Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Icey444
/
ttthyme-ckpts

Safetensors
Model card Files Files and versions
xet
Community
ttthyme-ckpts
66.4 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 9 commits
Icey444's picture
Icey444
Upload SFT training logs (bs128 main + bs64 deprecated)
74cb313 verified 22 days ago
  • SFT-baseline-bs128-seed42
    upload SFT-baseline-bs128-seed42/checkpoint-4251: MAIN: paper-config-matching bs128, 3 epochs 22 days ago
  • SFT-baseline-bs64-DEPRECATED-seed42
    upload SFT-baseline-bs64-DEPRECATED-seed42/checkpoint-8499: deprecated bs64 (half-batch) 3 epochs; what we partially eval'd 22 days ago
  • SFT-baseline-bs64-partial-seed42
    upload SFT-baseline-bs64-partial-seed42/checkpoint-1500: partial bs64 at step 1500 (transferred from h100 then killed) 22 days ago
  • SFT-no123-bs64-partial-seed42
    upload SFT-no123-bs64-partial-seed42/checkpoint-2000: partial no123 ablation at step 2000 22 days ago
  • eval_results
    Update eval-result bundle: add MathVista mini Overall=70.20 score 22 days ago
  • training_logs
    Upload SFT training logs (bs128 main + bs64 deprecated) 22 days ago
  • .gitattributes
    1.91 kB
    upload SFT-no123-bs64-partial-seed42/checkpoint-2000: partial no123 ablation at step 2000 22 days ago
  • README.md
    1.37 kB
    Upload README.md with huggingface_hub 22 days ago