初始化项目，由ModelHub XC社区提供模型

Model: arnav-yadav/jailbreak-attacker-l2 Source: Original Platform
2026-06-06 04:30:15 +08:00
commit 36e96bc2b2
127 changed files with 13501 additions and 0 deletions
--- a/checkpoint-350/README.md
+++ b/checkpoint-350/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit
+- grpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1
--- a/checkpoint-350/adapter_config.json
+++ b/checkpoint-350/adapter_config.json
@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
--- a/checkpoint-350/adapter_model.safetensors
+++ b/checkpoint-350/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c15416a03a5cdc4e75b72c792ddd593b6f4691a47e5010ced8d2aca7fc6241c
+size 17462432
--- a/checkpoint-350/chat_template.jinja
+++ b/checkpoint-350/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. 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|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- 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 + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + 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|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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' }}
+{%- endif %}
--- a/checkpoint-350/optimizer.pt
+++ b/checkpoint-350/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a8c7b5ce75204386d022d817feec1d6b704c9123e6baf28dc034450d4e2247
+size 9117643
--- a/checkpoint-350/rng_state.pth
+++ b/checkpoint-350/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13498e441e117878ad5ef63f21936541c2618640ab7ca677b078d0de5d93cfb3
+size 14645
--- a/checkpoint-350/scaler.pt
+++ b/checkpoint-350/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a3b7c7f6ae3d4b9e2fcb0774d91cea73c152177e3f6818dfc11db3a9a74275
+size 1383
--- a/checkpoint-350/scheduler.pt
+++ b/checkpoint-350/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de957f913cdcc25511d72448987f4ea6828e6a9818bfc6f84f3b177896760ef
+size 1465
--- a/checkpoint-350/tokenizer.json
+++ b/checkpoint-350/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5891a15588546db1ac7f2baf8fa94835a51a85c032c39793a55bb048b47446
+size 11422523
--- a/checkpoint-350/tokenizer_config.json
+++ b/checkpoint-350/tokenizer_config.json
@@ -0,0 +1,201 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}
--- a/checkpoint-350/trainer_state.json
+++ b/checkpoint-350/trainer_state.json
@@ -0,0 +1,979 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.1875,
+  "eval_steps": 500,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.0625,
+      "frac_reward_zero_std": 0.075,
+      "grad_norm": 0.12458323687314987,
+      "kl": 1.9381546007934957e-05,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 3.427267074584961e-08,
+      "num_tokens": 57908.0,
+      "reward": -1.4099999368190765,
+      "reward_std": 0.7305359303951263,
+      "rewards/reward_fn/mean": -1.409999930858612,
+      "rewards/reward_fn/std": 0.8336655974388123,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.125,
+      "frac_reward_zero_std": 0.05,
+      "grad_norm": 0.13424909114837646,
+      "kl": 3.758955572266132e-05,
+      "learning_rate": 1.9791666666666665e-05,
+      "loss": 2.0861625671386717e-08,
+      "num_tokens": 115744.0,
+      "reward": -1.5606249690055847,
+      "reward_std": 0.6338691949844361,
+      "rewards/reward_fn/mean": -1.5606249451637269,
+      "rewards/reward_fn/std": 0.6913031578063965,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.1875,
+      "frac_reward_zero_std": 0.025,
+      "grad_norm": 0.12381561845541,
+      "kl": 0.000246869730472099,
+      "learning_rate": 3.0208333333333334e-05,
+      "loss": 2.4400651454925537e-07,
+      "num_tokens": 173524.0,
+      "reward": -1.4581249356269836,
+      "reward_std": 0.7430005550384522,
+      "rewards/reward_fn/mean": -1.4581249117851258,
+      "rewards/reward_fn/std": 0.7565619319677352,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 0.025,
+      "grad_norm": 0.14411121606826782,
+      "kl": 0.0016107790230307727,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 1.6100704669952392e-06,
+      "num_tokens": 231416.0,
+      "reward": -1.3331249535083771,
+      "reward_std": 0.6972330152988434,
+      "rewards/reward_fn/mean": -1.3331249415874482,
+      "rewards/reward_fn/std": 0.766948527097702,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.3125,
+      "frac_reward_zero_std": 0.175,
