rica40325 | 1 | 1.0 | 1.0 | 1189.46 | 1260.48 | 3.32 | 10561 | 0.79 | 980.0 | rica40325-feedback-dpo-4_v1 | 8B | rica40325/feedback_dpo_4 | rica40325-feedback-dpo-3_v1 | 10561 | 809125 | 0.44 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_4 | 2024-09-10 | 0.92 | 0.03 | 2.57 | 1.75 | 16.0 | 1.0 | 46.0 | 1.0 | single | 2.0 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 2.0 | 1.0 | 1194.17 | 1260.48 | 3.09 | 14186 | 0.8 | 1224.0 | rica40325-feedback-dpo-8_v1 | 8B | rica40325/feedback_dpo_8 | rica40325-feedback-dpo-8_v1 | 14183 | 809125 | 0.45 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_8 | 2024-09-10 | 0.88 | 0.07 | 2.37 | 1.86 | 17.0 | 1.0 | 45.0 | 3.0 | single | 1.99 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 3.0 | 1.0 | 1248.35 | 1260.48 | 0.79 | 11545 | 0.73 | 985.0 | rica40325-lora32-first_v1 | 8B | rica40325/lora32_first | rica40325-lora32-first_v1 | 11545 | 809125 | 0.53 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_first | 2024-08-30 | 0.52 | 0.58 | 0.42 | 0.1 | 7.0 | 1.0 | 17.0 | 20.0 | single | | |
rica40325 | 1 | 4.0 | 1.0 | 1252.72 | 1260.48 | 0.69 | 11322 | 0.72 | 951.0 | rica40325-lora32-first_v3 | 8B | rica40325/lora32_first | rica40325-lora32-first_v1 | 11322 | 809125 | 0.53 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_first | 2024-08-30 | 0.52 | 0.62 | 0.33 | -0.04 | 6.0 | 1.0 | 12.0 | 23.0 | single | | |
rica40325 | 1 | 5.0 | 1.0 | 1258.54 | 1260.48 | 0.52 | 12027 | 0.72 | 1043.0 | rica40325-lora32-third-step_v3 | 8B | rica40325/lora32_third_step | rica40325-lora32-third-step_v2 | 12027 | 809125 | 0.53 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_third_s | 2024-08-31 | 0.5 | 0.67 | 0.19 | -0.26 | 1.0 | 1.0 | 3.0 | 25.0 | single | | |
rica40325 | 1 | 6.0 | 1.0 | 1242.89 | 1260.48 | 0.82 | 11679 | 0.74 | 985.0 | rica40325-lora32-secend_v5 | 8B | rica40325/lora32_secend | rica40325-lora32-secend_v1 | 11679 | 809125 | 0.51 | 0.53 | basic | | 8 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_secend | 2024-08-30 | 0.5 | 0.53 | 0.44 | 0.29 | 12.5 | 1.0 | 24.0 | 19.0 | single | | |
rica40325 | 1 | 7.0 | 1.0 | 1237.34 | 1260.48 | 0.94 | 11946 | 0.75 | 1044.0 | rica40325-feedback-11_v2 | 8B | rica40325/feedback-11 | rica40325-feedback-11_v1 | 11946 | 809125 | 0.49 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-11 | 2024-09-12 | 0.5 | 0.47 | 0.54 | 0.56 | 8.5 | 1.0 | 27.0 | 14.0 | single | 2.02 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 8.0 | 1.0 | 1239.92 | 1260.48 | 0.86 | 10374 | 0.72 | 940.0 | rica40325-lora32-secend_v6 | 8B | rica40325/lora32_secend | rica40325-lora32-secend_v1 | 10374 | 809125 | 0.51 | 0.53 | basic | | 8 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_secend | 2024-08-31 | 0.49 | 0.5 | 0.47 | -0.04 | 8.5 | 1.0 | 25.0 | 16.0 | single | | |
rica40325 | 1 | 9.0 | 1.0 | 1253.59 | 1260.48 | 0.56 | 11475 | 0.74 | 954.0 | rica40325-lora32-secend_v3 | 8B | rica40325/lora32_secend | rica40325-lora32-secend_v1 | 11475 | 809125 | 0.53 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_secend | 2024-08-30 | 0.48 | 0.63 | 0.21 | 0.29 | 4.5 | 1.0 | 10.0 | 24.0 | single | | |
