I hereby claim:
- I am varadhjain on github.
- I am varadh (https://keybase.io/varadh) on keybase.
- I have a public key whose fingerprint is 66DE 7361 62AA 7A83 D416 2A91 B67A 2005 A61F 9C1F
To claim this, I am signing this object:
I hereby claim:
To claim this, I am signing this object:
| Verifying my Blockstack ID is secured with the address 1M7sco3kdZy2qiSLBkRWQg2XKJaMDHHvQe https://explorer.blockstack.org/address/1M7sco3kdZy2qiSLBkRWQg2XKJaMDHHvQe |
| # train_grpo.py | |
| import re | |
| import torch | |
| from datasets import load_dataset, Dataset | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| from peft import LoraConfig | |
| from trl import GRPOConfig, GRPOTrainer | |
| # Load and prep dataset |
Duration: 12h 55m | Messages: 328 | Phases: 3
what's still pending to do here. do you ahve plans on how to improve this significantly. what would make it useful. why would people want to use it. how do you think they'd use it. what are their motivations. are we meeting them. are we helping them look good?
Duration: 13h 6m | Messages: 388 | Phases: 6
what's still pending to do here. do you ahve plans on how to improve this significantly. what would make it useful. why would people want to use it. how do you think they'd use it. what are their motivations. are we meeting them. are we helping them look good?