LoRA adapter at training step 150

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: peft
+---
+
+# 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 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ab34db1f4e7f90c1ec81b6bf73c51580f6d4d933fb4d5bfba6ae90932f89df
+size 513877864

added_tokens.json

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

chat_template.jinja

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

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:066faf318152c36e45c2f6d7e9d220c29765c22e7b74929974a120bef2487a2d
+size 1028078067

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d367f4f9c11be6f02e99ea7ae867e2afcbc7345f1d6a13cb41742a1e3644764
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad292b5d14b8f8d85544d7d54740ffc013a4923be9b6dca5a08e1479e52628cc
+size 1465

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de053c72a4ae289224ac988558897303006ceea1db22f30b97d0d856969ea6b9
+size 11422818

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,964 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.002736726874657909,
+  "eval_steps": 500,
+  "global_step": 150,
+  "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 530.0,
+      "completions/max_terminated_length": 530.0,
+      "completions/mean_length": 459.0875,
+      "completions/mean_terminated_length": 459.0875,
+      "completions/min_length": 382.6,
+      "completions/min_terminated_length": 382.6,
+      "epoch": 9.122422915526363e-05,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08330418169498444,
+      "learning_rate": 2e-05,
+      "loss": -0.017,
+      "num_tokens": 42647.0,
+      "reward": 1.7133710861206055,
+      "reward_std": 0.06495940759778022,
+      "rewards/reward_humanlike/mean": -0.0049063809216022495,
+      "rewards/reward_humanlike/std": 0.0013417582493275404,
+      "rewards/reward_nonslop/mean": 0.4698944389820099,
+      "rewards/reward_nonslop/std": 0.02207690291106701,
+      "rewards/reward_paragraph_structure/mean": 0.9225000023841858,
+      "rewards/reward_paragraph_structure/std": 0.05570792183279991,
+      "rewards/reward_variance_humanlike/mean": 0.3258830189704895,
+      "rewards/reward_variance_humanlike/std": 0.03409086093306542,
+      "step": 5
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 518.8,
+      "completions/max_terminated_length": 518.8,
+      "completions/mean_length": 457.8125,
+      "completions/mean_terminated_length": 457.8125,
+      "completions/min_length": 408.2,
+      "completions/min_terminated_length": 408.2,
+      "epoch": 0.00018244845831052726,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07756281644105911,
+      "learning_rate": 2e-05,
+      "loss": -0.0038,
+      "num_tokens": 85064.0,
+      "reward": 1.7329328775405883,
+      "reward_std": 0.059737163782119754,
+      "rewards/reward_humanlike/mean": -0.006193175911903381,
+      "rewards/reward_humanlike/std": 0.0012689156574197114,
+      "rewards/reward_nonslop/mean": 0.4595408201217651,
+      "rewards/reward_nonslop/std": 0.021954230777919293,
+      "rewards/reward_paragraph_structure/mean": 0.9339999556541443,
+      "rewards/reward_paragraph_structure/std": 0.034224916622042655,
+      "rewards/reward_variance_humanlike/mean": 0.34558519124984743,
+      "rewards/reward_variance_humanlike/std": 0.04318429157137871,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 522.0,
+      "completions/max_terminated_length": 522.0,
+      "completions/mean_length": 457.6625,
+      "completions/mean_terminated_length": 457.6625,
+      "completions/min_length": 404.6,
+      "completions/min_terminated_length": 404.6,
+      "epoch": 0.0002736726874657909,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07608332484960556,
+      "learning_rate": 2e-05,
+      "loss": -0.0146,
+      "num_tokens": 127517.0,
+      "reward": 1.6709249019622803,
+      "reward_std": 0.0486908458173275,
+      "rewards/reward_humanlike/mean": -0.006584349274635315,
+      "rewards/reward_humanlike/std": 0.000867948867380619,
+      "rewards/reward_nonslop/mean": 0.4447902083396912,
+      "rewards/reward_nonslop/std": 0.023332541435956956,
+      "rewards/reward_paragraph_structure/mean": 0.934500002861023,
+      "rewards/reward_paragraph_structure/std": 0.03865866586565971,
