Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- dpo
+- lora
+- transformers
+- trl
+---
+
+# 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

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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": 0.05,
+  "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",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d948e97ba9490fe78e6232c27bfb6d7fa48ca4c6e76a7b4d14eb15b5abe8832d
+size 36981856

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 %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7e2258180cb3e934c4452f437ea0866f29adc4f3ef52c501fc3b271f6cab99
+size 74194619

ref/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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": 0.05,
+  "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",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

ref/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f9d94657ed668f636e0c983388a97e23386ca701b294b2f543671a98c6ace9
+size 73911112

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20844a8d67ae7babe31200761bff082936966a9d3edf243d89f2faa041c354e5
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.512537270784378,
+      "epoch": 0.1038961038961039,
+      "grad_norm": 3.953125,
+      "learning_rate": 5e-05,
+      "logits/chosen": -0.8704199966929909,
+      "logits/rejected": -0.3084566421487745,
+      "logps/chosen": -135.72114944458008,
+      "logps/rejected": -185.16453552246094,
+      "loss": 0.6931471824645996,
+      "mean_token_accuracy": 0.5898260846734047,
+      "num_tokens": 7838.0,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "entropy": 1.5321979224681854,
+      "epoch": 0.2077922077922078,
+      "grad_norm": 3.203125,
+      "learning_rate": 4.9166666666666665e-05,
+      "logits/chosen": -1.1463743353817795,
+      "logits/rejected": -0.46985809672499795,
+      "logps/chosen": -128.28354263305664,
+      "logps/rejected": -196.00814056396484,
+      "loss": 0.5517404079437256,
+      "mean_token_accuracy": 0.5888336226344109,
+      "num_tokens": 15415.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.07305936858756468,
+      "rewards/margins": 0.3098052069544792,
+      "rewards/rejected": -0.23674583807587624,
+      "step": 2
+    },
+    {
+      "entropy": 1.5711090564727783,
+      "epoch": 0.3116883116883117,
+      "grad_norm": 2.6875,
+      "learning_rate": 4.8333333333333334e-05,
+      "logits/chosen": -0.9020447850475974,
+      "logits/rejected": -0.36287321495179026,
+      "logps/chosen": -158.0212106704712,
+      "logps/rejected": -212.57695960998535,
+      "loss": 0.44210872054100037,
+      "mean_token_accuracy": 0.5543163530528545,
+      "num_tokens": 23608.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.08782930835150182,
+      "rewards/margins": 0.6035905033349991,
+      "rewards/rejected": -0.5157611928880215,
+      "step": 3
+    },
+    {
+      "entropy": 1.4402711540460587,
+      "epoch": 0.4155844155844156,
+      "grad_norm": 2.109375,
+      "learning_rate": 4.75e-05,
+      "logits/chosen": -1.2677209306160548,
+      "logits/rejected": -0.4948322601683077,
+      "logps/chosen": -129.5712432861328,
+      "logps/rejected": -207.05406188964844,
+      "loss": 0.27849292755126953,
+      "mean_token_accuracy": 0.6066802740097046,
+      "num_tokens": 31225.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.31562281399965286,
+      "rewards/margins": 1.1901824250817299,
+      "rewards/rejected": -0.8745595999062061,
+      "step": 4
+    },
+    {
+      "entropy": 1.4334967136383057,
+      "epoch": 0.5194805194805194,
+      "grad_norm": 1.8984375,
+      "learning_rate": 4.666666666666667e-05,
+      "logits/chosen": -1.1399579628249235,
+      "logits/rejected": -0.5072241096172478,
+      "logps/chosen": -129.72084999084473,
+      "logps/rejected": -186.66267013549805,
+      "loss": 0.27793484926223755,
+      "mean_token_accuracy": 0.5961734727025032,
+      "num_tokens": 38819.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.1814193739555776,
+      "rewards/margins": 1.1725517585873604,
+      "rewards/rejected": -0.9911323636770248,
+      "step": 5
+    },
+    {
+      "entropy": 1.397928535938263,
+      "epoch": 0.6233766233766234,
+      "grad_norm": 1.3515625,
+      "learning_rate": 4.5833333333333334e-05,
+      "logits/chosen": -1.2421275742450641,
+      "logits/rejected": -0.5668832705948026,
+      "logps/chosen": -140.5345287322998,
+      "logps/rejected": -216.73953437805176,
+      "loss": 0.16265499591827393,
+      "mean_token_accuracy": 0.6151033267378807,
+      "num_tokens": 46735.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.21190567314624786,
+      "rewards/margins": 1.9610275849699974,
+      "rewards/rejected": -1.7491218969225883,
+      "step": 6
+    },
+    {
+      "entropy": 1.3962671607732773,
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.87109375,
