tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Process reward models (#2241)

Browse Source 
* adding model_cfg to set num_labels

* using a num_labels field instead

* linting

* WIP stepwise prompt tokenizer

* this should work?

* trainer working?

* pushing to runpod

* fixing saving

* updating conf

* updating config, adding docs

* adding stepwise supervision docpage

* updating tests

* adding test for dataset

* fixing tests

* linting

* addressing some comments

* adding additional cfg fields support

* updating tests, fixing cfg

* fixing tests

* updating loss

* Update test_process_reward_model_smollm2.py

* updating loss values and seed

* dumb pre-commit
This commit is contained in:
salman
2025-01-29 05:08:33 +00:00
committed by GitHub
parent c071a530f7
commit 54dd7abfc1
17 changed files with 542 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/gemma2/reward-model.yaml
View File

@@ -1,6 +1,7 @@
base_model: google/gemma-2-2b
# optionally might have model_type or tokenizer_type
model_type: AutoModelForSequenceClassification
num_labels: 1
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name