+      "rewards/reward_variance_humanlike/mean": 0.2982190430164337,
+      "rewards/reward_variance_humanlike/std": 0.032131852209568025,
+      "step": 15
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 541.6,
+      "completions/max_terminated_length": 541.6,
+      "completions/mean_length": 473.8875,
+      "completions/mean_terminated_length": 473.8875,
+      "completions/min_length": 418.2,
+      "completions/min_terminated_length": 418.2,
+      "epoch": 0.00036489691662105453,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07590995728969574,
+      "learning_rate": 2e-05,
+      "loss": -0.0135,
+      "num_tokens": 171220.0,
+      "reward": 1.655500054359436,
+      "reward_std": 0.05006450563669205,
+      "rewards/reward_humanlike/mean": -0.006528209149837494,
+      "rewards/reward_humanlike/std": 0.0008110307855531574,
+      "rewards/reward_nonslop/mean": 0.4389641106128693,
+      "rewards/reward_nonslop/std": 0.020602181926369666,
+      "rewards/reward_paragraph_structure/mean": 0.9475000023841857,
+      "rewards/reward_paragraph_structure/std": 0.035131752490997314,
+      "rewards/reward_variance_humanlike/mean": 0.2755641430616379,
+      "rewards/reward_variance_humanlike/std": 0.03498224206268787,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 552.6,
+      "completions/max_terminated_length": 552.6,
+      "completions/mean_length": 481.075,
+      "completions/mean_terminated_length": 481.075,
+      "completions/min_length": 421.6,
+      "completions/min_terminated_length": 421.6,
+      "epoch": 0.0004561211457763182,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08101129531860352,
+      "learning_rate": 2e-05,
+      "loss": -0.0111,
+      "num_tokens": 215578.0,
+      "reward": 1.686311173439026,
+      "reward_std": 0.05389990359544754,
+      "rewards/reward_humanlike/mean": -0.0063924640417099,
+      "rewards/reward_humanlike/std": 0.0013852458912879228,
+      "rewards/reward_nonslop/mean": 0.4303958237171173,
+      "rewards/reward_nonslop/std": 0.02291610725224018,
+      "rewards/reward_paragraph_structure/mean": 0.9554999947547913,
+      "rewards/reward_paragraph_structure/std": 0.03535142131149769,
+      "rewards/reward_variance_humanlike/mean": 0.3068078398704529,
+      "rewards/reward_variance_humanlike/std": 0.03916346058249474,
+      "step": 25
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 575.2,
+      "completions/max_terminated_length": 575.2,
+      "completions/mean_length": 506.4125,
+      "completions/mean_terminated_length": 506.4125,
+      "completions/min_length": 437.8,
+      "completions/min_terminated_length": 437.8,
+      "epoch": 0.0005473453749315818,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07839162647724152,
+      "learning_rate": 2e-05,
+      "loss": -0.003,
+      "num_tokens": 261915.0,
+      "reward": 1.6966917037963867,
+      "reward_std": 0.05147708132863045,
+      "rewards/reward_humanlike/mean": -0.005980825424194336,
+      "rewards/reward_humanlike/std": 0.0013130037346854805,
+      "rewards/reward_nonslop/mean": 0.43321479558944703,
+      "rewards/reward_nonslop/std": 0.022418199107050896,
+      "rewards/reward_paragraph_structure/mean": 0.965500020980835,
+      "rewards/reward_paragraph_structure/std": 0.03038812577724457,
+      "rewards/reward_variance_humanlike/mean": 0.3039577305316925,
+      "rewards/reward_variance_humanlike/std": 0.03852991610765457,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 588.4,
+      "completions/max_terminated_length": 588.4,
+      "completions/mean_length": 520.675,
+      "completions/mean_terminated_length": 520.675,
+      "completions/min_length": 449.8,
+      "completions/min_terminated_length": 449.8,
+      "epoch": 0.0006385696040868455,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08089983463287354,
+      "learning_rate": 2e-05,
+      "loss": 0.01,
+      "num_tokens": 309441.0,
+      "reward": 1.713779377937317,
+      "reward_std": 0.04969915598630905,
+      "rewards/reward_humanlike/mean": -0.005676886439323426,
+      "rewards/reward_humanlike/std": 0.001277495315298438,
+      "rewards/reward_nonslop/mean": 0.44167782068252565,
+      "rewards/reward_nonslop/std": 0.026974805071949957,
