grad_norm": 10.834942817687988,
+      "learning_rate": 7.142857142857143e-07,
+      "logits/chosen": -2.949937343597412,
+      "logits/rejected": -2.860502243041992,
+      "logps/chosen": -0.4562839865684509,
+      "logps/rejected": -0.4406251907348633,
+      "loss": 1.0003,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.9125679731369019,
+      "rewards/margins": -0.031317513436079025,
+      "rewards/rejected": -0.8812504410743713,
+      "step": 11
+    },
+    {
+      "epoch": 0.1766329346826127,
+      "grad_norm": 11.5885591506958,
+      "learning_rate": 7.857142857142856e-07,
+      "logits/chosen": -2.7742319107055664,
+      "logits/rejected": -2.8857803344726562,
+      "logps/chosen": -0.4672906696796417,
+      "logps/rejected": -0.434725821018219,
+      "loss": 1.0228,
+      "rewards/accuracies": 0.390625,
+      "rewards/chosen": -0.9345813393592834,
+      "rewards/margins": -0.06512977182865143,
+      "rewards/rejected": -0.869451642036438,
+      "step": 12
+    },
+    {
+      "epoch": 0.19135234590616376,
+      "grad_norm": 11.761482238769531,
+      "learning_rate": 8.57142857142857e-07,
+      "logits/chosen": -3.4971909523010254,
+      "logits/rejected": -3.3080244064331055,
+      "logps/chosen": -0.43734604120254517,
+      "logps/rejected": -0.40988171100616455,
+      "loss": 1.0224,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.8746920824050903,
+      "rewards/margins": -0.05492864176630974,
+      "rewards/rejected": -0.8197634220123291,
+      "step": 13
+    },
+    {
+      "epoch": 0.20607175712971482,
+      "grad_norm": 11.107159614562988,
+      "learning_rate": 9.285714285714285e-07,
+      "logits/chosen": -3.167203426361084,
+      "logits/rejected": -2.89117431640625,
+      "logps/chosen": -0.447818398475647,
+      "logps/rejected": -0.40924957394599915,
+      "loss": 1.0276,
+      "rewards/accuracies": 0.28125,
+      "rewards/chosen": -0.895636796951294,
+      "rewards/margins": -0.07713763415813446,
+      "rewards/rejected": -0.8184992074966431,
+      "step": 14
+    },
+    {
+      "epoch": 0.22079116835326587,
+      "grad_norm": 10.545300483703613,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.7851405143737793,
+      "logits/rejected": -3.0399112701416016,
+      "logps/chosen": -0.457728773355484,
+      "logps/rejected": -0.43849730491638184,
+      "loss": 1.0038,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.915457546710968,
+      "rewards/margins": -0.038462862372398376,
+      "rewards/rejected": -0.8769946694374084,
+      "step": 15
+    },
+    {
+      "epoch": 0.23551057957681693,
+      "grad_norm": 10.076902389526367,
+      "learning_rate": 9.918032786885245e-07,
+      "logits/chosen": -2.3796284198760986,
+      "logits/rejected": -2.758613109588623,
+      "logps/chosen": -0.4450618028640747,
+      "logps/rejected": -0.4445981979370117,
+      "loss": 0.9802,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.8901236057281494,
+      "rewards/margins": -0.0009272526949644089,
+      "rewards/rejected": -0.8891963958740234,
+      "step": 16
+    },
+    {
+      "epoch": 0.250229990800368,
+      "grad_norm": 9.330389976501465,
+      "learning_rate": 9.83606557377049e-07,
+      "logits/chosen": -3.1862754821777344,
+      "logits/rejected": -3.2526628971099854,
+      "logps/chosen": -0.3827851116657257,
+      "logps/rejected": -0.36282622814178467,
+      "loss": 1.0029,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.7655701637268066,
+      "rewards/margins": -0.039917729794979095,
+      "rewards/rejected": -0.7256523966789246,
+      "step": 17
+    },
+    {
+      "epoch": 0.26494940202391903,
+      "grad_norm": 11.906604766845703,
+      "learning_rate": 9.754098360655736e-07,
+      "logits/chosen": -2.927328586578369,
+      "logits/rejected": -3.00978422164917,
+      "logps/chosen": -0.43598276376724243,
+      "logps/rejected": -0.4090351462364197,
+      "loss": 1.0136,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.8719655275344849,
+      "rewards/margins": -0.053895253688097,
+      "rewards/rejected": -0.8180702328681946,
+      "step": 18
+    },
+    {
+      "epoch": 0.2796688132474701,
+      "grad_norm": 9.152690887451172,
+      "learning_rate": 9.672131147540984e-07,
+      "logits/chosen": -2.607306718826294,
+      "logits/rejected": -2.6976051330566406,
+      "logps/chosen": -0.4554919898509979,
+      "logps/rejected": -0.4455527663230896,
+      "loss": 0.9901,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.9109839200973511,
+      "rewards/margins": -0.019878461956977844,
+      "rewards/rejected": -0.8911055326461792,
+      "step": 19
+    },
+    {
+      "epoch": 0.29438822447102114,
+      "grad_norm": 8.773446083068848,
+      "learning_rate": 9.59016393442623e-07,
+      "logits/chosen": -2.664100408554077,
+      "logits/rejected": -2.849198341369629,
+      "logps/chosen": -0.4018637239933014,
+      "logps/rejected": -0.3902263939380646,
+      "loss": 0.9931,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.8037275075912476,
+      "rewards/margins": -0.023274658247828484,
+      "rewards/rejected": -0.7804527282714844,
+      "step": 20
+    },
+    {
+      "epoch": 0.3091076356945722,
+      "grad_norm": 9.694635391235352,
+      "learning_rate": 9.508196721311474e-07,
+      "logits/chosen": -2.7708492279052734,
+      "logits/rejected": -2.630173683166504,
+      "logps/chosen": -0.44786471128463745,
+      "logps/rejected": -0.43551987409591675,
+      "loss": 0.9931,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.8957293629646301,
+      "rewards/margins": -0.024689704179763794,
+      "rewards/rejected": -0.8710396885871887,
+      "step": 21
+    },
+    {
+      "epoch": 0.32382704691812325,
+      "grad_norm": 8.240747451782227,
+      "learning_rate": 9.426229508196721e-07,
+      "logits/chosen": -3.098659038543701,
+      "logits/rejected": -3.123976230621338,
+      "logps/chosen": -0.38691607117652893,
+      "logps/rejected": -0.3664763569831848,
+      "loss": 1.0038,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.7738322019577026,
+      "rewards/margins": -0.040879447013139725,
+      "rewards/rejected": -0.7329527139663696,
+      "step": 22
+    },
+    {
+      "epoch": 0.33854645814167433,
+      "grad_norm": 8.561594009399414,
+      "learning_rate": 9.344262295081968e-07,
+      "logits/chosen": -2.6878695487976074,
+      "logits/rejected": -2.800431489944458,
+      "logps/chosen": -0.3922501802444458,
+      "logps/rejected": -0.38519686460494995,
+      "loss": 0.9865,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.7845003008842468,
+      "rewards/margins": -0.01410655677318573,
+      "rewards/rejected": -0.7703937888145447,
+      "step": 23
+    },
+    {
+      "epoch": 0.3532658693652254,
+      "grad_norm": 8.64904499053955,
+      "learning_rate": 9.262295081967213e-07,
+      "logits/chosen": -3.2959938049316406,
+      "logits/rejected": -3.0946803092956543,
+      "logps/chosen": -0.3919060230255127,
+      "logps/rejected": -0.39727240800857544,
+      "loss": 0.9727,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.7838120460510254,
+      "rewards/margins": 0.010732805356383324,
+      "rewards/rejected": -0.7945448160171509,
+      "step": 24
+    },
+    {
+      "epoch": 0.36798528058877644,
+      "grad_norm": 11.180377006530762,
+      "learning_rate": 9.180327868852458e-07,
+      "logits/chosen": -2.71470046043396,
+      "logits/rejected": -2.9183754920959473,
+      "logps/chosen": -0.35864555835723877,
+      "logps/rejected": -0.33973294496536255,
+      "loss": 1.0008,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.7172911167144775,
+      "rewards/margins": -0.03782520815730095,
+      "rewards/rejected": -0.6794658899307251,
+      "step": 25
+    },
+    {
+      "epoch": 0.3827046918123275,
+      "grad_norm": 7.819973468780518,
+      "learning_rate": 9.098360655737705e-07,
+      "logits/chosen": -3.1228315830230713,
+      "logits/rejected": -2.978816032409668,
+      "logps/chosen": -0.3795928955078125,
+      "logps/rejected": -0.38733017444610596,
+      "loss": 0.9675,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.759185791015625,
+      "rewards/margins": 0.015474595129489899,
+      "rewards/rejected": -0.7746603488922119,
