Lizhecheng | 1 | 1.0 | 1.0 | 1258.6 | 1258.6 | 0.6 | 0.6 | lizhecheng-more-data-dp_15338_v1 | 13B | Lizhecheng/more-data-dpo-checkpoint-600-lower-lr | lizhecheng-more-data-dp_15338_v1 | 7844 | 230415 | 0.49 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/more-data-dpo | 2025-01-20 | single | | |
Lizhecheng | 1 | 2.0 | 1.0 | 1256.01 | 1258.6 | 0.6 | 0.6 | lizhecheng-more-data-dp_28614_v1 | 13B | Lizhecheng/more-data-dpo-checkpoint-737-lower-lr | lizhecheng-more-data-dp_28614_v1 | 11036 | 230415 | 0.49 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/more-data-dpo | 2025-01-20 | single | | |
Lizhecheng | 1 | 3.0 | 1.0 | 1253.73 | 1258.6 | 0.6 | 0.6 | lizhecheng-more-data-dp_44104_v1 | 13B | Lizhecheng/more-data-dpo-checkpoint-700-lower-lr | lizhecheng-more-data-dp_44104_v1 | 8036 | 230415 | 0.48 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/more-data-dpo | 2025-01-20 | single | | |
Lizhecheng | 1 | 4.0 | 1.0 | 1253.44 | 1258.6 | 0.59 | 0.6 | lizhecheng-more-data-dp_18878_v1 | 13B | Lizhecheng/more-data-dpo-ckpt-700 | lizhecheng-more-data-dp_18878_v1 | 9819 | 230415 | 0.48 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/more-data-dpo | 2025-01-20 | single | | |
Lizhecheng | 1 | 5.0 | 1.0 | 1252.43 | 1258.6 | 0.59 | 0.6 | chaiml-workshopsft_v4 | 13B | ChaiML/WorkshopSFT | chaiml-workshopsft_v4 | 7967 | 230415 | 0.48 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | ChaiML/WorkshopSFT | 2025-01-18 | single | | |
Lizhecheng | 1 | 6.0 | 1.0 | 1252.37 | 1258.6 | 0.59 | 0.6 | lizhecheng-ckpt-502-only-dpo_v2 | 13B | Lizhecheng/ckpt-502-only-dpo | lizhecheng-ckpt-502-only-dpo_v2 | 12378 | 230415 | 0.48 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/ckpt-502-only | 2025-01-19 | single | | |
Lizhecheng | 1 | 7.0 | 1.0 | 1252.09 | 1258.6 | 0.6 | 0.6 | lizhecheng-more-data-dp_32745_v1 | 13B | Lizhecheng/more-data-dpo-ckpt-650 | lizhecheng-more-data-dp_32745_v1 | 8138 | 230415 | 0.48 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/more-data-dpo | 2025-01-20 | single | | |
Lizhecheng | 1 | 8.0 | 1.0 | 1251.81 | 1258.6 | 0.6 | 0.6 | lizhecheng-more-data-dpo_1405_v1 | 13B | Lizhecheng/more-data-dpo-ckpt-737 | lizhecheng-more-data-dpo_1405_v1 | 10057 | 230415 | 0.48 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/more-data-dpo | 2025-01-20 | single | | |
Lizhecheng | 1 | 9.0 | 1.0 | 1250.19 | 1258.6 | 0.6 | 0.6 | lizhecheng-more-data-dp_43169_v1 | 13B | Lizhecheng/more-data-dpo-checkpoint-650-lower-lr | lizhecheng-more-data-dp_43169_v1 | 8587 | 230415 | 0.48 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/more-data-dpo | 2025-01-20 | single | | |
Lizhecheng | 1 | 10.0 | 1.0 | 1249.75 | 1258.6 | 0.6 | 0.6 | mistralai-mistral-nem_93303_v271 | 13B | mistralai/Mistral-Nemo-Instruct-2407 | mistralai-mistral-nem_93303_v271 | 8816 | 230415 | 0.48 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | mistralai/Mistral-Nemo-I | 2025-01-18 | single | | |
Lizhecheng | 1 | 11.0 | 1.0 | 1248.53 | 1258.6 | 0.6 | 0.6 | mistralai-mistral-nem_93303_v270 | 13B | mistralai/Mistral-Nemo-Instruct-2407 | mistralai-mistral-nem_93303_v270 | 14103 | 230415 | 0.47 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | mistralai/Mistral-Nemo-I | 2025-01-18 | single | | |