+      "rewards/reward_paragraph_structure/mean": 0.9735000133514404,
+      "rewards/reward_paragraph_structure/std": 0.02794780358672142,
+      "rewards/reward_variance_humanlike/mean": 0.3042784631252289,
+      "rewards/reward_variance_humanlike/std": 0.04240153580904007,
+      "step": 35
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 613.0,
+      "completions/max_terminated_length": 613.0,
+      "completions/mean_length": 532.15,
+      "completions/mean_terminated_length": 532.15,
+      "completions/min_length": 450.6,
+      "completions/min_terminated_length": 450.6,
+      "epoch": 0.0007297938332421091,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08725527673959732,
+      "learning_rate": 2e-05,
+      "loss": -0.0082,
+      "num_tokens": 357821.0,
+      "reward": 1.7072110414505004,
+      "reward_std": 0.08227875493466855,
+      "rewards/reward_humanlike/mean": -0.00399986058473587,
+      "rewards/reward_humanlike/std": 0.0019454783294349908,
+      "rewards/reward_nonslop/mean": 0.4142237663269043,
+      "rewards/reward_nonslop/std": 0.022323147021234037,
+      "rewards/reward_paragraph_structure/mean": 0.9635000228881836,
+      "rewards/reward_paragraph_structure/std": 0.06351297833025456,
+      "rewards/reward_variance_humanlike/mean": 0.33348714709281924,
+      "rewards/reward_variance_humanlike/std": 0.04445431642234325,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 586.0,
+      "completions/max_terminated_length": 586.0,
+      "completions/mean_length": 516.025,
+      "completions/mean_terminated_length": 516.025,
+      "completions/min_length": 429.2,
+      "completions/min_terminated_length": 429.2,
+      "epoch": 0.0008210180623973727,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07776515185832977,
+      "learning_rate": 2e-05,
+      "loss": 0.0029,
+      "num_tokens": 405039.0,
+      "reward": 1.758931827545166,
+      "reward_std": 0.07233260497450829,
+      "rewards/reward_humanlike/mean": -0.005538669228553772,
+      "rewards/reward_humanlike/std": 0.0021492485189810394,
+      "rewards/reward_nonslop/mean": 0.4442190766334534,
+      "rewards/reward_nonslop/std": 0.026956739276647566,
+      "rewards/reward_paragraph_structure/mean": 0.9730000257492065,
+      "rewards/reward_paragraph_structure/std": 0.05119010470807552,
+      "rewards/reward_variance_humanlike/mean": 0.34725142121315,
+      "rewards/reward_variance_humanlike/std": 0.045725250244140626,
+      "step": 45
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 625.8,
+      "completions/max_terminated_length": 625.8,
+      "completions/mean_length": 525.625,
+      "completions/mean_terminated_length": 525.625,
+      "completions/min_length": 442.8,
+      "completions/min_terminated_length": 442.8,
+      "epoch": 0.0009122422915526364,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0774134173989296,
+      "learning_rate": 2e-05,
+      "loss": 0.0049,
+      "num_tokens": 452961.0,
+      "reward": 1.7036024570465087,
+      "reward_std": 0.07441542074084281,
+      "rewards/reward_humanlike/mean": -0.006102602928876877,
+      "rewards/reward_humanlike/std": 0.0014865510282106697,
+      "rewards/reward_nonslop/mean": 0.4318544864654541,
+      "rewards/reward_nonslop/std": 0.026268348470330237,
+      "rewards/reward_paragraph_structure/mean": 0.9745000243186951,
+      "rewards/reward_paragraph_structure/std": 0.04429337792098522,
+      "rewards/reward_variance_humanlike/mean": 0.3033505916595459,
+      "rewards/reward_variance_humanlike/std": 0.04139695428311825,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 609.6,
+      "completions/max_terminated_length": 609.6,
+      "completions/mean_length": 521.1625,
+      "completions/mean_terminated_length": 521.1625,
+      "completions/min_length": 437.0,
+      "completions/min_terminated_length": 437.0,
+      "epoch": 0.0010034665207079,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0859595239162445,
+      "learning_rate": 2e-05,
+      "loss": -0.0142,
+      "num_tokens": 500574.0,
+      "reward": 1.7607794046401977,
+      "reward_std": 0.07357486188411713,
+      "rewards/reward_humanlike/mean": -0.005865442752838135,
+      "rewards/reward_humanlike/std": 0.0013492291327565908,
+      "rewards/reward_nonslop/mean": 0.448255854845047,
