Rename llama3_8b_layer16_k160_enc_freeze_1.0_cov_jpr_trainer_2/checkpoints/ae_init.pt to llama3_8b_layer16_k160_enc_freeze_1.0_cov_jpr_trainer_5/checkpoints/ae_init.pt
a16aec6
verified
- gemma2_2b_layer12_april_relu_l1_0p03139999999976756_trainer_0
- gemma2_2b_layer12_april_relu_l1_0p03766392490086496_trainer_1
- gemma2_2b_layer12_april_relu_l1_0p04517742799199034_trainer_2
- gemma2_2b_layer12_april_relu_l1_0p05418978519481381_trainer_3
- gemma2_2b_layer12_april_relu_l1_0p06499999999957261_trainer_4
- gemma2_2b_layer12_k115_dec_freeze_0.0_iso_btk_trainer_0
- gemma2_2b_layer12_k115_dec_freeze_0.0_iso_jpr_trainer_0
- gemma2_2b_layer12_k115_dec_freeze_0.8_iso_btk_trainer_1
- gemma2_2b_layer12_k115_dec_freeze_0.8_iso_jpr_trainer_1
- gemma2_2b_layer12_k115_dec_freeze_1.0_cov_btk_trainer_3
- gemma2_2b_layer12_k115_dec_freeze_1.0_cov_jpr_trainer_3
- gemma2_2b_layer12_k115_dec_freeze_1.0_iso_btk_trainer_2
- gemma2_2b_layer12_k115_dec_freeze_1.0_iso_jpr_trainer_2
- gemma2_2b_layer12_k115_enc_freeze_1.0_cov_btk_trainer_4
- gemma2_2b_layer12_k115_enc_freeze_1.0_cov_btk_trainer_5
- gemma2_2b_layer12_k115_enc_freeze_1.0_cov_jpr_trainer_4
- gemma2_2b_layer12_k115_enc_freeze_1.0_cov_jpr_trainer_5
- gemma2_2b_layer12_k160_dec_freeze_0.0_iso_btk_trainer_0
- gemma2_2b_layer12_k160_dec_freeze_0.0_iso_jpr_trainer_0
- gemma2_2b_layer12_k160_dec_freeze_0.0_iso_tk_trainer_0
- gemma2_2b_layer12_k160_dec_freeze_0.8_iso_btk_trainer_1
- gemma2_2b_layer12_k160_dec_freeze_0.8_iso_jpr_trainer_1
- gemma2_2b_layer12_k160_dec_freeze_0.8_iso_tk_trainer_1
- gemma2_2b_layer12_k160_dec_freeze_1.0_cov_btk_trainer_3
- gemma2_2b_layer12_k160_dec_freeze_1.0_cov_jpr_trainer_3
- gemma2_2b_layer12_k160_dec_freeze_1.0_cov_tk_trainer_3
- gemma2_2b_layer12_k160_dec_freeze_1.0_iso_btk_trainer_2
- gemma2_2b_layer12_k160_dec_freeze_1.0_iso_jpr_trainer_2
- gemma2_2b_layer12_k160_dec_freeze_1.0_iso_tk_trainer_2
- gemma2_2b_layer12_k160_enc_freeze_1.0_cov_btk_trainer_4
- gemma2_2b_layer12_k160_enc_freeze_1.0_cov_btk_trainer_5
- gemma2_2b_layer12_k160_enc_freeze_1.0_cov_jpr_trainer_4
- gemma2_2b_layer12_k160_enc_freeze_1.0_cov_jpr_trainer_5
- gemma2_2b_layer12_k160_enc_freeze_1.0_cov_tk_trainer_4
- gemma2_2b_layer12_k160_enc_freeze_1.0_cov_tk_trainer_5
- gemma2_2b_layer12_k225_dec_freeze_0.0_iso_btk_trainer_0
- gemma2_2b_layer12_k225_dec_freeze_0.0_iso_jpr_trainer_0
- gemma2_2b_layer12_k225_dec_freeze_0.8_iso_btk_trainer_1
- gemma2_2b_layer12_k225_dec_freeze_0.8_iso_jpr_trainer_1
- gemma2_2b_layer12_k225_dec_freeze_1.0_cov_btk_trainer_3
- gemma2_2b_layer12_k225_dec_freeze_1.0_cov_jpr_trainer_3
- gemma2_2b_layer12_k225_dec_freeze_1.0_iso_btk_trainer_2
- gemma2_2b_layer12_k225_dec_freeze_1.0_iso_jpr_trainer_2
- gemma2_2b_layer12_k225_enc_freeze_1.0_cov_btk_trainer_4
- gemma2_2b_layer12_k225_enc_freeze_1.0_cov_btk_trainer_5
- gemma2_2b_layer12_k225_enc_freeze_1.0_cov_jpr_trainer_4
- gemma2_2b_layer12_k225_enc_freeze_1.0_cov_jpr_trainer_5
- gemma2_2b_layer12_k320_dec_freeze_0.0_iso_btk_trainer_0
- gemma2_2b_layer12_k320_dec_freeze_0.0_iso_jpr_trainer_0
- gemma2_2b_layer12_k320_dec_freeze_0.8_iso_btk_trainer_1