brikdavies
/

deepscaleR

Reinforcement Learning

Model card Files Files and versions

deepscaleR / gdpo_lambda0.03_from_lambda0.1_ckpt100 /checkpoint-100

234 MB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

brikdavies's picture

Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100

4b400c5 verified 5 months ago

README.md
5.25 kB
Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
adapter_config.json
1.13 kB
Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
adapter_model.safetensors
73.9 MB
xet

Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
chat_template.jinja
2.25 kB
Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
optimizer.pt
148 MB
xet

Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
rng_state.pth
14.6 kB
xet

Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
scheduler.pt
1.47 kB
xet

Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
special_tokens_map.json
485 Bytes
Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
tokenizer.json
11.4 MB
xet

Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
tokenizer_config.json
4.49 kB
Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
trainer_state.json
153 kB
Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago
training_args.bin
7.95 kB
xet

Add gdpo_lambda0.03_from_lambda0.1_ckpt100/checkpoint-100 5 months ago