Model save

README.md

@@ -0,0 +1,69 @@
+---
+base_model: DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1
+library_name: transformers
+model_name: Phi-4-Argunaut-1-SPIN-dev1
+tags:
+- generated_from_trainer
+- dpo
+- trl
+licence: license
+---
+
+# Model Card for Phi-4-Argunaut-1-SPIN-dev1
+
+This model is a fine-tuned version of [DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1](https://huggingface.co/DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="DebateLabKIT/Phi-4-Argunaut-1-SPIN-dev1", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ggbetz/argunauts-training/runs/g7wyrguq) 
+
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- TRL: 0.19.1
+- Transformers: 4.53.3
+- Pytorch: 2.4.1
+- Datasets: 3.1.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 0.0,
+    "train_loss": 0.34146574610158015,
+    "train_runtime": 4832.1445,
+    "train_samples": 4838,
+    "train_samples_per_second": 2.002,
+    "train_steps_per_second": 0.063
+}

chat_template.jinja

@@ -0,0 +1,53 @@
+{%- if tools %}
+    {{- '<|im_start|>system<|im_sep|>' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Argunaut, created by DebateLab@KIT. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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|>" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system<|im_sep|>' + messages[0]['content'] + '<|im_end|>' }}
+    {%- else %}
+        {{- '<|im_start|>system<|im_sep|>{system_message}<|im_end|>' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '<|im_sep|>' + message.content + '<|im_end|>' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '<|im_sep|>'}}
+        {%- if message.content %}
+            {{- message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}            {{- '<|im_start|>user<|im_sep|>' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant<|im_sep|>' }}
+{%- endif %}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.15,
+  "bos_token_id": 100257,
+  "eos_token_id": 100265,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100351,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.3",
+  "use_cache": false,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100265,
+  "pad_token_id": 100351,
+  "transformers_version": "4.53.3"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80f16654bd69a9bf61ab58ff711594351aec75ae3a053fe72f250750cc2503a
+size 4933658528

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47f10ad788f41a9f53b194f6ff88d25819d1fb5e212b750fd4424e71169413a
+size 4954693112

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae514e2187be12286ac65679ff5bf8b43206430fa8032764ddd0ea27b88ce40
+size 4902243992

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27173e9497c7431cdad62f89289fd00782ca43904aa09270d9af5a65009aeb1f
+size 4954672440

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43358b6067c8d8e3e613b515c9a3304beca7a0cbe1ff009909eec02f1023d7f
+size 4954672432

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf59e535ca829d332b689c97cf31875ad50aaa5798ebf4f02d614ebaa018412e
+size 4619116224

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_parameters": 414720,
+    "total_size": 29319014400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|dummy_87|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "�",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,790 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "5809": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100256": {
+      "content": "<|dummy_0|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|dummy_1|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|dummy_2|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|dummy_3|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|im_sep|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|dummy_4|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|dummy_5|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|dummy_6|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|dummy_7|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|dummy_8|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|dummy_9|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|dummy_10|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|dummy_11|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|dummy_12|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|dummy_13|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<|dummy_14|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<|dummy_15|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<|dummy_16|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "<|dummy_17|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<|dummy_18|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "<|dummy_19|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|dummy_20|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|dummy_21|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|dummy_22|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|dummy_23|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|dummy_24|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