Upload folder using huggingface_hub

README.md

@@ -1,207 +1,73 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 library_name: peft
-pipeline_tag: text-generation
+model_name: FROX_FLEX_1_0_DPO
 tags:
 - base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- dpo
 - lora
 - transformers
+- trl
+licence: license
+pipeline_tag: text-generation
 ---
 
-# 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:**
+# Model Card for FROX_FLEX_1_0_DPO
 
-[More Information Needed]
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-## Glossary [optional]
+## Quick start
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+```python
+from transformers import pipeline
 
-[More Information Needed]
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device_map="auto")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-## More Information [optional]
+## Training procedure
 
-[More Information Needed]
+ 
 
-## Model Card Authors [optional]
 
-[More Information Needed]
 
-## Model Card Contact
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 
-[More Information Needed]
 ### Framework versions
 
-- PEFT 0.21.0
+- PEFT 0.21.2
+- TRL: 1.14.1
+- Transformers: 5.18.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 5.0.1
+- Tokenizers: 0.23.2
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -26,19 +26,19 @@
   "modules_to_save": null,
   "monteclora_config": null,
   "peft_type": "LORA",
-  "peft_version": "0.21.0",
+  "peft_version": "0.20.0",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
+    "gate_proj",
     "up_proj",
     "o_proj",
-    "q_proj",
-    "k_proj",
     "down_proj",
-    "gate_proj"
+    "q_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35013cd0735cf2635d1d3b5e58b19417211fb610c11e92ceb933dd5185ffcfde
+oid sha256:bc41da54d2a5c79da218d93ed8189f579a077187d9f54b52586859aec607d159
 size 73911112

checkpoint-200/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 0.21.2

checkpoint-200/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631b3f5777f70d6fea66eb6aa3be49bacee96a47f42e236051d6788d3fa0b6bc
+size 73911112

checkpoint-200/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 %}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d37284885d808ad386ae5ef878648557beb3fc6cbd39fed7b2d81521137428
+size 148053627

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eabb0f303017f3ec003b13a0e4706279cc499e14d646f7ecce8b67b57b8dae6
+size 14645

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8ac3f9a833cb5917535cf4cd36224cd48d6070007a9cdbde854eeb58f735b3
+size 1465

