laion/a3-rl-DCAgent_code-contests-noblock-5-8B
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/a3-rl-DCAgent_code-contests-noblock-5-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-07 12:29:36 +08:00
commit a508caa68d
55 changed files with 409528 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
training_logs/20260525_110326_metrics_job_485099.csv Normal file
View File

@@ -0,0 +1,6 @@
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_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError,batch_errors/avg_AgentEnvironmentTimeoutError,batch_errors/total_AgentEnvironmentTimeoutError,batch_errors/avg_DaytonaNotFoundError,batch_errors/total_DaytonaNotFoundError,batch_errors/avg_VerifierRuntimeError,batch_errors/total_VerifierRuntimeError,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,batch_errors/avg_RuntimeError,batch_errors/total_RuntimeError,batch_errors/avg_DaytonaValidationError,batch_errors/total_DaytonaValidationError,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,timing/cleanup_old_checkpoints,timing/save_checkpoints,timing/save_hf_model,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError
0.0,0,64,512,0,0.0,0,0.0,147.9727,3584.3333,1.0,8768,1,798.0622,0.041,0.4413,0.4415,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0052,-0.0178,0.0,1.0,0.0,0.0083,0.1719,0.041,6.1133,79.7606,624.197,27.2,857.9676,233.7706,0.1201,1.388,9.9059,57.0489,67.2439,8192.8398,18.3161,57.2174,8105.8915,0,1,128,1024,55,128,732,1.625,208,5.6640625,725,0.046875,6,0.15625,20,0.0234375,3.0,0.015625,2.0,0.0078125,1.0,0.0078125,1.0,0.0234375,3.0,,,,,
0.0,0,64,512,1,0.8438,0,0.8438,240.5703,3608.6471,1.0,11048,1,1028.2547,0.0664,0.3248,0.325,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0092,-0.0156,0.0,1.0,0.0,0.0059,0.2344,0.0664,6.7781,78.2899,614.3554,28.4,857.9676,243.6122,0.0338,1.6116,7.28,59.443,66.9312,7137.673,17.9631,59.6169,7051.1656,0,2,64,512,38,64,448,0.28125,18,6.875,440,0.03125,2,0.09375,6,0.03125,2.0,,,,,,,0.09375,6.0,18.2883,37.3028,,,
0.0,0,64,512,2,1.0156,1,1.0,282.0371,3787.6053,1.0,9828,1,1115.4254,0.0742,0.1271,0.1271,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0101,-0.0065,0.0,1.0,0.0,0.003,0.2656,0.0742,7.0157,78.3694,616.362,28.2,857.9676,241.6056,0.0345,1.5826,6.4797,60.6694,67.4008,614.3507,19.0175,60.8861,526.3485,0,3,64,512,7,64,452,0.6875,44,7.0,448,0.015625,1,0.125,8,,,,,,,0.015625,1.0,0.046875,3.0,,,,,
0.0,0,64,512,2,1.2031,0,0.6094,64.5625,4650.1429,1.0,10031,1,636.5514,0.0137,0.0703,0.0703,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0018,-0.002,0.0,1.0,0.0,0.0028,0.0938,0.0137,7.3373,78.4666,619.0092,27.9,857.9676,238.9584,0.0351,1.6766,4.2416,48.7129,53.1303,7011.6209,18.0381,48.8532,6938.7746,0,4,64,512,59,64,403,0.671875,43,6.203125,397,0.015625,1,0.09375,6,0.015625,1.0,,,,,0.015625,1.0,0.0625,4.0,0.0088,18.0874,,,
0.0,0,64,512,1,1.0,1,1.0,278.7383,2411.2034,1.0,4957,1,815.5083,0.1152,0.0935,0.0935,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0131,-0.0088,0.0,1.0,0.0,0.0065,0.2344,0.1152,7.5183,78.4538,621.5787,27.6,857.9676,236.3889,0.0216,1.0094,6.7753,55.4016,62.3349,734.6954,18.4983,55.5375,652.851,0,5,30,240,9,30,205,0.6666666666666666,20,6.733333333333333,202,0.06666666666666667,2,0.1,3,,,,,,,0.1,3.0,,,,,10.5996,0.03333333333333333,1.0
