Instructions to use Shaer-AI-2/Shaer-adapters-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shaer-AI-2/Shaer-adapters-grpo with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Shaer-AI-2/Shaer-adapters-grpo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| clip_ratio/high_max,clip_ratio/high_mean,clip_ratio/low_mean,clip_ratio/low_min,clip_ratio/region_mean,completions/clipped_ratio,completions/max_length,completions/max_terminated_length,completions/mean_length,completions/mean_terminated_length,completions/min_length,completions/min_terminated_length,entropy,epoch,eval_clip_ratio/high_max,eval_clip_ratio/high_mean,eval_clip_ratio/low_mean,eval_clip_ratio/low_min,eval_clip_ratio/region_mean,eval_completions/clipped_ratio,eval_completions/max_length,eval_completions/max_terminated_length,eval_completions/mean_length,eval_completions/mean_terminated_length,eval_completions/min_length,eval_completions/min_terminated_length,eval_entropy,eval_frac_reward_zero_std,eval_kl,eval_loss,eval_num_tokens,eval_reward,eval_reward_exact_count_bonus_mean,eval_reward_exact_count_bonus_std,eval_reward_meter_mean,eval_reward_meter_std,eval_reward_std,eval_reward_total_mean,eval_rewards/exact_count_bonus/mean,eval_rewards/exact_count_bonus/std,eval_rewards/meter/mean,eval_rewards/meter/std,eval_runtime,eval_samples_per_second,eval_sampling/importance_sampling_ratio/max,eval_sampling/importance_sampling_ratio/mean,eval_sampling/importance_sampling_ratio/min,eval_sampling/sampling_logp_difference/max,eval_sampling/sampling_logp_difference/mean,eval_steps_per_second,frac_reward_zero_std,global_step,grad_norm,kl,learning_rate,loss,mode,num_tokens,reward,reward_exact_count_bonus_mean,reward_exact_count_bonus_std,reward_meter_mean,reward_meter_std,reward_std,reward_total_mean,rewards/exact_count_bonus/mean,rewards/exact_count_bonus/std,rewards/meter/mean,rewards/meter/std,sampling/importance_sampling_ratio/max,sampling/importance_sampling_ratio/mean,sampling/importance_sampling_ratio/min,sampling/sampling_logp_difference/max,sampling/sampling_logp_difference/mean,timestamp_utc,total_flos,train_loss,train_runtime,train_samples_per_second,train_steps_per_second | |
| 0.10928299836814404,0.10928299836814404,0.09094957076013088,0.09094957076013088,0.20023256912827492,0.25,640.0,237.0,282.125,162.83334350585938,86.0,86.0,3.2345626056194305,0.5,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.0,1,4.5472893714904785,0.9608133509755135,1e-05,0.0268,train,3887.0,0.2736811637878418,0.25,0.4629100561141968,0.22368116676807404,0.30434706807136536,0.25279727578163147,0.2736811637878418,0.25,0.4629100561141968,0.22368116676807404,0.30434706807136536,2.0,0.9976902008056641,0.24163144826889038,1.4203417301177979,0.15930314362049103,2026-04-11T12:37:27Z,,,,, | |
| ,,,,,,,,,,,,,0.5,0.0,0.0,0.0,0.0,0.0,0.0,156.0,156.0,106.125,106.125,69.25,69.25,2.1008258759975433,0.0,1.3679395914077759,0.0866735428571701,3887.0,0.42203541100025177,0.9375,0.125,0.23453541472554207,0.22889509424567223,0.2391926608979702,0.42203541100025177,0.9375,0.125,0.23453541472554207,0.22889509424567223,15.7215,0.509,1.2397247850894928,0.9995981901884079,0.7994033098220825,0.24606388807296753,0.034631784074008465,0.127,,1,,,,,eval,,,,,,,,,,,,,,,,,,2026-04-11T12:37:42Z,,,,, | |
| 0.11229794658720493,0.11229794658720493,0.12490623071789742,0.12490623071789742,0.23720417730510235,0.0,146.0,146.0,71.875,71.875,35.0,35.0,2.25409172475338,1.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.0,2,10.63160228729248,1.4957870244979858,5e-06,0.0936,train,5744.0,0.5511556267738342,1.0,0.0,0.3511555790901184,0.30735185742378235,0.16572850942611694,0.5511556267738342,1.0,0.0,0.3511555790901184,0.30735185742378235,2.0,0.9942735433578491,0.17049983143806458,1.7690210342407227,0.18746040761470795,2026-04-11T12:37:51Z,,,,, | |
| ,,,,,,,,,,,,,1.0,0.0,0.0,0.0,0.0,0.0,0.0,140.75,140.75,97.8125,97.8125,69.0,69.0,2.2587124407291412,0.0,1.46183642745018,0.06863964349031448,5744.0,0.6070040911436081,1.0,0.0,0.40700408816337585,0.3741379380226135,0.30008064955472946,0.6070040911436081,1.0,0.0,0.40700408816337585,0.3741379380226135,14.0,0.571,1.2537521719932556,0.9988586455583572,0.7956851571798325,0.24058371782302856,0.03424238506704569,0.143,,2,,,,,eval,,,,,,,,,,,,,,,,,,2026-04-11T12:38:05Z,,,,, | |
| ,,,,,,,,,,,,,1.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,2,,,,,train,,,,,,,,,,,,,,,,,,2026-04-11T12:38:07Z,0.0,0.060226328670978546,62.6885,0.255,0.032 | |