|dummy_25|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|dummy_26|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|dummy_27|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|dummy_28|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|dummy_29|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|dummy_30|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|dummy_31|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|dummy_32|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|dummy_33|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|dummy_34|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|dummy_35|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|dummy_36|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|dummy_37|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|dummy_38|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|dummy_39|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|dummy_40|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|dummy_41|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|dummy_42|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|dummy_43|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|dummy_44|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|dummy_45|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|dummy_46|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|dummy_47|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|dummy_48|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|dummy_49|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|dummy_50|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|dummy_51|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|dummy_52|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|dummy_53|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|dummy_54|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|dummy_55|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|dummy_56|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|dummy_57|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|dummy_58|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|dummy_59|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|dummy_60|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|dummy_61|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|dummy_62|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|dummy_63|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|dummy_64|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|dummy_65|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|dummy_66|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|dummy_67|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|dummy_68|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|dummy_69|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|dummy_70|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|dummy_71|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|dummy_72|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|dummy_73|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|dummy_74|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|dummy_75|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|dummy_76|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|dummy_77|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|dummy_78|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|dummy_79|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|dummy_80|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|dummy_81|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|dummy_82|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|dummy_83|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|dummy_84|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|dummy_85|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|dummy_86|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|dummy_87|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|dummy_87|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 0.0,
+    "train_loss": 0.34146574610158015,
+    "train_runtime": 4832.1445,
+    "train_samples": 4838,
+    "train_samples_per_second": 2.002,
+    "train_steps_per_second": 0.063
+}

trainer_state.json

@@ -0,0 +1,943 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 304,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03305785123966942,
+      "grad_norm": 20.384813053174184,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": -1.9736328125,
+      "logits/rejected": -2.0150389671325684,
+      "logps/chosen": -101.9375,
+      "logps/rejected": -134.6875,
+      "loss": 0.7609,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -0.05767517164349556,
+      "rewards/margins": -0.02346496656537056,
+      "rewards/rejected": -0.03435821458697319,
+      "step": 5
+    },
+    {
+      "epoch": 0.06611570247933884,
+      "grad_norm": 94.01960102254296,
+      "learning_rate": 2.8125e-07,
+      "logits/chosen": -1.9695312976837158,
+      "logits/rejected": -1.9580078125,
+      "logps/chosen": -188.0031280517578,