+      "grad_norm": 0.14639103412628174,
+      "kl": 0.007588638024753891,
+      "learning_rate": 4.988425925925926e-05,
+      "loss": 7.59512186050415e-06,
+      "num_tokens": 289368.0,
+      "reward": -1.0006249606609345,
+      "reward_std": 0.6684236854314805,
+      "rewards/reward_fn/mean": -1.0006249785423278,
+      "rewards/reward_fn/std": 0.7909055948257446,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.375,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.1545860469341278,
+      "kl": 0.024985690240282566,
+      "learning_rate": 4.8726851851851855e-05,
+      "loss": 2.498328685760498e-05,
+      "num_tokens": 346964.0,
+      "reward": -0.6074999988079071,
+      "reward_std": 0.5110155880451203,
+      "rewards/reward_fn/mean": -0.6075000107288361,
+      "rewards/reward_fn/std": 0.6012047231197357,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.4375,
+      "frac_reward_zero_std": 0.725,
+      "grad_norm": 0.12491069734096527,
+      "kl": 0.042862199200317266,
+      "learning_rate": 4.756944444444444e-05,
+      "loss": 4.285752947907895e-05,
+      "num_tokens": 404676.0,
+      "reward": -0.41250000298023226,
+      "reward_std": 0.19732050001621246,
+      "rewards/reward_fn/mean": -0.41250000298023226,
+      "rewards/reward_fn/std": 0.3099328398704529,
+      "step": 70
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.825,
+      "grad_norm": 0.139762744307518,
+      "kl": 0.05795831000432372,
+      "learning_rate": 4.6412037037037034e-05,
+      "loss": 5.795210599899292e-05,
+      "num_tokens": 462404.0,
+      "reward": -0.3443750023841858,
+      "reward_std": 0.11552571803331375,
+      "rewards/reward_fn/mean": -0.344375005364418,
+      "rewards/reward_fn/std": 0.1971571922302246,
+      "step": 80
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.5625,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.0012635246384888887,
+      "kl": 0.0758059567771852,
+      "learning_rate": 4.525462962962963e-05,
+      "loss": 7.580451783724129e-05,
+      "num_tokens": 520292.0,
+      "reward": -0.341250005364418,
+      "reward_std": 0.06749999970197677,
+      "rewards/reward_fn/mean": -0.34125000834465025,
+      "rewards/reward_fn/std": 0.14239275455474854,
+      "step": 90
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.625,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.28265202045440674,
+      "kl": 0.10205610543489456,
+      "learning_rate": 4.4097222222222226e-05,
+      "loss": 0.00010205432772636414,
+      "num_tokens": 578164.0,
+      "reward": -0.31062501221895217,
+      "reward_std": 0.05374999940395355,
+      "rewards/reward_fn/mean": -0.31062501221895217,
+      "rewards/reward_fn/std": 0.0848927527666092,
+      "step": 100
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.6875,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.15435293316841125,
+      "kl": 0.11740942746400833,
+      "learning_rate": 4.293981481481482e-05,
+      "loss": 0.00011740787886083126,
+      "num_tokens": 635928.0,
+      "reward": -0.3262500077486038,
+      "reward_std": 0.052499999105930326,
+      "rewards/reward_fn/mean": -0.3262500077486038,
+      "rewards/reward_fn/std": 0.10499999821186065,
+      "step": 110
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.75,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0017832271987572312,
+      "kl": 0.1092877883464098,
+      "learning_rate": 4.178240740740741e-05,
+      "loss": 0.0001092874095775187,
+      "num_tokens": 693776.0,
+      "reward": -0.31125001013278963,
+      "reward_std": 0.02249999940395355,
+      "rewards/reward_fn/mean": -0.31125001013278963,
+      "rewards/reward_fn/std": 0.04499999582767487,
+      "step": 120
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.8125,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0019980475772172213,
+      "kl": 0.1017705887556076,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.00010176897048950196,
+      "num_tokens": 751704.0,
+      "reward": -0.3262500077486038,
+      "reward_std": 0.05249999761581421,
+      "rewards/reward_fn/mean": -0.3262500077486038,
+      "rewards/reward_fn/std": 0.10499999821186065,
+      "step": 130
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.875,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.006963597144931555,
+      "kl": 0.10655302237719297,
+      "learning_rate": 3.94675925925926e-05,