+      "step": 26
+    },
+    {
+      "epoch": 0.39742410303587855,
+      "grad_norm": 8.191493034362793,
+      "learning_rate": 9.01639344262295e-07,
+      "logits/chosen": -2.4528238773345947,
+      "logits/rejected": -2.5398683547973633,
+      "logps/chosen": -0.40499553084373474,
+      "logps/rejected": -0.4100068509578705,
+      "loss": 0.9707,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8099910616874695,
+      "rewards/margins": 0.010022655129432678,
+      "rewards/rejected": -0.820013701915741,
+      "step": 27
+    },
+    {
+      "epoch": 0.41214351425942963,
+      "grad_norm": 7.093197345733643,
+      "learning_rate": 8.934426229508196e-07,
+      "logits/chosen": -2.4629902839660645,
+      "logits/rejected": -2.5782675743103027,
+      "logps/chosen": -0.3413301706314087,
+      "logps/rejected": -0.3495180010795593,
+      "loss": 0.9673,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.6826603412628174,
+      "rewards/margins": 0.016375690698623657,
+      "rewards/rejected": -0.6990360617637634,
+      "step": 28
+    },
+    {
+      "epoch": 0.42686292548298066,
+      "grad_norm": 7.324411869049072,
+      "learning_rate": 8.852459016393443e-07,
+      "logits/chosen": -2.8721837997436523,
+      "logits/rejected": -2.7182796001434326,
+      "logps/chosen": -0.3609670400619507,
+      "logps/rejected": -0.3633623719215393,
+      "loss": 0.9737,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.7219340801239014,
+      "rewards/margins": 0.004790660459548235,
+      "rewards/rejected": -0.7267247438430786,
+      "step": 29
+    },
+    {
+      "epoch": 0.44158233670653174,
+      "grad_norm": 6.33624267578125,
+      "learning_rate": 8.770491803278688e-07,
+      "logits/chosen": -2.2950024604797363,
+      "logits/rejected": -2.551114082336426,
+      "logps/chosen": -0.33408358693122864,
+      "logps/rejected": -0.3281135559082031,
+      "loss": 0.9833,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.6681671738624573,
+      "rewards/margins": -0.011940006166696548,
+      "rewards/rejected": -0.6562271118164062,
+      "step": 30
+    },
+    {
+      "epoch": 0.4563017479300828,
+      "grad_norm": 7.2210211753845215,
+      "learning_rate": 8.688524590163933e-07,
+      "logits/chosen": -2.146829605102539,
+      "logits/rejected": -2.417693614959717,
+      "logps/chosen": -0.36344075202941895,
+      "logps/rejected": -0.35178840160369873,
+      "loss": 0.9906,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.7268815040588379,
+      "rewards/margins": -0.023304661735892296,
+      "rewards/rejected": -0.7035768032073975,
+      "step": 31
+    },
+    {
+      "epoch": 0.47102115915363385,
+      "grad_norm": 6.0392303466796875,
+      "learning_rate": 8.60655737704918e-07,
+      "logits/chosen": -2.360600471496582,
+      "logits/rejected": -2.4811832904815674,
+      "logps/chosen": -0.3448009788990021,
+      "logps/rejected": -0.3456505537033081,
+      "loss": 0.9748,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.6896018981933594,
+      "rewards/margins": 0.0016991421580314636,
+      "rewards/rejected": -0.6913011074066162,
+      "step": 32
+    },
+    {
+      "epoch": 0.48574057037718493,
+      "grad_norm": 6.579920291900635,
+      "learning_rate": 8.524590163934425e-07,
+      "logits/chosen": -2.5944058895111084,
+      "logits/rejected": -2.590837240219116,
+      "logps/chosen": -0.3355923593044281,
+      "logps/rejected": -0.3367539346218109,
+      "loss": 0.9736,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.6711846590042114,
+      "rewards/margins": 0.00232316879555583,
+      "rewards/rejected": -0.6735078692436218,
+      "step": 33
+    },
+    {
+      "epoch": 0.500459981600736,
+      "grad_norm": 5.514021873474121,
+      "learning_rate": 8.442622950819672e-07,
+      "logits/chosen": -2.2286832332611084,
+      "logits/rejected": -2.334184169769287,
+      "logps/chosen": -0.33515220880508423,
+      "logps/rejected": -0.3512744903564453,
+      "loss": 0.9562,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.6703044176101685,
+      "rewards/margins": 0.032244522124528885,
+      "rewards/rejected": -0.7025489807128906,
+      "step": 34
+    },
+    {
+      "epoch": 0.515179392824287,
+      "grad_norm": 5.068162441253662,
+      "learning_rate": 8.360655737704919e-07,
+      "logits/chosen": -1.8708163499832153,
+      "logits/rejected": -2.1949517726898193,
+      "logps/chosen": -0.319760799407959,
+      "logps/rejected": -0.32897067070007324,
+      "loss": 0.965,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.639521598815918,
+      "rewards/margins": 0.018419764935970306,
+      "rewards/rejected": -0.6579413414001465,
+      "step": 35
+    },
+    {
+      "epoch": 0.5298988040478381,
+      "grad_norm": 6.008891582489014,
+      "learning_rate": 8.278688524590164e-07,
+      "logits/chosen": -2.1621382236480713,
+      "logits/rejected": -2.482567310333252,
+      "logps/chosen": -0.32818323373794556,
+      "logps/rejected": -0.3238987326622009,
+      "loss": 0.9815,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.6563664674758911,
+      "rewards/margins": -0.008569043129682541,
+      "rewards/rejected": -0.6477974653244019,
+      "step": 36
+    },
+    {
+      "epoch": 0.5446182152713891,
+      "grad_norm": 5.96389627456665,
+      "learning_rate": 8.196721311475409e-07,
+      "logits/chosen": -1.713577389717102,
+      "logits/rejected": -2.0453085899353027,
+      "logps/chosen": -0.35343289375305176,
+      "logps/rejected": -0.3477077782154083,
+      "loss": 0.9836,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.7068657875061035,
+      "rewards/margins": -0.0114502664655447,
+      "rewards/rejected": -0.6954155564308167,
+      "step": 37
+    },
+    {
+      "epoch": 0.5593376264949402,
+      "grad_norm": 5.4984941482543945,
+      "learning_rate": 8.114754098360656e-07,
+      "logits/chosen": -2.169618606567383,
+      "logits/rejected": -2.206155776977539,
+      "logps/chosen": -0.3445884585380554,
+      "logps/rejected": -0.3500184118747711,
+      "loss": 0.9685,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.6891769170761108,
+      "rewards/margins": 0.010859915986657143,
+      "rewards/rejected": -0.7000367641448975,
+      "step": 38
+    },
+    {
+      "epoch": 0.5740570377184913,
+      "grad_norm": 5.409811973571777,
+      "learning_rate": 8.032786885245901e-07,
+      "logits/chosen": -2.129136562347412,
+      "logits/rejected": -2.266310214996338,
+      "logps/chosen": -0.32456666231155396,
+      "logps/rejected": -0.3323541283607483,
+      "loss": 0.9656,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.6491333246231079,
+      "rewards/margins": 0.015574917197227478,
+      "rewards/rejected": -0.6647082567214966,
+      "step": 39
+    },
+    {
+      "epoch": 0.5887764489420423,
+      "grad_norm": 6.400082588195801,
+      "learning_rate": 7.950819672131147e-07,
+      "logits/chosen": -2.295382261276245,
+      "logits/rejected": -2.189863443374634,
+      "logps/chosen": -0.3625165820121765,
+      "logps/rejected": -0.35861217975616455,
+      "loss": 0.9814,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.725033164024353,
+      "rewards/margins": -0.007808740250766277,
+      "rewards/rejected": -0.7172243595123291,
+      "step": 40
+    },
+    {
+      "epoch": 0.6034958601655934,
+      "grad_norm": 6.307469367980957,
+      "learning_rate": 7.868852459016393e-07,
+      "logits/chosen": -1.7075982093811035,
+      "logits/rejected": -1.929357886314392,
+      "logps/chosen": -0.3901516795158386,
+      "logps/rejected": -0.36571019887924194,
+      "loss": 1.008,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.7803032994270325,
+      "rewards/margins": -0.04888291284441948,
+      "rewards/rejected": -0.7314203977584839,
+      "step": 41
+    },
+    {
+      "epoch": 0.6182152713891444,
+      "grad_norm": 6.286430835723877,
+      "learning_rate": 7.786885245901639e-07,
+      "logits/chosen": -1.617011547088623,
+      "logits/rejected": -1.9047297239303589,
+      "logps/chosen": -0.3546293377876282,
+      "logps/rejected": -0.34627604484558105,
+      "loss": 0.9866,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.7092586755752563,