+      "logps/rejected": -213.8312530517578,
+      "loss": 0.7023,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": -0.0018112182151526213,
+      "rewards/margins": 0.08289947360754013,
+      "rewards/rejected": -0.08440055698156357,
+      "step": 10
+    },
+    {
+      "epoch": 0.09917355371900827,
+      "grad_norm": 21.211718326010597,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": -1.9630858898162842,
+      "logits/rejected": -2.010546922683716,
+      "logps/chosen": -121.1937484741211,
+      "logps/rejected": -157.6640625,
+      "loss": 0.7329,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.034603118896484375,
+      "rewards/margins": -0.02179870568215847,
+      "rewards/rejected": -0.01271667517721653,
+      "step": 15
+    },
+    {
+      "epoch": 0.1322314049586777,
+      "grad_norm": 20.70329807308497,
+      "learning_rate": 4.947916666666667e-07,
+      "logits/chosen": -1.928125023841858,
+      "logits/rejected": -2.0234375,
+      "logps/chosen": -112.5875015258789,
+      "logps/rejected": -97.15156555175781,
+      "loss": 0.6808,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": 0.06768341362476349,
+      "rewards/margins": 0.08130035549402237,
+      "rewards/rejected": -0.013789367862045765,
+      "step": 20
+    },
+    {
+      "epoch": 0.1652892561983471,
+      "grad_norm": 25.232267926711238,
+      "learning_rate": 4.861111111111111e-07,
+      "logits/chosen": -2.002734422683716,
+      "logits/rejected": -1.969335913658142,
+      "logps/chosen": -106.5374984741211,
+      "logps/rejected": -128.78125,
+      "loss": 0.6689,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.17589417099952698,
+      "rewards/margins": 0.202056884765625,
+      "rewards/rejected": -0.02575073204934597,
+      "step": 25
+    },
+    {
+      "epoch": 0.19834710743801653,
+      "grad_norm": 15.27943476263106,
+      "learning_rate": 4.774305555555555e-07,
+      "logits/chosen": -1.9646484851837158,
+      "logits/rejected": -2.035351514816284,
+      "logps/chosen": -97.609375,
+      "logps/rejected": -133.9968719482422,
+      "loss": 0.5863,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.27128297090530396,
+      "rewards/margins": 0.34486085176467896,
+      "rewards/rejected": -0.07353515923023224,
+      "step": 30
+    },
+    {
+      "epoch": 0.23140495867768596,
+      "grad_norm": 10.254397382545033,
+      "learning_rate": 4.6874999999999996e-07,
+      "logits/chosen": -1.9158203601837158,
+      "logits/rejected": -1.9259765148162842,
+      "logps/chosen": -76.8343734741211,
+      "logps/rejected": -93.0531234741211,
+      "loss": 0.5547,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.4645752012729645,
+      "rewards/margins": 0.45016783475875854,
+      "rewards/rejected": 0.014300537295639515,
+      "step": 35
+    },
+    {
+      "epoch": 0.2644628099173554,
+      "grad_norm": 14.380457410581087,
+      "learning_rate": 4.600694444444444e-07,
+      "logits/chosen": -1.8447265625,
+      "logits/rejected": -1.936914086341858,
+      "logps/chosen": -106.31562805175781,
+      "logps/rejected": -108.1734390258789,
+      "loss": 0.5251,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 0.601550281047821,
+      "rewards/margins": 0.5547240972518921,
+      "rewards/rejected": 0.047088623046875,
+      "step": 40
+    },
+    {
+      "epoch": 0.2975206611570248,
+      "grad_norm": 78.56584566869854,
+      "learning_rate": 4.513888888888889e-07,
+      "logits/chosen": -1.8576171398162842,
+      "logits/rejected": -1.8904297351837158,
+      "logps/chosen": -127.65937805175781,
+      "logps/rejected": -155.9734344482422,
+      "loss": 0.5159,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": 0.5876830816268921,
+      "rewards/margins": 0.611767590045929,
+      "rewards/rejected": -0.02455444261431694,
+      "step": 45
+    },
+    {
+      "epoch": 0.3305785123966942,
+      "grad_norm": 12.535466357743957,
+      "learning_rate": 4.427083333333333e-07,
+      "logits/chosen": -1.7546875476837158,
+      "logits/rejected": -1.8126952648162842,
+      "logps/chosen": -101.51875305175781,
+      "logps/rejected": -104.28593444824219,
+      "loss": 0.4631,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 0.7405639886856079,
+      "rewards/margins": 0.692065417766571,
+      "rewards/rejected": 0.0489349365234375,
+      "step": 50
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 17.87312710689112,
+      "learning_rate": 4.3402777777777775e-07,
+      "logits/chosen": -1.8767578601837158,
+      "logits/rejected": -1.91015625,
+      "logps/chosen": -108.8062515258789,
+      "logps/rejected": -112.98124694824219,
+      "loss": 0.4817,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": 0.802502453327179,
+      "rewards/margins": 0.7518310546875,
+      "rewards/rejected": 0.05042724683880806,
+      "step": 55
+    },
+    {
+      "epoch": 0.39669421487603307,
+      "grad_norm": 33.86478827382489,
+      "learning_rate": 4.253472222222222e-07,
+      "logits/chosen": -1.750585913658142,