rica40325 | 1 | 10.0 | 1.0 | 1258.85 | 1260.48 | 0.43 | 11389 | 0.74 | 943.0 | rica40325-lora32-first_v2 | 8B | rica40325/lora32_first | rica40325-lora32-first_v1 | 11389 | 809125 | 0.53 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_first | 2024-08-30 | 0.48 | 0.68 | 0.11 | 0.49 | 2.0 | 1.0 | 2.0 | 27.0 | single | | |
rica40325 | 1 | 11.0 | 1.0 | 1260.48 | 1260.48 | 0.39 | 10246 | 0.76 | 925.0 | rica40325-lora32-third-step_v4 | 8B | rica40325/lora32_third_step | rica40325-lora32-third-step_v2 | 10246 | 809125 | 0.53 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_third_s | 2024-08-31 | 0.47 | 0.69 | 0.07 | 0.88 | 3.0 | 1.0 | 1.0 | 29.0 | single | 1.94 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 12.0 | 1.0 | 1255.15 | 1260.48 | 0.47 | 11723 | 0.75 | 1022.0 | rica40325-lora32-secend_v2 | 8B | rica40325/lora32_secend | rica40325-lora32-secend_v1 | 11723 | 809125 | 0.53 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_secend | 2024-08-30 | 0.47 | 0.64 | 0.14 | 0.6 | 4.5 | 1.0 | 8.0 | 26.0 | single | | |
rica40325 | 1 | 13.0 | 1.0 | 1229.87 | 1260.48 | 0.95 | 11030 | 0.72 | 988.0 | rica40325-my-second-chai_v7 | 8B | rica40325/my-second-chai | rica40325-my-second-chai_v5 | 11030 | 809125 | 0.49 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/my-second-chai | 2024-08-26 | 0.46 | 0.4 | 0.55 | -0.28 | 15.0 | 1.0 | 33.0 | 13.0 | single | | |
rica40325 | 1 | 14.0 | 1.0 | 1231.94 | 1260.48 | 0.84 | 10857 | 0.73 | 913.0 | rica40325-my-second-chai_v8 | 8B | rica40325/my-second-chai | rica40325-my-second-chai_v5 | 10857 | 809125 | 0.49 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/my-second-chai | 2024-08-28 | 0.43 | 0.42 | 0.45 | 0.21 | 18.0 | 1.0 | 32.0 | 18.0 | single | | |
rica40325 | 1 | 15.0 | 1.0 | 1255.57 | 1260.48 | 0.28 | 12765 | 0.74 | 1141.0 | rica40325-alignment-first_v1 | 8B | rica40325/alignment-first | rica40325-alignment-first_v1 | 12764 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/alignment-firs | 2024-09-08 | 0.41 | 0.64 | -0.02 | 0.48 | 10.5 | 1.0 | 7.0 | 35.0 | single | 1.98 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 16.0 | 1.0 | 1254.72 | 1260.48 | 0.29 | 12191 | 0.73 | 1027.0 | rica40325-lora32-third-step_v5 | 8B | rica40325/lora32_third_step | rica40325-lora32-third-step_v2 | 12191 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_third_s | 2024-09-05 | 0.41 | 0.64 | -0.01 | 0.01 | 10.5 | 1.0 | 9.0 | 33.0 | single | 2.04 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 17.0 | 1.0 | 1232.34 | 1260.48 | 0.72 | 10683 | 0.74 | 912.0 | rica40325-there-dataset-chai_v5 | 8B | rica40325/there-dataset-chai | rica40325-there-dataset-chai_v1 | 10683 | 809125 | 0.5 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/there-dataset- | 2024-08-28 | 0.4 | 0.43 | 0.35 | 0.29 | 21.0 | 1.0 | 31.0 | 22.0 | single | | |
