laion/ablation-pymethods2test-seqmean-arm0-30-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: laion/ablation-pymethods2test-seqmean-arm0-30-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 18:02:02 +08:00
commit 0c293fc953
47 changed files with 292406 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
training_logs/20260612_220124_metrics_job_661735.csv Normal file
View File

@@ -0,0 +1,9 @@
async/discard_rate,async/discarded_count,async/effective_batch_groups,async/effective_batch_samples,async/staleness_max,async/staleness_mean,async/staleness_min,async/staleness_ratio,generate/avg_num_tokens,generate/avg_tokens_non_zero_rewards,generate/avg_tokens_zero_rewards,generate/max_num_tokens,generate/min_num_tokens,generate/std_num_tokens,loss/avg_final_rewards,loss/avg_raw_advantages,loss/avg_raw_advantages_abs,policy/final_loss,policy/log_ratio_abs_max,policy/log_ratio_abs_mean,policy/log_ratio_abs_p99,policy/log_ratio_abs_pos00,policy/log_ratio_abs_pos10,policy/log_ratio_abs_pos20,policy/log_ratio_abs_pos30,policy/log_ratio_abs_pos40,policy/log_ratio_abs_pos50,policy/log_ratio_abs_pos60,policy/log_ratio_abs_pos70,policy/log_ratio_abs_pos80,policy/log_ratio_abs_pos90,policy/n_tokens_dp_gt_10pct,policy/n_tokens_dp_gt_1pct,policy/n_tokens_dp_gt_50pct,policy/policy_entropy,policy/policy_loss,policy/policy_lr,policy/policy_update_steps,policy/ppo_clip_ratio,policy/raw_grad_norm,reward/avg_pass_at_8,reward/avg_raw_reward,system/process_rss_gb,system/process_vms_gb,system/ram_available_gb,system/ram_percent,system/ram_total_gb,system/ram_used_gb,timing/compute_advantages_and_returns,timing/convert_to_training_input,timing/fwd_logprobs_values_reward,timing/policy_train,timing/run_training,timing/step,timing/sync_weights,timing/train_critic_and_policy,timing/wait_for_generation_buffer,trainer/epoch,trainer/global_step,batch_errors/total_batches,batch_errors/total_instances,batch_errors/total_successful,batch_errors/total_failed,batch_errors/total_masked,batch_errors/avg_InvalidChatHistory,batch_errors/total_InvalidChatHistory,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,batch_errors/avg_VerifierTimeoutError,batch_errors/total_VerifierTimeoutError,timing/cleanup_old_checkpoints,timing/save_checkpoints,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,timing/save_hf_model,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError
0.0,0,64,512,3,0.3281,0,0.2188,4521.9473,4333.5193,4758.5198,31663,1,3365.2785,0.5566,0.0074,0.094,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0996,-0.0,0.0,1.0,0.0,0.0131,0.5965,0.5566,12.5978,50.5919,579.345,32.5,857.9676,278.6226,0.1569,4.5133,32.1738,167.8055,200.36,3675.9345,21.9439,168.0287,3449.1169,0,71,58,464,375,29,88,1.4137931034482758,82,0.20689655172413793,12,0.017241379310344827,1.0,,,,,,,,,
0.0,0,64,512,1,0.9375,0,0.9375,5361.2598,5767.993,5205.1622,31699,1,5207.4533,0.2773,-0.013,0.1323,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1151,0.0,0.0,1.0,0.0,0.017,0.4219,0.2773,12.8662,50.7994,576.8029,32.8,857.9676,281.1647,0.0648,4.6437,37.3367,229.2593,266.8776,1642.3033,25.4393,229.4755,1345.3366,0,72,56,448,364,24,80,1.3392857142857142,75,0.16071428571428573,9,0.07142857142857142,4.0,11.424,21.2849,0.16071428571428573,9.0,0.05357142857142857,3.0,,,
0.0,0,64,512,2,1.6406,1,1.0,4303.7402,4841.9941,4036.1871,31778,1,4623.5614,0.332,0.0023,0.0825,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0977,0.0,0.0,1.0,0.0,0.0095,0.4062,0.332,13.201,51.0858,576.4416,32.8,857.9676,281.526,0.0649,4.6475,32.7604,195.3408,228.4104,875.421,23.4598,195.5846,618.8995,0,73,63,504,471,12,33,0.47619047619047616,30,0.07936507936507936,5,,,,,0.047619047619047616,3.0,,,,,
