invoiceguard-code / training /train_grpo.py

Commit History

Upload training/train_grpo.py with huggingface_hub
06b7563
verified

piyush-mk commited on

v6: GRPO with --resume-adapter to start from SFT checkpoint
59ed7f3
verified

piyush-mk commited on

v5: remove 4-bit quant, variable-length traces, submit oversampling, GRPO exploration fixes
1d75102
verified

piyush-mk commited on

Upload folder using huggingface_hub
4cd2128
verified

piyush-mk commited on

Fix Qwen3 thinking mode + increase max_new_tokens: training/train_grpo.py
9d40fed
verified

piyush-mk commited on

Sync InvoiceGuard code for GRPO training job
02767f3
verified

piyush-mk commited on

Sync InvoiceGuard code for GRPO training job
7db1128
verified

piyush-mk commited on

Sync InvoiceGuard code for GRPO training job
7c278c9
verified

piyush-mk commited on

Sync InvoiceGuard code for GRPO training job
c5cfe6d
verified

piyush-mk commited on

Sync InvoiceGuard code for GRPO training job
d1e9e92
verified

piyush-mk commited on

Sync InvoiceGuard code for GRPO training job
c01c661
verified

piyush-mk commited on

Sync InvoiceGuard code for GRPO training job
fdd2256
verified

piyush-mk commited on

Sync InvoiceGuard code for GRPO training job
9a88af0
verified

piyush-mk commited on