+      "learning_rate": 4.5e-05,
+      "logits/chosen": -1.3785747536026947,
+      "logits/rejected": -0.7622838923063787,
+      "logps/chosen": -149.59703826904297,
+      "logps/rejected": -215.6246738433838,
+      "loss": 0.0853467807173729,
+      "mean_token_accuracy": 0.5751035511493683,
+      "num_tokens": 54606.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3336143558844924,
+      "rewards/margins": 2.5562889873981476,
+      "rewards/rejected": -2.222674608230591,
+      "step": 7
+    },
+    {
+      "entropy": 1.3736034631729126,
+      "epoch": 0.8311688311688312,
+      "grad_norm": 1.078125,
+      "learning_rate": 4.4166666666666665e-05,
+      "logits/chosen": -1.5070403658179665,
+      "logits/rejected": -0.5901145721115999,
+      "logps/chosen": -135.39935779571533,
+      "logps/rejected": -214.47946739196777,
+      "loss": 0.10686549544334412,
+      "mean_token_accuracy": 0.583378367125988,
+      "num_tokens": 62397.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.11785926297307014,
+      "rewards/margins": 2.4758750796318054,
+      "rewards/rejected": -2.3580158352851868,
+      "step": 8
+    },
+    {
+      "entropy": 1.2798690795898438,
+      "epoch": 0.935064935064935,
+      "grad_norm": 0.474609375,
+      "learning_rate": 4.3333333333333334e-05,
+      "logits/chosen": -1.5770302287927562,
+      "logits/rejected": -1.0807285246276348,
+      "logps/chosen": -143.6166696548462,
+      "logps/rejected": -231.476957321167,
+      "loss": 0.04057425633072853,
+      "mean_token_accuracy": 0.6233189776539803,
+      "num_tokens": 70570.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.40784178394824266,
+      "rewards/margins": 3.4395263493061066,
+      "rewards/rejected": -3.0316845774650574,
+      "step": 9
+    },
+    {
+      "entropy": 1.3829500436782838,
+      "epoch": 1.0,
+      "grad_norm": 1.0234375,
+      "learning_rate": 4.25e-05,
+      "logits/chosen": -1.6479851532264296,
+      "logits/rejected": -0.9067774452457833,
+      "logps/chosen": -151.33749084472657,
+      "logps/rejected": -232.5306884765625,
+      "loss": 0.08217030763626099,
+      "mean_token_accuracy": 0.6009067416191101,
+      "num_tokens": 75516.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.06317704170942307,
+      "rewards/margins": 2.9441545248031615,
+      "rewards/rejected": -3.007331609725952,
+      "step": 10
+    },
+    {
+      "entropy": 1.3026847392320633,
+      "epoch": 1.103896103896104,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 4.166666666666667e-05,
+      "logits/chosen": -1.7204814031981435,
+      "logits/rejected": -1.1328579956673597,
+      "logps/chosen": -164.92389488220215,
+      "logps/rejected": -254.53803253173828,
+      "loss": 0.01344618946313858,
+      "mean_token_accuracy": 0.5737045928835869,
+      "num_tokens": 83403.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.21888723596930504,
+      "rewards/margins": 5.129873305559158,
+      "rewards/rejected": -4.910986036062241,
+      "step": 11
+    },
+    {
+      "entropy": 1.2513943165540695,
+      "epoch": 1.2077922077922079,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 4.0833333333333334e-05,
+      "logits/chosen": -2.019919467615345,
+      "logits/rejected": -1.371831380074324,
+      "logps/chosen": -136.46048736572266,
+      "logps/rejected": -227.8621711730957,
+      "loss": 0.014287861995398998,
+      "mean_token_accuracy": 0.6023998335003853,
+      "num_tokens": 91399.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.47683279449120164,
+      "rewards/margins": 4.8368901014328,
+      "rewards/rejected": -4.360057294368744,
+      "step": 12
+    },
+    {
+      "entropy": 1.2212176620960236,
+      "epoch": 1.3116883116883118,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 4e-05,
+      "logits/chosen": -1.7292757979585844,
+      "logits/rejected": -1.1263007681151962,
+      "logps/chosen": -116.3019323348999,
+      "logps/rejected": -227.41853141784668,
+      "loss": 0.015741553157567978,
+      "mean_token_accuracy": 0.6425232589244843,
+      "num_tokens": 99387.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.29560147132724524,
+      "rewards/margins": 4.693124741315842,
+      "rewards/rejected": -4.39752334356308,
+      "step": 13
+    },
+    {
+      "entropy": 1.2582492232322693,
+      "epoch": 1.4155844155844157,
+      "grad_norm": 0.039794921875,
+      "learning_rate": 3.9166666666666665e-05,
+      "logits/chosen": -1.8986988604942008,
+      "logits/rejected": -1.2704682493398296,
+      "logps/chosen": -130.53850650787354,
+      "logps/rejected": -259.06455993652344,
+      "loss": 0.002613399177789688,
+      "mean_token_accuracy": 0.6116124093532562,
+      "num_tokens": 106985.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.37937870621681213,
+      "rewards/margins": 6.370364427566528,
+      "rewards/rejected": -5.990985751152039,
+      "step": 14
+    },
+    {