rica40325 | 1 | 18.0 | 1.0 | 1250.61 | 1260.48 | 0.34 | 11101 | 0.74 | 991.0 | rica40325-lora32-secend_v4 | 8B | rica40325/lora32_secend | rica40325-lora32-secend_v1 | 11101 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_secend | 2024-08-30 | 0.4 | 0.6 | 0.03 | 0.33 | 14.0 | 1.0 | 14.0 | 31.0 | single | | |
rica40325 | 1 | 19.0 | 1.0 | 1245.07 | 1260.48 | 0.42 | 11361 | 0.73 | 1021.0 | rica40325-lora32-third-step_v2 | 8B | rica40325/lora32_third_step | rica40325-lora32-third-step_v2 | 11361 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_third_s | 2024-08-31 | 0.39 | 0.55 | 0.1 | 0.17 | 19.5 | 1.0 | 23.0 | 28.0 | single | | |
rica40325 | 1 | 20.0 | 1.0 | 1258.19 | 1260.48 | 0.15 | 14761 | 0.75 | 1285.0 | rica40325-alignment-first_v2 | 8B | rica40325/alignment-first | rica40325-alignment-first_v1 | 14761 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/alignment-firs | 2024-09-08 | 0.39 | 0.67 | -0.14 | 0.66 | 12.5 | 1.0 | 4.0 | 39.0 | single | 1.95 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 21.0 | 1.0 | 1221.92 | 1260.48 | 0.84 | 10839 | 0.7 | 961.0 | rica40325-there-dataset-chai_v3 | 8B | rica40325/there-dataset-chai | rica40325-there-dataset-chai_v1 | 10839 | 809125 | 0.48 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/there-dataset- | 2024-08-28 | 0.37 | 0.33 | 0.45 | -0.77 | 22.0 | 1.0 | 38.0 | 17.0 | single | | |
rica40325 | 1 | 22.0 | 1.0 | 1187.56 | 1260.48 | 1.4 | 11435 | 0.73 | 1050.0 | rica40325-there-dataset-chai_v4 | 8B | rica40325/there-dataset-chai | rica40325-there-dataset-chai_v1 | 11435 | 809125 | 0.43 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/there-dataset- | 2024-08-28 | 0.33 | 0.01 | 0.93 | 0.09 | 23.5 | 1.0 | 47.0 | 11.0 | single | | |
rica40325 | 1 | 23.0 | 1.0 | 1256.4 | 1260.48 | -0.07 | 17814 | 0.75 | 1595.0 | rica40325-alignment-first_v5 | 8B | rica40325/alignment-first | rica40325-alignment-first_v1 | 17812 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/alignment-firs | 2024-09-08 | 0.31 | 0.65 | -0.32 | 0.67 | 19.5 | 1.0 | 6.0 | 45.0 | single | 2.0 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 24.0 | 1.0 | 1248.38 | 1260.48 | 0.05 | 15441 | 0.73 | 1308.0 | rica40325-alignment-first_v3 | 8B | rica40325/alignment-first | rica40325-alignment-first_v1 | 15441 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/alignment-firs | 2024-09-08 | 0.3 | 0.58 | -0.22 | 0.23 | 23.5 | 1.0 | 16.0 | 42.0 | single | 1.97 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 25.0 | 1.0 | 1237.9 | 1260.48 | 0.17 | 11629 | 0.73 | 971.0 | rica40325-my-second-chai_v3 | 8B | rica40325/my-second-chai | rica40325-my-second-chai_v3 | 11629 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/my-second-chai | 2024-08-26 | 0.27 | 0.48 | -0.11 | -0.0 | 29.0 | 1.0 | 26.0 | 38.0 | single | | |
rica40325 | 1 | 26.0 | 1.0 | 1229.14 | 1260.48 | 0.32 | 11482 | 0.72 | 967.0 | rica40325-my-first-dpo_v4 | 8B | rica40325/my-first-dpo | rica40325-my-first-dpo_v1 | 11482 | 809125 | 0.49 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/my-first-dpo | 2024-08-28 | 0.26 | 0.4 | 0.01 | -0.09 | 32.5 | 1.0 | 34.0 | 32.0 | single | | |