+      "rewards/margins": -0.01670663431286812,
+      "rewards/rejected": -0.6925520896911621,
+      "step": 42
+    },
+    {
+      "epoch": 0.6329346826126955,
+      "grad_norm": 6.484315872192383,
+      "learning_rate": 7.704918032786884e-07,
+      "logits/chosen": -1.8632745742797852,
+      "logits/rejected": -2.245807409286499,
+      "logps/chosen": -0.36142784357070923,
+      "logps/rejected": -0.3599178194999695,
+      "loss": 0.9796,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.7228556871414185,
+      "rewards/margins": -0.003020005766302347,
+      "rewards/rejected": -0.719835638999939,
+      "step": 43
+    },
+    {
+      "epoch": 0.6476540938362465,
+      "grad_norm": 7.016959190368652,
+      "learning_rate": 7.62295081967213e-07,
+      "logits/chosen": -1.63113534450531,
+      "logits/rejected": -2.070380926132202,
+      "logps/chosen": -0.35701748728752136,
+      "logps/rejected": -0.337637335062027,
+      "loss": 1.001,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.7140350341796875,
+      "rewards/margins": -0.03876036778092384,
+      "rewards/rejected": -0.6752746105194092,
+      "step": 44
+    },
+    {
+      "epoch": 0.6623735050597976,
+      "grad_norm": 6.19422721862793,
+      "learning_rate": 7.540983606557376e-07,
+      "logits/chosen": -2.178931713104248,
+      "logits/rejected": -2.422787666320801,
+      "logps/chosen": -0.3165867328643799,
+      "logps/rejected": -0.32036393880844116,
+      "loss": 0.9713,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.6331734657287598,
+      "rewards/margins": 0.007554395589977503,
+      "rewards/rejected": -0.6407278776168823,
+      "step": 45
+    },
+    {
+      "epoch": 0.6770929162833487,
+      "grad_norm": 5.218748092651367,
+      "learning_rate": 7.459016393442623e-07,
+      "logits/chosen": -2.395150661468506,
+      "logits/rejected": -2.530268907546997,
+      "logps/chosen": -0.32682573795318604,
+      "logps/rejected": -0.32383865118026733,
+      "loss": 0.9792,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.6536514163017273,
+      "rewards/margins": -0.005974169354885817,
+      "rewards/rejected": -0.6476773023605347,
+      "step": 46
+    },
+    {
+      "epoch": 0.6918123275068997,
+      "grad_norm": 4.995746612548828,
+      "learning_rate": 7.377049180327869e-07,
+      "logits/chosen": -2.11518931388855,
+      "logits/rejected": -2.542222738265991,
+      "logps/chosen": -0.31639549136161804,
+      "logps/rejected": -0.32215774059295654,
+      "loss": 0.9677,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.6327909827232361,
+      "rewards/margins": 0.011524486355483532,
+      "rewards/rejected": -0.6443154811859131,
+      "step": 47
+    },
+    {
+      "epoch": 0.7065317387304508,
+      "grad_norm": 8.630620956420898,
+      "learning_rate": 7.295081967213115e-07,
+      "logits/chosen": -2.2222516536712646,
+      "logits/rejected": -2.3696556091308594,
+      "logps/chosen": -0.33347755670547485,
+      "logps/rejected": -0.35106533765792847,
+      "loss": 0.9541,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.6669551134109497,
+      "rewards/margins": 0.03517553582787514,
+      "rewards/rejected": -0.7021306753158569,
+      "step": 48
+    },
+    {
+      "epoch": 0.7212511499540019,
+      "grad_norm": 6.239405155181885,
+      "learning_rate": 7.21311475409836e-07,
+      "logits/chosen": -2.3627071380615234,
+      "logits/rejected": -2.582144260406494,
+      "logps/chosen": -0.34942522644996643,
+      "logps/rejected": -0.3538520336151123,
+      "loss": 0.9716,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.6988504528999329,
+      "rewards/margins": 0.008853599429130554,
+      "rewards/rejected": -0.7077040672302246,
+      "step": 49
+    },
+    {
+      "epoch": 0.7359705611775529,
+      "grad_norm": 5.054786682128906,
+      "learning_rate": 7.131147540983606e-07,
+      "logits/chosen": -2.7542896270751953,
+      "logits/rejected": -2.8403894901275635,
+      "logps/chosen": -0.31503599882125854,
+      "logps/rejected": -0.3082734942436218,
+      "loss": 0.9855,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.6300719976425171,
+      "rewards/margins": -0.01352505013346672,
+      "rewards/rejected": -0.6165469884872437,
+      "step": 50
+    },
+    {
+      "epoch": 0.7506899724011039,
+      "grad_norm": 5.122381687164307,
+      "learning_rate": 7.049180327868852e-07,
+      "logits/chosen": -2.8105831146240234,
+      "logits/rejected": -2.856302499771118,
+      "logps/chosen": -0.32194629311561584,
+      "logps/rejected": -0.3357662558555603,
+      "loss": 0.9597,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.6438925862312317,
+      "rewards/margins": 0.027639910578727722,
+      "rewards/rejected": -0.6715325117111206,
+      "step": 51
+    },
+    {
+      "epoch": 0.765409383624655,
+      "grad_norm": 5.99705696105957,
+      "learning_rate": 6.967213114754098e-07,
+      "logits/chosen": -3.04000186920166,
+      "logits/rejected": -2.8034870624542236,
+      "logps/chosen": -0.33719968795776367,
+      "logps/rejected": -0.33283817768096924,
+      "loss": 0.9818,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.6743993759155273,
+      "rewards/margins": -0.008722986094653606,
+      "rewards/rejected": -0.6656763553619385,
+      "step": 52
+    },
+    {
+      "epoch": 0.7801287948482061,
+      "grad_norm": 4.380398273468018,
+      "learning_rate": 6.885245901639343e-07,
+      "logits/chosen": -3.1191301345825195,
+      "logits/rejected": -3.2772610187530518,
+      "logps/chosen": -0.2899811267852783,
+      "logps/rejected": -0.29639169573783875,
+      "loss": 0.9674,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.5799622535705566,
+      "rewards/margins": 0.012821085751056671,
+      "rewards/rejected": -0.5927833914756775,
+      "step": 53
+    },
+    {
+      "epoch": 0.7948482060717571,
+      "grad_norm": 6.095130920410156,
+      "learning_rate": 6.80327868852459e-07,
+      "logits/chosen": -2.5826096534729004,
+      "logits/rejected": -2.715819835662842,
+      "logps/chosen": -0.3463515341281891,
+      "logps/rejected": -0.35433435440063477,
+      "loss": 0.9664,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.692703127861023,
+      "rewards/margins": 0.01596560701727867,
+      "rewards/rejected": -0.7086687088012695,
+      "step": 54
+    },
+    {
+      "epoch": 0.8095676172953082,
+      "grad_norm": 5.1041951179504395,
+      "learning_rate": 6.721311475409835e-07,
+      "logits/chosen": -3.31288480758667,
+      "logits/rejected": -3.182924747467041,
+      "logps/chosen": -0.31364989280700684,
+      "logps/rejected": -0.3094671964645386,
+      "loss": 0.9809,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.6272997856140137,
+      "rewards/margins": -0.008365361019968987,
+      "rewards/rejected": -0.6189343929290771,
+      "step": 55
+    },
+    {
+      "epoch": 0.8242870285188593,
+      "grad_norm": 5.590980052947998,
+      "learning_rate": 6.639344262295081e-07,
+      "logits/chosen": -2.5883703231811523,
+      "logits/rejected": -2.679048538208008,
+      "logps/chosen": -0.3323555290699005,
+      "logps/rejected": -0.32933926582336426,
+      "loss": 0.9797,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.664711058139801,
+      "rewards/margins": -0.006032535340636969,
+      "rewards/rejected": -0.6586785316467285,
+      "step": 56
+    },
+    {
+      "epoch": 0.8390064397424103,
+      "grad_norm": 5.798619747161865,
+      "learning_rate": 6.557377049180327e-07,
+      "logits/chosen": -2.8983383178710938,
+      "logits/rejected": -3.162022113800049,
+      "logps/chosen": -0.3113633394241333,
+      "logps/rejected": -0.3264388144016266,
+      "loss": 0.9571,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.6227266788482666,
+      "rewards/margins": 0.030150914564728737,
+      "rewards/rejected": -0.6528776288032532,
+      "step": 57
+    },
+    {
+      "epoch": 0.8537258509659613,
+      "grad_norm": 6.8788862228393555,
+      "learning_rate": 6.475409836065574e-07,
+      "logits/chosen": -3.176103115081787,
+      "logits/rejected": -3.0832886695861816,
+      "logps/chosen": -0.3261672556400299,
+      "logps/rejected": -0.32974904775619507,