+      "entropy": 1.2522720396518707,
+      "epoch": 1.5194805194805194,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 3.8333333333333334e-05,
+      "logits/chosen": -2.005344554741843,
+      "logits/rejected": -1.3727889740878687,
+      "logps/chosen": -155.52635955810547,
+      "logps/rejected": -286.3923683166504,
+      "loss": 0.002808060497045517,
+      "mean_token_accuracy": 0.5796493962407112,
+      "num_tokens": 114781.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3164886636659503,
+      "rewards/margins": 7.638198435306549,
+      "rewards/rejected": -7.3217098116874695,
+      "step": 15
+    },
+    {
+      "entropy": 1.2523068189620972,
+      "epoch": 1.6233766233766234,
+      "grad_norm": 0.038330078125,
+      "learning_rate": 3.7500000000000003e-05,
+      "logits/chosen": -1.9715578454090756,
+      "logits/rejected": -1.2781532380406784,
+      "logps/chosen": -150.2594985961914,
+      "logps/rejected": -280.48920822143555,
+      "loss": 0.002301866188645363,
+      "mean_token_accuracy": 0.6012703776359558,
+      "num_tokens": 122871.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.19919815217144787,
+      "rewards/margins": 7.385057747364044,
+      "rewards/rejected": -7.1858596205711365,
+      "step": 16
+    },
+    {
+      "entropy": 1.234215423464775,
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.045654296875,
+      "learning_rate": 3.6666666666666666e-05,
+      "logits/chosen": -1.9352984235246145,
+      "logits/rejected": -1.3910207936164074,
+      "logps/chosen": -142.13225173950195,
+      "logps/rejected": -268.2549476623535,
+      "loss": 0.002515692263841629,
+      "mean_token_accuracy": 0.5971521884202957,
+      "num_tokens": 130530.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.42800588643876836,
+      "rewards/margins": 7.45609712600708,
+      "rewards/rejected": -7.028091222047806,
+      "step": 17
+    },
+    {
+      "entropy": 1.190779373049736,
+      "epoch": 1.8311688311688312,
+      "grad_norm": 0.0390625,
+      "learning_rate": 3.5833333333333335e-05,
+      "logits/chosen": -2.0085451937187595,
+      "logits/rejected": -1.6083773573241704,
+      "logps/chosen": -131.45305252075195,
+      "logps/rejected": -244.74785995483398,
+      "loss": 0.0026926116552203894,
+      "mean_token_accuracy": 0.5924705117940903,
+      "num_tokens": 138371.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.27736073173582554,
+      "rewards/margins": 6.875377118587494,
+      "rewards/rejected": -6.598016321659088,
+      "step": 18
+    },
+    {
+      "entropy": 1.2075671404600143,
+      "epoch": 1.935064935064935,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 3.5e-05,
+      "logits/chosen": -2.134337462790497,
+      "logits/rejected": -1.6570472501112965,
+      "logps/chosen": -120.83753395080566,
+      "logps/rejected": -264.36783027648926,
+      "loss": 0.001522539067082107,
+      "mean_token_accuracy": 0.5812797658145428,
+      "num_tokens": 146105.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.5302159509155899,
+      "rewards/margins": 7.605401933193207,
+      "rewards/rejected": -7.075186014175415,
+      "step": 19
+    },
+    {
+      "entropy": 1.116961932182312,
+      "epoch": 2.0,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 3.4166666666666666e-05,
+      "logits/chosen": -1.9841584232594507,
+      "logits/rejected": -1.6315209771433286,
+      "logps/chosen": -129.09716339111327,
+      "logps/rejected": -246.24557495117188,
+      "loss": 0.0038437608163803816,
+      "mean_token_accuracy": 0.6218155741691589,
+      "num_tokens": 151032.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.2574792455881834,
+      "rewards/margins": 7.590111160278321,
+      "rewards/rejected": -7.332631969451905,
+      "step": 20
+    },
+    {
+      "entropy": 1.1428246572613716,
+      "epoch": 2.103896103896104,
+      "grad_norm": 0.046142578125,
+      "learning_rate": 3.3333333333333335e-05,
+      "logits/chosen": -2.1280286073627903,
+      "logits/rejected": -1.6765060194642971,
+      "logps/chosen": -124.37408638000488,
+      "logps/rejected": -268.4387798309326,
+      "loss": 0.002784793497994542,
+      "mean_token_accuracy": 0.6262179091572762,
+      "num_tokens": 158898.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.4877193462452851,
+      "rewards/margins": 8.688470482826233,
+      "rewards/rejected": -8.20075112581253,
+      "step": 21
+    },
+    {
+      "entropy": 1.1632115840911865,
+      "epoch": 2.207792207792208,
+      "grad_norm": 0.00421142578125,
+      "learning_rate": 3.2500000000000004e-05,
+      "logits/chosen": -2.2110131627297314,
+      "logits/rejected": -1.624031390186785,
+      "logps/chosen": -143.07822036743164,
+      "logps/rejected": -304.6781883239746,
+      "loss": 0.00020159759151283652,
+      "mean_token_accuracy": 0.582977369427681,
+      "num_tokens": 166715.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3669938058592379,
