summaries
463 rows
This data as json, CSV (advanced)
Suggested facets: task_name, total_examples
| id ▼ | task_name | model_tag | total_examples | correct | accuracy | no_answer_count | stop_reason_counts | duration_human | pass_k | temperature | top_p | max_tokens | error | model |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | gsm8k_main(0) | Qwen_Qwen2.5-1.5B-Instruct | 1319 | 920 | 0.6974981046247157 | 44 | {"stop:-": 1311, "length:-": 8} | 25s | 1 | 0.0 | 0.95 | 1024 | /mnt/2data/Documents/safetensors/Qwen_Qwen2.5-1.5B-Instruct | |
| 2 | hendrycks_math(0) | Qwen_Qwen2.5-1.5B-Instruct | 5000 | 2471 | 0.4942 | 620 | {"stop:-": 4467, "length:-": 525, "stop:Problem:": 8} | 2m 32s | 1 | 0.0 | 0.95 | 1024 | /mnt/2data/Documents/safetensors/Qwen_Qwen2.5-1.5B-Instruct | |
| 3 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_50 | 1319 | 925 | 0.7012888551933283 | 36 | {"stop:-": 1313, "length:-": 6} | 23s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_50/huggingface | |
| 4 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_50 | 5000 | 2449 | 0.4898 | 621 | {"stop:-": 4465, "length:-": 526, "stop:Problem:": 9} | 2m 30s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_50/huggingface | |
| 5 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_100 | 1319 | 938 | 0.711144806671721 | 28 | {"stop:-": 1312, "length:-": 7} | 24s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_100/huggingface | |
| 6 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_100 | 5000 | 2439 | 0.4878 | 654 | {"stop:-": 4429, "length:-": 564, "stop:Problem:": 7} | 2m 31s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_100/huggingface | |
| 7 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_150 | 1319 | 934 | 0.7081122062168309 | 21 | {"stop:-": 1314, "length:-": 5} | 24s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_150/huggingface | |
| 8 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_150 | 5000 | 2431 | 0.4862 | 641 | {"stop:-": 4435, "length:-": 560, "stop:Problem:": 5} | 2m 31s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_150/huggingface | |
| 9 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_200 | 1319 | 925 | 0.7012888551933283 | 66 | {"stop:-": 1307, "length:-": 12} | 24s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_200/huggingface | |
| 10 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_200 | 5000 | 2456 | 0.4912 | 655 | {"stop:-": 4425, "length:-": 569, "stop:Problem:": 6} | 2m 30s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_200/huggingface | |
| 11 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_250 | 1319 | 818 | 0.620166793025019 | 54 | {"stop:-": 1296, "length:-": 23} | 20s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_250/huggingface | |
| 12 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_250 | 5000 | 2419 | 0.4838 | 680 | {"stop:-": 4400, "length:-": 589, "stop:Problem:": 11} | 2m 28s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_250/huggingface | |
| 13 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_300 | 1319 | 755 | 0.5724033358605004 | 68 | {"stop:-": 1280, "length:-": 39} | 18s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_300/huggingface | |
| 14 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_300 | 5000 | 2395 | 0.479 | 655 | {"stop:-": 4430, "length:-": 562, "stop:Problem:": 8} | 2m 27s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_300/huggingface | |
| 15 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_350 | 1319 | 725 | 0.5496588324488249 | 89 | {"stop:-": 1257, "length:-": 62} | 18s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_350/huggingface | |
| 16 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_350 | 5000 | 2341 | 0.4682 | 654 | {"stop:-": 4429, "length:-": 566, "stop:Problem:": 5} | 2m 26s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_350/huggingface | |
| 17 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_400 | 1319 | 741 | 0.5617892342683851 | 62 | {"stop:-": 1266, "length:-": 53} | 17s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_400/huggingface | |
| 18 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_400 | 5000 | 2357 | 0.4714 | 662 | {"stop:-": 4426, "length:-": 568, "stop:Problem:": 6} | 2m 22s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_400/huggingface | |
| 19 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_450 | 1319 | 728 | 0.5519332827899924 | 61 | {"stop:-": 1272, "length:-": 47} | 17s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_450/huggingface | |