checkpoint-200/tokenizer.json

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

checkpoint-200/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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,394 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 100.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.3850007222248957,
+      "epoch": 5.0,
+      "grad_norm": 5.218133926391602,
+      "learning_rate": 4.85e-06,
+      "logits/chosen": 0.5955334049959196,
+      "logits/rejected": 0.32116526582606625,
+      "logps/chosen": -41.78460889963003,
+      "logps/rejected": -46.04202065101037,
+      "loss": 0.5778924465179444,
+      "mean_token_accuracy": 0.48216897593094754,
+      "num_tokens": 3045.0,
+      "rewards/accuracies": 0.676923076923077,
+      "rewards/chosen": 1.8768298184642425,
+      "rewards/margins": 1.1801037300091524,
+      "rewards/rejected": 0.696726090231767,
+      "step": 10
+    },
+    {
+      "entropy": 2.314448336454538,
+      "epoch": 10.0,
+      "grad_norm": 2.3608832359313965,
+      "learning_rate": 4.683333333333334e-06,
+      "logits/chosen": 0.5266339006231595,
+      "logits/rejected": 0.21806011517835058,
+      "logps/chosen": -39.94469804030199,
+      "logps/rejected": -49.08440563495343,
+      "loss": 0.36816518306732177,
+      "mean_token_accuracy": 0.5069385063189726,
+      "num_tokens": 6090.0,
+      "rewards/accuracies": 0.9692307692307692,
+      "rewards/chosen": 2.0608209357811855,
+      "rewards/margins": 1.668333342900643,
+      "rewards/rejected": 0.3924875888579453,
+      "step": 20
+    },
+    {
+      "entropy": 2.2045343949244574,
+      "epoch": 15.0,
+      "grad_norm": 1.2208229303359985,
+      "learning_rate": 4.516666666666667e-06,
+      "logits/chosen": 0.42076279344647916,
+      "logits/rejected": 0.0795841027230604,
+      "logps/chosen": -38.261579630925105,
+      "logps/rejected": -52.489193872305066,
+      "loss": 0.25407335758209226,
+      "mean_token_accuracy": 0.5410144303853696,
+      "num_tokens": 9135.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.22913277057501,
+      "rewards/margins": 2.1771240174770354,
+      "rewards/rejected": 0.05200875710982543,
+      "step": 30
+    },
+    {
+      "entropy": 2.0643920261126296,
+      "epoch": 20.0,
+      "grad_norm": 1.1566054821014404,
+      "learning_rate": 4.350000000000001e-06,
+      "logits/chosen": 0.2660081956584437,
+      "logits/rejected": -0.11877416602934321,
+      "logps/chosen": -36.715302041860724,
+      "logps/rejected": -56.045902252197266,
+      "loss": 0.18806705474853516,
+      "mean_token_accuracy": 0.5574041231320455,
+      "num_tokens": 12180.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.3837605155431305,
+      "rewards/margins": 2.687422578609907,
+      "rewards/rejected": -0.3036620749733769,
+      "step": 40
+    },
+    {
+      "entropy": 1.9192953155590937,
+      "epoch": 25.0,
+      "grad_norm": 1.2787108421325684,
+      "learning_rate": 4.183333333333334e-06,
+      "logits/chosen": 0.06328228399595424,
+      "logits/rejected": -0.36550493553391344,
+      "logps/chosen": -35.36447745103102,
+      "logps/rejected": -59.87469277015099,
+      "loss": 0.1385887861251831,
+      "mean_token_accuracy": 0.5706025022726793,
+      "num_tokens": 15225.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.5188429571115054,
+      "rewards/margins": 3.205384102234474,
+      "rewards/rejected": -0.6865411404806834,
+      "step": 50
+    },
+    {
+      "entropy": 1.7868539026150336,
+      "epoch": 30.0,
+      "grad_norm": 0.8686179518699646,
+      "learning_rate": 4.0166666666666675e-06,
+      "logits/chosen": -0.1935140321445184,
+      "logits/rejected": -0.6839043743711061,
+      "logps/chosen": -34.12935148385855,
+      "logps/rejected": -64.12931248591497,
+      "loss": 0.0951196312904358,
+      "mean_token_accuracy": 0.5941899987367484,
+      "num_tokens": 18270.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.64235560802313,
+      "rewards/margins": 3.754358713443463,
+      "rewards/rejected": -1.112003114934151,
+      "step": 60
+    },
+    {
+      "entropy": 1.6745153069496155,
+      "epoch": 35.0,
+      "grad_norm": 0.9338397979736328,
+      "learning_rate": 3.85e-06,
+      "logits/chosen": -0.3970043551674374,
+      "logits/rejected": -0.9072793044553101,
+      "logps/chosen": -33.13469376197228,