+      "rewards/reward_nonslop/std": 0.023698090761899947,
+      "rewards/reward_paragraph_structure/mean": 0.9675000071525574,
+      "rewards/reward_paragraph_structure/std": 0.051267866417765616,
+      "rewards/reward_variance_humanlike/mean": 0.3508889973163605,
+      "rewards/reward_variance_humanlike/std": 0.04507431238889694,
+      "step": 55
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 634.4,
+      "completions/max_terminated_length": 634.4,
+      "completions/mean_length": 535.475,
+      "completions/mean_terminated_length": 535.475,
+      "completions/min_length": 460.4,
+      "completions/min_terminated_length": 460.4,
+      "epoch": 0.0010946907498631637,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.084259532392025,
+      "learning_rate": 2e-05,
+      "loss": -0.0101,
+      "num_tokens": 549252.0,
+      "reward": 1.8035558938980103,
+      "reward_std": 0.07631172686815262,
+      "rewards/reward_humanlike/mean": -0.004114150255918503,
+      "rewards/reward_humanlike/std": 0.004924690327607095,
+      "rewards/reward_nonslop/mean": 0.4565321087837219,
+      "rewards/reward_nonslop/std": 0.027938447147607803,
+      "rewards/reward_paragraph_structure/mean": 0.9730000257492065,
+      "rewards/reward_paragraph_structure/std": 0.029559650644659995,
+      "rewards/reward_variance_humanlike/mean": 0.37813796401023864,
+      "rewards/reward_variance_humanlike/std": 0.05382424220442772,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 707.4,
+      "completions/max_terminated_length": 707.4,
+      "completions/mean_length": 573.4125,
+      "completions/mean_terminated_length": 573.4125,
+      "completions/min_length": 457.2,
+      "completions/min_terminated_length": 457.2,
+      "epoch": 0.0011859149790184272,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07620154321193695,
+      "learning_rate": 2e-05,
+      "loss": 0.0091,
+      "num_tokens": 600917.0,
+      "reward": 1.9338277339935304,
+      "reward_std": 0.0893137887120247,
+      "rewards/reward_humanlike/mean": 0.027831324189901353,
+      "rewards/reward_humanlike/std": 0.05132205095142126,
+      "rewards/reward_nonslop/mean": 0.5073926866054534,
+      "rewards/reward_nonslop/std": 0.03192124664783478,
+      "rewards/reward_paragraph_structure/mean": 0.9870000123977661,
+      "rewards/reward_paragraph_structure/std": 0.02150080054998398,
+      "rewards/reward_variance_humanlike/mean": 0.4116037130355835,
+      "rewards/reward_variance_humanlike/std": 0.04968324154615402,
+      "step": 65
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 794.8,
+      "completions/max_terminated_length": 794.8,
+      "completions/mean_length": 620.4,
+      "completions/mean_terminated_length": 620.4,
+      "completions/min_length": 506.0,
+      "completions/min_terminated_length": 506.0,
+      "epoch": 0.001277139208173691,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0841197744011879,
+      "learning_rate": 2e-05,
+      "loss": 0.0085,
+      "num_tokens": 656421.0,
+      "reward": 1.9778348207473755,
+      "reward_std": 0.11839056089520454,
+      "rewards/reward_humanlike/mean": 0.061939971148967744,
+      "rewards/reward_humanlike/std": 0.07601089626550675,
+      "rewards/reward_nonslop/mean": 0.5069686353206635,
+      "rewards/reward_nonslop/std": 0.0309759434312582,
+      "rewards/reward_paragraph_structure/mean": 0.9830000162124634,
+      "rewards/reward_paragraph_structure/std": 0.02774263098835945,
+      "rewards/reward_variance_humanlike/mean": 0.4259262323379517,
+      "rewards/reward_variance_humanlike/std": 0.04722812995314598,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 722.2,
+      "completions/max_terminated_length": 722.2,
+      "completions/mean_length": 592.0625,
+      "completions/mean_terminated_length": 592.0625,
+      "completions/min_length": 475.0,
+      "completions/min_terminated_length": 475.0,
+      "epoch": 0.0013683634373289546,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09270209819078445,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "num_tokens": 709642.0,
+      "reward": 1.9815738677978516,
+      "reward_std": 0.15368602126836778,
+      "rewards/reward_humanlike/mean": 0.06852133497595787,