+      "rewards/margins": 9.80722576379776,
+      "rewards/rejected": -9.440232157707214,
+      "step": 22
+    },
+    {
+      "entropy": 1.163627065718174,
+      "epoch": 2.311688311688312,
+      "grad_norm": 0.0189208984375,
+      "learning_rate": 3.1666666666666666e-05,
+      "logits/chosen": -2.151204727301539,
+      "logits/rejected": -1.5880060075596425,
+      "logps/chosen": -161.0470733642578,
+      "logps/rejected": -283.40243339538574,
+      "loss": 0.0010750408982858062,
+      "mean_token_accuracy": 0.5792371965944767,
+      "num_tokens": 174871.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.393167894333601,
+      "rewards/margins": 8.00706958770752,
+      "rewards/rejected": -8.400237500667572,
+      "step": 23
+    },
+    {
+      "entropy": 1.179183878004551,
+      "epoch": 2.4155844155844157,
+      "grad_norm": 0.01806640625,
+      "learning_rate": 3.0833333333333335e-05,
+      "logits/chosen": -2.1281537439249174,
+      "logits/rejected": -1.5609932878048027,
+      "logps/chosen": -129.24316215515137,
+      "logps/rejected": -269.68304443359375,
+      "loss": 0.001012458698824048,
+      "mean_token_accuracy": 0.6229125708341599,
+      "num_tokens": 182581.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.30742750596255064,
+      "rewards/margins": 8.548649609088898,
+      "rewards/rejected": -8.241222083568573,
+      "step": 24
+    },
+    {
+      "entropy": 1.2349543124437332,
+      "epoch": 2.5194805194805197,
+      "grad_norm": 0.0118408203125,
+      "learning_rate": 3e-05,
+      "logits/chosen": -2.1954152548130956,
+      "logits/rejected": -1.8124665579280124,
+      "logps/chosen": -139.44278526306152,
+      "logps/rejected": -276.38891220092773,
+      "loss": 0.000593633740209043,
+      "mean_token_accuracy": 0.5867471769452095,
+      "num_tokens": 190414.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.11138467863202095,
+      "rewards/margins": 8.101492822170258,
+      "rewards/rejected": -7.990108132362366,
+      "step": 25
+    },
+    {
+      "entropy": 1.1430687606334686,
+      "epoch": 2.6233766233766236,
+      "grad_norm": 0.0186767578125,
+      "learning_rate": 2.916666666666667e-05,
+      "logits/chosen": -2.184405102771366,
+      "logits/rejected": -1.768430591565442,
+      "logps/chosen": -162.35870456695557,
+      "logps/rejected": -284.31261253356934,
+      "loss": 0.001006356906145811,
+      "mean_token_accuracy": 0.5789020732045174,
+      "num_tokens": 198352.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.32843170780688524,
+      "rewards/margins": 8.667101621627808,
+      "rewards/rejected": -8.995533287525177,
+      "step": 26
+    },
+    {
+      "entropy": 1.1707737743854523,
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.00994873046875,
+      "learning_rate": 2.8333333333333335e-05,
+      "logits/chosen": -2.2829095936666026,
+      "logits/rejected": -1.5454627881242438,
+      "logps/chosen": -127.9923505783081,
+      "logps/rejected": -269.86738777160645,
+      "loss": 0.000537040235940367,
+      "mean_token_accuracy": 0.5975877344608307,
+      "num_tokens": 206134.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.15700979018583894,
+      "rewards/margins": 8.28273743391037,
+      "rewards/rejected": -8.439747273921967,
+      "step": 27
+    },
+    {
+      "entropy": 1.1310725212097168,
+      "epoch": 2.8311688311688314,
+      "grad_norm": 0.00567626953125,
+      "learning_rate": 2.7500000000000004e-05,
+      "logits/chosen": -2.319415917931936,
+      "logits/rejected": -1.8342084919918709,
+      "logps/chosen": -150.00816440582275,
+      "logps/rejected": -293.56144523620605,
+      "loss": 0.000298125552944839,
+      "mean_token_accuracy": 0.6064256802201271,
+      "num_tokens": 214297.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.005369566380977631,
+      "rewards/margins": 9.238496720790863,
+      "rewards/rejected": -9.243866205215454,
+      "step": 28
+    },
+    {
+      "entropy": 1.1214349120855331,
+      "epoch": 2.935064935064935,
+      "grad_norm": 0.0010833740234375,
+      "learning_rate": 2.6666666666666667e-05,
+      "logits/chosen": -2.39867742884011,
+      "logits/rejected": -1.938792760577064,
+      "logps/chosen": -129.17547798156738,
+      "logps/rejected": -291.3078727722168,
+      "loss": 5.1582956075435504e-05,
+      "mean_token_accuracy": 0.5967546105384827,
+      "num_tokens": 221900.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.385247141122818,
+      "rewards/margins": 11.02652394771576,
+      "rewards/rejected": -10.641276895999908,
+      "step": 29
+    },
+    {
+      "entropy": 1.1968913316726684,
+      "epoch": 3.0,
+      "grad_norm": 0.000522613525390625,
+      "learning_rate": 2.5833333333333336e-05,
+      "logits/chosen": -2.3927515248399525,
+      "logits/rejected": -1.7979455730124954,