rica40325 | 1 | 27.0 | 1.0 | 1249.24 | 1260.48 | -0.12 | 12201 | 0.74 | 1041.0 | rica40325-feedback-retry_v1 | 8B | rica40325/feedback_retry | rica40325-feedback-retry_v1 | 12201 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_retry | 2024-09-06 | 0.25 | 0.59 | -0.37 | 0.49 | 27.0 | 1.0 | 15.0 | 48.0 | single | 2.02 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 28.0 | 1.0 | 1247.21 | 1260.48 | -0.09 | 11249 | 0.74 | 967.0 | rica40325-feedback-7000_v1 | 8B | rica40325/feedback_7000 | rica40325-feedback-7000_v1 | 11249 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_7000 | 2024-09-09 | 0.25 | 0.57 | -0.34 | 0.49 | 32.5 | 1.0 | 20.0 | 46.0 | single | 2.06 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 29.0 | 1.0 | 1166.32 | 1260.48 | 1.54 | 12811 | 0.74 | 1064.0 | rica40325-lora32-secend_v1 | 8B | rica40325/lora32_secend | rica40325-lora32-secend_v1 | 12811 | 809125 | 0.4 | 0.53 | basic | | 1 | 512 | 64 | LlamaForCausalLM | rica40325/lora32_secend | 2024-08-30 | 0.24 | -0.19 | 1.05 | 0.36 | 27.0 | 1.0 | 53.0 | 10.0 | single | | |
rica40325 | 1 | 30.0 | 1.0 | 1257.15 | 1260.48 | -0.38 | 12590 | 0.76 | 1133.0 | rica40325-feedback-2000_v3 | 8B | rica40325/feedback_2000 | rica40325-feedback-2000_v1 | 12590 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_2000 | 2024-09-07 | 0.23 | 0.66 | -0.58 | 0.88 | 25.0 | 1.0 | 5.0 | 54.0 | single | 2.0 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 31.0 | 1.0 | 1223.21 | 1260.48 | 0.25 | 10835 | 0.74 | 940.0 | rica40325-yui-new-chai_v12 | 8B | rica40325/yui-new-chai | rica40325-yui-new-chai_v10 | 10835 | 809125 | 0.48 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/yui-new-chai | 2024-08-26 | 0.21 | 0.34 | -0.04 | 0.44 | 47.0 | 1.0 | 37.0 | 37.0 | single | | |
rica40325 | 1 | 32.0 | 1.0 | 1253.08 | 1260.48 | -0.36 | 14656 | 0.74 | 1238.0 | rica40325-feedback-2000_v2 | 8B | rica40325/feedback_2000 | rica40325-feedback-2000_v1 | 14655 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_2000 | 2024-09-07 | 0.21 | 0.62 | -0.57 | 0.48 | 27.0 | 1.0 | 11.0 | 52.0 | single | 2.03 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 33.0 | 1.0 | 1246.34 | 1260.48 | -0.23 | 10823 | 0.73 | 921.0 | rica40325-feedback-dpo-10_v1 | 8B | rica40325/feedback_dpo_10 | rica40325-feedback-dpo-10_v1 | 10823 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_1 | 2024-09-10 | 0.2 | 0.56 | -0.46 | 0.21 | 42.0 | 1.0 | 21.0 | 51.0 | single | 1.99 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 34.0 | 1.0 | 1213.47 | 1260.48 | 0.37 | 11376 | 0.74 | 960.0 | rica40325-yui-new-chai_v13 | 8B | rica40325/yui-new-chai | rica40325-yui-new-chai_v13 | 11376 | 809125 | 0.47 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/yui-new-chai | 2024-08-26 | 0.18 | 0.25 | 0.06 | 0.47 | 40.0 | 1.0 | 41.0 | 30.0 | single | | |