+      "loss": 0.9727,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.6523345708847046,
+      "rewards/margins": 0.0071635497733950615,
+      "rewards/rejected": -0.6594980955123901,
+      "step": 58
+    },
+    {
+      "epoch": 0.8684452621895125,
+      "grad_norm": 5.570962429046631,
+      "learning_rate": 6.393442622950819e-07,
+      "logits/chosen": -2.4592795372009277,
+      "logits/rejected": -2.800849437713623,
+      "logps/chosen": -0.3107580542564392,
+      "logps/rejected": -0.34081941843032837,
+      "loss": 0.9387,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.6215161085128784,
+      "rewards/margins": 0.060122713446617126,
+      "rewards/rejected": -0.681638777256012,
+      "step": 59
+    },
+    {
+      "epoch": 0.8831646734130635,
+      "grad_norm": 6.777514457702637,
+      "learning_rate": 6.311475409836066e-07,
+      "logits/chosen": -2.9372458457946777,
+      "logits/rejected": -3.095715045928955,
+      "logps/chosen": -0.330186128616333,
+      "logps/rejected": -0.3394075632095337,
+      "loss": 0.9652,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.660372257232666,
+      "rewards/margins": 0.01844284124672413,
+      "rewards/rejected": -0.6788151264190674,
+      "step": 60
+    },
+    {
+      "epoch": 0.8978840846366145,
+      "grad_norm": 6.811728477478027,
+      "learning_rate": 6.229508196721311e-07,
+      "logits/chosen": -3.002053737640381,
+      "logits/rejected": -3.0411558151245117,
+      "logps/chosen": -0.3336254358291626,
+      "logps/rejected": -0.34820815920829773,
+      "loss": 0.9577,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.6672508716583252,
+      "rewards/margins": 0.029165498912334442,
+      "rewards/rejected": -0.6964163184165955,
+      "step": 61
+    },
+    {
+      "epoch": 0.9126034958601656,
+      "grad_norm": 6.526244163513184,
+      "learning_rate": 6.147540983606557e-07,
+      "logits/chosen": -2.9746174812316895,
+      "logits/rejected": -3.024784564971924,
+      "logps/chosen": -0.3487308621406555,
+      "logps/rejected": -0.344043493270874,
+      "loss": 0.9812,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.697461724281311,
+      "rewards/margins": -0.009374706074595451,
+      "rewards/rejected": -0.688086986541748,
+      "step": 62
+    },
+    {
+      "epoch": 0.9273229070837167,
+      "grad_norm": 6.0199785232543945,
+      "learning_rate": 6.065573770491803e-07,
+      "logits/chosen": -3.471893548965454,
+      "logits/rejected": -3.154780864715576,
+      "logps/chosen": -0.3194906711578369,
+      "logps/rejected": -0.31385791301727295,
+      "loss": 0.9831,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.6389813423156738,
+      "rewards/margins": -0.011265482753515244,
+      "rewards/rejected": -0.6277158856391907,
+      "step": 63
+    },
+    {
+      "epoch": 0.9420423183072677,
+      "grad_norm": 5.7925262451171875,
+      "learning_rate": 5.983606557377049e-07,
+      "logits/chosen": -2.928650379180908,
+      "logits/rejected": -3.0489816665649414,
+      "logps/chosen": -0.3156253695487976,
+      "logps/rejected": -0.33363330364227295,
+      "loss": 0.9533,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.6312507390975952,
+      "rewards/margins": 0.0360158234834671,
+      "rewards/rejected": -0.6672665476799011,
+      "step": 64
+    },
+    {
+      "epoch": 0.9567617295308187,
+      "grad_norm": 5.304396152496338,
+      "learning_rate": 5.901639344262294e-07,
+      "logits/chosen": -2.7677812576293945,
+      "logits/rejected": -2.918884754180908,
+      "logps/chosen": -0.3248683512210846,
+      "logps/rejected": -0.3287356197834015,
+      "loss": 0.9704,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.6497367024421692,
+      "rewards/margins": 0.0077345771715044975,
+      "rewards/rejected": -0.6574712991714478,
+      "step": 65
+    },
+    {
+      "epoch": 0.9714811407543699,
+      "grad_norm": 6.466002464294434,
+      "learning_rate": 5.819672131147541e-07,
+      "logits/chosen": -2.5215635299682617,
+      "logits/rejected": -3.0989413261413574,
+      "logps/chosen": -0.34512242674827576,
+      "logps/rejected": -0.34232115745544434,
+      "loss": 0.9792,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.6902447938919067,
+      "rewards/margins": -0.00560246966779232,
+      "rewards/rejected": -0.6846423745155334,
+      "step": 66
+    },
+    {
+      "epoch": 0.9862005519779209,
+      "grad_norm": 5.751663684844971,
+      "learning_rate": 5.737704918032786e-07,
+      "logits/chosen": -2.967613697052002,
+      "logits/rejected": -3.0896427631378174,
+      "logps/chosen": -0.32376572489738464,
+      "logps/rejected": -0.3302830159664154,
+      "loss": 0.9682,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.6475313901901245,
+      "rewards/margins": 0.013034624047577381,
+      "rewards/rejected": -0.6605660319328308,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.688215732574463,
+      "learning_rate": 5.655737704918032e-07,
+      "logits/chosen": -2.593557119369507,
+      "logits/rejected": -2.572288990020752,
+      "logps/chosen": -0.35654735565185547,
+      "logps/rejected": -0.36155587434768677,
+      "loss": 0.9114,
+      "rewards/accuracies": 0.5500000715255737,
+      "rewards/chosen": -0.7130947113037109,
+      "rewards/margins": 0.010017056949436665,
+      "rewards/rejected": -0.7231118083000183,
+      "step": 68
+    },
+    {
+      "epoch": 1.0147194112235511,
+      "grad_norm": 5.89481782913208,
+      "learning_rate": 5.573770491803278e-07,
+      "logits/chosen": -2.667405605316162,
+      "logits/rejected": -2.9011430740356445,
+      "logps/chosen": -0.3504785895347595,
+      "logps/rejected": -0.3745538592338562,
+      "loss": 0.9459,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.700957179069519,
+      "rewards/margins": 0.048150498420000076,
+      "rewards/rejected": -0.7491077184677124,
+      "step": 69
+    },
+    {
+      "epoch": 1.029438822447102,
+      "grad_norm": 5.436809062957764,
+      "learning_rate": 5.491803278688525e-07,
+      "logits/chosen": -3.7802786827087402,
+      "logits/rejected": -3.2489778995513916,
+      "logps/chosen": -0.3161553144454956,
+      "logps/rejected": -0.3399825096130371,
+      "loss": 0.9474,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.6323106288909912,
+      "rewards/margins": 0.04765439033508301,
+      "rewards/rejected": -0.6799650192260742,
+      "step": 70
+    },
+    {
+      "epoch": 1.0441582336706532,
+      "grad_norm": 5.984342575073242,
+      "learning_rate": 5.40983606557377e-07,
+      "logits/chosen": -3.4014768600463867,
+      "logits/rejected": -3.056406021118164,
+      "logps/chosen": -0.3482527434825897,
+      "logps/rejected": -0.3865743577480316,
+      "loss": 0.9301,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.6965054273605347,
+      "rewards/margins": 0.07664325833320618,
+      "rewards/rejected": -0.7731487154960632,
+      "step": 71
+    },
+    {
+      "epoch": 1.0588776448942043,
+      "grad_norm": 4.9069623947143555,
+      "learning_rate": 5.327868852459017e-07,
+      "logits/chosen": -3.8456344604492188,
+      "logits/rejected": -3.4291088581085205,
+      "logps/chosen": -0.3101879954338074,
+      "logps/rejected": -0.3360385298728943,
+      "loss": 0.9439,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.6203759908676147,
+      "rewards/margins": 0.05170107260346413,
+      "rewards/rejected": -0.6720770597457886,
+      "step": 72
+    },
+    {
+      "epoch": 1.0735970561177552,
+      "grad_norm": 5.373537540435791,
+      "learning_rate": 5.245901639344262e-07,
+      "logits/chosen": -3.189006805419922,
+      "logits/rejected": -3.131258249282837,
+      "logps/chosen": -0.3355609178543091,
+      "logps/rejected": -0.3480716943740845,
+      "loss": 0.9606,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.6711218357086182,
+      "rewards/margins": 0.025021512061357498,
+      "rewards/rejected": -0.6961433291435242,
+      "step": 73
+    },
+    {
+      "epoch": 1.0883164673413064,
+      "grad_norm": 5.561800479888916,
+      "learning_rate": 5.163934426229508e-07,
+      "logits/chosen": -2.8683199882507324,
+      "logits/rejected": -2.8707809448242188,
+      "logps/chosen": -0.31854379177093506,