+      "logps/chosen": -134.36846923828125,
+      "logps/rejected": -315.8888793945313,
+      "loss": 2.0089810277568176e-05,
+      "mean_token_accuracy": 0.5749531865119935,
+      "num_tokens": 226548.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.5599890232086182,
+      "rewards/margins": 11.858483695983887,
+      "rewards/rejected": -11.298494720458985,
+      "step": 30
+    },
+    {
+      "entropy": 1.0848063379526138,
+      "epoch": 3.103896103896104,
+      "grad_norm": 0.00848388671875,
+      "learning_rate": 2.5e-05,
+      "logits/chosen": -2.3630775053643998,
+      "logits/rejected": -2.0637178830428264,
+      "logps/chosen": -136.13608932495117,
+      "logps/rejected": -278.8615074157715,
+      "loss": 0.00036562219611369073,
+      "mean_token_accuracy": 0.628660149872303,
+      "num_tokens": 234538.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.31311475299298763,
+      "rewards/margins": 9.501745641231537,
+      "rewards/rejected": -9.188630878925323,
+      "step": 31
+    },
+    {
+      "entropy": 1.162983387708664,
+      "epoch": 3.207792207792208,
+      "grad_norm": 0.00115203857421875,
+      "learning_rate": 2.4166666666666667e-05,
+      "logits/chosen": -2.406029792298791,
+      "logits/rejected": -1.9060521152655108,
+      "logps/chosen": -126.35858535766602,
+      "logps/rejected": -303.76181411743164,
+      "loss": 5.3637420933227986e-05,
+      "mean_token_accuracy": 0.5992156118154526,
+      "num_tokens": 242224.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3918016329407692,
+      "rewards/margins": 10.524143934249878,
+      "rewards/rejected": -10.132342457771301,
+      "step": 32
+    },
+    {
+      "entropy": 1.1035910472273827,
+      "epoch": 3.311688311688312,
+      "grad_norm": 0.00885009765625,
+      "learning_rate": 2.3333333333333336e-05,
+      "logits/chosen": -2.4029672208683124,
+      "logits/rejected": -1.8559939119150626,
+      "logps/chosen": -164.47723293304443,
+      "logps/rejected": -307.7430419921875,
+      "loss": 0.0004137605137657374,
+      "mean_token_accuracy": 0.5645543709397316,
+      "num_tokens": 250221.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.5422927811741829,
+      "rewards/margins": 10.185687839984894,
+      "rewards/rejected": -10.72798067331314,
+      "step": 33
+    },
+    {
+      "entropy": 1.1141554564237595,
+      "epoch": 3.4155844155844157,
+      "grad_norm": 0.007110595703125,
+      "learning_rate": 2.25e-05,
+      "logits/chosen": -2.3687534580534138,
+      "logits/rejected": -2.050704117333944,
+      "logps/chosen": -138.01462364196777,
+      "logps/rejected": -276.9965763092041,
+      "loss": 0.0003196091565769166,
+      "mean_token_accuracy": 0.5838265940546989,
+      "num_tokens": 258004.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.1458825245499611,
+      "rewards/margins": 10.098270773887634,
+      "rewards/rejected": -9.952388286590576,
+      "step": 34
+    },
+    {
+      "entropy": 1.2330412343144417,
+      "epoch": 3.5194805194805197,
+      "grad_norm": 0.0016021728515625,
+      "learning_rate": 2.1666666666666667e-05,
+      "logits/chosen": -2.099665713097579,
+      "logits/rejected": -1.4495526677555262,
+      "logps/chosen": -147.08791255950928,
+      "logps/rejected": -340.46545028686523,
+      "loss": 6.672517338301986e-05,
+      "mean_token_accuracy": 0.5911035016179085,
+      "num_tokens": 265864.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.028002352453768253,
+      "rewards/margins": 11.662676930427551,
+      "rewards/rejected": -11.690679430961609,
+      "step": 35
+    },
+    {
+      "entropy": 1.1366761773824692,
+      "epoch": 3.6233766233766236,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 2.0833333333333336e-05,
+      "logits/chosen": -2.328846034176437,
+      "logits/rejected": -1.992655699239898,
+      "logps/chosen": -135.61105346679688,
+      "logps/rejected": -271.5671138763428,
+      "loss": 0.0011770055862143636,
+      "mean_token_accuracy": 0.6069249212741852,
+      "num_tokens": 273581.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.13576746042235754,
+      "rewards/margins": 8.846820831298828,
+      "rewards/rejected": -8.711053371429443,
+      "step": 36
+    },
+    {
+      "entropy": 1.1373939514160156,
+      "epoch": 3.7272727272727275,
+      "grad_norm": 0.006072998046875,
+      "learning_rate": 2e-05,
+      "logits/chosen": -2.2702114795686574,
+      "logits/rejected": -1.7482615971180808,
+      "logps/chosen": -140.26164054870605,
+      "logps/rejected": -294.61451530456543,
+      "loss": 0.0003134559956379235,
+      "mean_token_accuracy": 0.5956408530473709,
+      "num_tokens": 281309.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.032456397311761975,
+      "rewards/margins": 10.235666334629059,
+      "rewards/rejected": -10.203210055828094,
+      "step": 37
+    },
+    {
+      "entropy": 1.1416693180799484,