+      "logps/rejected": -67.47981532170222,
+      "loss": 0.06889303326606751,
+      "mean_token_accuracy": 0.6142469997589405,
+      "num_tokens": 21315.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.7418213651730463,
+      "rewards/margins": 4.188874772878793,
+      "rewards/rejected": -1.4470534209806758,
+      "step": 70
+    },
+    {
+      "entropy": 1.5280305674442878,
+      "epoch": 40.0,
+      "grad_norm": 0.33691903948783875,
+      "learning_rate": 3.6833333333333338e-06,
+      "logits/chosen": -0.645527713806289,
+      "logits/rejected": -1.192322842277305,
+      "logps/chosen": -32.71983912541316,
+      "logps/rejected": -71.29921434842623,
+      "loss": 0.05013889670372009,
+      "mean_token_accuracy": 0.6215091819946582,
+      "num_tokens": 24360.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.783306827911964,
+      "rewards/margins": 4.612300166716943,
+      "rewards/rejected": -1.8289933227289181,
+      "step": 80
+    },
+    {
+      "entropy": 1.4477157487319066,
+      "epoch": 45.0,
+      "grad_norm": 0.0781475231051445,
+      "learning_rate": 3.516666666666667e-06,
+      "logits/chosen": -0.8208894431606327,
+      "logits/rejected": -1.3862875261002638,
+      "logps/chosen": -32.24270979074331,
+      "logps/rejected": -74.3404776939979,
+      "loss": 0.037910228967666625,
+      "mean_token_accuracy": 0.6225866313164051,
+      "num_tokens": 27405.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.831019756427178,
+      "rewards/margins": 4.964139417501596,
+      "rewards/rejected": -2.133119664513148,
+      "step": 90
+    },
+    {
+      "entropy": 1.3916929373374352,
+      "epoch": 50.0,
+      "grad_norm": 0.1870872527360916,
+      "learning_rate": 3.3500000000000005e-06,
+      "logits/chosen": -0.9026928408855097,
+      "logits/rejected": -1.4932921680317246,
+      "logps/chosen": -31.6792912703294,
+      "logps/rejected": -76.95603843102089,
+      "loss": 0.029496246576309205,
+      "mean_token_accuracy": 0.6238097415520595,
+      "num_tokens": 30450.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.8873616236906785,
+      "rewards/margins": 5.282037371855516,
+      "rewards/rejected": -2.3946757453708694,
+      "step": 100
+    },
+    {
+      "entropy": 1.3489822713228372,
+      "epoch": 55.0,
+      "grad_norm": 0.15059450268745422,
+      "learning_rate": 3.183333333333334e-06,
+      "logits/chosen": -0.9584337553499183,
+      "logits/rejected": -1.5809670771118987,
+      "logps/chosen": -31.16159066420335,
+      "logps/rejected": -79.13991223848782,
+      "loss": 0.025989437103271486,
+      "mean_token_accuracy": 0.6313372121407436,
+      "num_tokens": 33495.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.9391316624788137,
+      "rewards/margins": 5.552194802577679,
+      "rewards/rejected": -2.6130631179190598,
+      "step": 110
+    },
+    {
+      "entropy": 1.3076109152573805,
+      "epoch": 60.0,
+      "grad_norm": 0.4038887619972229,
+      "learning_rate": 3.0166666666666673e-06,
+      "logits/chosen": -1.0143513353856966,
+      "logits/rejected": -1.6518468357354557,
+      "logps/chosen": -30.717048087486855,
+      "logps/rejected": -80.81175912710337,
+      "loss": 0.019894377887248994,
+      "mean_token_accuracy": 0.6305825824920948,
+      "num_tokens": 36540.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.983585899609786,
+      "rewards/margins": 5.763833695191604,
+      "rewards/rejected": -2.7802478168589566,
+      "step": 120
+    },
+    {
+      "entropy": 1.2777886221042045,
+      "epoch": 65.0,
+      "grad_norm": 0.11832690238952637,
+      "learning_rate": 2.85e-06,
+      "logits/chosen": -1.0513172948777008,
+      "logits/rejected": -1.70667886808449,
+      "logps/chosen": -30.33043086712177,
+      "logps/rejected": -82.26801863450271,
+      "loss": 0.017130233347415924,
+      "mean_token_accuracy": 0.6363077672628256,
+      "num_tokens": 39585.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.022247677582961,
+      "rewards/margins": 5.94812143949362,
+      "rewards/rejected": -2.9258737678711233,
+      "step": 130
+    },
+    {
+      "entropy": 1.250800774189142,
+      "epoch": 70.0,
+      "grad_norm": 0.07396625727415085,
+      "learning_rate": 2.683333333333333e-06,
+      "logits/chosen": -1.0829184006557993,