+      "logits/rejected": -1.828710913658142,
+      "logps/chosen": -95.0843734741211,
+      "logps/rejected": -84.9000015258789,
+      "loss": 0.4742,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.8693481683731079,
+      "rewards/margins": 0.792254626750946,
+      "rewards/rejected": 0.07660599052906036,
+      "step": 60
+    },
+    {
+      "epoch": 0.4297520661157025,
+      "grad_norm": 14.995895485980972,
+      "learning_rate": 4.1666666666666667e-07,
+      "logits/chosen": -1.761132836341858,
+      "logits/rejected": -1.8439452648162842,
+      "logps/chosen": -83.8453140258789,
+      "logps/rejected": -218.5031280517578,
+      "loss": 0.4289,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 0.879650890827179,
+      "rewards/margins": 0.8621460199356079,
+      "rewards/rejected": 0.017832566052675247,
+      "step": 65
+    },
+    {
+      "epoch": 0.4628099173553719,
+      "grad_norm": 16.046927552557996,
+      "learning_rate": 4.079861111111111e-07,
+      "logits/chosen": -1.7744140625,
+      "logits/rejected": -1.7898437976837158,
+      "logps/chosen": -115.00468444824219,
+      "logps/rejected": -108.6343765258789,
+      "loss": 0.4529,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.887927234172821,
+      "rewards/margins": 0.950427234172821,
+      "rewards/rejected": -0.062247466295957565,
+      "step": 70
+    },
+    {
+      "epoch": 0.49586776859504134,
+      "grad_norm": 16.03572269046516,
+      "learning_rate": 3.993055555555556e-07,
+      "logits/chosen": -1.7394530773162842,
+      "logits/rejected": -1.7888672351837158,
+      "logps/chosen": -116.4124984741211,
+      "logps/rejected": -133.37655639648438,
+      "loss": 0.4293,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.8433440923690796,
+      "rewards/margins": 0.95654296875,
+      "rewards/rejected": -0.11332092434167862,
+      "step": 75
+    },
+    {
+      "epoch": 0.5289256198347108,
+      "grad_norm": 22.37349972383721,
+      "learning_rate": 3.9062499999999997e-07,
+      "logits/chosen": -1.75390625,
+      "logits/rejected": -1.704687476158142,
+      "logps/chosen": -71.3265609741211,
+      "logps/rejected": -139.4250030517578,
+      "loss": 0.3767,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.1237304210662842,
+      "rewards/margins": 1.17822265625,
+      "rewards/rejected": -0.05453949049115181,
+      "step": 80
+    },
+    {
+      "epoch": 0.5619834710743802,
+      "grad_norm": 20.509754459037634,
+      "learning_rate": 3.819444444444444e-07,
+      "logits/chosen": -1.729101538658142,
+      "logits/rejected": -1.7654297351837158,
+      "logps/chosen": -75.62968444824219,
+      "logps/rejected": -91.04374694824219,
+      "loss": 0.3517,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.2136719226837158,
+      "rewards/margins": 1.282470703125,
+      "rewards/rejected": -0.06860504299402237,
+      "step": 85
+    },
+    {
+      "epoch": 0.5950413223140496,
+      "grad_norm": 9.352262418999281,
+      "learning_rate": 3.732638888888889e-07,
+      "logits/chosen": -1.715429663658142,
+      "logits/rejected": -1.8029296398162842,
+      "logps/chosen": -94.9625015258789,
+      "logps/rejected": -106.2046890258789,
+      "loss": 0.363,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": 0.999072253704071,
+      "rewards/margins": 1.187744140625,
+      "rewards/rejected": -0.188883975148201,
+      "step": 90
+    },
+    {
+      "epoch": 0.628099173553719,
+      "grad_norm": 23.688934732030923,
+      "learning_rate": 3.645833333333333e-07,
+      "logits/chosen": -1.700781226158142,
+      "logits/rejected": -1.7039062976837158,
+      "logps/chosen": -112.2484359741211,
+      "logps/rejected": -159.9812469482422,
+      "loss": 0.3718,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 1.14593505859375,
+      "rewards/margins": 1.391357421875,
+      "rewards/rejected": -0.24615478515625,
+      "step": 95
+    },
+    {
+      "epoch": 0.6611570247933884,
+      "grad_norm": 15.499132967124797,
+      "learning_rate": 3.5590277777777775e-07,
+      "logits/chosen": -1.759179711341858,
+      "logits/rejected": -1.74609375,
+      "logps/chosen": -113.99687194824219,
+      "logps/rejected": -290.7093811035156,
+      "loss": 0.3336,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": 1.349707007408142,
+      "rewards/margins": 1.653967261314392,
+      "rewards/rejected": -0.30389100313186646,
+      "step": 100
+    },
+    {
+      "epoch": 0.6942148760330579,
+      "grad_norm": 8.99540374074108,
+      "learning_rate": 3.472222222222222e-07,
+      "logits/chosen": -1.693359375,
+      "logits/rejected": -1.745703101158142,
+      "logps/chosen": -78.84843444824219,
+      "logps/rejected": -206.0625,
+      "loss": 0.3079,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.15185546875,
+      "rewards/margins": 1.513940453529358,
+      "rewards/rejected": -0.361959844827652,
+      "step": 105
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 13.110466529706155,
+      "learning_rate": 3.3854166666666667e-07,