+      "epoch": 3.8311688311688314,
+      "grad_norm": 0.00628662109375,
+      "learning_rate": 1.9166666666666667e-05,
+      "logits/chosen": -2.324989094221912,
+      "logits/rejected": -1.6231121376823092,
+      "logps/chosen": -123.99202156066895,
+      "logps/rejected": -272.5278739929199,
+      "loss": 0.000329699891153723,
+      "mean_token_accuracy": 0.6103288903832436,
+      "num_tokens": 289131.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.029055589344352484,
+      "rewards/margins": 8.933434963226318,
+      "rewards/rejected": -8.962490499019623,
+      "step": 38
+    },
+    {
+      "entropy": 1.1619316935539246,
+      "epoch": 3.935064935064935,
+      "grad_norm": 0.006805419921875,
+      "learning_rate": 1.8333333333333333e-05,
+      "logits/chosen": -2.277468688630792,
+      "logits/rejected": -1.6969099471315172,
+      "logps/chosen": -139.51892566680908,
+      "logps/rejected": -279.6028060913086,
+      "loss": 0.00035776293952949345,
+      "mean_token_accuracy": 0.6005248352885246,
+      "num_tokens": 297124.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.09404934721533209,
+      "rewards/margins": 9.114178478717804,
+      "rewards/rejected": -9.208227813243866,
+      "step": 39
+    },
+    {
+      "entropy": 1.1786307096481323,
+      "epoch": 4.0,
+      "grad_norm": 0.003021240234375,
+      "learning_rate": 1.75e-05,
+      "logits/chosen": -2.4174767570194224,
+      "logits/rejected": -1.7008187103422685,
+      "logps/chosen": -175.12867736816406,
+      "logps/rejected": -322.8905456542969,
+      "loss": 0.00012227564002387226,
+      "mean_token_accuracy": 0.5624364495277405,
+      "num_tokens": 302064.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.3554480280727148,
+      "rewards/margins": 10.46877145767212,
+      "rewards/rejected": -10.824219512939454,
+      "step": 40
+    },
+    {
+      "entropy": 1.1589677780866623,
+      "epoch": 4.103896103896104,
+      "grad_norm": 0.003875732421875,
+      "learning_rate": 1.6666666666666667e-05,
+      "logits/chosen": -2.2044642238095227,
+      "logits/rejected": -1.7255148326997178,
+      "logps/chosen": -153.97796630859375,
+      "logps/rejected": -309.2699508666992,
+      "loss": 0.0002002128167077899,
+      "mean_token_accuracy": 0.5704852566123009,
+      "num_tokens": 310049.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.3379343111300841,
+      "rewards/margins": 10.036688327789307,
+      "rewards/rejected": -10.374622523784637,
+      "step": 41
+    },
+    {
+      "entropy": 1.1579881459474564,
+      "epoch": 4.207792207792208,
+      "grad_norm": 0.002685546875,
+      "learning_rate": 1.5833333333333333e-05,
+      "logits/chosen": -2.295833219188626,
+      "logits/rejected": -1.7928715027581368,
+      "logps/chosen": -160.39765167236328,
+      "logps/rejected": -318.446325302124,
+      "loss": 0.00013650115579366684,
+      "mean_token_accuracy": 0.5852783843874931,
+      "num_tokens": 317868.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.28954305313527584,
+      "rewards/margins": 10.830901622772217,
+      "rewards/rejected": -11.120444595813751,
+      "step": 42
+    },
+    {
+      "entropy": 1.1567590683698654,
+      "epoch": 4.311688311688312,
+      "grad_norm": 0.003326416015625,
+      "learning_rate": 1.5e-05,
+      "logits/chosen": -2.4376148204179304,
+      "logits/rejected": -1.8646480940962602,
+      "logps/chosen": -138.2414083480835,
+      "logps/rejected": -304.6367073059082,
+      "loss": 0.0001619597605895251,
+      "mean_token_accuracy": 0.5863501876592636,
+      "num_tokens": 325576.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.11933107685763389,
+      "rewards/margins": 10.622458934783936,
+      "rewards/rejected": -10.741789996623993,
+      "step": 43
+    },
+    {
+      "entropy": 1.1223484426736832,
+      "epoch": 4.415584415584416,
+      "grad_norm": 0.0019378662109375,
+      "learning_rate": 1.4166666666666668e-05,
+      "logits/chosen": -2.4513975092431988,
+      "logits/rejected": -2.025179191831654,
+      "logps/chosen": -116.16583919525146,
+      "logps/rejected": -285.6050682067871,
+      "loss": 9.024493920151144e-05,
+      "mean_token_accuracy": 0.6130669489502907,
+      "num_tokens": 333071.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3361262381076813,
+      "rewards/margins": 9.84731376171112,
+      "rewards/rejected": -9.511187613010406,
+      "step": 44
+    },
+    {
+      "entropy": 1.1869630813598633,
+      "epoch": 4.51948051948052,
+      "grad_norm": 0.005157470703125,
+      "learning_rate": 1.3333333333333333e-05,
+      "logits/chosen": -2.1769293477016354,
+      "logits/rejected": -1.4691006673227756,
+      "logps/chosen": -158.22007369995117,
+      "logps/rejected": -318.19568634033203,
+      "loss": 0.0002636132121551782,
+      "mean_token_accuracy": 0.5729746297001839,
+      "num_tokens": 341054.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.34203997533768415,