rica40325 | 1 | 35.0 | 1.0 | 1237.27 | 1260.48 | -0.14 | 12125 | 0.75 | 1012.0 | rica40325-feedback-and-d_8178_v3 | 8B | rica40325/feedback-and-dpo3kstep | rica40325-feedbac_8178_v2 | 12125 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-and-d | 2024-09-01 | 0.18 | 0.47 | -0.38 | 0.64 | 49.0 | 1.0 | 28.0 | 49.0 | single | | |
rica40325 | 1 | 36.0 | 1.0 | 1233.51 | 1260.48 | -0.06 | 10522 | 0.76 | 894.0 | rica40325-my-first-dpo_v1 | 8B | rica40325/my-first-dpo | rica40325-my-first-dpo_v1 | 10522 | 809125 | 0.5 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/my-first-dpo | 2024-08-28 | 0.18 | 0.44 | -0.31 | 0.95 | 44.5 | 1.0 | 29.0 | 44.0 | single | | |
rica40325 | 1 | 37.0 | 1.0 | 1247.91 | 1260.48 | -0.39 | 11020 | 0.72 | 998.0 | rica40325-feedback-7000steps_v1 | 8B | rica40325/feedback_7000steps | rica40325-feedback-7000steps_v1 | 11020 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_7000s | 2024-09-09 | 0.16 | 0.57 | -0.59 | -0.15 | 44.5 | 1.0 | 18.0 | 55.0 | single | 2.03 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 38.0 | 1.0 | 1221.06 | 1260.48 | 0.14 | 11438 | 0.75 | 971.0 | rica40325-my-first-dpo_v3 | 8B | rica40325/my-first-dpo | rica40325-my-first-dpo_v1 | 11438 | 809125 | 0.48 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/my-first-dpo | 2024-08-28 | 0.16 | 0.32 | -0.14 | 0.55 | 50.0 | 1.0 | 39.0 | 40.0 | single | | |
rica40325 | 1 | 39.0 | 1.0 | 1247.69 | 1260.48 | -0.44 | 14940 | 0.73 | 1281.0 | rica40325-feedback-retry-4500_v1 | 8B | rica40325/feedback-retry-4500 | rica40325-feedback-retry-4500_v1 | 14940 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-retry | 2024-09-08 | 0.15 | 0.57 | -0.63 | 0.16 | 48.0 | 1.0 | 19.0 | 56.0 | single | | |
rica40325 | 1 | 40.0 | 1.0 | 1228.55 | 1260.48 | -0.1 | 12869 | 0.72 | 1120.0 | rica40325-feedback-dpo-10_v2 | 8B | rica40325/feedback_dpo_10 | rica40325-feedback-dpo-10_v1 | 12868 | 809125 | 0.48 | 0.53 | basic | | 8 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_1 | 2024-09-11 | 0.13 | 0.39 | -0.34 | -0.22 | 54.0 | 1.0 | 35.0 | 47.0 | single | 3.3 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 41.0 | 1.0 | 1216.87 | 1260.48 | 0.08 | 10179 | 0.74 | 911.0 | rica40325-there-dataset-chai_v1 | 8B | rica40325/there-dataset-chai | rica40325-there-dataset-chai_v1 | 10179 | 809125 | 0.47 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/there-dataset- | 2024-08-27 | 0.12 | 0.28 | -0.19 | 0.4 | 53.0 | 1.0 | 40.0 | 41.0 | single | | |
rica40325 | 1 | 42.0 | 1.0 | 1227.67 | 1260.48 | -0.22 | 12654 | 0.73 | 1063.0 | rica40325-feedback-and-d_8178_v2 | 8B | rica40325/feedback-and-dpo3kstep | rica40325-feedback-and-d_8178_v2 | 12654 | 809125 | 0.49 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-and-d | 2024-09-01 | 0.09 | 0.38 | -0.44 | 0.0 | 56.0 | 1.0 | 36.0 | 50.0 | single | | |
rica40325 | 1 | 43.0 | 1.0 | 1233.23 | 1260.48 | -0.37 | 12651 | 0.74 | 1053.0 | rica40325-feedback-and-dpo_v2 | 8B | rica40325/feedback-and-dpo | rica40325-feedback-and-dpo_v1 | 12651 | 809125 | 0.5 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-and-d | 2024-09-01 | 0.08 | 0.44 | -0.58 | 0.39 | 55.0 | 1.0 | 30.0 | 53.0 | single | | |