+      "logits/rejected": -1.7563719300860305,
+      "logps/chosen": -30.013790159959058,
+      "logps/rejected": -83.55414663461538,
+      "loss": 0.014281480014324189,
+      "mean_token_accuracy": 0.6392337904526637,
+      "num_tokens": 42630.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.053911742797265,
+      "rewards/margins": 6.1083983182907104,
+      "rewards/rejected": -3.054486560019163,
+      "step": 140
+    },
+    {
+      "entropy": 1.223134689606153,
+      "epoch": 75.0,
+      "grad_norm": 0.05753239244222641,
+      "learning_rate": 2.5166666666666666e-06,
+      "logits/chosen": -1.1195608680355456,
+      "logits/rejected": -1.8052698192809788,
+      "logps/chosen": -29.635238119272085,
+      "logps/rejected": -84.57547466571515,
+      "loss": 0.012452676892280579,
+      "mean_token_accuracy": 0.6391755163669586,
+      "num_tokens": 45675.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.091766904867612,
+      "rewards/margins": 6.248386273017297,
+      "rewards/rejected": -3.1566193484343015,
+      "step": 150
+    },
+    {
+      "entropy": 1.2027296034189372,
+      "epoch": 80.0,
+      "grad_norm": 0.3149576485157013,
+      "learning_rate": 2.35e-06,
+      "logits/chosen": -1.1491697674350145,
+      "logits/rejected": -1.8513586526299164,
+      "logps/chosen": -29.390566752507137,
+      "logps/rejected": -85.54401256854717,
+      "loss": 0.010251734405755997,
+      "mean_token_accuracy": 0.6281787042434399,
+      "num_tokens": 48720.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.1162340833590583,
+      "rewards/margins": 6.369707246927114,
+      "rewards/rejected": -3.253473144081923,
+      "step": 160
+    },
+    {
+      "entropy": 1.1893031638402205,
+      "epoch": 85.0,
+      "grad_norm": 0.27565744519233704,
+      "learning_rate": 2.1833333333333333e-06,
+      "logits/chosen": -1.1672777094357023,
+      "logits/rejected": -1.8822302021351611,
+      "logps/chosen": -29.235072796161358,
+      "logps/rejected": -86.43060050377478,
+      "loss": 0.010401710867881775,
+      "mean_token_accuracy": 0.6251530615183023,
+      "num_tokens": 51765.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.1317834468988273,
+      "rewards/margins": 6.473915430215689,
+      "rewards/rejected": -3.3421319489295667,
+      "step": 170
+    },
+    {
+      "entropy": 1.1756579087330745,
+      "epoch": 90.0,
+      "grad_norm": 0.06536174565553665,
+      "learning_rate": 2.0166666666666667e-06,
+      "logits/chosen": -1.1910031234123657,
+      "logits/rejected": -1.9204785576885457,
+      "logps/chosen": -28.8819152538593,
+      "logps/rejected": -87.1160526569073,
+      "loss": 0.007509545981884002,
+      "mean_token_accuracy": 0.6323185668541835,
+      "num_tokens": 54810.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.167099202596224,
+      "rewards/margins": 6.577776369681725,
+      "rewards/rejected": -3.410677168002495,
+      "step": 180
+    },
+    {
+      "entropy": 1.1582091863338764,
+      "epoch": 95.0,
+      "grad_norm": 0.07627511024475098,
+      "learning_rate": 1.85e-06,
+      "logits/chosen": -1.2080450987055713,
+      "logits/rejected": -1.953039308066732,
+      "logps/chosen": -28.834403258103592,
+      "logps/rejected": -87.93590979942908,
+      "loss": 0.006308925151824951,
+      "mean_token_accuracy": 0.6208858558764825,
+      "num_tokens": 57855.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.17185040804056,
+      "rewards/margins": 6.6645133348611685,
+      "rewards/rejected": -3.4926629029787506,
+      "step": 190
+    },
+    {
+      "entropy": 1.1551778793334961,
+      "epoch": 100.0,
+      "grad_norm": 0.05331544205546379,
+      "learning_rate": 1.6833333333333335e-06,
+      "logits/chosen": -1.220794750164101,
+      "logits/rejected": -1.981571992290679,
+      "logps/chosen": -28.619847635122447,
+      "logps/rejected": -88.4375508235051,
+      "loss": 0.0059698235243558885,
+      "mean_token_accuracy": 0.6226402415679051,
+      "num_tokens": 60900.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.1933059848271883,
+      "rewards/margins": 6.736132926207322,
+      "rewards/rejected": -3.542826987229861,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 559692824371200.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed20121d523371613736c42432815014a46c49492bcc18f46d1eee9d38e70d8
+size 5905