+      "rewards/reward_humanlike/std": 0.06154889091849327,
+      "rewards/reward_nonslop/mean": 0.5125557720661164,
+      "rewards/reward_nonslop/std": 0.029540616273880004,
+      "rewards/reward_paragraph_structure/mean": 0.9577499985694885,
+      "rewards/reward_paragraph_structure/std": 0.10273886024951935,
+      "rewards/reward_variance_humanlike/mean": 0.4427467882633209,
+      "rewards/reward_variance_humanlike/std": 0.054600483179092406,
+      "step": 75
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 853.2,
+      "completions/max_terminated_length": 853.2,
+      "completions/mean_length": 616.2375,
+      "completions/mean_terminated_length": 616.2375,
+      "completions/min_length": 445.6,
+      "completions/min_terminated_length": 445.6,
+      "epoch": 0.0014595876664842181,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10215070843696594,
+      "learning_rate": 2e-05,
+      "loss": 0.0248,
+      "num_tokens": 764701.0,
+      "reward": 2.004007887840271,
+      "reward_std": 0.2644025519490242,
+      "rewards/reward_humanlike/mean": 0.1717693842947483,
+      "rewards/reward_humanlike/std": 0.1171185165643692,
+      "rewards/reward_nonslop/mean": 0.5301854729652404,
+      "rewards/reward_nonslop/std": 0.03163186460733414,
+      "rewards/reward_paragraph_structure/mean": 0.8657500147819519,
+      "rewards/reward_paragraph_structure/std": 0.18628381602466107,
+      "rewards/reward_variance_humanlike/mean": 0.43630297780036925,
+      "rewards/reward_variance_humanlike/std": 0.05638228878378868,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 795.4,
+      "completions/max_terminated_length": 795.4,
+      "completions/mean_length": 640.3875,
+      "completions/mean_terminated_length": 640.3875,
+      "completions/min_length": 509.0,
+      "completions/min_terminated_length": 509.0,
+      "epoch": 0.0015508118956394819,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09339434653520584,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "num_tokens": 821788.0,
+      "reward": 2.144613170623779,
+      "reward_std": 0.23063226491212846,
+      "rewards/reward_humanlike/mean": 0.19965834692120552,
+      "rewards/reward_humanlike/std": 0.13735320046544075,
+      "rewards/reward_nonslop/mean": 0.5291796326637268,
+      "rewards/reward_nonslop/std": 0.029852544143795966,
+      "rewards/reward_paragraph_structure/mean": 0.9427500247955323,
+      "rewards/reward_paragraph_structure/std": 0.1141851708292961,
+      "rewards/reward_variance_humanlike/mean": 0.47302510142326354,
+      "rewards/reward_variance_humanlike/std": 0.0692625693976879,
+      "step": 85
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 721.8,
+      "completions/max_terminated_length": 721.8,
+      "completions/mean_length": 580.7,
+      "completions/mean_terminated_length": 580.7,
+      "completions/min_length": 473.0,
+      "completions/min_terminated_length": 473.0,
+      "epoch": 0.0016420361247947454,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11648150533437729,
+      "learning_rate": 2e-05,
+      "loss": 0.0059,
+      "num_tokens": 874132.0,
+      "reward": 2.3740207672119142,
+      "reward_std": 0.261104553937912,
+      "rewards/reward_humanlike/mean": 0.42321614623069764,
+      "rewards/reward_humanlike/std": 0.19679208099842072,
+      "rewards/reward_nonslop/mean": 0.5563819169998169,
+      "rewards/reward_nonslop/std": 0.029575036093592643,
+      "rewards/reward_paragraph_structure/mean": 0.9480000257492065,
+      "rewards/reward_paragraph_structure/std": 0.11947859562933445,
+      "rewards/reward_variance_humanlike/mean": 0.4464226603507996,
+      "rewards/reward_variance_humanlike/std": 0.054964589327573775,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 704.0,
+      "completions/max_terminated_length": 704.0,
+      "completions/mean_length": 539.575,
+      "completions/mean_terminated_length": 539.575,
+      "completions/min_length": 411.6,
+      "completions/min_terminated_length": 411.6,
+      "epoch": 0.0017332603539500092,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12348563224077225,
+      "learning_rate": 2e-05,
+      "loss": -0.0104,
+      "num_tokens": 923090.0,
+      "reward": 2.377066421508789,
+      "reward_std": 0.2692029863595963,