+      "logps/rejected": -0.36209046840667725,
+      "loss": 0.9235,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.6370875835418701,
+      "rewards/margins": 0.0870932936668396,
+      "rewards/rejected": -0.7241808772087097,
+      "step": 74
+    },
+    {
+      "epoch": 1.1030358785648575,
+      "grad_norm": 4.990414142608643,
+      "learning_rate": 5.081967213114754e-07,
+      "logits/chosen": -3.194347858428955,
+      "logits/rejected": -3.092930793762207,
+      "logps/chosen": -0.32476598024368286,
+      "logps/rejected": -0.35717323422431946,
+      "loss": 0.9365,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.6495320200920105,
+      "rewards/margins": 0.0648144781589508,
+      "rewards/rejected": -0.7143464088439941,
+      "step": 75
+    },
+    {
+      "epoch": 1.1177552897884084,
+      "grad_norm": 4.96919584274292,
+      "learning_rate": 5e-07,
+      "logits/chosen": -3.0481834411621094,
+      "logits/rejected": -3.0204482078552246,
+      "logps/chosen": -0.31437885761260986,
+      "logps/rejected": -0.34356942772865295,
+      "loss": 0.9397,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.6287577152252197,
+      "rewards/margins": 0.05838116630911827,
+      "rewards/rejected": -0.6871389150619507,
+      "step": 76
+    },
+    {
+      "epoch": 1.1324747010119596,
+      "grad_norm": 5.780066013336182,
+      "learning_rate": 4.918032786885245e-07,
+      "logits/chosen": -3.1936581134796143,
+      "logits/rejected": -3.0110840797424316,
+      "logps/chosen": -0.3270755112171173,
+      "logps/rejected": -0.36666250228881836,
+      "loss": 0.9284,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.6541510224342346,
+      "rewards/margins": 0.0791739821434021,
+      "rewards/rejected": -0.7333249449729919,
+      "step": 77
+    },
+    {
+      "epoch": 1.1471941122355105,
+      "grad_norm": 5.684655666351318,
+      "learning_rate": 4.836065573770492e-07,
+      "logits/chosen": -2.4972476959228516,
+      "logits/rejected": -2.833545207977295,
+      "logps/chosen": -0.3543640375137329,
+      "logps/rejected": -0.38385263085365295,
+      "loss": 0.9395,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.708728015422821,
+      "rewards/margins": 0.05897724628448486,
+      "rewards/rejected": -0.7677052617073059,
+      "step": 78
+    },
+    {
+      "epoch": 1.1619135234590616,
+      "grad_norm": 4.93048095703125,
+      "learning_rate": 4.754098360655737e-07,
+      "logits/chosen": -3.211378812789917,
+      "logits/rejected": -3.1379148960113525,
+      "logps/chosen": -0.31901848316192627,
+      "logps/rejected": -0.3422248363494873,
+      "loss": 0.9467,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": -0.6380370259284973,
+      "rewards/margins": 0.046412669122219086,
+      "rewards/rejected": -0.6844496726989746,
+      "step": 79
+    },
+    {
+      "epoch": 1.1766329346826128,
+      "grad_norm": 5.538037300109863,
+      "learning_rate": 4.672131147540984e-07,
+      "logits/chosen": -2.736569404602051,
+      "logits/rejected": -2.8682150840759277,
+      "logps/chosen": -0.34923046827316284,
+      "logps/rejected": -0.3685604929924011,
+      "loss": 0.9517,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.6984609365463257,
+      "rewards/margins": 0.038660045713186264,
+      "rewards/rejected": -0.7371209859848022,
+      "step": 80
+    },
+    {
+      "epoch": 1.1913523459061637,
+      "grad_norm": 5.049704074859619,
+      "learning_rate": 4.590163934426229e-07,
+      "logits/chosen": -2.698671340942383,
+      "logits/rejected": -3.129981517791748,
+      "logps/chosen": -0.3192306160926819,
+      "logps/rejected": -0.34711503982543945,
+      "loss": 0.9425,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.6384612321853638,
+      "rewards/margins": 0.05576884746551514,
+      "rewards/rejected": -0.6942300796508789,
+      "step": 81
+    },
+    {
+      "epoch": 1.2060717571297148,
+      "grad_norm": 6.073709487915039,
+      "learning_rate": 4.508196721311475e-07,
+      "logits/chosen": -3.247349739074707,
+      "logits/rejected": -3.0602288246154785,
+      "logps/chosen": -0.34253838658332825,
+      "logps/rejected": -0.3857520818710327,
+      "loss": 0.9242,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.6850768327713013,
+      "rewards/margins": 0.08642742037773132,
+      "rewards/rejected": -0.7715041637420654,
+      "step": 82
+    },
+    {
+      "epoch": 1.220791168353266,
+      "grad_norm": 5.996784210205078,
+      "learning_rate": 4.426229508196721e-07,
+      "logits/chosen": -2.3361268043518066,
+      "logits/rejected": -2.6752443313598633,
+      "logps/chosen": -0.34017816185951233,
+      "logps/rejected": -0.36880531907081604,
+      "loss": 0.9412,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.6803563237190247,
+      "rewards/margins": 0.05725434422492981,
+      "rewards/rejected": -0.7376106381416321,
+      "step": 83
+    },
+    {
+      "epoch": 1.2355105795768169,
+      "grad_norm": 5.233430862426758,
+      "learning_rate": 4.3442622950819667e-07,
+      "logits/chosen": -3.2010231018066406,
+      "logits/rejected": -3.1768579483032227,
+      "logps/chosen": -0.33099696040153503,
+      "logps/rejected": -0.3604615032672882,
+      "loss": 0.9396,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.6619938611984253,
+      "rewards/margins": 0.058929093182086945,
+      "rewards/rejected": -0.7209229469299316,
+      "step": 84
+    },
+    {
+      "epoch": 1.250229990800368,
+      "grad_norm": 5.6451311111450195,
+      "learning_rate": 4.2622950819672127e-07,
+      "logits/chosen": -2.11002254486084,
+      "logits/rejected": -2.832841634750366,
+      "logps/chosen": -0.31466031074523926,
+      "logps/rejected": -0.3550466299057007,
+      "loss": 0.9275,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": -0.6293206214904785,
+      "rewards/margins": 0.08077271282672882,
+      "rewards/rejected": -0.7100933194160461,
+      "step": 85
+    },
+    {
+      "epoch": 1.2649494020239191,
+      "grad_norm": 6.1917877197265625,
+      "learning_rate": 4.180327868852459e-07,
+      "logits/chosen": -2.6735427379608154,
+      "logits/rejected": -2.9040236473083496,
+      "logps/chosen": -0.3471025228500366,
+      "logps/rejected": -0.3789517283439636,
+      "loss": 0.9368,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.6942050457000732,
+      "rewards/margins": 0.063698410987854,
+      "rewards/rejected": -0.7579034566879272,
+      "step": 86
+    },
+    {
+      "epoch": 1.27966881324747,
+      "grad_norm": 5.865265369415283,
+      "learning_rate": 4.0983606557377047e-07,
+      "logits/chosen": -2.7643613815307617,
+      "logits/rejected": -2.8559346199035645,
+      "logps/chosen": -0.33007344603538513,
+      "logps/rejected": -0.36891335248947144,
+      "loss": 0.9295,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.6601468920707703,
+      "rewards/margins": 0.07767981290817261,
+      "rewards/rejected": -0.7378267049789429,
+      "step": 87
+    },
+    {
+      "epoch": 1.2943882244710212,
+      "grad_norm": 5.28799295425415,
+      "learning_rate": 4.0163934426229507e-07,
+      "logits/chosen": -3.2653579711914062,
+      "logits/rejected": -3.030381679534912,
+      "logps/chosen": -0.3344501852989197,
+      "logps/rejected": -0.371614933013916,
+      "loss": 0.9317,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.6689003705978394,
+      "rewards/margins": 0.07432954013347626,
+      "rewards/rejected": -0.743229866027832,
+      "step": 88
+    },
+    {
+      "epoch": 1.3091076356945721,
+      "grad_norm": 5.84768533706665,
+      "learning_rate": 3.9344262295081967e-07,
+      "logits/chosen": -2.64261531829834,
+      "logits/rejected": -2.9684834480285645,
+      "logps/chosen": -0.34116652607917786,
+      "logps/rejected": -0.37209397554397583,
+      "loss": 0.9391,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.6823331117630005,
+      "rewards/margins": 0.06185486912727356,
+      "rewards/rejected": -0.7441879510879517,
+      "step": 89
+    },
+    {
+      "epoch": 1.3238270469181233,
+      "grad_norm": 6.20886754989624,
+      "learning_rate": 3.852459016393442e-07,
+      "logits/chosen": -2.8721776008605957,