checkpoint-300/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 0.21.2

checkpoint-300/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc41da54d2a5c79da218d93ed8189f579a077187d9f54b52586859aec607d159
+size 73911112

checkpoint-300/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 %}

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064c3f1bd1991880adb22e2f1024b639f69c9dfde0b658d63eafbb0f0c74b40d
+size 148053627

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a5654c57cc126b5c598225c4a6284d613b5469c9cd86453b7fd133fefaaa3f
+size 14645

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73803a757f07fdc3affe355b72e98d0dd69ecf6ab604f22f34d34efbe21826ce
+size 1465

checkpoint-300/tokenizer.json

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

checkpoint-300/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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 150.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.3850007222248957,
+      "epoch": 5.0,
+      "grad_norm": 5.218133926391602,
+      "learning_rate": 4.85e-06,
+      "logits/chosen": 0.5955334049959196,
+      "logits/rejected": 0.32116526582606625,
+      "logps/chosen": -41.78460889963003,
+      "logps/rejected": -46.04202065101037,
+      "loss": 0.5778924465179444,
+      "mean_token_accuracy": 0.48216897593094754,
+      "num_tokens": 3045.0,
+      "rewards/accuracies": 0.676923076923077,
+      "rewards/chosen": 1.8768298184642425,
+      "rewards/margins": 1.1801037300091524,
+      "rewards/rejected": 0.696726090231767,
+      "step": 10
+    },
+    {
+      "entropy": 2.314448336454538,
+      "epoch": 10.0,
+      "grad_norm": 2.3608832359313965,
+      "learning_rate": 4.683333333333334e-06,
+      "logits/chosen": 0.5266339006231595,
+      "logits/rejected": 0.21806011517835058,
+      "logps/chosen": -39.94469804030199,
+      "logps/rejected": -49.08440563495343,
+      "loss": 0.36816518306732177,
+      "mean_token_accuracy": 0.5069385063189726,
+      "num_tokens": 6090.0,
+      "rewards/accuracies": 0.9692307692307692,
+      "rewards/chosen": 2.0608209357811855,
+      "rewards/margins": 1.668333342900643,
+      "rewards/rejected": 0.3924875888579453,
+      "step": 20
+    },
+    {
+      "entropy": 2.2045343949244574,
+      "epoch": 15.0,
+      "grad_norm": 1.2208229303359985,
+      "learning_rate": 4.516666666666667e-06,
+      "logits/chosen": 0.42076279344647916,
+      "logits/rejected": 0.0795841027230604,
+      "logps/chosen": -38.261579630925105,
+      "logps/rejected": -52.489193872305066,
+      "loss": 0.25407335758209226,
+      "mean_token_accuracy": 0.5410144303853696,
+      "num_tokens": 9135.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.22913277057501,
+      "rewards/margins": 2.1771240174770354,
+      "rewards/rejected": 0.05200875710982543,
+      "step": 30
+    },
+    {
+      "entropy": 2.0643920261126296,
+      "epoch": 20.0,
+      "grad_norm": 1.1566054821014404,
+      "learning_rate": 4.350000000000001e-06,
+      "logits/chosen": 0.2660081956584437,
+      "logits/rejected": -0.11877416602934321,
+      "logps/chosen": -36.715302041860724,
+      "logps/rejected": -56.045902252197266,
+      "loss": 0.18806705474853516,
+      "mean_token_accuracy": 0.5574041231320455,
+      "num_tokens": 12180.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.3837605155431305,
+      "rewards/margins": 2.687422578609907,
+      "rewards/rejected": -0.3036620749733769,
+      "step": 40
+    },
+    {
+      "entropy": 1.9192953155590937,
+      "epoch": 25.0,
+      "grad_norm": 1.2787108421325684,
+      "learning_rate": 4.183333333333334e-06,
+      "logits/chosen": 0.06328228399595424,
+      "logits/rejected": -0.36550493553391344,
+      "logps/chosen": -35.36447745103102,
+      "logps/rejected": -59.87469277015099,
+      "loss": 0.1385887861251831,
+      "mean_token_accuracy": 0.5706025022726793,
+      "num_tokens": 15225.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.5188429571115054,
+      "rewards/margins": 3.205384102234474,
+      "rewards/rejected": -0.6865411404806834,
+      "step": 50
+    },
+    {
+      "entropy": 1.7868539026150336,
+      "epoch": 30.0,
+      "grad_norm": 0.8686179518699646,
+      "learning_rate": 4.0166666666666675e-06,
+      "logits/chosen": -0.1935140321445184,
+      "logits/rejected": -0.6839043743711061,
+      "logps/chosen": -34.12935148385855,
+      "logps/rejected": -64.12931248591497,
+      "loss": 0.0951196312904358,
+      "mean_token_accuracy": 0.5941899987367484,
+      "num_tokens": 18270.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.64235560802313,
+      "rewards/margins": 3.754358713443463,
+      "rewards/rejected": -1.112003114934151,
+      "step": 60
+    },
+    {
+      "entropy": 1.6745153069496155,
+      "epoch": 35.0,
+      "grad_norm": 0.9338397979736328,
+      "learning_rate": 3.85e-06,
+      "logits/chosen": -0.3970043551674374,
+      "logits/rejected": -0.9072793044553101,
+      "logps/chosen": -33.13469376197228,
+      "logps/rejected": -67.47981532170222,
+      "loss": 0.06889303326606751,