0.0,0,64,512,3,1.6406,0,0.8906,5242.7773,4926.2055,5552.0154,31761,1,4678.9952,0.4941,0.0138,0.1243,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1009,-0.0,0.0,1.0,0.0,0.0145,0.5938,0.4941,13.4431,51.3293,575.8802,32.9,857.9676,282.0874,0.062,4.6498,37.0456,231.3918,268.7201,1733.9771,23.6881,231.6122,1436.9161,0,74,59,472,401,23,56,0.847457627118644,50,0.1864406779661017,11,0.2542372881355932,15.0,0.007,10.013,0.03389830508474576,2.0,0.05084745762711865,3.0,,,
0.0,0,64,512,4,1.9844,1,1.0,4678.0137,4390.89,4862.0673,31720,1,4446.3943,0.3906,-0.0162,0.1412,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1014,-0.002,0.0,1.0,0.0,0.0143,0.5625,0.3906,13.5915,51.5202,575.6154,32.9,857.9676,282.3522,0.0636,4.5241,34.8828,208.4871,243.6766,1567.8023,22.6625,208.7299,1296.9223,0,75,61,488,422,25,66,0.7704918032786885,47,0.21311475409836064,13,,,,,0.06557377049180328,4.0,0.09836065573770492,6.0,6.424,,
0.0,0,64,512,4,2.4219,2,1.0,4572.6895,4582.679,4568.0657,31799,1,4302.6602,0.3164,-0.0023,0.112,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.103,0.0,0.0,1.0,0.0,0.0129,0.4531,0.3164,13.6858,51.5748,574.5665,33.0,857.9676,283.4011,0.0663,4.6913,30.5968,200.2044,231.0996,1415.5476,24.2091,200.4362,1155.5266,0,76,61,488,415,22,64,0.7868852459016393,48,0.21311475409836064,13,0.14754098360655737,9.0,0.0074,9.8798,0.04918032786885246,3.0,0.11475409836065574,7.0,,,
0.0,0,64,512,4,3.0312,3,1.0,4597.7812,4086.6667,4944.6689,31759,1,4559.7375,0.4043,0.0013,0.0431,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0996,-0.0033,0.0,1.0,0.0,0.0068,0.4688,0.4043,14.3994,51.5634,573.7055,33.1,857.9676,284.2621,0.0642,4.5039,32.7244,196.2376,229.2847,1161.9454,21.4738,196.4958,906.6629,0,77,63,504,414,32,86,0.8095238095238095,51,0.4603174603174603,29,0.15873015873015872,10.0,,,,,0.09523809523809523,6.0,,0.015873015873015872,1.0
0.0,0,64,512,4,4.0,4,1.0,5291.9141,6195.0086,5027.3712,28898,1,4117.8095,0.2266,0.0072,0.1052,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1143,0.0,0.0,1.0,0.0,0.0105,0.375,0.2266,14.2961,51.5109,573.1121,33.2,857.9676,284.8555,0.1485,4.4428,33.4904,188.476,222.3217,1837.7946,17.1266,188.6825,1593.8676,0,78,67,536,466,24,64,0.6567164179104478,44,0.23880597014925373,16,0.08955223880597014,6.0,0.0588,10.9374,0.029850746268656716,2.0,0.029850746268656716,2.0,,,
1 async/discard_rate async/discarded_count async/effective_batch_groups async/effective_batch_samples async/staleness_max async/staleness_mean async/staleness_min async/staleness_ratio generate/avg_num_tokens generate/avg_tokens_non_zero_rewards generate/avg_tokens_zero_rewards generate/max_num_tokens generate/min_num_tokens generate/std_num_tokens loss/avg_final_rewards loss/avg_raw_advantages loss/avg_raw_advantages_abs policy/final_loss policy/log_ratio_abs_max policy/log_ratio_abs_mean policy/log_ratio_abs_p99 policy/log_ratio_abs_pos00 policy/log_ratio_abs_pos10 policy/log_ratio_abs_pos20 policy/log_ratio_abs_pos30 policy/log_ratio_abs_pos40 policy/log_ratio_abs_pos50 policy/log_ratio_abs_pos60 policy/log_ratio_abs_pos70 policy/log_ratio_abs_pos80 policy/log_ratio_abs_pos90 policy/n_tokens_dp_gt_10pct policy/n_tokens_dp_gt_1pct policy/n_tokens_dp_gt_50pct policy/policy_entropy policy/policy_loss policy/policy_lr policy/policy_update_steps policy/ppo_clip_ratio policy/raw_grad_norm reward/avg_pass_at_8 reward/avg_raw_reward system/process_rss_gb system/process_vms_gb system/ram_available_gb system/ram_percent system/ram_total_gb system/ram_used_gb timing/compute_advantages_and_returns timing/convert_to_training_input timing/fwd_logprobs_values_reward timing/policy_train timing/run_training timing/step timing/sync_weights timing/train_critic_and_policy timing/wait_for_generation_buffer trainer/epoch trainer/global_step batch_errors/total_batches batch_errors/total_instances batch_errors/total_successful batch_errors/total_failed batch_errors/total_masked batch_errors/avg_InvalidChatHistory batch_errors/total_InvalidChatHistory batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError batch_errors/avg_VerifierTimeoutError batch_errors/total_VerifierTimeoutError timing/cleanup_old_checkpoints timing/save_checkpoints batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError batch_errors/avg_DaytonaError batch_errors/total_DaytonaError timing/save_hf_model batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError
2 0.0 0 64 512 3 0.3281 0 0.2188 4521.9473 4333.5193 4758.5198 31663 1 3365.2785 0.5566 0.0074 0.094 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0996 -0.0 0.0 1.0 0.0 0.0131 0.5965 0.5566 12.5978 50.5919 579.345 32.5 857.9676 278.6226 0.1569 4.5133 32.1738 167.8055 200.36 3675.9345 21.9439 168.0287 3449.1169 0 71 58 464 375 29 88 1.4137931034482758 82 0.20689655172413793 12 0.017241379310344827 1.0
3 0.0 0 64 512 1 0.9375 0 0.9375 5361.2598 5767.993 5205.1622 31699 1 5207.4533 0.2773 -0.013 0.1323 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1151 0.0 0.0 1.0 0.0 0.017 0.4219 0.2773 12.8662 50.7994 576.8029 32.8 857.9676 281.1647 0.0648 4.6437 37.3367 229.2593 266.8776 1642.3033 25.4393 229.4755 1345.3366 0 72 56 448 364 24 80 1.3392857142857142 75 0.16071428571428573 9 0.07142857142857142 4.0 11.424 21.2849 0.16071428571428573 9.0 0.05357142857142857 3.0
4 0.0 0 64 512 2 1.6406 1 1.0 4303.7402 4841.9941 4036.1871 31778 1 4623.5614 0.332 0.0023 0.0825 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0977 0.0 0.0 1.0 0.0 0.0095 0.4062 0.332 13.201 51.0858 576.4416 32.8 857.9676 281.526 0.0649 4.6475 32.7604 195.3408 228.4104 875.421 23.4598 195.5846 618.8995 0 73 63 504 471 12 33 0.47619047619047616 30 0.07936507936507936 5 0.047619047619047616 3.0
5 0.0 0 64 512 3 1.6406 0 0.8906 5242.7773 4926.2055 5552.0154 31761 1 4678.9952 0.4941 0.0138 0.1243 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1009 -0.0 0.0 1.0 0.0 0.0145 0.5938 0.4941 13.4431 51.3293 575.8802 32.9 857.9676 282.0874 0.062 4.6498 37.0456 231.3918 268.7201 1733.9771 23.6881 231.6122 1436.9161 0 74 59 472 401 23 56 0.847457627118644 50 0.1864406779661017 11 0.2542372881355932 15.0 0.007 10.013 0.03389830508474576 2.0 0.05084745762711865 3.0
6 0.0 0 64 512 4 1.9844 1 1.0 4678.0137 4390.89 4862.0673 31720 1 4446.3943 0.3906 -0.0162 0.1412 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1014 -0.002 0.0 1.0 0.0 0.0143 0.5625 0.3906 13.5915 51.5202 575.6154 32.9 857.9676 282.3522 0.0636 4.5241 34.8828 208.4871 243.6766 1567.8023 22.6625 208.7299 1296.9223 0 75 61 488 422 25 66 0.7704918032786885 47 0.21311475409836064 13 0.06557377049180328 4.0 0.09836065573770492 6.0 6.424
7 0.0 0 64 512 4 2.4219 2 1.0 4572.6895 4582.679 4568.0657 31799 1 4302.6602 0.3164 -0.0023 0.112 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.103 0.0 0.0 1.0 0.0 0.0129 0.4531 0.3164 13.6858 51.5748 574.5665 33.0 857.9676 283.4011 0.0663 4.6913 30.5968 200.2044 231.0996 1415.5476 24.2091 200.4362 1155.5266 0 76 61 488 415 22 64 0.7868852459016393 48 0.21311475409836064 13 0.14754098360655737 9.0 0.0074 9.8798 0.04918032786885246 3.0 0.11475409836065574 7.0
8 0.0 0 64 512 4 3.0312 3 1.0 4597.7812 4086.6667 4944.6689 31759 1 4559.7375 0.4043 0.0013 0.0431 -0.0001 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0996 -0.0033 0.0 1.0 0.0 0.0068 0.4688 0.4043 14.3994 51.5634 573.7055 33.1 857.9676 284.2621 0.0642 4.5039 32.7244 196.2376 229.2847 1161.9454 21.4738 196.4958 906.6629 0 77 63 504 414 32 86 0.8095238095238095 51 0.4603174603174603 29 0.15873015873015872 10.0 0.09523809523809523 6.0 0.015873015873015872 1.0
9 0.0 0 64 512 4 4.0 4 1.0 5291.9141 6195.0086 5027.3712 28898 1 4117.8095 0.2266 0.0072 0.1052 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1143 0.0 0.0 1.0 0.0 0.0105 0.375 0.2266 14.2961 51.5109 573.1121 33.2 857.9676 284.8555 0.1485 4.4428 33.4904 188.476 222.3217 1837.7946 17.1266 188.6825 1593.8676 0 78 67 536 466 24 64 0.6567164179104478 44 0.23880597014925373 16 0.08955223880597014 6.0 0.0588 10.9374 0.029850746268656716 2.0 0.029850746268656716 2.0