+      "logits/chosen": -1.701171875,
+      "logits/rejected": -1.7404296398162842,
+      "logps/chosen": -89.875,
+      "logps/rejected": -91.78437805175781,
+      "loss": 0.3093,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.142968773841858,
+      "rewards/margins": 1.448095679283142,
+      "rewards/rejected": -0.30474853515625,
+      "step": 110
+    },
+    {
+      "epoch": 0.7603305785123967,
+      "grad_norm": 16.946974264461762,
+      "learning_rate": 3.298611111111111e-07,
+      "logits/chosen": -1.6511719226837158,
+      "logits/rejected": -1.7580077648162842,
+      "logps/chosen": -68.44999694824219,
+      "logps/rejected": -56.02031326293945,
+      "loss": 0.351,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": 1.1487548351287842,
+      "rewards/margins": 1.403710961341858,
+      "rewards/rejected": -0.254721075296402,
+      "step": 115
+    },
+    {
+      "epoch": 0.7933884297520661,
+      "grad_norm": 21.478896017415543,
+      "learning_rate": 3.211805555555556e-07,
+      "logits/chosen": -1.775781273841858,
+      "logits/rejected": -1.765039086341858,
+      "logps/chosen": -85.5171890258789,
+      "logps/rejected": -311.77813720703125,
+      "loss": 0.3856,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 1.138818383216858,
+      "rewards/margins": 1.498632788658142,
+      "rewards/rejected": -0.35924071073532104,
+      "step": 120
+    },
+    {
+      "epoch": 0.8264462809917356,
+      "grad_norm": 16.699686019608645,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -1.739843726158142,
+      "logits/rejected": -1.7394530773162842,
+      "logps/chosen": -85.05937194824219,
+      "logps/rejected": -78.09687805175781,
+      "loss": 0.3181,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.241113305091858,
+      "rewards/margins": 1.596777319908142,
+      "rewards/rejected": -0.35357969999313354,
+      "step": 125
+    },
+    {
+      "epoch": 0.859504132231405,
+      "grad_norm": 22.059878721649408,
+      "learning_rate": 3.038194444444444e-07,
+      "logits/chosen": -1.7470703125,
+      "logits/rejected": -1.7429687976837158,
+      "logps/chosen": -84.1734390258789,
+      "logps/rejected": -108.15625,
+      "loss": 0.2781,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.319189429283142,
+      "rewards/margins": 1.7539551258087158,
+      "rewards/rejected": -0.435638427734375,
+      "step": 130
+    },
+    {
+      "epoch": 0.8925619834710744,
+      "grad_norm": 26.55552523822837,
+      "learning_rate": 2.951388888888889e-07,
+      "logits/chosen": -1.7365233898162842,
+      "logits/rejected": -1.753320336341858,
+      "logps/chosen": -86.8499984741211,
+      "logps/rejected": -123.36250305175781,
+      "loss": 0.3303,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 1.180883765220642,
+      "rewards/margins": 1.699804663658142,
+      "rewards/rejected": -0.5188751220703125,
+      "step": 135
+    },
+    {
+      "epoch": 0.9256198347107438,
+      "grad_norm": 5.21454541019512,
+      "learning_rate": 2.864583333333333e-07,
+      "logits/chosen": -1.759765625,
+      "logits/rejected": -1.7794921398162842,
+      "logps/chosen": -72.8609390258789,
+      "logps/rejected": -104.01875305175781,
+      "loss": 0.3237,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.08544921875,
+      "rewards/margins": 1.622802734375,
+      "rewards/rejected": -0.5378357172012329,
+      "step": 140
+    },
+    {
+      "epoch": 0.9586776859504132,
+      "grad_norm": 17.08783452785935,
+      "learning_rate": 2.7777777777777776e-07,
+      "logits/chosen": -1.7380859851837158,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -113.3609390258789,
+      "logps/rejected": -135.9968719482422,
+      "loss": 0.362,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 1.2180664539337158,
+      "rewards/margins": 1.650537133216858,
+      "rewards/rejected": -0.43310603499412537,
+      "step": 145
+    },
+    {
+      "epoch": 0.9917355371900827,
+      "grad_norm": 9.807839504587346,
+      "learning_rate": 2.690972222222222e-07,
+      "logits/chosen": -1.691015601158142,
+      "logits/rejected": -1.718164086341858,
+      "logps/chosen": -91.4906234741211,
+      "logps/rejected": -189.89688110351562,
+      "loss": 0.2705,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.2189452648162842,
+      "rewards/margins": 1.797998070716858,
+      "rewards/rejected": -0.5793823003768921,
+      "step": 150
+    },
+    {
+      "epoch": 1.0198347107438017,
+      "grad_norm": 9.768977700612497,
+      "learning_rate": 2.604166666666667e-07,
+      "logits/chosen": -1.625229835510254,
+      "logits/rejected": -1.6571691036224365,
+      "logps/chosen": -57.45036697387695,
+      "logps/rejected": -53.50367736816406,
+      "loss": 0.2231,
+      "rewards/accuracies": 0.9558823704719543,
+      "rewards/chosen": 1.252814769744873,
+      "rewards/margins": 1.7216222286224365,
+      "rewards/rejected": -0.46808579564094543,
+      "step": 155
+    },
+    {
+      "epoch": 1.052892561983471,
