rewardfm
/

rfm

rewind_transformer

preference_comparisons

Model card Files Files and versions

rfm

536 MB

1 contributor

History: 4 commits

aliangdw's picture

Checkpoint: avg_score=0.3481 at step 400 | p_rank_spearman_mw_eval=0.2971, rew_align_pearson_mw_eval=0.3992

2a89bbe verified about 1 month ago

.gitattributes
1.52 kB

initial commit about 1 month ago
README.md
425 Bytes

Checkpoint: avg_score=0.2714 at step 200 | p_rank_spearman_mw_eval=0.1760, rew_align_pearson_mw_eval=0.3669 about 1 month ago
config.json
307 Bytes

Checkpoint: avg_score=0.2714 at step 200 | p_rank_spearman_mw_eval=0.1760, rew_align_pearson_mw_eval=0.3669 about 1 month ago
config.yaml
6.35 kB

Upload config.yaml with huggingface_hub about 1 month ago
model.safetensors
535 MB
xet

Checkpoint: avg_score=0.3481 at step 400 | p_rank_spearman_mw_eval=0.2971, rew_align_pearson_mw_eval=0.3992 about 1 month ago
special_tokens_map.json
695 Bytes

Checkpoint: avg_score=0.2714 at step 200 | p_rank_spearman_mw_eval=0.1760, rew_align_pearson_mw_eval=0.3669 about 1 month ago
tokenizer.json
712 kB

Checkpoint: avg_score=0.2714 at step 200 | p_rank_spearman_mw_eval=0.1760, rew_align_pearson_mw_eval=0.3669 about 1 month ago
tokenizer_config.json
1.46 kB

Checkpoint: avg_score=0.2714 at step 200 | p_rank_spearman_mw_eval=0.1760, rew_align_pearson_mw_eval=0.3669 about 1 month ago
trainer_state.json
69.9 kB

Checkpoint: avg_score=0.3481 at step 400 | p_rank_spearman_mw_eval=0.2971, rew_align_pearson_mw_eval=0.3992 about 1 month ago
training_args.bin
5.78 kB
xet

Checkpoint: avg_score=0.2714 at step 200 | p_rank_spearman_mw_eval=0.1760, rew_align_pearson_mw_eval=0.3669 about 1 month ago
vocab.txt
232 kB

Checkpoint: avg_score=0.2714 at step 200 | p_rank_spearman_mw_eval=0.1760, rew_align_pearson_mw_eval=0.3669 about 1 month ago