| 20 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_450 | 5000 | 2326 | 0.4652 | 648 | {"stop:-": 4415, "length:-": 581, "stop:Problem:": 4} | 2m 23s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_450/huggingface | |
| 21 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_500 | 1319 | 720 | 0.5458680818802123 | 65 | {"stop:-": 1263, "length:-": 56} | 17s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_500/huggingface | |
| 22 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_500 | 5000 | 2269 | 0.4538 | 692 | {"stop:-": 4383, "length:-": 612, "stop:Problem:": 5} | 2m 22s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_500/huggingface | |
| 23 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_550 | 1319 | 745 | 0.5648218347232752 | 49 | {"stop:-": 1276, "length:-": 43} | 16s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_550/huggingface | |
| 24 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_550 | 5000 | 2202 | 0.4404 | 686 | {"stop:-": 4397, "length:-": 599, "stop:Problem:": 4} | 2m 20s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_550/huggingface | |
| 25 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_600 | 1319 | 743 | 0.5633055344958302 | 50 | {"stop:-": 1273, "length:-": 46} | 16s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_600/huggingface | |
| 26 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_600 | 5000 | 2145 | 0.429 | 697 | {"stop:-": 4386, "length:-": 610, "stop:Problem:": 4} | 2m 18s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_600/huggingface | |
| 27 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_650 | 1319 | 746 | 0.5655799848369977 | 47 | {"stop:-": 1275, "length:-": 44} | 16s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_650/huggingface | |
| 28 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_650 | 5000 | 2144 | 0.4288 | 709 | {"stop:-": 4378, "length:-": 618, "stop:Problem:": 4} | 2m 16s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_650/huggingface | |
| 29 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_700 | 1319 | 741 | 0.5617892342683851 | 29 | {"stop:-": 1290, "length:-": 29} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_700/huggingface | |
| 30 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_700 | 5000 | 2154 | 0.4308 | 690 | {"stop:-": 4389, "length:-": 608, "stop:Problem:": 3} | 2m 16s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_700/huggingface | |
| 31 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_750 | 1319 | 749 | 0.5678544351781653 | 27 | {"stop:-": 1294, "length:-": 25} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_750/huggingface | |
| 32 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_750 | 5000 | 2125 | 0.425 | 707 | {"stop:-": 4378, "length:-": 618, "stop:Problem:": 4} | 2m 16s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_750/huggingface | |
| 33 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_800 | 1319 | 761 | 0.5769522365428355 | 25 | {"stop:-": 1294, "length:-": 25} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_800/huggingface | |
| 34 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_800 | 5000 | 2000 | 0.4 | 725 | {"stop:-": 4359, "length:-": 636, "stop:Problem:": 5} | 2m 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_800/huggingface | |
| 35 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_850 | 1319 | 763 | 0.5784685367702805 | 28 | {"stop:-": 1291, "length:-": 28} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_850/huggingface | |
| 36 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_850 | 5000 | 2055 | 0.411 | 720 | {"stop:-": 4373, "length:-": 624, "stop:Problem:": 3} | 2m 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_850/huggingface | |
| 37 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_900 | 1319 | 769 | 0.5830174374526156 | 29 | {"stop:-": 1290, "length:-": 29} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_900/huggingface | |
| 38 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_900 | 5000 | 1968 | 0.3936 | 735 | {"stop:-": 4349, "length:-": 642, "stop:Problem:": 9} | 2m 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_900/huggingface | |
| 39 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_950 | 1319 | 765 | 0.5799848369977255 | 24 | {"stop:-": 1295, "length:-": 24} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_950/huggingface | |
| 40 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_950 | 5000 | 1809 | 0.3618 | 852 | {"stop:-": 4237, "length:-": 758, "stop:Problem:": 5} | 2m 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_950/huggingface | |