+      "mean_token_accuracy": 0.6142469997589405,
+      "num_tokens": 21315.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.7418213651730463,
+      "rewards/margins": 4.188874772878793,
+      "rewards/rejected": -1.4470534209806758,
+      "step": 70
+    },
+    {
+      "entropy": 1.5280305674442878,
+      "epoch": 40.0,
+      "grad_norm": 0.33691903948783875,
+      "learning_rate": 3.6833333333333338e-06,
+      "logits/chosen": -0.645527713806289,
+      "logits/rejected": -1.192322842277305,
+      "logps/chosen": -32.71983912541316,
+      "logps/rejected": -71.29921434842623,
+      "loss": 0.05013889670372009,
+      "mean_token_accuracy": 0.6215091819946582,
+      "num_tokens": 24360.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.783306827911964,
+      "rewards/margins": 4.612300166716943,
+      "rewards/rejected": -1.8289933227289181,
+      "step": 80
+    },
+    {
+      "entropy": 1.4477157487319066,
+      "epoch": 45.0,
+      "grad_norm": 0.0781475231051445,
+      "learning_rate": 3.516666666666667e-06,
+      "logits/chosen": -0.8208894431606327,
+      "logits/rejected": -1.3862875261002638,
+      "logps/chosen": -32.24270979074331,
+      "logps/rejected": -74.3404776939979,
+      "loss": 0.037910228967666625,
+      "mean_token_accuracy": 0.6225866313164051,
+      "num_tokens": 27405.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.831019756427178,
+      "rewards/margins": 4.964139417501596,
+      "rewards/rejected": -2.133119664513148,
+      "step": 90
+    },
+    {
+      "entropy": 1.3916929373374352,
+      "epoch": 50.0,
+      "grad_norm": 0.1870872527360916,
+      "learning_rate": 3.3500000000000005e-06,
+      "logits/chosen": -0.9026928408855097,
+      "logits/rejected": -1.4932921680317246,
+      "logps/chosen": -31.6792912703294,
+      "logps/rejected": -76.95603843102089,
+      "loss": 0.029496246576309205,
+      "mean_token_accuracy": 0.6238097415520595,
+      "num_tokens": 30450.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.8873616236906785,
+      "rewards/margins": 5.282037371855516,
+      "rewards/rejected": -2.3946757453708694,
+      "step": 100
+    },
+    {
+      "entropy": 1.3489822713228372,
+      "epoch": 55.0,
+      "grad_norm": 0.15059450268745422,
+      "learning_rate": 3.183333333333334e-06,
+      "logits/chosen": -0.9584337553499183,
+      "logits/rejected": -1.5809670771118987,
+      "logps/chosen": -31.16159066420335,
+      "logps/rejected": -79.13991223848782,
+      "loss": 0.025989437103271486,
+      "mean_token_accuracy": 0.6313372121407436,
+      "num_tokens": 33495.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.9391316624788137,
+      "rewards/margins": 5.552194802577679,
+      "rewards/rejected": -2.6130631179190598,
+      "step": 110
+    },
+    {
+      "entropy": 1.3076109152573805,
+      "epoch": 60.0,
+      "grad_norm": 0.4038887619972229,
+      "learning_rate": 3.0166666666666673e-06,
+      "logits/chosen": -1.0143513353856966,
+      "logits/rejected": -1.6518468357354557,
+      "logps/chosen": -30.717048087486855,
+      "logps/rejected": -80.81175912710337,
+      "loss": 0.019894377887248994,
+      "mean_token_accuracy": 0.6305825824920948,
+      "num_tokens": 36540.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.983585899609786,
+      "rewards/margins": 5.763833695191604,
+      "rewards/rejected": -2.7802478168589566,
+      "step": 120
+    },
+    {
+      "entropy": 1.2777886221042045,
+      "epoch": 65.0,
+      "grad_norm": 0.11832690238952637,
+      "learning_rate": 2.85e-06,
+      "logits/chosen": -1.0513172948777008,
+      "logits/rejected": -1.70667886808449,
+      "logps/chosen": -30.33043086712177,
+      "logps/rejected": -82.26801863450271,
+      "loss": 0.017130233347415924,
+      "mean_token_accuracy": 0.6363077672628256,
+      "num_tokens": 39585.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.022247677582961,
+      "rewards/margins": 5.94812143949362,
+      "rewards/rejected": -2.9258737678711233,
+      "step": 130
+    },
+    {
+      "entropy": 1.250800774189142,
+      "epoch": 70.0,
+      "grad_norm": 0.07396625727415085,
+      "learning_rate": 2.683333333333333e-06,
+      "logits/chosen": -1.0829184006557993,
+      "logits/rejected": -1.7563719300860305,
+      "logps/chosen": -30.013790159959058,
+      "logps/rejected": -83.55414663461538,
+      "loss": 0.014281480014324189,
+      "mean_token_accuracy": 0.6392337904526637,
+      "num_tokens": 42630.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.053911742797265,
+      "rewards/margins": 6.1083983182907104,
+      "rewards/rejected": -3.054486560019163,
+      "step": 140
+    },
+    {
+      "entropy": 1.223134689606153,
+      "epoch": 75.0,
+      "grad_norm": 0.05753239244222641,
+      "learning_rate": 2.5166666666666666e-06,
+      "logits/chosen": -1.1195608680355456,
+      "logits/rejected": -1.8052698192809788,
+      "logps/chosen": -29.635238119272085,
+      "logps/rejected": -84.57547466571515,
+      "loss": 0.012452676892280579,
+      "mean_token_accuracy": 0.6391755163669586,
