laion/explore-tis-minp-40-8B
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/explore-tis-minp-40-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-09 12:53:53 +08:00
commit cab2418769
39 changed files with 299193 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
training_logs/20260612_111844_metrics_explore-tis-minp_736736.csv Normal file
View File

@@ -0,0 +1,2 @@
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,generate/tis/aligned_tokens,generate/tis/alignment_fail_count,generate/tis/exact_match_fraction,generate/tis/lcs_fallback_fraction,generate/tis/lcs_fallback_messages,generate/tis/unaligned_fraction,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,policy/rollout_train_prob_diff_mean,policy/rollout_train_prob_diff_std,policy/tis/imp_ratio_capped_fraction,policy/tis/imp_ratio_mean,policy/tis/log_ratio_abs_mean,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/cleanup_old_checkpoints,timing/compute_advantages_and_returns,timing/convert_to_training_input,timing/fwd_logprobs_values_reward,timing/policy_train,timing/run_training,timing/save_checkpoints,timing/step,timing/sync_weights,timing/train_critic_and_policy,timing/wait_for_generation_buffer,tis/batch_skipped_no_logprobs,tis/skipped_fraction,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
0.0,0,64,512,0,0.0,0,0.0,5654.4453,5353.0026,6587.712,28928,1,4725.7614,1927742.0,72.0,0.9711,0.0,0.0,0.0289,0.7559,0.0008,0.1311,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.2268,-0.0,0.0,1.0,0.0,0.0,88782.2891,63976296.0,0.0,0.9844,0.0147,0.8281,0.7559,12.9979,50.8105,565.9492,34.0,857.9675,292.0183,13.2045,0.0921,6.0133,48.3401,231.647,280.3072,21.3833,1769.7243,22.0313,231.8745,1461.3722,0.0,0.0,1,86,24,192,192,0,0
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 generate/tis/aligned_tokens generate/tis/alignment_fail_count generate/tis/exact_match_fraction generate/tis/lcs_fallback_fraction generate/tis/lcs_fallback_messages generate/tis/unaligned_fraction 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 policy/rollout_train_prob_diff_mean policy/rollout_train_prob_diff_std policy/tis/imp_ratio_capped_fraction policy/tis/imp_ratio_mean policy/tis/log_ratio_abs_mean 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/cleanup_old_checkpoints timing/compute_advantages_and_returns timing/convert_to_training_input timing/fwd_logprobs_values_reward timing/policy_train timing/run_training timing/save_checkpoints timing/step timing/sync_weights timing/train_critic_and_policy timing/wait_for_generation_buffer tis/batch_skipped_no_logprobs tis/skipped_fraction 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
2 0.0 0 64 512 0 0.0 0 0.0 5654.4453 5353.0026 6587.712 28928 1 4725.7614 1927742.0 72.0 0.9711 0.0 0.0 0.0289 0.7559 0.0008 0.1311 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.2268 -0.0 0.0 1.0 0.0 0.0 88782.2891 63976296.0 0.0 0.9844 0.0147 0.8281 0.7559 12.9979 50.8105 565.9492 34.0 857.9675 292.0183 13.2045 0.0921 6.0133 48.3401 231.647 280.3072 21.3833 1769.7243 22.0313 231.8745 1461.3722 0.0 0.0 1 86 24 192 192 0 0