| 41 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1000 | 1319 | 771 | 0.5845337376800607 | 13 | {"stop:-": 1306, "length:-": 13} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1000/huggingface | |
| 42 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1000 | 5000 | 1904 | 0.3808 | 746 | {"stop:-": 4338, "length:-": 657, "stop:Problem:": 5} | 2m 10s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1000/huggingface | |
| 43 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1050 | 1319 | 776 | 0.5883244882486732 | 13 | {"stop:-": 1306, "length:-": 13} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1050/huggingface | |
| 44 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1050 | 5000 | 1819 | 0.3638 | 794 | {"stop:-": 4290, "length:-": 705, "stop:Problem:": 5} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1050/huggingface | |
| 45 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1100 | 1319 | 800 | 0.6065200909780136 | 20 | {"stop:-": 1299, "length:-": 20} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1100/huggingface | |
| 46 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1100 | 5000 | 1781 | 0.3562 | 820 | {"stop:-": 4267, "length:-": 728, "stop:Problem:": 5} | 2m 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1100/huggingface | |
| 47 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1150 | 1319 | 785 | 0.5951478392721758 | 14 | {"stop:-": 1305, "length:-": 14} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1150/huggingface | |
| 48 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1150 | 5000 | 1695 | 0.339 | 832 | {"stop:-": 4251, "length:-": 744, "stop:Problem:": 5} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1150/huggingface | |
| 49 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1200 | 1319 | 785 | 0.5951478392721758 | 13 | {"stop:-": 1306, "length:-": 13} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1200/huggingface | |
| 50 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1200 | 5000 | 1688 | 0.3376 | 920 | {"stop:-": 4175, "length:-": 820, "stop:Problem:": 5} | 2m 12s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1200/huggingface | |
| 51 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1250 | 1319 | 790 | 0.5989385898407885 | 15 | {"stop:-": 1304, "length:-": 15} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1250/huggingface | |
| 52 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1250 | 5000 | 1587 | 0.3174 | 975 | {"stop:-": 4101, "length:-": 896, "stop:Problem:": 3} | 2m 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1250/huggingface | |
| 53 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1300 | 1319 | 794 | 0.6019711902956786 | 10 | {"stop:-": 1309, "length:-": 10} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1300/huggingface | |
| 54 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1300 | 5000 | 1594 | 0.3188 | 911 | {"stop:-": 4167, "length:-": 831, "stop:Problem:": 2} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1300/huggingface | |
| 55 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1350 | 1319 | 783 | 0.5936315390447309 | 14 | {"stop:-": 1305, "length:-": 14} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1350/huggingface | |
| 56 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1350 | 5000 | 1560 | 0.312 | 910 | {"stop:-": 4164, "length:-": 832, "stop:Problem:": 4} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1350/huggingface | |
| 57 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1400 | 1319 | 792 | 0.6004548900682335 | 11 | {"stop:-": 1308, "length:-": 11} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1400/huggingface | |
| 58 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1400 | 5000 | 1592 | 0.3184 | 906 | {"stop:-": 4164, "length:-": 832, "stop:Problem:": 4} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1400/huggingface | |
| 59 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1450 | 1319 | 806 | 0.6110689916603488 | 8 | {"stop:-": 1312, "length:-": 7} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1450/huggingface | |
| 60 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1450 | 5000 | 1621 | 0.3242 | 844 | {"stop:-": 4233, "length:-": 765, "stop:Problem:": 2} | 2m 09s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1450/huggingface | |
| 61 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1500 | 1319 | 816 | 0.6186504927975739 | 7 | {"stop:-": 1312, "length:-": 7} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1500/huggingface | |