+      "rewards/reward_humanlike/mean": 0.4465336114168167,
+      "rewards/reward_humanlike/std": 0.1494969144463539,
+      "rewards/reward_nonslop/mean": 0.5796692132949829,
+      "rewards/reward_nonslop/std": 0.03210240751504898,
+      "rewards/reward_paragraph_structure/mean": 0.8950000047683716,
+      "rewards/reward_paragraph_structure/std": 0.2005697786808014,
+      "rewards/reward_variance_humanlike/mean": 0.4558635771274567,
+      "rewards/reward_variance_humanlike/std": 0.05469868220388889,
+      "step": 95
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 713.4,
+      "completions/max_terminated_length": 713.4,
+      "completions/mean_length": 576.2,
+      "completions/mean_terminated_length": 576.2,
+      "completions/min_length": 481.0,
+      "completions/min_terminated_length": 481.0,
+      "epoch": 0.0018244845831052727,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14696431159973145,
+      "learning_rate": 2e-05,
+      "loss": 0.0089,
+      "num_tokens": 974898.0,
+      "reward": 2.410014200210571,
+      "reward_std": 0.2251954436302185,
+      "rewards/reward_humanlike/mean": 0.37983823418617246,
+      "rewards/reward_humanlike/std": 0.1678072690963745,
+      "rewards/reward_nonslop/mean": 0.577713418006897,
+      "rewards/reward_nonslop/std": 0.027568070217967033,
+      "rewards/reward_paragraph_structure/mean": 0.9690000176429748,
+      "rewards/reward_paragraph_structure/std": 0.08311126083135605,
+      "rewards/reward_variance_humanlike/mean": 0.483462518453598,
+      "rewards/reward_variance_humanlike/std": 0.06756387576460839,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 656.8,
+      "completions/max_terminated_length": 656.8,
+      "completions/mean_length": 535.975,
+      "completions/mean_terminated_length": 535.975,
+      "completions/min_length": 416.8,
+      "completions/min_terminated_length": 416.8,
+      "epoch": 0.0019157088122605363,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.18615105748176575,
+      "learning_rate": 2e-05,
+      "loss": 0.0131,
+      "num_tokens": 1023584.0,
+      "reward": 2.5038723945617676,
+      "reward_std": 0.238946396112442,
+      "rewards/reward_humanlike/mean": 0.49884518384933474,
+      "rewards/reward_humanlike/std": 0.21602095067501068,
+      "rewards/reward_nonslop/mean": 0.5793979167938232,
+      "rewards/reward_nonslop/std": 0.02930229380726814,
+      "rewards/reward_paragraph_structure/mean": 0.9612500309944153,
+      "rewards/reward_paragraph_structure/std": 0.07978770323097706,
+      "rewards/reward_variance_humanlike/mean": 0.46437926292419435,
+      "rewards/reward_variance_humanlike/std": 0.05132201015949249,
+      "step": 105
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 643.6,
+      "completions/max_terminated_length": 643.6,
+      "completions/mean_length": 521.25,
+      "completions/mean_terminated_length": 521.25,
+      "completions/min_length": 425.8,
+      "completions/min_terminated_length": 425.8,
+      "epoch": 0.0020069330414158,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.13929621875286102,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "num_tokens": 1071124.0,
+      "reward": 2.473823308944702,
+      "reward_std": 0.23840838074684143,
+      "rewards/reward_humanlike/mean": 0.4755378872156143,
+      "rewards/reward_humanlike/std": 0.1941240608692169,
+      "rewards/reward_nonslop/mean": 0.5697908401489258,
+      "rewards/reward_nonslop/std": 0.026583903655409812,
+      "rewards/reward_paragraph_structure/mean": 0.9547500252723694,
+      "rewards/reward_paragraph_structure/std": 0.06304138824343682,
+      "rewards/reward_variance_humanlike/mean": 0.4737445771694183,
+      "rewards/reward_variance_humanlike/std": 0.05234875530004501,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 619.8,
+      "completions/max_terminated_length": 619.8,
+      "completions/mean_length": 507.4125,
+      "completions/mean_terminated_length": 507.4125,
+      "completions/min_length": 432.6,
+      "completions/min_terminated_length": 432.6,
+      "epoch": 0.0020981572705710636,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.16545040905475616,
+      "learning_rate": 2e-05,
+      "loss": 0.0016,
+      "num_tokens": 1117509.0,
+      "reward": 2.329833173751831,