+      "grad_norm": 10.908210786207713,
+      "learning_rate": 2.517361111111111e-07,
+      "logits/chosen": -1.7646484375,
+      "logits/rejected": -1.7109375,
+      "logps/chosen": -83.1937484741211,
+      "logps/rejected": -91.83125305175781,
+      "loss": 0.2587,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.206628441810608,
+      "rewards/margins": 1.848486304283142,
+      "rewards/rejected": -0.641589343547821,
+      "step": 160
+    },
+    {
+      "epoch": 1.0859504132231406,
+      "grad_norm": 9.103890657754624,
+      "learning_rate": 2.4305555555555555e-07,
+      "logits/chosen": -1.7931640148162842,
+      "logits/rejected": -1.7109375,
+      "logps/chosen": -131.7624969482422,
+      "logps/rejected": -376.5375061035156,
+      "loss": 0.2809,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.186181664466858,
+      "rewards/margins": 1.97705078125,
+      "rewards/rejected": -0.7916015386581421,
+      "step": 165
+    },
+    {
+      "epoch": 1.1190082644628099,
+      "grad_norm": 20.108066106111135,
+      "learning_rate": 2.3437499999999998e-07,
+      "logits/chosen": -1.7462890148162842,
+      "logits/rejected": -1.751367211341858,
+      "logps/chosen": -112.19218444824219,
+      "logps/rejected": -107.296875,
+      "loss": 0.3179,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 1.1929657459259033,
+      "rewards/margins": 1.8135497570037842,
+      "rewards/rejected": -0.62066650390625,
+      "step": 170
+    },
+    {
+      "epoch": 1.1520661157024794,
+      "grad_norm": 11.06192152881459,
+      "learning_rate": 2.2569444444444444e-07,
+      "logits/chosen": -1.7449219226837158,
+      "logits/rejected": -1.755273461341858,
+      "logps/chosen": -78.3671875,
+      "logps/rejected": -112.86250305175781,
+      "loss": 0.2205,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.427587866783142,
+      "rewards/margins": 2.342089891433716,
+      "rewards/rejected": -0.9125610589981079,
+      "step": 175
+    },
+    {
+      "epoch": 1.1851239669421487,
+      "grad_norm": 16.74266747693132,
+      "learning_rate": 2.1701388888888887e-07,
+      "logits/chosen": -1.722265601158142,
+      "logits/rejected": -1.7253906726837158,
+      "logps/chosen": -80.3187484741211,
+      "logps/rejected": -82.3359375,
+      "loss": 0.2836,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.2846190929412842,
+      "rewards/margins": 2.060546875,
+      "rewards/rejected": -0.7765258550643921,
+      "step": 180
+    },
+    {
+      "epoch": 1.2181818181818183,
+      "grad_norm": 21.202358098219463,
+      "learning_rate": 2.0833333333333333e-07,
+      "logits/chosen": -1.7423827648162842,
+      "logits/rejected": -1.75390625,
+      "logps/chosen": -128.7578125,
+      "logps/rejected": -135.2375030517578,
+      "loss": 0.2561,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 1.331298828125,
+      "rewards/margins": 2.1512694358825684,
+      "rewards/rejected": -0.820111095905304,
+      "step": 185
+    },
+    {
+      "epoch": 1.2512396694214876,
+      "grad_norm": 15.516819767863538,
+      "learning_rate": 1.996527777777778e-07,
+      "logits/chosen": -1.74609375,
+      "logits/rejected": -1.717187523841858,
+      "logps/chosen": -103.02030944824219,
+      "logps/rejected": -207.6875,
+      "loss": 0.2562,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.2101562023162842,
+      "rewards/margins": 2.2046875953674316,
+      "rewards/rejected": -0.9949951171875,
+      "step": 190
+    },
+    {
+      "epoch": 1.284297520661157,
+      "grad_norm": 14.467425156894965,
+      "learning_rate": 1.909722222222222e-07,
+      "logits/chosen": -1.755468726158142,
+      "logits/rejected": -1.7345702648162842,
+      "logps/chosen": -86.8140640258789,
+      "logps/rejected": -247.21875,
+      "loss": 0.248,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.2613525390625,
+      "rewards/margins": 2.2603516578674316,
+      "rewards/rejected": -0.998150646686554,
+      "step": 195
+    },
+    {
+      "epoch": 1.3173553719008264,
+      "grad_norm": 21.767064372417554,
+      "learning_rate": 1.8229166666666666e-07,
+      "logits/chosen": -1.6640625,
+      "logits/rejected": -1.691992163658142,
+      "logps/chosen": -119.8218765258789,
+      "logps/rejected": -178.82186889648438,
+      "loss": 0.2761,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.3565673828125,
+      "rewards/margins": 2.1192383766174316,
+      "rewards/rejected": -0.7636810541152954,
+      "step": 200
+    },
+    {
+      "epoch": 1.350413223140496,
+      "grad_norm": 10.54750059469599,
+      "learning_rate": 1.736111111111111e-07,
+      "logits/chosen": -1.7587890625,
+      "logits/rejected": -1.725195288658142,
+      "logps/chosen": -78.1890640258789,
+      "logps/rejected": -85.6890640258789,
+      "loss": 0.2541,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.3107421398162842,
+      "rewards/margins": 2.126415967941284,
+      "rewards/rejected": -0.8150528073310852,
+      "step": 205
+    },
+    {
+      "epoch": 1.3834710743801653,