+      "rewards/margins": 10.176166713237762,
+      "rewards/rejected": -10.518206655979156,
+      "step": 45
+    },
+    {
+      "entropy": 1.0994098782539368,
+      "epoch": 4.623376623376624,
+      "grad_norm": 0.015380859375,
+      "learning_rate": 1.25e-05,
+      "logits/chosen": -2.385909726689113,
+      "logits/rejected": -2.06952027102175,
+      "logps/chosen": -155.6819829940796,
+      "logps/rejected": -289.1867733001709,
+      "loss": 0.0008207751670852304,
+      "mean_token_accuracy": 0.592678390443325,
+      "num_tokens": 349010.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.43019715102855116,
+      "rewards/margins": 9.629965007305145,
+      "rewards/rejected": -10.060162127017975,
+      "step": 46
+    },
+    {
+      "entropy": 1.1601977199316025,
+      "epoch": 4.7272727272727275,
+      "grad_norm": 0.005950927734375,
+      "learning_rate": 1.1666666666666668e-05,
+      "logits/chosen": -2.420713169641715,
+      "logits/rejected": -1.8245980237599728,
+      "logps/chosen": -144.67862510681152,
+      "logps/rejected": -291.76464462280273,
+      "loss": 0.00025797143462114036,
+      "mean_token_accuracy": 0.5996529385447502,
+      "num_tokens": 356729.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.29097576648928225,
+      "rewards/margins": 10.346692860126495,
+      "rewards/rejected": -10.05571711063385,
+      "step": 47
+    },
+    {
+      "entropy": 1.0812865048646927,
+      "epoch": 4.8311688311688314,
+      "grad_norm": 0.014892578125,
+      "learning_rate": 1.0833333333333334e-05,
+      "logits/chosen": -2.4253862823366603,
+      "logits/rejected": -2.1636441064851186,
+      "logps/chosen": -130.41874885559082,
+      "logps/rejected": -258.45995330810547,
+      "loss": 0.0008855840424075723,
+      "mean_token_accuracy": 0.6128160208463669,
+      "num_tokens": 364748.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.4050205182284117,
+      "rewards/margins": 9.163773000240326,
+      "rewards/rejected": -8.758752465248108,
+      "step": 48
+    },
+    {
+      "entropy": 1.1632622331380844,
+      "epoch": 4.935064935064935,
+      "grad_norm": 0.00103759765625,
+      "learning_rate": 1e-05,
+      "logits/chosen": -2.427656775691583,
+      "logits/rejected": -1.7417183049324467,
+      "logps/chosen": -140.4052562713623,
+      "logps/rejected": -312.4628715515137,
+      "loss": 4.9687190767144784e-05,
+      "mean_token_accuracy": 0.5939344391226768,
+      "num_tokens": 372678.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.09225330897606909,
+      "rewards/margins": 10.836278080940247,
+      "rewards/rejected": -10.744024753570557,
+      "step": 49
+    },
+    {
+      "entropy": 1.0998417615890503,
+      "epoch": 5.0,
+      "grad_norm": 0.0089111328125,
+      "learning_rate": 9.166666666666666e-06,
+      "logits/chosen": -2.108919317236185,
+      "logits/rejected": -1.5721664481497553,
+      "logps/chosen": -105.09717407226563,
+      "logps/rejected": -249.9797332763672,
+      "loss": 0.00041876244358718395,
+      "mean_token_accuracy": 0.6374574661254883,
+      "num_tokens": 377580.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.32345535755157473,
+      "rewards/margins": 8.785911655426025,
+      "rewards/rejected": -8.462456226348877,
+      "step": 50
+    },
+    {
+      "entropy": 1.1008698269724846,
+      "epoch": 5.103896103896104,
+      "grad_norm": 0.0166015625,
+      "learning_rate": 8.333333333333334e-06,
+      "logits/chosen": -2.1886847202899142,
+      "logits/rejected": -1.709530236018181,
+      "logps/chosen": -142.05830669403076,
+      "logps/rejected": -258.09220123291016,
+      "loss": 0.0009700299706310034,
+      "mean_token_accuracy": 0.6027038618922234,
+      "num_tokens": 385524.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.39982338063418865,
+      "rewards/margins": 7.7835773229599,
+      "rewards/rejected": -8.183400690555573,
+      "step": 51
+    },
+    {
+      "entropy": 1.0808009058237076,
+      "epoch": 5.207792207792208,
+      "grad_norm": 0.0011444091796875,
+      "learning_rate": 7.5e-06,
+      "logits/chosen": -2.445027329506914,
+      "logits/rejected": -2.0271617790401937,
+      "logps/chosen": -128.9005184173584,
+      "logps/rejected": -312.5902729034424,
+      "loss": 5.263146886136383e-05,
+      "mean_token_accuracy": 0.6171352416276932,
+      "num_tokens": 393111.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.2731950767338276,
+      "rewards/margins": 11.596651911735535,
+      "rewards/rejected": -11.323456883430481,
+      "step": 52
+    },
+    {
+      "entropy": 1.1334418207406998,
+      "epoch": 5.311688311688312,
+      "grad_norm": 0.006622314453125,
+      "learning_rate": 6.666666666666667e-06,
+      "logits/chosen": -2.271390373833539,
+      "logits/rejected": -1.6907872117642864,
+      "logps/chosen": -141.5786190032959,