+      "reward_std": 0.2713765025138855,
+      "rewards/reward_humanlike/mean": 0.39990985989570615,
+      "rewards/reward_humanlike/std": 0.21587005853652955,
+      "rewards/reward_nonslop/mean": 0.5789480090141297,
+      "rewards/reward_nonslop/std": 0.025028055533766747,
+      "rewards/reward_paragraph_structure/mean": 0.8872500061988831,
+      "rewards/reward_paragraph_structure/std": 0.1905163235962391,
+      "rewards/reward_variance_humanlike/mean": 0.4637253522872925,
+      "rewards/reward_variance_humanlike/std": 0.04791286364197731,
+      "step": 115
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 595.8,
+      "completions/max_terminated_length": 595.8,
+      "completions/mean_length": 478.6125,
+      "completions/mean_terminated_length": 478.6125,
+      "completions/min_length": 380.2,
+      "completions/min_terminated_length": 380.2,
+      "epoch": 0.0021893814997263274,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.16097059845924377,
+      "learning_rate": 2e-05,
+      "loss": 0.0021,
+      "num_tokens": 1161750.0,
+      "reward": 2.625237512588501,
+      "reward_std": 0.2037688374519348,
+      "rewards/reward_humanlike/mean": 0.6083793044090271,
+      "rewards/reward_humanlike/std": 0.17816392779350282,
+      "rewards/reward_nonslop/mean": 0.6056123375892639,
+      "rewards/reward_nonslop/std": 0.024472470954060556,
+      "rewards/reward_paragraph_structure/mean": 0.9285000205039978,
+      "rewards/reward_paragraph_structure/std": 0.09179038554430008,
+      "rewards/reward_variance_humanlike/mean": 0.4827458918094635,
+      "rewards/reward_variance_humanlike/std": 0.05933259278535843,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 541.6,
+      "completions/max_terminated_length": 541.6,
+      "completions/mean_length": 454.65,
+      "completions/mean_terminated_length": 454.65,
+      "completions/min_length": 338.2,
+      "completions/min_terminated_length": 338.2,
+      "epoch": 0.002280605728881591,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1858094334602356,
+      "learning_rate": 2e-05,
+      "loss": -0.0045,
+      "num_tokens": 1203898.0,
+      "reward": 2.687197732925415,
+      "reward_std": 0.19041271209716798,
+      "rewards/reward_humanlike/mean": 0.7062256932258606,
+      "rewards/reward_humanlike/std": 0.12540495842695237,
+      "rewards/reward_nonslop/mean": 0.6103421688079834,
+      "rewards/reward_nonslop/std": 0.02627619281411171,
+      "rewards/reward_paragraph_structure/mean": 0.8820000052452087,
+      "rewards/reward_paragraph_structure/std": 0.1271403595805168,
+      "rewards/reward_variance_humanlike/mean": 0.4886298537254333,
+      "rewards/reward_variance_humanlike/std": 0.060777902603149414,
+      "step": 125
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 558.4,
+      "completions/max_terminated_length": 558.4,
+      "completions/mean_length": 465.975,
+      "completions/mean_terminated_length": 465.975,
+      "completions/min_length": 366.8,
+      "completions/min_terminated_length": 366.8,
+      "epoch": 0.0023718299580368545,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1734333336353302,
+      "learning_rate": 2e-05,
+      "loss": -0.0112,
+      "num_tokens": 1246984.0,
+      "reward": 2.850187349319458,
+      "reward_std": 0.1544615089893341,
+      "rewards/reward_humanlike/mean": 0.8162331223487854,
+      "rewards/reward_humanlike/std": 0.09603091776371002,
+      "rewards/reward_nonslop/mean": 0.6191692113876343,
+      "rewards/reward_nonslop/std": 0.02178177759051323,
+      "rewards/reward_paragraph_structure/mean": 0.9102500081062317,
+      "rewards/reward_paragraph_structure/std": 0.08548486456274987,
+      "rewards/reward_variance_humanlike/mean": 0.5045349895954132,
+      "rewards/reward_variance_humanlike/std": 0.046382848918437955,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 585.4,
+      "completions/max_terminated_length": 585.4,
+      "completions/mean_length": 472.6625,
+      "completions/mean_terminated_length": 472.6625,
+      "completions/min_length": 369.2,
+      "completions/min_terminated_length": 369.2,
+      "epoch": 0.0024630541871921183,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.17723867297172546,
+      "learning_rate": 2e-05,
