habanoz's picture
Adding Evaluation Results (#1)
a851295 verified
metadata
language:
  - en
license: apache-2.0
datasets:
  - databricks/databricks-dolly-15k
pipeline_tag: text-generation
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T
model-index:
  - name: TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 30.55
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 53.7
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 26.07
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 35.85
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 58.09
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 0
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
          name: Open LLM Leaderboard

TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T finetuned using dolly dataset.

Training took 1 hour on an 'ml.g5.xlarge' instance.

hyperparameters ={
  'num_train_epochs': 3,                            # number of training epochs
  'per_device_train_batch_size': 6,                 # batch size for training
  'gradient_accumulation_steps': 2,                 # Number of updates steps to accumulate
  'gradient_checkpointing': True,                   # save memory but slower backward pass
  'bf16': True,                                     # use bfloat16 precision
  'tf32': True,                                     # use tf32 precision
  'learning_rate': 2e-4,                            # learning rate
  'max_grad_norm': 0.3,                             # Maximum norm (for gradient clipping)
  'warmup_ratio': 0.03,                             # warmup ratio
  "lr_scheduler_type":"constant",                   # learning rate scheduler
  'save_strategy': "epoch",                         # save strategy for checkpoints
  "logging_steps": 10,                              # log every x steps
  'merge_adapters': True,                           # wether to merge LoRA into the model (needs more memory)
  'use_flash_attn': True,                           # Whether to use Flash Attention
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 34.04
AI2 Reasoning Challenge (25-Shot) 30.55
HellaSwag (10-Shot) 53.70
MMLU (5-Shot) 26.07
TruthfulQA (0-shot) 35.85
Winogrande (5-shot) 58.09
GSM8k (5-shot) 0.00