+      "loss": 0.00010655303485691547,
+      "num_tokens": 809360.0,
+      "reward": -0.31125001013278963,
+      "reward_std": 0.02249999940395355,
+      "rewards/reward_fn/mean": -0.31125001013278963,
+      "rewards/reward_fn/std": 0.04499999582767487,
+      "step": 140
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.9375,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0015019988641142845,
+      "kl": 0.10568692134693265,
+      "learning_rate": 3.831018518518519e-05,
+      "loss": 0.00010568510042503476,
+      "num_tokens": 867440.0,
+      "reward": -0.33375000655651094,
+      "reward_std": 0.06749999821186066,
+      "rewards/reward_fn/mean": -0.33375000655651094,
+      "rewards/reward_fn/std": 0.1349999874830246,
+      "step": 150
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0008070049225352705,
+      "kl": 0.07564885132014751,
+      "learning_rate": 3.715277777777778e-05,
+      "loss": 7.564762490801513e-05,
+      "num_tokens": 925440.0,
+      "reward": -0.30750001072883604,
+      "reward_std": 0.015000000596046448,
+      "rewards/reward_fn/mean": -0.30750001072883604,
+      "rewards/reward_fn/std": 0.030000001192092896,
+      "step": 160
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.0625,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0015270161675289273,
+      "kl": 0.06843139906413853,
+      "learning_rate": 3.5995370370370376e-05,
+      "loss": 6.842819275334477e-05,
+      "num_tokens": 983304.0,
+      "reward": -0.33375000655651094,
+      "reward_std": 0.06749999821186066,
+      "rewards/reward_fn/mean": -0.33375000655651094,
+      "rewards/reward_fn/std": 0.1349999874830246,
+      "step": 170
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0007024089572951198,
+      "kl": 0.06553028370253741,
+      "learning_rate": 3.483796296296297e-05,
+      "loss": 6.553027196787298e-05,
+      "num_tokens": 1041204.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 180
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.1875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.001360859489068389,
+      "kl": 0.058797695627436045,
+      "learning_rate": 3.368055555555556e-05,
+      "loss": 5.8797706151381136e-05,
+      "num_tokens": 1099072.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 190
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.25,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0012780348770320415,
+      "kl": 0.05732685485854745,
+      "learning_rate": 3.252314814814815e-05,
+      "loss": 5.732685676775873e-05,
+      "num_tokens": 1156860.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 200
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.3125,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0007964351680129766,
+      "kl": 0.0754379843827337,
+      "learning_rate": 3.136574074074074e-05,
+      "loss": 7.543485262431204e-05,
+      "num_tokens": 1214784.0,
+      "reward": -0.3150000095367432,
+      "reward_std": 0.029999998956918718,
+      "rewards/reward_fn/mean": -0.3150000095367432,
+      "rewards/reward_fn/std": 0.059999996423721315,
+      "step": 210
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.375,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0004977025673724711,
+      "kl": 0.05669140527024865,
+      "learning_rate": 3.0208333333333334e-05,
+      "loss": 5.669001257047057e-05,
+      "num_tokens": 1272932.0,
+      "reward": -0.3187500089406967,
+      "reward_std": 0.03749999850988388,
+      "rewards/reward_fn/mean": -0.3187500089406967,
+      "rewards/reward_fn/std": 0.07499999701976776,
+      "step": 220
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.4375,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0008227138314396143,
+      "kl": 0.0492351729888469,
+      "learning_rate": 2.9050925925925926e-05,
+      "loss": 4.923430969938636e-05,
+      "num_tokens": 1330828.0,
+      "reward": -0.30750001072883604,
+      "reward_std": 0.014999999105930329,
+      "rewards/reward_fn/mean": -0.30750001072883604,
+      "rewards/reward_fn/std": 0.030000001192092896,
+      "step": 230
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.5,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0008481480763293803,
+      "kl": 0.05081965173594653,
+      "learning_rate": 2.789351851851852e-05,
+      "loss": 5.0819659372791647e-05,
+      "num_tokens": 1388588.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 240