rica40325 | 1 | 44.0 | 1.0 | 1131.43 | 1260.48 | 1.67 | 10412 | 0.73 | 991.0 | rica40325-yui-new-chai_v9 | 8B | rica40325/yui-new-chai | rica40325-yui-new-chai_v9 | 10412 | 809125 | 0.35 | 0.53 | basic | | 1 | 512 | 64 | LlamaForCausalLM | rica40325/yui-new-chai | 2024-08-24 | 0.07 | -0.51 | 1.16 | 0.15 | 30.0 | 1.0 | 58.0 | 7.0 | single | | |
rica40325 | 1 | 45.0 | 1.0 | 1245.84 | 1260.48 | -0.67 | 13023 | 0.75 | 1089.0 | rica40325-reference_v1 | 8B | rica40325/reference | rica40325-reference_v1 | 13023 | 809125 | 0.51 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/reference | 2024-09-04 | 0.07 | 0.55 | -0.83 | 0.69 | 51.5 | 1.0 | 22.0 | 58.0 | single | | |
rica40325 | 1 | 46.0 | 1.0 | 1251.76 | 1260.48 | -0.8 | 14206 | 0.76 | 1173.0 | rica40325-feedback-1000_v1 | 8B | rica40325/feedback-1000 | rica40325-feedback-1000_v1 | 14206 | 809125 | 0.52 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-1000 | 2024-09-07 | 0.07 | 0.61 | -0.94 | 1.03 | 44.5 | 1.0 | 13.0 | 60.0 | single | 2.02 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 47.0 | 1.0 | 1197.66 | 1260.48 | 0.28 | 13519 | 0.73 | 1164.0 | rica40325-alignment-first_v4 | 8B | rica40325/alignment-first | rica40325-alignment-first_v1 | 13518 | 809125 | 0.44 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/alignment-firs | 2024-09-08 | 0.06 | 0.1 | -0.02 | 0.06 | 51.5 | 1.0 | 44.0 | 36.0 | single | 1.99 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 48.0 | 1.0 | 1171.68 | 1260.48 | 0.79 | 13212 | 0.73 | 1171.0 | rica40325-dpo0904_v1 | 8B | rica40325/dpo0904 | rica40325-dpo0904_v1 | 13212 | 809125 | 0.41 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/dpo0904 | 2024-09-04 | 0.05 | -0.14 | 0.41 | 0.04 | 44.5 | 1.0 | 52.0 | 21.0 | single | 1.96 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 49.0 | 1.0 | 1131.39 | 1260.48 | 1.59 | 11553 | 0.73 | 950.0 | rica40325-yui-new-chai_v10 | 8B | rica40325/yui-new-chai | rica40325-yui-new-chai_v10 | 11553 | 809125 | 0.35 | 0.53 | basic | | 1 | 512 | 64 | LlamaForCausalLM | rica40325/yui-new-chai | 2024-08-26 | 0.05 | -0.51 | 1.09 | 0.23 | 35.0 | 1.0 | 59.0 | 9.0 | single | | |
rica40325 | 1 | 50.0 | 1.0 | 1100.78 | 1260.48 | 1.9 | 10986 | 0.72 | 966.0 | rica40325-my-second-chai_v4 | 8B | rica40325/my-second-chai | rica40325-my-second-chai_v4 | 10986 | 809125 | 0.32 | 0.53 | basic | | 1 | 512 | 64 | LlamaForCausalLM | rica40325/my-second-chai | 2024-08-26 | -0.04 | -0.8 | 1.36 | -0.07 | 32.5 | 1.0 | 60.0 | 6.0 | single | | |
rica40325 | 1 | 51.0 | 1.0 | 1139.62 | 1260.48 | 1.09 | 12641 | 0.74 | 1075.0 | rica40325-feedback-and-d_8178_v1 | 8B | rica40325/feedback-and-dpo3kstep | rica40325-feedback-and-d_8178_v1 | 12641 | 809125 | 0.37 | 0.53 | basic | | 1 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-and-d | 2024-09-01 | -0.05 | -0.44 | 0.67 | 0.31 | 37.0 | 1.0 | 57.0 | 12.0 | single | | |
