Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-125m",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61dd16f4451afbc193a9d47acc928f16b0fa5b6ea6ee421824cbaf00da971bb9
+size 2365968

checkpoint-207/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: facebook/opt-125m
+---
+
+# 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 0.7.1

checkpoint-207/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-125m",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-207/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61dd16f4451afbc193a9d47acc928f16b0fa5b6ea6ee421824cbaf00da971bb9
+size 2365968

checkpoint-207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a930f639ef47f31d583944dce1f791a1f64cd45a30cbed88379c5f142481bc
+size 4759290

checkpoint-207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a10d25356fc848658ab6077f967757c03e72dbd7b8f4d952543ecd3839b5ee
+size 14244

checkpoint-207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b8b1984e1e44a8fd350b81fd556b7a0b12289949ee9b1650d946dc99d4b73c
+size 1064

checkpoint-207/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-207/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

checkpoint-207/trainer_state.json

@@ -0,0 +1,231 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 207,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.5714285714285715e-05,
+      "logits/chosen": -1.823734998703003,
+      "logits/rejected": -1.96222984790802,
+      "logps/chosen": -984.5184936523438,
+      "logps/rejected": -29.066242218017578,
+      "loss": 0.7963,
+      "rewards/accuracies": 0.6538461446762085,
+      "rewards/chosen": 0.2930363118648529,
+      "rewards/margins": 0.29948848485946655,
+      "rewards/rejected": -0.00645211897790432,
+      "step": 13
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.9516129032258067e-05,
+      "logits/chosen": -1.7756704092025757,
+      "logits/rejected": -1.890375018119812,
+      "logps/chosen": -1008.671630859375,
+      "logps/rejected": -30.05452537536621,
+      "loss": 0.5675,
+      "rewards/accuracies": 0.6538461446762085,
+      "rewards/chosen": 0.6647549867630005,
+      "rewards/margins": 0.7006121277809143,
+      "rewards/rejected": -0.03585716709494591,
+      "step": 26
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.7419354838709678e-05,
+      "logits/chosen": -1.837444543838501,
+      "logits/rejected": -1.8552197217941284,
+      "logps/chosen": -1084.7537841796875,
+      "logps/rejected": -30.599714279174805,
+      "loss": 0.4647,
+      "rewards/accuracies": 0.7692307829856873,
+      "rewards/chosen": 0.9935499429702759,
+      "rewards/margins": 1.160874366760254,
+      "rewards/rejected": -0.16732460260391235,
+      "step": 39
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.532258064516129e-05,
+      "logits/chosen": -1.745394229888916,
+      "logits/rejected": -1.8828259706497192,
+      "logps/chosen": -1103.2149658203125,
+      "logps/rejected": -32.83525085449219,
+      "loss": 0.2193,
+      "rewards/accuracies": 0.8846153616905212,
+      "rewards/chosen": 2.401637077331543,
+      "rewards/margins": 2.809011697769165,
+      "rewards/rejected": -0.4073745608329773,
+      "step": 52
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.3225806451612902e-05,
+      "logits/chosen": -1.6953773498535156,
+      "logits/rejected": -2.03174090385437,
+      "logps/chosen": -1086.2177734375,
+      "logps/rejected": -34.20427703857422,
+      "loss": 0.1084,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.713472843170166,
+      "rewards/margins": 3.305988073348999,
+      "rewards/rejected": -0.5925151109695435,
+      "step": 65
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.1129032258064516e-05,
+      "logits/chosen": -1.7250920534133911,
+      "logits/rejected": -1.886851191520691,
+      "logps/chosen": -902.3397827148438,
+      "logps/rejected": -36.79640579223633,
+      "loss": 0.0972,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.591458797454834,
+      "rewards/margins": 3.4001564979553223,
+      "rewards/rejected": -0.8086973428726196,
+      "step": 78
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.903225806451613e-05,
+      "logits/chosen": -1.6640688180923462,
+      "logits/rejected": -1.9599171876907349,
+      "logps/chosen": -1034.3873291015625,
+      "logps/rejected": -38.65880584716797,
+      "loss": 0.0428,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.461390495300293,
+      "rewards/margins": 4.427910327911377,
+      "rewards/rejected": -0.9665195941925049,
+      "step": 91
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.6935483870967744e-05,
+      "logits/chosen": -1.6940295696258545,
+      "logits/rejected": -1.9844238758087158,
+      "logps/chosen": -1174.732666015625,
+      "logps/rejected": -41.705257415771484,
+      "loss": 0.0235,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.3263399600982666,
+      "rewards/margins": 4.630356788635254,
+      "rewards/rejected": -1.3040169477462769,
+      "step": 104
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.4838709677419355e-05,
+      "logits/chosen": -1.6856719255447388,
+      "logits/rejected": -1.8793022632598877,
+      "logps/chosen": -1046.614990234375,
+      "logps/rejected": -43.94160842895508,
+      "loss": 0.0238,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.614682912826538,
+      "rewards/margins": 5.117927074432373,
+      "rewards/rejected": -1.5032439231872559,
+      "step": 117
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.274193548387097e-05,
+      "logits/chosen": -1.7377840280532837,
+      "logits/rejected": -1.8570376634597778,
+      "logps/chosen": -1106.663330078125,
+      "logps/rejected": -47.238887786865234,
+      "loss": 0.0242,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.449557304382324,
+      "rewards/margins": 5.24083137512207,
+      "rewards/rejected": -1.7912741899490356,
+      "step": 130
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.0645161290322582e-05,
+      "logits/chosen": -1.7412984371185303,
+      "logits/rejected": -1.9490795135498047,
+      "logps/chosen": -1117.510009765625,
+      "logps/rejected": -47.68777084350586,
+      "loss": 0.0227,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.141476631164551,
+      "rewards/margins": 5.044860363006592,
+      "rewards/rejected": -1.903383731842041,
+      "step": 143
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.548387096774194e-06,
+      "logits/chosen": -1.6916511058807373,
+      "logits/rejected": -1.9522241353988647,
+      "logps/chosen": -1196.82861328125,
+      "logps/rejected": -49.64944076538086,
+      "loss": 0.015,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.8758084774017334,
+      "rewards/margins": 5.988270282745361,
+      "rewards/rejected": -2.1124606132507324,
+      "step": 156
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 6.451612903225806e-06,
+      "logits/chosen": -1.760750651359558,
+      "logits/rejected": -1.925395131111145,
+      "logps/chosen": -701.3285522460938,
+      "logps/rejected": -50.479835510253906,
+      "loss": 0.0169,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.707566261291504,
+      "rewards/margins": 4.906687259674072,
+      "rewards/rejected": -2.1991212368011475,
+      "step": 169
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 4.35483870967742e-06,
+      "logits/chosen": -1.6971558332443237,
+      "logits/rejected": -1.9400659799575806,
+      "logps/chosen": -959.2064208984375,
+      "logps/rejected": -51.388999938964844,
+      "loss": 0.0085,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.8825502395629883,
+      "rewards/margins": 6.139618873596191,
+      "rewards/rejected": -2.2570688724517822,
+      "step": 182
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 2.2580645161290324e-06,
+      "logits/chosen": -1.7328979969024658,
+      "logits/rejected": -2.0168874263763428,
+      "logps/chosen": -926.796875,
+      "logps/rejected": -52.40264129638672,
+      "loss": 0.0097,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.548464059829712,
+      "rewards/margins": 5.864409446716309,
+      "rewards/rejected": -2.3159451484680176,
+      "step": 195
+    }
+  ],
+  "logging_steps": 13,
+  "max_steps": 207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d64c109af6c5f1f4d56f908da5434d25bb340c76c0033059b374ee3ac80ba79
+size 4728