+      "grad_norm": 3.7118818864195466,
+      "learning_rate": 1.6493055555555555e-07,
+      "logits/chosen": -1.722265601158142,
+      "logits/rejected": -1.691015601158142,
+      "logps/chosen": -83.59375,
+      "logps/rejected": -128.953125,
+      "loss": 0.2053,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.312109351158142,
+      "rewards/margins": 2.3080077171325684,
+      "rewards/rejected": -0.995330810546875,
+      "step": 210
+    },
+    {
+      "epoch": 1.4165289256198348,
+      "grad_norm": 13.111903944179245,
+      "learning_rate": 1.5624999999999999e-07,
+      "logits/chosen": -1.746679663658142,
+      "logits/rejected": -1.7384765148162842,
+      "logps/chosen": -92.25,
+      "logps/rejected": -143.0031280517578,
+      "loss": 0.2477,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.2750976085662842,
+      "rewards/margins": 2.1878905296325684,
+      "rewards/rejected": -0.9129577875137329,
+      "step": 215
+    },
+    {
+      "epoch": 1.449586776859504,
+      "grad_norm": 8.98243357316642,
+      "learning_rate": 1.4756944444444445e-07,
+      "logits/chosen": -1.7062499523162842,
+      "logits/rejected": -1.7119140625,
+      "logps/chosen": -54.498435974121094,
+      "logps/rejected": -75.37187194824219,
+      "loss": 0.2179,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.424560546875,
+      "rewards/margins": 2.394970655441284,
+      "rewards/rejected": -0.9706786870956421,
+      "step": 220
+    },
+    {
+      "epoch": 1.4826446280991736,
+      "grad_norm": 12.808066286335526,
+      "learning_rate": 1.3888888888888888e-07,
+      "logits/chosen": -1.7238280773162842,
+      "logits/rejected": -1.69140625,
+      "logps/chosen": -84.2437515258789,
+      "logps/rejected": -208.33438110351562,
+      "loss": 0.1979,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 1.435449242591858,
+      "rewards/margins": 2.487499952316284,
+      "rewards/rejected": -1.053137183189392,
+      "step": 225
+    },
+    {
+      "epoch": 1.515702479338843,
+      "grad_norm": 12.264081534579313,
+      "learning_rate": 1.3020833333333334e-07,
+      "logits/chosen": -1.7414062023162842,
+      "logits/rejected": -1.8126952648162842,
+      "logps/chosen": -104.0718765258789,
+      "logps/rejected": -214.6531219482422,
+      "loss": 0.2108,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.247045874595642,
+      "rewards/margins": 2.327441453933716,
+      "rewards/rejected": -1.0798766613006592,
+      "step": 230
+    },
+    {
+      "epoch": 1.5487603305785123,
+      "grad_norm": 13.542480117605272,
+      "learning_rate": 1.2152777777777777e-07,
+      "logits/chosen": -1.7566406726837158,
+      "logits/rejected": -1.7218749523162842,
+      "logps/chosen": -94.53125,
+      "logps/rejected": -159.43124389648438,
+      "loss": 0.2589,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.1764647960662842,
+      "rewards/margins": 2.2066407203674316,
+      "rewards/rejected": -1.030126929283142,
+      "step": 235
+    },
+    {
+      "epoch": 1.5818181818181818,
+      "grad_norm": 12.091282830905666,
+      "learning_rate": 1.1284722222222222e-07,
+      "logits/chosen": -1.726953148841858,
+      "logits/rejected": -1.731054663658142,
+      "logps/chosen": -103.51875305175781,
+      "logps/rejected": -142.2843780517578,
+      "loss": 0.2465,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.175048828125,
+      "rewards/margins": 2.24957275390625,
+      "rewards/rejected": -1.075646996498108,
+      "step": 240
+    },
+    {
+      "epoch": 1.6148760330578513,
+      "grad_norm": 10.386454689797876,
+      "learning_rate": 1.0416666666666667e-07,
+      "logits/chosen": -1.7158203125,
+      "logits/rejected": -1.738867163658142,
+      "logps/chosen": -149.1125030517578,
+      "logps/rejected": -225.484375,
+      "loss": 0.2091,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.264672875404358,
+      "rewards/margins": 2.459765672683716,
+      "rewards/rejected": -1.1947753429412842,
+      "step": 245
+    },
+    {
+      "epoch": 1.6479338842975206,
+      "grad_norm": 11.535999334661906,
+      "learning_rate": 9.54861111111111e-08,
+      "logits/chosen": -1.6787109375,
+      "logits/rejected": -1.705468773841858,
+      "logps/chosen": -110.4765625,
+      "logps/rejected": -99.65937805175781,
+      "loss": 0.2224,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.3373291492462158,
+      "rewards/margins": 2.2801756858825684,
+      "rewards/rejected": -0.9426910281181335,
+      "step": 250
+    },
+    {
+      "epoch": 1.68099173553719,
+      "grad_norm": 12.221384548644076,
+      "learning_rate": 8.680555555555555e-08,
+      "logits/chosen": -1.7462890148162842,
+      "logits/rejected": -1.6970703601837158,
+      "logps/chosen": -77.2984390258789,
+      "logps/rejected": -157.0281219482422,
+      "loss": 0.2205,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.394323706626892,
+      "rewards/margins": 2.5204100608825684,
+      "rewards/rejected": -1.124169945716858,
+      "step": 255
+    },