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.5625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00036746280966326594,
+      "kl": 0.046290718484669924,
+      "learning_rate": 2.6736111111111112e-05,
+      "loss": 4.6290719183161855e-05,
+      "num_tokens": 1446308.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 250
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0007307095802389085,
+      "kl": 0.04613759703934193,
+      "learning_rate": 2.5578703703703705e-05,
+      "loss": 4.613760684151203e-05,
+      "num_tokens": 1503988.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 260
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.6875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0006135129951871932,
+      "kl": 0.051912948861718176,
+      "learning_rate": 2.4421296296296298e-05,
+      "loss": 5.191295058466494e-05,
+      "num_tokens": 1561968.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 270
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.75,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0008430331945419312,
+      "kl": 0.05388685767538846,
+      "learning_rate": 2.326388888888889e-05,
+      "loss": 5.3886871319264175e-05,
+      "num_tokens": 1619908.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 280
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.8125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00030109184444881976,
+      "kl": 0.04647140288725495,
+      "learning_rate": 2.2106481481481483e-05,
+      "loss": 4.6471410314552486e-05,
+      "num_tokens": 1677612.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 290
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00029493175679817796,
+      "kl": 0.04179914747364819,
+      "learning_rate": 2.0949074074074073e-05,
+      "loss": 4.17991541326046e-05,
+      "num_tokens": 1735372.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 300
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.9375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0018822322599589825,
+      "kl": 0.04672949458472431,
+      "learning_rate": 1.9791666666666665e-05,
+      "loss": 4.672949435189366e-05,
+      "num_tokens": 1793268.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 310
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 2.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0006305224960669875,
+      "kl": 0.044585675746202466,
+      "learning_rate": 1.863425925925926e-05,
+      "loss": 4.458568291738629e-05,
+      "num_tokens": 1850880.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 320
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 2.0625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0003445159236434847,
+      "kl": 0.04190994901582599,
+      "learning_rate": 1.747685185185185e-05,
+      "loss": 4.190995532553643e-05,
+      "num_tokens": 1908628.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 330
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 2.125,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.00043421241571195424,
+      "kl": 0.04299232084304094,
+      "learning_rate": 1.6319444444444444e-05,
+      "loss": 4.2992207454517484e-05,
+      "num_tokens": 1966240.0,
+      "reward": -0.30750001072883604,
+      "reward_std": 0.014999999105930329,
+      "rewards/reward_fn/mean": -0.30750001072883604,
+      "rewards/reward_fn/std": 0.030000001192092896,
+      "step": 340
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 256.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 256.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 256.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 2.1875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0005787091795355082,
+      "kl": 0.047347473446279764,
+      "learning_rate": 1.5162037037037038e-05,
+      "loss": 4.7347473446279766e-05,
+      "num_tokens": 2024200.0,
+      "reward": -0.30000001192092896,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": -0.30000001192092896,
+      "rewards/reward_fn/std": 0.0,
+      "step": 350
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 480,
+  "num_input_tokens_seen": 2024200,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/checkpoint-350/training_args.bin
+++ b/checkpoint-350/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb5eec9fa732effecc39928ed0f7eda205a0e16573a345963766968a1a8e3e2
+size 6737