+      "logps/rejected": -274.7357540130615,
+      "loss": 0.00031432509422302246,
+      "mean_token_accuracy": 0.6188977956771851,
+      "num_tokens": 401012.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.02617559058126062,
+      "rewards/margins": 9.21671599149704,
+      "rewards/rejected": -9.242891550064087,
+      "step": 53
+    },
+    {
+      "entropy": 1.2137573212385178,
+      "epoch": 5.415584415584416,
+      "grad_norm": 0.005767822265625,
+      "learning_rate": 5.833333333333334e-06,
+      "logits/chosen": -2.392515574831131,
+      "logits/rejected": -1.7596199848269718,
+      "logps/chosen": -154.2357759475708,
+      "logps/rejected": -323.3644905090332,
+      "loss": 0.000225663956371136,
+      "mean_token_accuracy": 0.5656630396842957,
+      "num_tokens": 408880.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.2048426689580083,
+      "rewards/margins": 10.830295145511627,
+      "rewards/rejected": -11.035137951374054,
+      "step": 54
+    },
+    {
+      "entropy": 1.1423105299472809,
+      "epoch": 5.51948051948052,
+      "grad_norm": 0.00146484375,
+      "learning_rate": 5e-06,
+      "logits/chosen": -2.5769469207427296,
+      "logits/rejected": -2.021839826037388,
+      "logps/chosen": -133.6878776550293,
+      "logps/rejected": -303.7228317260742,
+      "loss": 7.118787470972165e-05,
+      "mean_token_accuracy": 0.5749763548374176,
+      "num_tokens": 416393.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.456505686044693,
+      "rewards/margins": 11.555195212364197,
+      "rewards/rejected": -11.098689556121826,
+      "step": 55
+    },
+    {
+      "entropy": 1.1627247333526611,
+      "epoch": 5.623376623376624,
+      "grad_norm": 0.003143310546875,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": -2.370901666728044,
+      "logits/rejected": -1.86991563775274,
+      "logps/chosen": -124.0777416229248,
+      "logps/rejected": -270.50224685668945,
+      "loss": 0.0001636260567465797,
+      "mean_token_accuracy": 0.6245841830968857,
+      "num_tokens": 424280.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.14732323656789958,
+      "rewards/margins": 8.864274621009827,
+      "rewards/rejected": -8.716951310634613,
+      "step": 56
+    },
+    {
+      "entropy": 1.167588233947754,
+      "epoch": 5.7272727272727275,
+      "grad_norm": 0.000553131103515625,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": -2.316611971228025,
+      "logits/rejected": -1.8084765653291615,
+      "logps/chosen": -154.08188915252686,
+      "logps/rejected": -332.9342460632324,
+      "loss": 2.3091437469702214e-05,
+      "mean_token_accuracy": 0.5768461301922798,
+      "num_tokens": 432075.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.24338199198246002,
+      "rewards/margins": 12.503851771354675,
+      "rewards/rejected": -12.260469794273376,
+      "step": 57
+    },
+    {
+      "entropy": 1.1254538595676422,
+      "epoch": 5.8311688311688314,
+      "grad_norm": 0.01214599609375,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": -2.1240879253748455,
+      "logits/rejected": -1.683307431601137,
+      "logps/chosen": -132.05009174346924,
+      "logps/rejected": -276.7969856262207,
+      "loss": 0.0006776420050300658,
+      "mean_token_accuracy": 0.6085913628339767,
+      "num_tokens": 439920.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.0067318761721253395,
+      "rewards/margins": 8.990104794502258,
+      "rewards/rejected": -8.996836602687836,
+      "step": 58
+    },
+    {
+      "entropy": 1.1096209362149239,
+      "epoch": 5.935064935064935,
+      "grad_norm": 0.00762939453125,
+      "learning_rate": 1.6666666666666667e-06,
+      "logits/chosen": -2.464917742945188,
+      "logits/rejected": -2.0316993109334662,
+      "logps/chosen": -165.6044044494629,
+      "logps/rejected": -321.6104621887207,
+      "loss": 0.0003184170927852392,
+      "mean_token_accuracy": 0.5715851411223412,
+      "num_tokens": 448088.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.5723045284976251,
+      "rewards/margins": 10.441723942756653,
+      "rewards/rejected": -11.01402860879898,
+      "step": 59
+    },
+    {
+      "entropy": 1.177198052406311,
+      "epoch": 6.0,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": -2.246316011456704,
+      "logits/rejected": -1.7093484860379249,
+      "logps/chosen": -140.52530975341796,
+      "logps/rejected": -272.9529998779297,
+      "loss": 0.00047754126717336476,
+      "mean_token_accuracy": 0.584682285785675,
+      "num_tokens": 453096.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.20170196890830994,
+      "rewards/margins": 8.390394496917725,
+      "rewards/rejected": -8.592096328735352,
+      "step": 60
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3689526234746880.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8847b0afe553d50b3dbf2376440faa37a685b58ab0173fabda56ea326fdd0b9
+size 5905