+      "logits/rejected": -2.935757637023926,
+      "logps/chosen": -0.32490894198417664,
+      "logps/rejected": -0.3719860315322876,
+      "loss": 0.9191,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.6498178839683533,
+      "rewards/margins": 0.0941542536020279,
+      "rewards/rejected": -0.74397212266922,
+      "step": 90
+    },
+    {
+      "epoch": 1.3385464581416744,
+      "grad_norm": 5.540692329406738,
+      "learning_rate": 3.770491803278688e-07,
+      "logits/chosen": -2.457730293273926,
+      "logits/rejected": -2.8065922260284424,
+      "logps/chosen": -0.363670289516449,
+      "logps/rejected": -0.39088112115859985,
+      "loss": 0.9424,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.7273405194282532,
+      "rewards/margins": 0.05442170053720474,
+      "rewards/rejected": -0.7817622423171997,
+      "step": 91
+    },
+    {
+      "epoch": 1.3532658693652255,
+      "grad_norm": 4.544013977050781,
+      "learning_rate": 3.6885245901639347e-07,
+      "logits/chosen": -3.041391134262085,
+      "logits/rejected": -3.200744390487671,
+      "logps/chosen": -0.30500367283821106,
+      "logps/rejected": -0.3335219621658325,
+      "loss": 0.941,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.6100073456764221,
+      "rewards/margins": 0.05703658610582352,
+      "rewards/rejected": -0.667043924331665,
+      "step": 92
+    },
+    {
+      "epoch": 1.3679852805887764,
+      "grad_norm": 5.325432300567627,
+      "learning_rate": 3.60655737704918e-07,
+      "logits/chosen": -3.339791774749756,
+      "logits/rejected": -3.3530054092407227,
+      "logps/chosen": -0.32377439737319946,
+      "logps/rejected": -0.347787469625473,
+      "loss": 0.9469,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.6475488543510437,
+      "rewards/margins": 0.048026055097579956,
+      "rewards/rejected": -0.6955748796463013,
+      "step": 93
+    },
+    {
+      "epoch": 1.3827046918123276,
+      "grad_norm": 4.834715843200684,
+      "learning_rate": 3.524590163934426e-07,
+      "logits/chosen": -2.9240317344665527,
+      "logits/rejected": -3.0863239765167236,
+      "logps/chosen": -0.30060070753097534,
+      "logps/rejected": -0.33696314692497253,
+      "loss": 0.9317,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.6012013554573059,
+      "rewards/margins": 0.07272489368915558,
+      "rewards/rejected": -0.6739262938499451,
+      "step": 94
+    },
+    {
+      "epoch": 1.3974241030358785,
+      "grad_norm": 6.076785564422607,
+      "learning_rate": 3.4426229508196717e-07,
+      "logits/chosen": -2.790525436401367,
+      "logits/rejected": -2.9921529293060303,
+      "logps/chosen": -0.31479692459106445,
+      "logps/rejected": -0.3640579581260681,
+      "loss": 0.9165,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.6295938491821289,
+      "rewards/margins": 0.09852204471826553,
+      "rewards/rejected": -0.7281159162521362,
+      "step": 95
+    },
+    {
+      "epoch": 1.4121435142594296,
+      "grad_norm": 6.245033264160156,
+      "learning_rate": 3.3606557377049177e-07,
+      "logits/chosen": -2.711641788482666,
+      "logits/rejected": -2.811826705932617,
+      "logps/chosen": -0.368450790643692,
+      "logps/rejected": -0.39056143164634705,
+      "loss": 0.9495,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.7369015216827393,
+      "rewards/margins": 0.04422131925821304,
+      "rewards/rejected": -0.7811228036880493,
+      "step": 96
+    },
+    {
+      "epoch": 1.4268629254829808,
+      "grad_norm": 7.023751258850098,
+      "learning_rate": 3.2786885245901637e-07,
+      "logits/chosen": -2.939385175704956,
+      "logits/rejected": -2.9760098457336426,
+      "logps/chosen": -0.35348090529441833,
+      "logps/rejected": -0.39679813385009766,
+      "loss": 0.9238,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.7069618105888367,
+      "rewards/margins": 0.08663442730903625,
+      "rewards/rejected": -0.7935962677001953,
+      "step": 97
+    },
+    {
+      "epoch": 1.4415823367065317,
+      "grad_norm": 12.996735572814941,
+      "learning_rate": 3.1967213114754097e-07,
+      "logits/chosen": -2.7201128005981445,
+      "logits/rejected": -2.9376893043518066,
+      "logps/chosen": -0.33448997139930725,
+      "logps/rejected": -0.3776443600654602,
+      "loss": 0.9244,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.6689799427986145,
+      "rewards/margins": 0.08630875498056412,
+      "rewards/rejected": -0.7552887201309204,
+      "step": 98
+    },
+    {
+      "epoch": 1.4563017479300828,
+      "grad_norm": 5.664161682128906,
+      "learning_rate": 3.1147540983606557e-07,
+      "logits/chosen": -3.10605525970459,
+      "logits/rejected": -3.1280431747436523,
+      "logps/chosen": -0.3306281268596649,
+      "logps/rejected": -0.3685624599456787,
+      "loss": 0.9296,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": -0.6612562537193298,
+      "rewards/margins": 0.07586869597434998,
+      "rewards/rejected": -0.7371249198913574,
+      "step": 99
+    },
+    {
+      "epoch": 1.4710211591536337,
+      "grad_norm": 5.440978050231934,
+      "learning_rate": 3.0327868852459017e-07,
+      "logits/chosen": -3.1456902027130127,
+      "logits/rejected": -3.1661486625671387,
+      "logps/chosen": -0.33667102456092834,
+      "logps/rejected": -0.38138431310653687,
+      "loss": 0.9216,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.6733420491218567,
+      "rewards/margins": 0.08942660689353943,
+      "rewards/rejected": -0.7627686262130737,
+      "step": 100
+    },
+    {
+      "epoch": 1.4857405703771849,
+      "grad_norm": 5.968519687652588,
+      "learning_rate": 2.950819672131147e-07,
+      "logits/chosen": -2.4848227500915527,
+      "logits/rejected": -2.7680301666259766,
+      "logps/chosen": -0.3308497965335846,
+      "logps/rejected": -0.37560707330703735,
+      "loss": 0.9231,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.661699652671814,
+      "rewards/margins": 0.08951465040445328,
+      "rewards/rejected": -0.7512142062187195,
+      "step": 101
+    },
+    {
+      "epoch": 1.500459981600736,
+      "grad_norm": 5.029065132141113,
+      "learning_rate": 2.868852459016393e-07,
+      "logits/chosen": -2.8473854064941406,
+      "logits/rejected": -3.1287717819213867,
+      "logps/chosen": -0.307930052280426,
+      "logps/rejected": -0.3468787968158722,
+      "loss": 0.929,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.615860104560852,
+      "rewards/margins": 0.07789750397205353,
+      "rewards/rejected": -0.6937576532363892,
+      "step": 102
+    },
+    {
+      "epoch": 1.5151793928242872,
+      "grad_norm": 5.741458892822266,
+      "learning_rate": 2.786885245901639e-07,
+      "logits/chosen": -3.060265302658081,
+      "logits/rejected": -3.086451768875122,
+      "logps/chosen": -0.3198442757129669,
+      "logps/rejected": -0.3637600839138031,
+      "loss": 0.9235,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.6396886110305786,
+      "rewards/margins": 0.08783160150051117,
+      "rewards/rejected": -0.7275201678276062,
+      "step": 103
+    },
+    {
+      "epoch": 1.529898804047838,
+      "grad_norm": 5.51586389541626,
+      "learning_rate": 2.704918032786885e-07,
+      "logits/chosen": -2.7921199798583984,
+      "logits/rejected": -2.949281692504883,
+      "logps/chosen": -0.35858044028282166,
+      "logps/rejected": -0.38384395837783813,
+      "loss": 0.9457,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.7171608805656433,
+      "rewards/margins": 0.05052705854177475,
+      "rewards/rejected": -0.7676879167556763,
+      "step": 104
+    },
+    {
+      "epoch": 1.544618215271389,
+      "grad_norm": 6.046347618103027,
+      "learning_rate": 2.622950819672131e-07,
+      "logits/chosen": -2.7023696899414062,
+      "logits/rejected": -2.9308128356933594,
+      "logps/chosen": -0.35011446475982666,
+      "logps/rejected": -0.3880847096443176,
+      "loss": 0.9303,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.7002289295196533,
+      "rewards/margins": 0.07594041526317596,
+      "rewards/rejected": -0.7761694192886353,
+      "step": 105
+    },
+    {
+      "epoch": 1.5593376264949401,
+      "grad_norm": 5.501741886138916,
+      "learning_rate": 2.540983606557377e-07,