+    {
+      "epoch": 1.7140495867768595,
+      "grad_norm": 7.1842584754057635,
+      "learning_rate": 7.812499999999999e-08,
+      "logits/chosen": -1.6804687976837158,
+      "logits/rejected": -1.671289086341858,
+      "logps/chosen": -121.0609359741211,
+      "logps/rejected": -221.22811889648438,
+      "loss": 0.2036,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.3713257312774658,
+      "rewards/margins": 2.472705125808716,
+      "rewards/rejected": -1.101171851158142,
+      "step": 260
+    },
+    {
+      "epoch": 1.747107438016529,
+      "grad_norm": 10.198371331055432,
+      "learning_rate": 6.944444444444444e-08,
+      "logits/chosen": -1.7517578601837158,
+      "logits/rejected": -1.7761719226837158,
+      "logps/chosen": -107.21875,
+      "logps/rejected": -152.17813110351562,
+      "loss": 0.1913,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 1.3739745616912842,
+      "rewards/margins": 2.637890577316284,
+      "rewards/rejected": -1.2629883289337158,
+      "step": 265
+    },
+    {
+      "epoch": 1.7801652892561983,
+      "grad_norm": 7.641943419372844,
+      "learning_rate": 6.076388888888889e-08,
+      "logits/chosen": -1.6964843273162842,
+      "logits/rejected": -1.694921851158142,
+      "logps/chosen": -69.37812805175781,
+      "logps/rejected": -61.01250076293945,
+      "loss": 0.1954,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.41259765625,
+      "rewards/margins": 2.5541014671325684,
+      "rewards/rejected": -1.141119360923767,
+      "step": 270
+    },
+    {
+      "epoch": 1.8132231404958676,
+      "grad_norm": 11.114602201507525,
+      "learning_rate": 5.208333333333333e-08,
+      "logits/chosen": -1.6591796875,
+      "logits/rejected": -1.7351562976837158,
+      "logps/chosen": -87.42655944824219,
+      "logps/rejected": -105.8843765258789,
+      "loss": 0.2048,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.306982398033142,
+      "rewards/margins": 2.4515624046325684,
+      "rewards/rejected": -1.14251708984375,
+      "step": 275
+    },
+    {
+      "epoch": 1.8462809917355372,
+      "grad_norm": 15.379731063683517,
+      "learning_rate": 4.340277777777777e-08,
+      "logits/chosen": -1.618749976158142,
+      "logits/rejected": -1.649999976158142,
+      "logps/chosen": -119.0171890258789,
+      "logps/rejected": -173.796875,
+      "loss": 0.2651,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.188745141029358,
+      "rewards/margins": 2.2294921875,
+      "rewards/rejected": -1.0393798351287842,
+      "step": 280
+    },
+    {
+      "epoch": 1.8793388429752067,
+      "grad_norm": 6.061786674310964,
+      "learning_rate": 3.472222222222222e-08,
+      "logits/chosen": -1.7941405773162842,
+      "logits/rejected": -1.791601538658142,
+      "logps/chosen": -74.0921859741211,
+      "logps/rejected": -139.1843719482422,
+      "loss": 0.2076,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.3419921398162842,
+      "rewards/margins": 2.566699266433716,
+      "rewards/rejected": -1.22357177734375,
+      "step": 285
+    },
+    {
+      "epoch": 1.912396694214876,
+      "grad_norm": 5.230589963566852,
+      "learning_rate": 2.6041666666666667e-08,
+      "logits/chosen": -1.738671898841858,
+      "logits/rejected": -1.742773413658142,
+      "logps/chosen": -71.78593444824219,
+      "logps/rejected": -128.6593780517578,
+      "loss": 0.1771,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.4137451648712158,
+      "rewards/margins": 2.7740235328674316,
+      "rewards/rejected": -1.360070824623108,
+      "step": 290
+    },
+    {
+      "epoch": 1.9454545454545453,
+      "grad_norm": 9.184910311105565,
+      "learning_rate": 1.736111111111111e-08,
+      "logits/chosen": -1.646484375,
+      "logits/rejected": -1.681054711341858,
+      "logps/chosen": -52.390625,
+      "logps/rejected": -72.6812515258789,
+      "loss": 0.217,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.3534667491912842,
+      "rewards/margins": 2.360156297683716,
+      "rewards/rejected": -1.006866455078125,
+      "step": 295
+    },
+    {
+      "epoch": 1.9785123966942149,
+      "grad_norm": 25.401166784551016,
+      "learning_rate": 8.680555555555555e-09,
+      "logits/chosen": -1.756445288658142,
+      "logits/rejected": -1.7527344226837158,
+      "logps/chosen": -120.4921875,
+      "logps/rejected": -117.88749694824219,
+      "loss": 0.2535,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.1732177734375,
+      "rewards/margins": 2.3089842796325684,
+      "rewards/rejected": -1.13714599609375,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "step": 304,
+      "total_flos": 0.0,
+      "train_loss": 0.34146574610158015,
+      "train_runtime": 4832.1445,
+      "train_samples_per_second": 2.002,
+      "train_steps_per_second": 0.063
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 304,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "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:ad24b45b62b0a1c980a89307b40b1ecff57cdd44870e1adae756f8b457ce66a9
+size 7800