+      "num_tokens": 45675.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.091766904867612,
+      "rewards/margins": 6.248386273017297,
+      "rewards/rejected": -3.1566193484343015,
+      "step": 150
+    },
+    {
+      "entropy": 1.2027296034189372,
+      "epoch": 80.0,
+      "grad_norm": 0.3149576485157013,
+      "learning_rate": 2.35e-06,
+      "logits/chosen": -1.1491697674350145,
+      "logits/rejected": -1.8513586526299164,
+      "logps/chosen": -29.390566752507137,
+      "logps/rejected": -85.54401256854717,
+      "loss": 0.010251734405755997,
+      "mean_token_accuracy": 0.6281787042434399,
+      "num_tokens": 48720.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.1162340833590583,
+      "rewards/margins": 6.369707246927114,
+      "rewards/rejected": -3.253473144081923,
+      "step": 160
+    },
+    {
+      "entropy": 1.1893031638402205,
+      "epoch": 85.0,
+      "grad_norm": 0.27565744519233704,
+      "learning_rate": 2.1833333333333333e-06,
+      "logits/chosen": -1.1672777094357023,
+      "logits/rejected": -1.8822302021351611,
+      "logps/chosen": -29.235072796161358,
+      "logps/rejected": -86.43060050377478,
+      "loss": 0.010401710867881775,
+      "mean_token_accuracy": 0.6251530615183023,
+      "num_tokens": 51765.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.1317834468988273,
+      "rewards/margins": 6.473915430215689,
+      "rewards/rejected": -3.3421319489295667,
+      "step": 170
+    },
+    {
+      "entropy": 1.1756579087330745,
+      "epoch": 90.0,
+      "grad_norm": 0.06536174565553665,
+      "learning_rate": 2.0166666666666667e-06,
+      "logits/chosen": -1.1910031234123657,
+      "logits/rejected": -1.9204785576885457,
+      "logps/chosen": -28.8819152538593,
+      "logps/rejected": -87.1160526569073,
+      "loss": 0.007509545981884002,
+      "mean_token_accuracy": 0.6323185668541835,
+      "num_tokens": 54810.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.167099202596224,
+      "rewards/margins": 6.577776369681725,
+      "rewards/rejected": -3.410677168002495,
+      "step": 180
+    },
+    {
+      "entropy": 1.1582091863338764,
+      "epoch": 95.0,
+      "grad_norm": 0.07627511024475098,
+      "learning_rate": 1.85e-06,
+      "logits/chosen": -1.2080450987055713,
+      "logits/rejected": -1.953039308066732,
+      "logps/chosen": -28.834403258103592,
+      "logps/rejected": -87.93590979942908,
+      "loss": 0.006308925151824951,
+      "mean_token_accuracy": 0.6208858558764825,
+      "num_tokens": 57855.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.17185040804056,
+      "rewards/margins": 6.6645133348611685,
+      "rewards/rejected": -3.4926629029787506,
+      "step": 190
+    },
+    {
+      "entropy": 1.1551778793334961,
+      "epoch": 100.0,
+      "grad_norm": 0.05331544205546379,
+      "learning_rate": 1.6833333333333335e-06,
+      "logits/chosen": -1.220794750164101,
+      "logits/rejected": -1.981571992290679,
+      "logps/chosen": -28.619847635122447,
+      "logps/rejected": -88.4375508235051,
+      "loss": 0.0059698235243558885,
+      "mean_token_accuracy": 0.6226402415679051,
+      "num_tokens": 60900.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.1933059848271883,
+      "rewards/margins": 6.736132926207322,
+      "rewards/rejected": -3.542826987229861,
+      "step": 200
+    },
+    {
+      "entropy": 1.1426296073656816,
+      "epoch": 105.0,
+      "grad_norm": 0.05480801314115524,
+      "learning_rate": 1.5166666666666668e-06,
+      "logits/chosen": -1.231853422725045,
+      "logits/rejected": -2.0020896033092983,
+      "logps/chosen": -28.58630635188176,
+      "logps/rejected": -89.03529874361479,
+      "loss": 0.005416269600391388,
+      "mean_token_accuracy": 0.6206193428773147,
+      "num_tokens": 63945.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.196660072986896,
+      "rewards/margins": 6.799261859747079,
+      "rewards/rejected": -3.6026018018905934,
+      "step": 210
+    },
+    {
+      "entropy": 1.1356208879214067,
+      "epoch": 110.0,
+      "grad_norm": 0.1870356947183609,
+      "learning_rate": 1.3500000000000002e-06,
+      "logits/chosen": -1.242897494818351,
+      "logits/rejected": -2.017118331043808,
+      "logps/chosen": -28.472275719275842,
+      "logps/rejected": -89.66436227651742,
+      "loss": 0.0053675461560487745,
+      "mean_token_accuracy": 0.6187149167060852,
+      "num_tokens": 66990.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.208063186131991,
+      "rewards/margins": 6.873571296838613,
+      "rewards/rejected": -3.665508143718426,
+      "step": 220
+    },
+    {
+      "entropy": 1.1326277191822345,
+      "epoch": 115.0,
+      "grad_norm": 0.17812301218509674,
+      "learning_rate": 1.1833333333333334e-06,
+      "logits/chosen": -1.2533293434899542,
+      "logits/rejected": -2.039634911561449,
+      "logps/chosen": -28.25326312138484,
+      "logps/rejected": -89.78828330406776,
+      "loss": 0.0052538376301527025,
+      "mean_token_accuracy": 0.6225874048012954,
+      "num_tokens": 70035.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2299644268476047,