+      "logits/chosen": -2.6256351470947266,
+      "logits/rejected": -3.093425750732422,
+      "logps/chosen": -0.3132556080818176,
+      "logps/rejected": -0.3510013222694397,
+      "loss": 0.9302,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.62651127576828,
+      "rewards/margins": 0.07549147307872772,
+      "rewards/rejected": -0.702002763748169,
+      "step": 106
+    },
+    {
+      "epoch": 1.5740570377184913,
+      "grad_norm": 6.958146572113037,
+      "learning_rate": 2.4590163934426226e-07,
+      "logits/chosen": -2.88631010055542,
+      "logits/rejected": -2.882737636566162,
+      "logps/chosen": -0.33777421712875366,
+      "logps/rejected": -0.3951508700847626,
+      "loss": 0.9072,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.6755484342575073,
+      "rewards/margins": 0.1147533506155014,
+      "rewards/rejected": -0.7903016805648804,
+      "step": 107
+    },
+    {
+      "epoch": 1.5887764489420424,
+      "grad_norm": 5.5533623695373535,
+      "learning_rate": 2.3770491803278686e-07,
+      "logits/chosen": -2.6153483390808105,
+      "logits/rejected": -2.914055347442627,
+      "logps/chosen": -0.33533841371536255,
+      "logps/rejected": -0.3664292097091675,
+      "loss": 0.938,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.6706768274307251,
+      "rewards/margins": 0.062181562185287476,
+      "rewards/rejected": -0.732858419418335,
+      "step": 108
+    },
+    {
+      "epoch": 1.6034958601655935,
+      "grad_norm": 6.642143249511719,
+      "learning_rate": 2.2950819672131146e-07,
+      "logits/chosen": -2.60856294631958,
+      "logits/rejected": -2.7908551692962646,
+      "logps/chosen": -0.3444288969039917,
+      "logps/rejected": -0.38877052068710327,
+      "loss": 0.9233,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.6888577938079834,
+      "rewards/margins": 0.0886833518743515,
+      "rewards/rejected": -0.7775410413742065,
+      "step": 109
+    },
+    {
+      "epoch": 1.6182152713891444,
+      "grad_norm": 5.208906173706055,
+      "learning_rate": 2.2131147540983606e-07,
+      "logits/chosen": -3.353736162185669,
+      "logits/rejected": -3.3088865280151367,
+      "logps/chosen": -0.32407790422439575,
+      "logps/rejected": -0.3433798551559448,
+      "loss": 0.9516,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.6481558084487915,
+      "rewards/margins": 0.03860398009419441,
+      "rewards/rejected": -0.6867598295211792,
+      "step": 110
+    },
+    {
+      "epoch": 1.6329346826126954,
+      "grad_norm": 5.580318927764893,
+      "learning_rate": 2.1311475409836064e-07,
+      "logits/chosen": -2.904496908187866,
+      "logits/rejected": -2.884878635406494,
+      "logps/chosen": -0.32563793659210205,
+      "logps/rejected": -0.3524249792098999,
+      "loss": 0.944,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.6512758731842041,
+      "rewards/margins": 0.05357404053211212,
+      "rewards/rejected": -0.704849898815155,
+      "step": 111
+    },
+    {
+      "epoch": 1.6476540938362465,
+      "grad_norm": 5.989292621612549,
+      "learning_rate": 2.0491803278688524e-07,
+      "logits/chosen": -2.916060209274292,
+      "logits/rejected": -3.008087635040283,
+      "logps/chosen": -0.3634881377220154,
+      "logps/rejected": -0.39244192838668823,
+      "loss": 0.9439,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.7269763350486755,
+      "rewards/margins": 0.05790755897760391,
+      "rewards/rejected": -0.7848838567733765,
+      "step": 112
+    },
+    {
+      "epoch": 1.6623735050597976,
+      "grad_norm": 6.971791744232178,
+      "learning_rate": 1.9672131147540984e-07,
+      "logits/chosen": -2.5411109924316406,
+      "logits/rejected": -2.6886777877807617,
+      "logps/chosen": -0.37233471870422363,
+      "logps/rejected": -0.4020453989505768,
+      "loss": 0.9404,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.7446693778038025,
+      "rewards/margins": 0.059421420097351074,
+      "rewards/rejected": -0.8040907979011536,
+      "step": 113
+    },
+    {
+      "epoch": 1.6770929162833488,
+      "grad_norm": 6.173042297363281,
+      "learning_rate": 1.885245901639344e-07,
+      "logits/chosen": -2.249495506286621,
+      "logits/rejected": -2.596745491027832,
+      "logps/chosen": -0.3725017309188843,
+      "logps/rejected": -0.43299970030784607,
+      "loss": 0.9139,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7450034618377686,
+      "rewards/margins": 0.12099599093198776,
+      "rewards/rejected": -0.8659994602203369,
+      "step": 114
+    },
+    {
+      "epoch": 1.6918123275068997,
+      "grad_norm": 5.885793209075928,
+      "learning_rate": 1.80327868852459e-07,
+      "logits/chosen": -2.219787359237671,
+      "logits/rejected": -2.843722105026245,
+      "logps/chosen": -0.3552049398422241,
+      "logps/rejected": -0.4021163582801819,
+      "loss": 0.9206,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.7104098796844482,
+      "rewards/margins": 0.09382288157939911,
+      "rewards/rejected": -0.8042327761650085,
+      "step": 115
+    },
+    {
+      "epoch": 1.7065317387304508,
+      "grad_norm": 6.8436665534973145,
+      "learning_rate": 1.7213114754098358e-07,
+      "logits/chosen": -2.7685060501098633,
+      "logits/rejected": -2.891371726989746,
+      "logps/chosen": -0.35419946908950806,
+      "logps/rejected": -0.38518092036247253,
+      "loss": 0.9386,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.7083989381790161,
+      "rewards/margins": 0.06196289137005806,
+      "rewards/rejected": -0.7703619003295898,
+      "step": 116
+    },
+    {
+      "epoch": 1.7212511499540017,
+      "grad_norm": 6.383307456970215,
+      "learning_rate": 1.6393442622950818e-07,
+      "logits/chosen": -2.6302192211151123,
+      "logits/rejected": -2.7831718921661377,
+      "logps/chosen": -0.3403049409389496,
+      "logps/rejected": -0.37697887420654297,
+      "loss": 0.9326,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.6806098818778992,
+      "rewards/margins": 0.07334783673286438,
+      "rewards/rejected": -0.7539578080177307,
+      "step": 117
+    },
+    {
+      "epoch": 1.7359705611775529,
+      "grad_norm": 6.035743713378906,
+      "learning_rate": 1.5573770491803278e-07,
+      "logits/chosen": -3.153184175491333,
+      "logits/rejected": -3.0809226036071777,
+      "logps/chosen": -0.3405628204345703,
+      "logps/rejected": -0.37279361486434937,
+      "loss": 0.9374,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.6811257004737854,
+      "rewards/margins": 0.06446149945259094,
+      "rewards/rejected": -0.7455872297286987,
+      "step": 118
+    },
+    {
+      "epoch": 1.750689972401104,
+      "grad_norm": 6.280840873718262,
+      "learning_rate": 1.4754098360655736e-07,
+      "logits/chosen": -2.436659097671509,
+      "logits/rejected": -2.6618547439575195,
+      "logps/chosen": -0.35082828998565674,
+      "logps/rejected": -0.3988627791404724,
+      "loss": 0.9186,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7016565799713135,
+      "rewards/margins": 0.09606888145208359,
+      "rewards/rejected": -0.7977255582809448,
+      "step": 119
+    },
+    {
+      "epoch": 1.7654093836246552,
+      "grad_norm": 6.461415767669678,
+      "learning_rate": 1.3934426229508196e-07,
+      "logits/chosen": -2.553762674331665,
+      "logits/rejected": -2.8313937187194824,
+      "logps/chosen": -0.36426275968551636,
+      "logps/rejected": -0.3945803642272949,
+      "loss": 0.9394,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": -0.7285255193710327,
+      "rewards/margins": 0.06063529849052429,
+      "rewards/rejected": -0.7891607880592346,
+      "step": 120
+    },
+    {
+      "epoch": 1.780128794848206,
+      "grad_norm": 5.7529778480529785,
+      "learning_rate": 1.3114754098360656e-07,
+      "logits/chosen": -3.030463933944702,
+      "logits/rejected": -3.133709192276001,
+      "logps/chosen": -0.33007901906967163,
+      "logps/rejected": -0.3561002016067505,
+      "loss": 0.9452,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.6601580381393433,
+      "rewards/margins": 0.05204241722822189,
+      "rewards/rejected": -0.7122004628181458,
+      "step": 121
+    },
+    {
+      "epoch": 1.794848206071757,