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_DaytonaAuthenticationError batch_errors/total_DaytonaAuthenticationError batch_errors/avg_AgentEnvironmentTimeoutError batch_errors/total_AgentEnvironmentTimeoutError batch_errors/avg_DaytonaNotFoundError batch_errors/total_DaytonaNotFoundError batch_errors/avg_VerifierRuntimeError batch_errors/total_VerifierRuntimeError batch_errors/avg_DaytonaError batch_errors/total_DaytonaError batch_errors/avg_RuntimeError batch_errors/total_RuntimeError batch_errors/avg_DaytonaValidationError batch_errors/total_DaytonaValidationError batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError timing/cleanup_old_checkpoints timing/save_checkpoints timing/save_hf_model batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError
2 0.0 0 64 512 0 0.0 0 0.0 147.9727 3584.3333 1.0 8768 1 798.0622 0.041 0.4413 0.4415 -0.0003 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 0.0052 -0.0178 0.0 1.0 0.0 0.0083 0.1719 0.041 6.1133 79.7606 624.197 27.2 857.9676 233.7706 0.1201 1.388 9.9059 57.0489 67.2439 8192.8398 18.3161 57.2174 8105.8915 0 1 128 1024 55 128 732 1.625 208 5.6640625 725 0.046875 6 0.15625 20 0.0234375 3.0 0.015625 2.0 0.0078125 1.0 0.0078125 1.0 0.0234375 3.0
3 0.0 0 64 512 1 0.8438 0 0.8438 240.5703 3608.6471 1.0 11048 1 1028.2547 0.0664 0.3248 0.325 -0.0002 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 0.0092 -0.0156 0.0 1.0 0.0 0.0059 0.2344 0.0664 6.7781 78.2899 614.3554 28.4 857.9676 243.6122 0.0338 1.6116 7.28 59.443 66.9312 7137.673 17.9631 59.6169 7051.1656 0 2 64 512 38 64 448 0.28125 18 6.875 440 0.03125 2 0.09375 6 0.03125 2.0 0.09375 6.0 18.2883 37.3028
4 0.0 0 64 512 2 1.0156 1 1.0 282.0371 3787.6053 1.0 9828 1 1115.4254 0.0742 0.1271 0.1271 -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 0.0101 -0.0065 0.0 1.0 0.0 0.003 0.2656 0.0742 7.0157 78.3694 616.362 28.2 857.9676 241.6056 0.0345 1.5826 6.4797 60.6694 67.4008 614.3507 19.0175 60.8861 526.3485 0 3 64 512 7 64 452 0.6875 44 7.0 448 0.015625 1 0.125 8 0.015625 1.0 0.046875 3.0
5 0.0 0 64 512 2 1.2031 0 0.6094 64.5625 4650.1429 1.0 10031 1 636.5514 0.0137 0.0703 0.0703 -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 0.0018 -0.002 0.0 1.0 0.0 0.0028 0.0938 0.0137 7.3373 78.4666 619.0092 27.9 857.9676 238.9584 0.0351 1.6766 4.2416 48.7129 53.1303 7011.6209 18.0381 48.8532 6938.7746 0 4 64 512 59 64 403 0.671875 43 6.203125 397 0.015625 1 0.09375 6 0.015625 1.0 0.015625 1.0 0.0625 4.0 0.0088 18.0874
6 0.0 0 64 512 1 1.0 1 1.0 278.7383 2411.2034 1.0 4957 1 815.5083 0.1152 0.0935 0.0935 -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 0.0131 -0.0088 0.0 1.0 0.0 0.0065 0.2344 0.1152 7.5183 78.4538 621.5787 27.6 857.9676 236.3889 0.0216 1.0094 6.7753 55.4016 62.3349 734.6954 18.4983 55.5375 652.851 0 5 30 240 9 30 205 0.6666666666666666 20 6.733333333333333 202 0.06666666666666667 2 0.1 3 0.1 3.0 10.5996 0.03333333333333333 1.0