| 62 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1500 | 5000 | 1416 | 0.2832 | 972 | {"stop:-": 4096, "length:-": 901, "stop:Problem:": 3} | 2m 10s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1500/huggingface | |
| 63 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1550 | 1319 | 818 | 0.620166793025019 | 11 | {"stop:-": 1308, "length:-": 11} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1550/huggingface | |
| 64 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1550 | 5000 | 1400 | 0.28 | 977 | {"stop:-": 4078, "length:-": 918, "stop:Problem:": 4} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1550/huggingface | |
| 65 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1600 | 1319 | 829 | 0.6285064442759667 | 11 | {"stop:-": 1308, "length:-": 11} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1600/huggingface | |
| 66 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1600 | 5000 | 1526 | 0.3052 | 966 | {"stop:-": 4096, "length:-": 902, "stop:Problem:": 2} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1600/huggingface | |
| 67 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1650 | 1319 | 804 | 0.6095526914329037 | 5 | {"stop:-": 1314, "length:-": 5} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1650/huggingface | |
| 68 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1650 | 5000 | 1552 | 0.3104 | 952 | {"stop:-": 4125, "length:-": 873, "stop:Problem:": 2} | 2m 13s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1650/huggingface | |
| 69 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1700 | 1319 | 821 | 0.6224412433661866 | 8 | {"stop:-": 1313, "length:-": 6} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1700/huggingface | |
| 70 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1700 | 5000 | 1423 | 0.2846 | 1009 | {"stop:-": 4051, "length:-": 944, "stop:Problem:": 5} | 2m 13s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1700/huggingface | |
| 71 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1750 | 1319 | 832 | 0.6307808946171342 | 10 | {"stop:-": 1310, "length:-": 9} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1750/huggingface | |
| 72 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1750 | 5000 | 1421 | 0.2842 | 1063 | {"stop:-": 4005, "length:-": 992, "stop:Problem:": 3} | 2m 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1750/huggingface | |
| 73 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1800 | 1319 | 828 | 0.6277482941622441 | 5 | {"stop:-": 1314, "length:-": 5} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1800/huggingface | |
| 74 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1800 | 5000 | 1460 | 0.292 | 920 | {"stop:-": 4148, "length:-": 847, "stop:Problem:": 5} | 2m 08s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1800/huggingface | |
| 75 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1850 | 1319 | 813 | 0.6163760424564063 | 10 | {"stop:-": 1310, "length:-": 9} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1850/huggingface | |
| 76 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1850 | 5000 | 1510 | 0.302 | 905 | {"stop:-": 4157, "length:-": 840, "stop:Problem:": 3} | 2m 09s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1850/huggingface | |
| 77 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1900 | 1319 | 833 | 0.6315390447308568 | 11 | {"stop:-": 1309, "length:-": 10} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1900/huggingface | |
| 78 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1900 | 5000 | 1489 | 0.2978 | 947 | {"stop:-": 4128, "length:-": 868, "stop:Problem:": 4} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1900/huggingface | |
| 79 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_1950 | 1319 | 837 | 0.6345716451857468 | 9 | {"stop:-": 1313, "length:-": 6} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1950/huggingface | |
| 80 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_1950 | 5000 | 1257 | 0.2514 | 1125 | {"stop:-": 3925, "length:-": 1072, "stop:Problem:": 3} | 2m 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_1950/huggingface | |
| 81 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2000 | 1319 | 841 | 0.6376042456406369 | 11 | {"stop:-": 1310, "length:-": 9} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2000/huggingface | |
| 82 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2000 | 5000 | 1293 | 0.2586 | 1031 | {"stop:-": 4018, "length:-": 979, "stop:Problem:": 3} | 2m 10s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2000/huggingface | |