+      "loss": 0.0057,
+      "num_tokens": 1290557.0,
+      "reward": 2.770927333831787,
+      "reward_std": 0.11463789045810699,
+      "rewards/reward_humanlike/mean": 0.7220260500907898,
+      "rewards/reward_humanlike/std": 0.09653217196464539,
+      "rewards/reward_nonslop/mean": 0.6141273856163025,
+      "rewards/reward_nonslop/std": 0.02344125583767891,
+      "rewards/reward_paragraph_structure/mean": 0.9445000052452087,
+      "rewards/reward_paragraph_structure/std": 0.049851450324058535,
+      "rewards/reward_variance_humanlike/mean": 0.4902738809585571,
+      "rewards/reward_variance_humanlike/std": 0.06265307739377021,
+      "step": 135
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 639.6,
+      "completions/max_terminated_length": 639.6,
+      "completions/mean_length": 526.5875,
+      "completions/mean_terminated_length": 526.5875,
+      "completions/min_length": 399.0,
+      "completions/min_terminated_length": 399.0,
+      "epoch": 0.002554278416347382,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.17909909784793854,
+      "learning_rate": 2e-05,
+      "loss": 0.0033,
+      "num_tokens": 1338524.0,
+      "reward": 2.925887870788574,
+      "reward_std": 0.10286579728126526,
+      "rewards/reward_humanlike/mean": 0.8502010822296142,
+      "rewards/reward_humanlike/std": 0.06637604311108589,
+      "rewards/reward_nonslop/mean": 0.5938733458518982,
+      "rewards/reward_nonslop/std": 0.026048434898257256,
+      "rewards/reward_paragraph_structure/mean": 0.9660000085830689,
+      "rewards/reward_paragraph_structure/std": 0.05240304078906775,
+      "rewards/reward_variance_humanlike/mean": 0.5158135175704956,
+      "rewards/reward_variance_humanlike/std": 0.05239577367901802,
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 609.4,
+      "completions/max_terminated_length": 609.4,
+      "completions/mean_length": 512.9,
+      "completions/mean_terminated_length": 512.9,
+      "completions/min_length": 433.6,
+      "completions/min_terminated_length": 433.6,
+      "epoch": 0.0026455026455026454,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2014007717370987,
+      "learning_rate": 2e-05,
+      "loss": -0.0164,
+      "num_tokens": 1385460.0,
+      "reward": 2.9562798023223875,
+      "reward_std": 0.1210786946117878,
+      "rewards/reward_humanlike/mean": 0.8488089680671692,
+      "rewards/reward_humanlike/std": 0.05001975782215595,
+      "rewards/reward_nonslop/mean": 0.6070125579833985,
+      "rewards/reward_nonslop/std": 0.01961589902639389,
+      "rewards/reward_paragraph_structure/mean": 0.9575000047683716,
+      "rewards/reward_paragraph_structure/std": 0.0841983575373888,
+      "rewards/reward_variance_humanlike/mean": 0.5429582834243775,
+      "rewards/reward_variance_humanlike/std": 0.056052941083908084,
+      "step": 145
+    },
+    {
+      "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,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 656.6,
+      "completions/max_terminated_length": 656.6,
+      "completions/mean_length": 539.1,
+      "completions/mean_terminated_length": 539.1,
+      "completions/min_length": 427.2,
+      "completions/min_terminated_length": 427.2,
+      "epoch": 0.002736726874657909,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.18585863709449768,
+      "learning_rate": 2e-05,
+      "loss": -0.0012,
+      "num_tokens": 1434460.0,
+      "reward": 2.91634521484375,
+      "reward_std": 0.17835799604654312,
+      "rewards/reward_humanlike/mean": 0.7916194796562195,
+      "rewards/reward_humanlike/std": 0.09777315035462379,
+      "rewards/reward_nonslop/mean": 0.6098103404045105,
+      "rewards/reward_nonslop/std": 0.023180909641087055,
+      "rewards/reward_paragraph_structure/mean": 0.9540000200271607,
+      "rewards/reward_paragraph_structure/std": 0.07906086668372155,
+      "rewards/reward_variance_humanlike/mean": 0.560915470123291,
+      "rewards/reward_variance_humanlike/std": 0.06453037708997726,
+      "step": 150
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 250,
+  "num_input_tokens_seen": 1434460,
+  "num_train_epochs": 1,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113ba4c7a54c6a76d168427ab6dc3b7e51dc684feb89f3210fcbb085800c4b67
+size 6865