rica40325 | 1 | 52.0 | 1.0 | 1145.38 | 1260.48 | 0.9 | 11447 | 0.74 | 982.0 | rica40325-feedback-and-dpo_v1 | 8B | rica40325/feedback-and-dpo | rica40325-feedback-and-dpo_v1 | 11447 | 809125 | 0.37 | 0.53 | basic | | 1 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-and-d | 2024-09-01 | -0.07 | -0.38 | 0.51 | 0.35 | 40.0 | 1.0 | 56.0 | 15.0 | single | | |
rica40325 | 1 | 53.0 | 1.0 | 1151.62 | 1260.48 | 0.29 | 12508 | 0.74 | 1044.0 | rica40325-feedback-and-dpo_v3 | 8B | rica40325/feedback-and-dpo | rica40325-feedback-and-dpo_v1 | 12508 | 809125 | 0.38 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-and-d | 2024-09-03 | -0.22 | -0.33 | -0.01 | 0.38 | 57.0 | 1.0 | 55.0 | 34.0 | single | | |
rica40325 | 1 | 54.0 | 1.0 | 1184.22 | 1260.48 | -0.76 | 10900 | 0.73 | 925.0 | rica40325-there-dataset-chai_v9 | 8B | rica40325/there-dataset-chai | rica40325-there-dataset-chai_v1 | 10900 | 809125 | 0.43 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/there-dataset- | 2024-08-28 | -0.33 | -0.02 | -0.91 | 0.15 | 59.5 | 1.0 | 49.0 | 59.0 | single | | |
rica40325 | 1 | 55.0 | 1.0 | 1068.2 | 1260.48 | 1.6 | 11444 | 0.7 | 1040.0 | rica40325-feedback-dpo-2_v1 | 8B | rica40325/feedback_dpo_2 | rica40325-feedback-dpo-2_v1 | 11444 | 809125 | 0.29 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_2 | 2024-09-09 | -0.33 | -1.1 | 1.11 | -0.7 | 37.0 | 1.0 | 61.0 | 8.0 | single | 2.0 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 56.0 | 1.0 | 1212.72 | 1260.48 | -1.73 | 14870 | 0.72 | 1311.0 | rica40325-llama3_v2 | 8B | rica40325/llama3 | rica40325-llama3_v1 | 14870 | 809125 | 0.46 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/llama3 | 2024-09-04 | -0.45 | 0.24 | -1.73 | -0.22 | 58.0 | 1.0 | 42.0 | 63.0 | single | | |
rica40325 | 1 | 57.0 | 1.0 | 1182.22 | 1260.48 | -1.57 | 13167 | 0.72 | 1177.0 | rica40325-dpo0903-1300_v1 | 8B | rica40325/dpo0903-1300 | rica40325-dpo0903-1300_v1 | 13167 | 809125 | 0.42 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/dpo0903-1300 | 2024-09-04 | -0.59 | -0.04 | -1.6 | -0.15 | 62.0 | 1.0 | 50.0 | 61.0 | single | 2.02 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 58.0 | 1.0 | 983.1 | 1260.48 | 2.3 | 10866 | 0.65 | 916.0 | rica40325-feedback-dpo-2_v2 | 8B | rica40325/feedback_dpo_2 | rica40325-feedback-dpo-2_v1 | 10866 | 809125 | 0.2 | 0.53 | basic | | 1 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_2 | 2024-09-09 | -0.64 | -1.9 | 1.7 | -2.07 | 32.5 | 1.0 | 62.0 | 4.0 | single | 7.27 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 59.0 | 1.0 | 1200.04 | 1260.48 | -2.23 | 10879 | 0.7 | 948.0 | rica40325-feedback-dpo-1_v1 | 8B | rica40325/feedback_dpo_1 | rica40325-feedback-dpo-1_v1 | 10879 | 809125 | 0.45 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_1 | 2024-09-09 | -0.68 | 0.13 | -2.16 | -0.66 | 61.0 | 1.0 | 43.0 | 66.0 | single | 1.97 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 60.0 | 1.0 | 1165.22 | 