handler.py

@@ -0,0 +1,31 @@
+from typing import  Dict, List, Any
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+from peft import PeftModel
+import json
+import os
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        base_model_path = json.load(open(os.path.join(path, "training_params.json")))["model"]
+        model = AutoModelForCausalLM.from_pretrained(
+            base_model_path,
+            torch_dtype=torch.float16,
+            low_cpu_mem_usage=True,
+            trust_remote_code=True,
+            device_map="auto",
+        )
+        tokenizer = AutoTokenizer.from_pretrained(base_model_path, trust_remote_code=True)
+        model = PeftModel.from_pretrained(model, path)
+        model = model.merge_and_unload()
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+        if parameters is not None:
+            prediction = self.pipeline(inputs, **parameters)
+        else:
+            prediction = self.pipeline(inputs)
+        return prediction

requirements.txt

@@ -0,0 +1,2 @@
+peft==0.7.1
+transformers==4.36.1

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d64c109af6c5f1f4d56f908da5434d25bb340c76c0033059b374ee3ac80ba79
+size 4728

training_params.json

@@ -0,0 +1,46 @@
+{
+    "model": "facebook/opt-125m",
+    "project_name": "/tmp/model",
+    "data_path": "hibana2077/autotrain-data-TEST-3",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "trainer": "dpo",
+    "use_flash_attention_2": false,
+    "log": "none",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 3e-05,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "apply_chat_template": false,
+    "quantization": "int4",
+    "target_modules": "",
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "repo_id": "hibana2077/TEST-3",
+    "username": "hibana2077"
+}