lm-human-preference-details/train_policy_accelerate__sentiment_offline_5k.json__seed1
Text Generation
•
Updated
•
130
lm-human-preference-details
https://github.com/vwxyzjn/lm-human-preference-details
-
-
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed5
Text Generation • Updated • 130 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed3
Text Generation • Updated • 127 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed2
Text Generation • Updated • 129 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed4
Text Generation • Updated • 124 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed1
Text Generation • Updated • 124 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed7
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed6
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed8
Text Generation • Updated • 132 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed9
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__sentiment_offline_5k.json__seed10
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed1
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed2
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed5
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed3
Text Generation • Updated • 129 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed6
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed2
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed4
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed3
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed1
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed8
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed7
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed10
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2__descriptiveness_offline_5k.json__seed9
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__descriptiveness_offline_5k.json__seed5
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_grad_accu__descriptiveness_offline_5k.json__seed1
Text Generation • Updated • 130 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_grad_accu__descriptiveness_offline_5k.json__seed2
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_grad_accu__descriptiveness_offline_5k.json__seed3
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_grad_accu__descriptiveness_offline_5k.json__seed5
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed5
Text Generation • Updated • 126 -
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed1
Text Generation • Updated • 126 -
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed3
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed4
Text Generation • Updated • 126 -
lm-human-preference-details/train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed2
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed4
Text Generation • Updated • 138 -
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed3
Text Generation • Updated • 136 -
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed2
Text Generation • Updated • 138 -
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed1
Text Generation • Updated • 137 -
lm-human-preference-details/train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed5
Text Generation • Updated • 137 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed3
Text Generation • Updated • 83 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed2
Text Generation • Updated • 84 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed4
Text Generation • Updated • 83 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed1
Text Generation • Updated • 83 • 1 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed5
Text Generation • Updated • 85 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed4
Text Generation • Updated • 83 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed2
Text Generation • Updated • 83 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed5
Text Generation • Updated • 84 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed3
Text Generation • Updated • 91 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed1
Text Generation • Updated • 83 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed1
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed3
Text Generation • Updated • 126 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed4
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed2
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed5
Text Generation • Updated • 128 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed4
Text Generation • Updated • 82 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed2
Text Generation • Updated • 83 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed5
Text Generation • Updated • 84 -
lm-human-preference-details/train_policy_accelerate_pt_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed3
Text Generation • Updated • 87 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed2
Text Generation • Updated • 84 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed4
Text Generation • Updated • 83 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed3
Text Generation • Updated • 84 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed5
Text Generation • Updated • 84 -
lm-human-preference-details/train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__sentiment_offline_5k.json__seed1
Text Generation • Updated • 83