1260.48 | -1.66 | 11391 | 0.69 | 988.0 | rica40325-feedback-dpo-3_v1 | 8B | rica40325/feedback_dpo_3 | rica40325-feedback-dpo-3_v1 | 11391 | 809125 | 0.42 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_3 | 2024-09-09 | -0.72 | -0.2 | -1.68 | -1.04 | 64.0 | 1.0 | 54.0 | 62.0 | single | 2.04 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 61.0 | 1.0 | 1184.91 | 1260.48 | -2.2 | 11433 | 0.74 | 946.0 | rica40325-feedback-merged-7_v1 | 8B | rica40325/feedback-merged_7 | rica40325-feedback-and_v1 | 11433 | 809125 | 0.41 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback-merge | 2024-09-05 | -0.76 | -0.02 | -2.14 | 0.28 | 63.0 | 1.0 | 48.0 | 65.0 | single | 2.02 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 62.0 | 1.0 | 1179.24 | 1260.48 | -2.36 | 13104 | 0.74 | 1149.0 | rica40325-1300-dpo-v4_v1 | 8B | rica40325/1300-dpo-v4 | rica40325-1300-dpo-v4_v1 | 13104 | 809125 | 0.41 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/1300-dpo-v4 | 2024-09-05 | -0.84 | -0.07 | -2.27 | 0.27 | 65.0 | 1.0 | 51.0 | 67.0 | single | 1.98 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 63.0 | 1.0 | 855.75 | 1260.48 | 2.06 | 10731 | 0.64 | 952.0 | rica40325-feedback-dpo-5_v1 | 8B | rica40325/feedback_dpo_5 | rica40325-feedback-dpo-5_v1 | 10731 | 809125 | 0.12 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_5 | 2024-09-10 | -1.48 | -3.09 | 1.5 | -2.36 | 40.0 | 1.0 | 66.0 | 5.0 | single | 2.02 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 64.0 | 1.0 | 792.67 | 1260.48 | 3.25 | 11935 | 0.56 | 1061.0 | rica40325-feedback-dpo-5_v2 | 8B | rica40325/feedback_dpo_5 | rica40325-feedback-dpo-5_v1 | 11935 | 809125 | 0.09 | 0.53 | basic | | 1 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_5 | 2024-09-10 | -1.51 | -3.68 | 2.51 | -4.34 | 37.0 | 1.0 | 67.0 | 2.0 | single | 7.27 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 65.0 | 1.0 | 876.02 | 1260.48 | -0.05 | 11426 | 0.62 | 924.0 | rica40325-feedback-dpo-6_v1 | 8B | rica40325/feedback_dpo_6 | rica40325-feedback-dpo-5_v1 | 11426 | 809125 | 0.13 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_6 | 2024-09-10 | -1.99 | -2.9 | -0.3 | -2.94 | 59.5 | 1.0 | 65.0 | 43.0 | single | 2.02 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 66.0 | 1.0 | 883.58 | 1260.48 | -0.57 | 13545 | 0.64 | 1178.0 | rica40325-feedback-dpo-7_v1 | 8B | rica40325/feedback_dpo_7 | rica40325-feedback-dpo-7_v1 | 13544 | 809125 | 0.11 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_7 | 2024-09-10 | -2.1 | -2.83 | -0.74 | -2.18 | 66.0 | 1.0 | 63.0 | 57.0 | single | 2.0 | {'NVIDIA RTX A5000': 1} |
rica40325 | 1 | 67.0 | 1.0 | 881.33 | 1260.48 | -1.74 | 13136 | 0.64 | 1086.0 | rica40325-feedback-dpo-9_v1 | 8B | rica40325/feedback_dpo_9 | rica40325-feedback-dpo-9_v1 | 13136 | 809125 | 0.11 | 0.53 | basic | | 16 | 512 | 64 | LlamaForCausalLM | rica40325/feedback_dpo_9 | 2024-09-10 | -2.46 | -2.85 | -1.74 | -2.23 | 67.0 | 1.0 | 64.0 | 64.0 | single | 1.98 | {'NVIDIA RTX A5000': 1} |