+      "rewards/margins": 6.907864669653086,
+      "rewards/rejected": -3.677900252892421,
+      "step": 230
+    },
+    {
+      "entropy": 1.1250401950799502,
+      "epoch": 120.0,
+      "grad_norm": 0.15003784000873566,
+      "learning_rate": 1.0166666666666667e-06,
+      "logits/chosen": -1.257569145451956,
+      "logits/rejected": -2.050265735691312,
+      "logps/chosen": -28.221469380305365,
+      "logps/rejected": -90.19944645808293,
+      "loss": 0.004942169412970543,
+      "mean_token_accuracy": 0.6183986746347867,
+      "num_tokens": 73080.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2331438321333663,
+      "rewards/margins": 6.95216036943289,
+      "rewards/rejected": -3.719016566643348,
+      "step": 240
+    },
+    {
+      "entropy": 1.1205400155140803,
+      "epoch": 125.0,
+      "grad_norm": 0.042884498834609985,
+      "learning_rate": 8.500000000000001e-07,
+      "logits/chosen": -1.2690723238716755,
+      "logits/rejected": -2.069106913013174,
+      "logps/chosen": -28.168808775681715,
+      "logps/rejected": -90.60292575542744,
+      "loss": 0.004609152302145958,
+      "mean_token_accuracy": 0.6232292890548706,
+      "num_tokens": 76125.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2384098566495454,
+      "rewards/margins": 6.9977743405562185,
+      "rewards/rejected": -3.7593644994955797,
+      "step": 250
+    },
+    {
+      "entropy": 1.1178178645097292,
+      "epoch": 130.0,
+      "grad_norm": 0.05744079872965813,
+      "learning_rate": 6.833333333333334e-07,
+      "logits/chosen": -1.2737910903590781,
+      "logits/rejected": -2.07357408100483,
+      "logps/chosen": -28.046851026094878,
+      "logps/rejected": -90.76857217641977,
+      "loss": 0.00424395315349102,
+      "mean_token_accuracy": 0.6194670512126043,
+      "num_tokens": 79170.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2506056253726667,
+      "rewards/margins": 7.0265347260695235,
+      "rewards/rejected": -3.7759291373766386,
+      "step": 260
+    },
+    {
+      "entropy": 1.1141802962009724,
+      "epoch": 135.0,
+      "grad_norm": 0.15264171361923218,
+      "learning_rate": 5.166666666666667e-07,
+      "logits/chosen": -1.2837046704770079,
+      "logits/rejected": -2.0861976738101147,
+      "logps/chosen": -28.00541998056265,
+      "logps/rejected": -90.9417841397799,
+      "loss": 0.004570071399211883,
+      "mean_token_accuracy": 0.6172198827450092,
+      "num_tokens": 82215.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.254748777242807,
+      "rewards/margins": 7.047999128928551,
+      "rewards/rejected": -3.793250336096837,
+      "step": 270
+    },
+    {
+      "entropy": 1.1152964940437904,
+      "epoch": 140.0,
+      "grad_norm": 0.0695829838514328,
+      "learning_rate": 3.5000000000000004e-07,
+      "logits/chosen": -1.2849921549972774,
+      "logits/rejected": -2.0898888408580025,
+      "logps/chosen": -28.04736768282377,
+      "logps/rejected": -91.21173999492939,
+      "loss": 0.0037465617060661316,
+      "mean_token_accuracy": 0.6219463788546049,
+      "num_tokens": 85260.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2505539692365204,
+      "rewards/margins": 7.070799944950984,
+      "rewards/rejected": -3.820245937200693,
+      "step": 280
+    },
+    {
+      "entropy": 1.1116300225257874,
+      "epoch": 145.0,
+      "grad_norm": 0.13623295724391937,
+      "learning_rate": 1.8333333333333336e-07,
+      "logits/chosen": -1.2863314429379384,
+      "logits/rejected": -2.0972242711900613,
+      "logps/chosen": -27.95127751277043,
+      "logps/rejected": -91.2013175377479,
+      "loss": 0.004024703800678253,
+      "mean_token_accuracy": 0.629658029629634,
+      "num_tokens": 88305.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2601629972457884,
+      "rewards/margins": 7.079366680291983,
+      "rewards/rejected": -3.819203683046194,
+      "step": 290
+    },
+    {
+      "entropy": 1.1074378174084885,
+      "epoch": 150.0,
+      "grad_norm": 0.05619078502058983,
+      "learning_rate": 1.666666666666667e-08,
+      "logits/chosen": -1.2918823478513337,
+      "logits/rejected": -2.1033061557173203,
+      "logps/chosen": -27.983433268620416,
+      "logps/rejected": -91.42072965181791,
+      "loss": 0.0036425717175006867,
+      "mean_token_accuracy": 0.6180295990063593,
+      "num_tokens": 91350.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2569474348655114,
+      "rewards/margins": 7.0980922919053295,
+      "rewards/rejected": -3.841144861624791,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 839539236556800.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed20121d523371613736c42432815014a46c49492bcc18f46d1eee9d38e70d8
+size 5905

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f55e63353d3d978b390d346bae531be8b83bc9532c0be500d62b7253aa4c595
-size 11421991
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a0dace2cc4eb22cc895e26540e9207a0c24ec0150b8e0768b062a4fcc440ba
-size 5201
+oid sha256:fed20121d523371613736c42432815014a46c49492bcc18f46d1eee9d38e70d8
+size 5905