+      "grad_norm": 6.557502269744873,
+      "learning_rate": 1.2295081967213113e-07,
+      "logits/chosen": -2.496763229370117,
+      "logits/rejected": -2.722606658935547,
+      "logps/chosen": -0.3488333821296692,
+      "logps/rejected": -0.3847794532775879,
+      "loss": 0.9323,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.6976668238639832,
+      "rewards/margins": 0.07189209759235382,
+      "rewards/rejected": -0.769558846950531,
+      "step": 122
+    },
+    {
+      "epoch": 1.8095676172953081,
+      "grad_norm": 6.7690277099609375,
+      "learning_rate": 1.1475409836065573e-07,
+      "logits/chosen": -2.468517303466797,
+      "logits/rejected": -2.8185667991638184,
+      "logps/chosen": -0.3616328537464142,
+      "logps/rejected": -0.3974328637123108,
+      "loss": 0.9348,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.7232657074928284,
+      "rewards/margins": 0.0716000348329544,
+      "rewards/rejected": -0.7948658466339111,
+      "step": 123
+    },
+    {
+      "epoch": 1.8242870285188593,
+      "grad_norm": 5.662026405334473,
+      "learning_rate": 1.0655737704918032e-07,
+      "logits/chosen": -2.563282012939453,
+      "logits/rejected": -3.0523743629455566,
+      "logps/chosen": -0.3303174078464508,
+      "logps/rejected": -0.3804895877838135,
+      "loss": 0.9163,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.6606348156929016,
+      "rewards/margins": 0.10034434497356415,
+      "rewards/rejected": -0.760979175567627,
+      "step": 124
+    },
+    {
+      "epoch": 1.8390064397424104,
+      "grad_norm": 5.673758506774902,
+      "learning_rate": 9.836065573770492e-08,
+      "logits/chosen": -2.9448227882385254,
+      "logits/rejected": -2.9346063137054443,
+      "logps/chosen": -0.32242119312286377,
+      "logps/rejected": -0.350904643535614,
+      "loss": 0.941,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.6448423862457275,
+      "rewards/margins": 0.05696691572666168,
+      "rewards/rejected": -0.701809287071228,
+      "step": 125
+    },
+    {
+      "epoch": 1.8537258509659613,
+      "grad_norm": 5.837872505187988,
+      "learning_rate": 9.01639344262295e-08,
+      "logits/chosen": -3.052157402038574,
+      "logits/rejected": -3.0036213397979736,
+      "logps/chosen": -0.35162875056266785,
+      "logps/rejected": -0.3706502318382263,
+      "loss": 0.9525,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.7032575011253357,
+      "rewards/margins": 0.03804299607872963,
+      "rewards/rejected": -0.7413004636764526,
+      "step": 126
+    },
+    {
+      "epoch": 1.8684452621895125,
+      "grad_norm": 6.1533613204956055,
+      "learning_rate": 8.196721311475409e-08,
+      "logits/chosen": -2.717515230178833,
+      "logits/rejected": -2.8103432655334473,
+      "logps/chosen": -0.36272749304771423,
+      "logps/rejected": -0.39639797806739807,
+      "loss": 0.9356,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.7254549860954285,
+      "rewards/margins": 0.06734100729227066,
+      "rewards/rejected": -0.7927959561347961,
+      "step": 127
+    },
+    {
+      "epoch": 1.8831646734130634,
+      "grad_norm": 7.13803243637085,
+      "learning_rate": 7.377049180327868e-08,
+      "logits/chosen": -2.4307665824890137,
+      "logits/rejected": -2.7688546180725098,
+      "logps/chosen": -0.3650929629802704,
+      "logps/rejected": -0.4157169759273529,
+      "loss": 0.9164,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.7301859259605408,
+      "rewards/margins": 0.10124801099300385,
+      "rewards/rejected": -0.8314339518547058,
+      "step": 128
+    },
+    {
+      "epoch": 1.8978840846366145,
+      "grad_norm": 6.0640716552734375,
+      "learning_rate": 6.557377049180328e-08,
+      "logits/chosen": -2.6504528522491455,
+      "logits/rejected": -2.816641092300415,
+      "logps/chosen": -0.35474810004234314,
+      "logps/rejected": -0.3936282992362976,
+      "loss": 0.9298,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7094961404800415,
+      "rewards/margins": 0.0777604728937149,
+      "rewards/rejected": -0.7872565984725952,
+      "step": 129
+    },
+    {
+      "epoch": 1.9126034958601656,
+      "grad_norm": 5.700585842132568,
+      "learning_rate": 5.7377049180327866e-08,
+      "logits/chosen": -2.6422119140625,
+      "logits/rejected": -2.972996711730957,
+      "logps/chosen": -0.3482939600944519,
+      "logps/rejected": -0.3821781575679779,
+      "loss": 0.9354,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.6965879201889038,
+      "rewards/margins": 0.06776841729879379,
+      "rewards/rejected": -0.7643563747406006,
+      "step": 130
+    },
+    {
+      "epoch": 1.9273229070837168,
+      "grad_norm": 8.303826332092285,
+      "learning_rate": 4.918032786885246e-08,
+      "logits/chosen": -2.9017281532287598,
+      "logits/rejected": -2.9597935676574707,
+      "logps/chosen": -0.3572656810283661,
+      "logps/rejected": -0.3903231620788574,
+      "loss": 0.9359,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.7145313620567322,
+      "rewards/margins": 0.06611500680446625,
+      "rewards/rejected": -0.7806463837623596,
+      "step": 131
+    },
+    {
+      "epoch": 1.9420423183072677,
+      "grad_norm": 6.356776714324951,
+      "learning_rate": 4.0983606557377046e-08,
+      "logits/chosen": -2.724161386489868,
+      "logits/rejected": -2.8108153343200684,
+      "logps/chosen": -0.35084962844848633,
+      "logps/rejected": -0.39324939250946045,
+      "loss": 0.9253,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.7016993165016174,
+      "rewards/margins": 0.08479949086904526,
+      "rewards/rejected": -0.7864987850189209,
+      "step": 132
+    },
+    {
+      "epoch": 1.9567617295308186,
+      "grad_norm": 5.675929069519043,
+      "learning_rate": 3.278688524590164e-08,
+      "logits/chosen": -2.453089714050293,
+      "logits/rejected": -2.8991174697875977,
+      "logps/chosen": -0.3394642770290375,
+      "logps/rejected": -0.38700026273727417,
+      "loss": 0.9188,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.6789284944534302,
+      "rewards/margins": 0.09507202357053757,
+      "rewards/rejected": -0.7740005850791931,
+      "step": 133
+    },
+    {
+      "epoch": 1.9714811407543698,
+      "grad_norm": 6.218247413635254,
+      "learning_rate": 2.459016393442623e-08,
+      "logits/chosen": -2.6867618560791016,
+      "logits/rejected": -2.796144962310791,
+      "logps/chosen": -0.36361926794052124,
+      "logps/rejected": -0.4098837971687317,
+      "loss": 0.9204,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.7272385358810425,
+      "rewards/margins": 0.09252903610467911,
+      "rewards/rejected": -0.8197675943374634,
+      "step": 134
+    },
+    {
+      "epoch": 1.986200551977921,
+      "grad_norm": 6.011038303375244,
+      "learning_rate": 1.639344262295082e-08,
+      "logits/chosen": -2.8169169425964355,
+      "logits/rejected": -2.9251537322998047,
+      "logps/chosen": -0.3600449562072754,
+      "logps/rejected": -0.40678220987319946,
+      "loss": 0.9194,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": -0.7200899124145508,
+      "rewards/margins": 0.09347459673881531,
+      "rewards/rejected": -0.8135644197463989,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.664433479309082,
+      "learning_rate": 8.19672131147541e-09,
+      "logits/chosen": -2.7600553035736084,
+      "logits/rejected": -2.893031597137451,
+      "logps/chosen": -0.37107592821121216,
+      "logps/rejected": -0.40161800384521484,
+      "loss": 0.8813,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": -0.7421518564224243,
+      "rewards/margins": 0.06108412146568298,
+      "rewards/rejected": -0.8032360076904297,
+      "step": 136
+    },
+    {
+      "epoch": 2.0,
+      "step": 136,
+      "total_flos": 44833908572160.0,
+      "train_loss": 0.9574610433157753,
+      "train_runtime": 3050.2608,
+      "train_samples_per_second": 2.849,
+      "train_steps_per_second": 0.045
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 136,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 44833908572160.0,
+  "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:ff7e472145be8d6e1e2851533d82765b018879f2c5c1356794cbc3649e225f78
+size 8145