| 83 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2050 | 1319 | 831 | 0.6300227445034117 | 9 | {"stop:-": 1311, "length:-": 8} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2050/huggingface | |
| 84 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2050 | 5000 | 1335 | 0.267 | 1037 | {"stop:-": 4025, "length:-": 971, "stop:Problem:": 4} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2050/huggingface | |
| 85 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2100 | 1319 | 821 | 0.6224412433661866 | 8 | {"stop:-": 1313, "length:-": 6} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2100/huggingface | |
| 86 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2100 | 5000 | 1355 | 0.271 | 945 | {"stop:-": 4104, "length:-": 892, "stop:Problem:": 4} | 2m 09s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2100/huggingface | |
| 87 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2150 | 1319 | 847 | 0.6421531463229719 | 9 | {"stop:-": 1312, "length:-": 7} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2150/huggingface | |
| 88 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2150 | 5000 | 1357 | 0.2714 | 1017 | {"stop:-": 4050, "length:-": 944, "stop:Problem:": 6} | 2m 11s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2150/huggingface | |
| 89 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2200 | 1319 | 841 | 0.6376042456406369 | 8 | {"stop:-": 1313, "length:-": 6} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2200/huggingface | |
| 90 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2200 | 5000 | 1315 | 0.263 | 1013 | {"stop:-": 4054, "length:-": 943, "stop:Problem:": 3} | 2m 10s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2200/huggingface | |
| 91 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2250 | 1319 | 835 | 0.6330553449583017 | 7 | {"stop:-": 1313, "length:-": 6} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2250/huggingface | |
| 92 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2250 | 5000 | 1239 | 0.2478 | 1078 | {"stop:-": 3979, "length:-": 1018, "stop:Problem:": 3} | 2m 10s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2250/huggingface | |
| 93 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2300 | 1319 | 831 | 0.6300227445034117 | 4 | {"stop:-": 1315, "length:-": 4} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2300/huggingface | |
| 94 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2300 | 5000 | 1303 | 0.2606 | 1009 | {"stop:-": 4050, "length:-": 946, "stop:Problem:": 4} | 2m 09s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2300/huggingface | |
| 95 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2350 | 1319 | 829 | 0.6285064442759667 | 5 | {"stop:-": 1315, "length:-": 4} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2350/huggingface | |
| 96 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2350 | 5000 | 1302 | 0.2604 | 963 | {"stop:-": 4104, "length:-": 889, "stop:Problem:": 7} | 2m 05s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2350/huggingface | |
| 97 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2400 | 1319 | 848 | 0.6429112964366944 | 6 | {"stop:-": 1314, "length:-": 5} | 14s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2400/huggingface | |
| 98 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2400 | 5000 | 1319 | 0.2638 | 916 | {"stop:-": 4155, "length:-": 836, "stop:Problem:": 9} | 2m 04s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2400/huggingface | |
| 99 | gsm8k_main(0) | sft-gsm8k-test-docker_global_step_2450 | 1319 | 827 | 0.6269901440485216 | 7 | {"stop:-": 1313, "length:-": 6} | 15s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2450/huggingface | |
| 100 | hendrycks_math(0) | sft-gsm8k-test-docker_global_step_2450 | 5000 | 1273 | 0.2546 | 1024 | {"stop:-": 4041, "length:-": 953, "stop:Problem:": 6} | 2m 08s | 1 | 0.0 | 0.95 | 1024 | /mnt/data8tb/Documents/project/rlvr_winter/verl-my-rlvr/outputs/sft-gsm8k-test-docker/global_step_2450/huggingface |
Advanced export
JSON shape: default, array, newline-delimited, object
CREATE TABLE summaries (
id INTEGER PRIMARY KEY AUTOINCREMENT,
task_name TEXT NOT NULL,
model_tag TEXT NOT NULL,
total_examples INTEGER,
correct INTEGER,
accuracy REAL,
no_answer_count INTEGER,
stop_reason_counts TEXT,
duration_human TEXT,
pass_k INTEGER,
temperature REAL,
top_p REAL,
max_tokens INTEGER,
error TEXT,
model TEXT NOT NULL
);
CREATE INDEX idx_summaries_model ON summaries(model_tag);
CREATE INDEX idx_summaries_task ON summaries(task_name);