---
library_name: peft
base_model: mistralai/Mistral-7B-Instruct-v0.3
tags:
- amr-fma
- lora_sft
- domain:math
- phase:P1
---

# tkwiecinski/amr-fma-Mistral-7B-Instruct-v0.3-lora_sft-math-p1_sft_math_tooluse-s42

amr-fma training run.

- **Method**: `lora_sft`
- **Base model**: `mistralai/Mistral-7B-Instruct-v0.3`
- **Dataset**: `DigitalLearningGmbH/MATH-lighteval` (slug: `math`)
- **Seed**: `42`
- **Git commit**: `8b979a30de6dfbf3b5a1052e42d8c0453b214d3f`
- **Exp name**: `p1_sft_math_tooluse`
- **WandB run**: `gz9oxnrb`

## Tags
- phase:P1
- domain:math

## Checkpoints (branches)
- step 1 → revision `step-00001`
- step 3 → revision `step-00003`
- step 6 → revision `step-00006`
- step 13 → revision `step-00013`
- step 25 → revision `step-00025`
- step 48 → revision `step-00048`
- step 92 → revision `step-00092`
- step 93 → revision `step-00093`

Pin a specific checkpoint with `revision=...` in
`AutoModelForCausalLM.from_pretrained` / `PeftModel.from_pretrained`.

## Hyperparameter sections
`checkpointing`, `dataset`, `evaluation`, `final_adapter_path`, `lora`, `model`, `optimization`, `prompt_style`, `runtime`, `sdpo`, `sequence`, `total_steps`