Training (New)

​

Supervised Fine-Tuning (SFT) Guide

​

Starting a Training Experiment

• Base Model: Select a supported model from the list below.
• Source Type: Currently supports models from Hugging Face.
• Model Type: Auto-filled based on the selected base model.

• meta-llama/Llama-3.1-8B-Instruct
• meta-llama/Llama-3.2-1B-Instruct
• meta-llama/Llama-3.2-3B-Instruct
• meta-llama/Llama-3.2-11B-Vision-Instruct
• Qwen/Qwen2.5-3B-Instruct
• Qwen/Qwen2.5-14B-Instruct
• Qwen/Qwen2.5-VL-7B-Instruct
• tiiuae/falcon-7b-instruct

​

Dataset Selection

• Source Options: Select the source of your dataset. Supported options include
  • Hugging Face (public Hub)
  • AWS S3
  • GCP Storage (GCS)
• Dataset Name
  This should be unique within your organization to help with organizing and reusing datasets.
• Dataset Path
  Specify the dataset location. For AWS S3, use the full path in the format.
  e.g., s3://your-bucket/your-file.jsonl
• Dataset Description (Optional)
  Provide a brief description of the dataset’s contents or purpose. Optional but useful for reference.
• Secret (Required for AWS S3 or GCP GCS)
  Provide your cloud credentials to enable secure access to private storage buckets.
• Region (Required for AWS S3 or GCP GCS)
  Select the region where your storage bucket is located.

​

Dataset Format

• jsonl (JSON Lines)
• zipThe directory should be archived in a .zip file and stored in an object storage.
  Example zip command:cd path/to/dataset_dir && zip -r dataset_dir.zip ./*

1. ShareGPT Format
   Copy

   Ask AI

   {
     "system": "<system>",
     "conversation": [
       {"human": "<query1>", "assistant": "<response1>"},
       {"human": "<query2>", "assistant": "<response2>"}
     ]
   }
   

2. OpenAI SFT Format
   Copy

   Ask AI

   {
     "messages": [
       {"role": "system", "content": "<system>"},
       {"role": "user", "content": "<query1>"},
       {"role": "assistant", "content": "<response1>"},
       {"role": "user", "content": "<query2>"},
       {"role": "assistant", "content": "<response2>"}
     ]
   }
   

3. OpenAI DPO Format (for preference training)
   Copy

   Ask AI

   {
     "messages": [
       {"role": "system", "content": "You are a useful and harmless assistant"},
       {"role": "user", "content": "Tell me tomorrow's weather"},
       {"role": "assistant", "content": "Tomorrow's weather will be sunny"}
     ],
     "rejected_response": "I don't know"
   }    
   

​

Dataset Configuration

• Lazy Tokenize: Delay tokenization until needed. Speeds up dataset loading for large files.
• Streaming: Enable only for public HF Datasets to load records on-the-fly, reducing local storage needs.
• Prompt Max Length: Maximum token length for prompt. Longer sequences will be truncated.

  Recommended: 2048
  Note: Must be a multiple of 1024

• System Prompt: (Optional) A global prefix to every example, e.g., You are a helpful assistant.
• Prompt Template: (Optional) If your data needs wrapping in a custom template, e.g., <system> {system_prompt} <user> {prompt}.
• Train/Validation Split: Percentage or absolute count for splitting your .jsonl into training and validation sets.
  • Split Type
    Currently, only random split is supported. The dataset will be randomly divided into training and validation sets.
  • Train Split Ratio
    Enter the ratio of data to be used for training (e.g., 0.9 for 90%).
  • Validation Split Ratio
    Enter the ratio of data to be used for validation (e.g., 0.1 for 10%).
    Train Split Ratio should be greater than 0.8

​

Training Configuration

1. Core Options

2. Optimization Hyperparameters

   Parameter	Description	Default Values	Recommended Values	Permissible Range
   Num Epochs	Number of full passes through the dataset	1	2-5	50
   Gradient Accumulation Steps	Steps to accumulate gradients before an optimizer step	1	1-2	<256
   Train Batch Size	Samples per device for training	8	8	16
   Eval Batch Size	Samples per device for evaluation	1	8	16
   Max Steps	Total training steps; overrides epochs if specified (Applicable only when the num_epochs = 1)	100	100	1000
   Learning Rate	Initial learning rate for optimizer	0.0001	1×10⁻⁵ to 2×10⁻⁵	< 5×10⁻⁵
   Dataloader Num Workers	Parallel data-loading threads per device	1	4	<10
   Gradient Checkpointing	Saves memory by checkpointing activations	Disabled	Disabled	NA

3. Checkpointing & Monitoring

   Parameter	Description	Default	Recommended Values	Permissible Range
   Save Steps	Interval (in steps) between saving model checkpoints.	100	100	<= Max Steps
   Save Total Limit	Max number of checkpoints to keep locally.	2	2-5	<10
   Eval Steps	Interval (in steps) between running evaluation loop.	100	100	100 - 200
   Logging Steps	Interval (in steps) between logging metrics to the dashboard.	5	5	< 20

​

LoRA Adapter Configuration

​

Distributed Training Configuration

​

Infrastructure Configuration

• GPU Type: Select instance GPU, e.g., H100, L40s.
• GPU Count: Number of GPUs to allocate for this job.

​

Launching Your Job

1. Review all settings.
2. Click Create Job.
3. Monitor progress under My Trainings > Your Training Job > Metrics .
4. Compile the model and deploy when training completes.