• Model creator: https://huggingface.co/BEE-spoke-data/
• Original model: https://huggingface.co/BEE-spoke-data/TinyLlama-3T-1.1bee/

Original model description:

• en license: apache-2.0 tags:
• bees
• bzz
• honey
• oprah winfrey datasets:
• BEE-spoke-data/bees-internal metrics:
• accuracy base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T inference: parameters: max_new_tokens: 64 do_sample: true renormalize_logits: true repetition_penalty: 1.05 no_repeat_ngram_size: 6 temperature: 0.9 top_p: 0.95 epsilon_cutoff: 0.0008 widget:
• text: In beekeeping, the term "queen excluder" refers to example_title: Queen Excluder
• text: One way to encourage a honey bee colony to produce more honey is by example_title: Increasing Honey Production
• text: The lifecycle of a worker bee consists of several stages, starting with example_title: Lifecycle of a Worker Bee
• text: Varroa destructor is a type of mite that example_title: Varroa Destructor
• text: In the world of beekeeping, the acronym PPE stands for example_title: Beekeeping PPE
• text: The term "robbing" in beekeeping refers to the act of example_title: Robbing in Beekeeping
• text: 'Question: What''s the primary function of drone bees in a hive?
  Answer:' example_title: Role of Drone Bees
• text: To harvest honey from a hive, beekeepers often use a device known as a example_title: Honey Harvesting Device
• text: 'Problem: You have a hive that produces 60 pounds of honey per year. You decide to split the hive into two. Assuming each hive now produces at a 70% rate compared to before, how much honey will you get from both hives next year?
  To calculate' example_title: Beekeeping Math Problem
• text: In beekeeping, "swarming" is the process where example_title: Swarming pipeline_tag: text-generation model-index:
• name: TinyLlama-3T-1.1bee 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: 33.79 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee 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: 60.29 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee 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: 25.86 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee 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: 38.13 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee 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: 60.22 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee 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: 0.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee name: Open LLM Leaderboard

---

TinyLlama-3T-1.1bee

• start from finished 3T TinyLlama
• vastly improved and expanded SoTA beekeeping dataset

Model description

• Loss: 2.1640
• Accuracy: 0.5406

Training hyperparameters

• learning_rate: 0.0001
• train_batch_size: 4
• eval_batch_size: 2
• seed: 13707
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0
• Datasets 2.16.1
• Tokenizers 0.15.0

Open LLM Leaderboard Evaluation Results