Lizhecheng | 1 | 12.0 | 1.0 | 1246.57 | 1258.6 | 0.59 | 0.6 | mistralai-mistral-nem_93303_v273 | 13B | mistralai/Mistral-Nemo-Instruct-2407 | mistralai-mistral-nem_93303_v273 | 16671 | 230415 | 0.47 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | mistralai/Mistral-Nemo-I | 2025-01-18 | single | | |
Lizhecheng | 1 | 13.0 | 1.0 | 1245.11 | 1258.6 | 0.6 | 0.6 | mistralai-mistral-nem_93303_v272 | 13B | mistralai/Mistral-Nemo-Instruct-2407 | mistralai-mistral-nem_93303_v272 | 8948 | 230415 | 0.47 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | mistralai/Mistral-Nemo-I | 2025-01-18 | single | | |
Lizhecheng | 1 | 14.0 | 1.0 | 1244.08 | 1258.6 | 0.59 | 0.6 | lizhecheng-ckpt-400-sec_41027_v1 | 13B | Lizhecheng/ckpt-400-second-experiment | lizhecheng-ckpt-400-sec_41027_v1 | 11449 | 230415 | 0.46 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/ckpt-400-seco | 2025-01-18 | single | | |
Lizhecheng | 1 | 15.0 | 1.0 | 1243.86 | 1258.6 | 0.6 | 0.6 | lizhecheng-ckpt-502-only-dpo_v1 | 13B | Lizhecheng/ckpt-502-only-dpo | lizhecheng-ckpt-502-only-dpo_v1 | 11914 | 230415 | 0.46 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/ckpt-502-only | 2025-01-19 | single | | |
Lizhecheng | 1 | 16.0 | 1.0 | 1237.45 | 1258.6 | 0.6 | 0.6 | lizhecheng-ckpt-300-fir_50681_v1 | 13B | Lizhecheng/ckpt-300-first-experiment | lizhecheng-ckpt-300-fir_50681_v1 | 12819 | 230415 | 0.46 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/ckpt-300-firs | 2025-01-18 | single | | |
Lizhecheng | 1 | 17.0 | 1.0 | 1237.11 | 1258.6 | 0.6 | 0.6 | mistralai-mistral-nem_93303_v274 | 13B | mistralai/Mistral-Nemo-Instruct-2407 | mistralai-mistral-nem_93303_v274 | 10055 | 230415 | 0.45 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | mistralai/Mistral-Nemo-I | 2025-01-18 | single | | |
Lizhecheng | 1 | 18.0 | 1.0 | 1236.4 | 1258.6 | 0.6 | 0.6 | lizhecheng-ckpt-30-firs_41168_v1 | 13B | Lizhecheng/ckpt-30-first-experiment | lizhecheng-ckpt-30-firs_41168_v1 | 10569 | 230415 | 0.46 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/ckpt-30-first | 2025-01-18 | single | | |
Lizhecheng | 1 | 19.0 | 1.0 | 1229.1 | 1258.6 | 0.6 | 0.6 | lizhecheng-ckpt-1450-th_67513_v1 | 13B | Lizhecheng/ckpt-1450-third-experiment | lizhecheng-ckpt-1450-th_67513_v1 | 17202 | 230415 | 0.45 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/ckpt-1450-thi | 2025-01-19 | single | | |
Lizhecheng | 1 | 20.0 | 1.0 | 1229.0 | 1258.6 | 0.6 | 0.6 | lizhecheng-ckpt-1400-th_52593_v1 | 13B | Lizhecheng/ckpt-1400-third-experiment | lizhecheng-ckpt-1400-th_52593_v1 | 14809 | 230415 | 0.45 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/ckpt-1400-thi | 2025-01-19 | single | | |
Lizhecheng | 1 | 21.0 | 1.0 | 1227.78 | 1258.6 | 0.6 | 0.6 | lizhecheng-ckpt-600-sec_99087_v1 | 13B | Lizhecheng/ckpt-600-second-experiment | lizhecheng-ckpt-600-sec_99087_v1 | 9198 | 230415 | 0.44 | 0.49 | basic | | 8 | 1024 | 64 | MistralForCausalLM | Lizhecheng/ckpt-600-seco | 2025-01-18 | single | | |