lm-human-preference-details/train_policy_accelerate__sentiment_offline_5k.json__seed1 Text Generation • 0.1B • Updated Oct 4, 2023 • 11
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed5 Text Generation • 0.1B • Updated Oct 4, 2023 • 10
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed3 Text Generation • 0.1B • Updated Oct 4, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed2 Text Generation • 0.1B • Updated Oct 4, 2023 • 8
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed4 Text Generation • 0.1B • Updated Oct 4, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed1 Text Generation • 0.1B • Updated Oct 4, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed7 Text Generation • 0.1B • Updated Oct 4, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed6 Text Generation • 0.1B • Updated Oct 4, 2023 • 8
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed8 Text Generation • 0.1B • Updated Oct 4, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed9 Text Generation • 0.1B • Updated Oct 4, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed10 Text Generation • 0.1B • Updated Oct 4, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed1 Text Generation • 0.1B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed2 Text Generation • 0.1B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed5 Text Generation • 0.1B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed3 Text Generation • 0.1B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed6 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed2 Text Generation • 0.1B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed4 Text Generation • 0.1B • Updated Oct 5, 2023 • 10
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed3 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed1 Text Generation • 0.1B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed8 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed7 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed10 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed9 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed5 Text Generation • 0.1B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_grad_accu__descriptiveness_offline_5k.json__seed1 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_grad_accu__descriptiveness_offline_5k.json__seed2 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_grad_accu__descriptiveness_offline_5k.json__seed3 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_grad_accu__descriptiveness_offline_5k.json__seed5 Text Generation • 0.1B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed5 Text Generation • 0.1B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed1 Text Generation • 0.1B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed3 Text Generation • 0.1B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed4 Text Generation • 0.1B • Updated Oct 5, 2023 • 10
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed2 Text Generation • 0.1B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed4 Text Generation • 0.2B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed3 Text Generation • 0.2B • Updated Oct 5, 2023 • 16
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed2 Text Generation • 0.2B • Updated Oct 5, 2023 • 11
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed1 Text Generation • 0.2B • Updated Oct 5, 2023 • 23
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed5 Text Generation • 0.2B • Updated Oct 5, 2023 • 16
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed3 Text Generation • 2B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed2 Text Generation • 2B • Updated Oct 5, 2023 • 22
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed4 Text Generation • 2B • Updated Oct 5, 2023 • 11
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed1 Text Generation • 2B • Updated Oct 5, 2023 • 8 • 1
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed5 Text Generation • 2B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed4 Text Generation • 2B • Updated Oct 5, 2023 • 11
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed2 Text Generation • 2B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed5 Text Generation • 2B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed3 Text Generation • 2B • Updated Oct 5, 2023 • 9
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed1 Text Generation • 2B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed1 Text Generation • 0.1B • Updated Oct 5, 2023 • 7
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed3 Text Generation • 0.1B • Updated Oct 5, 2023 • 11
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed4 Text Generation • 0.1B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed2 Text Generation • 0.1B • Updated Oct 5, 2023 • 8
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed5 Text Generation • 0.1B • Updated Oct 6, 2023 • 9
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed4 Text Generation • 2B • Updated Oct 6, 2023 • 8
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed2 Text Generation • 2B • Updated Oct 6, 2023 • 13
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed5 Text Generation • 2B • Updated Oct 6, 2023 • 12
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed3 Text Generation • 2B • Updated Oct 6, 2023 • 10
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed2 Text Generation • 2B • Updated Oct 6, 2023 • 13
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed4 Text Generation • 2B • Updated Oct 6, 2023 • 7
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed3 Text Generation • 2B • Updated Oct 6, 2023 • 10
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed5 Text Generation • 2B • Updated Oct 6, 2023 • 11
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed1 Text Generation • 2B • Updated Oct 6, 2023 • 9