Add parsed training metrics and plots

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+training_logs/20260428_194732_reward_vs_steps.png filter=lfs diff=lfs merge=lfs -text

training_logs/20260428_194732_metrics_a2_rl_methods2test_v2_389761.csv

@@ -0,0 +1,15 @@
+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/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/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,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,timing/save_hf_model,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError
+0.0,0,64,512,0,0.0,0,0.0,5106.7188,0.0,5106.7188,15677,1619,2185.3688,0.0,0.0,0.0,0.0,0.2223,0.0,0.0,1.0,0.0,0.0,0.0,0.0,12.7415,73.1251,378.4116,55.9,857.9687,479.5571,9.9919,0.1715,2.8801,64.354,638.5748,703.3682,43.9261,3427.9835,58.8195,638.8424,2662.9154,0,1,128.0,1024.0,1024.0,0.0,0.0,,,
+0.0,0,64,512,1,1.0,1,1.0,6248.166,18067.5,6155.1004,29410,1270,3915.2344,0.0078,0.013,0.0322,0.0,0.2196,0.0,0.0,1.0,0.0,0.0051,0.0625,0.0078,21.6705,73.6664,367.7108,57.1,857.9687,490.2579,0.0081,0.109,4.6803,86.3502,816.2377,902.993,33.7455,1605.6566,56.3303,816.5334,641.6262,0,2,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,2,2.0,2,1.0,6357.0273,13508.0,6286.5049,30895,1388,3634.7855,0.0098,0.0066,0.0293,0.0,0.2251,0.0,0.0,1.0,0.0,0.0052,0.0469,0.0098,22.7518,73.9107,365.9809,57.3,857.9687,491.9878,0.0166,0.0903,5.0536,93.4424,785.2264,879.1039,27.3005,1867.0723,53.3037,785.5707,929.575,0,3,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,3,3.0,3,1.0,5928.8125,9741.0,5845.1118,26706,1675,3223.1948,0.0215,0.0042,0.0424,-0.0,0.2236,-0.0,0.0,1.0,0.0,0.0074,0.0625,0.0215,22.9205,73.9024,364.6489,57.5,857.9687,493.3198,0.0154,0.1508,4.868,75.1605,731.5847,807.2278,26.1899,1428.4654,52.7378,731.9162,563.5984,0,4,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,4,4.0,4,1.0,6558.0508,15410.1667,6453.085,30435,1300,3858.2506,0.0117,0.0141,0.041,0.0,0.2284,0.0,0.0,1.0,0.0,0.0071,0.0938,0.0117,23.7376,73.9656,360.9219,57.9,857.9687,497.0468,0.008,0.0908,4.971,93.7531,786.2253,880.3861,26.1649,1914.8962,54.5565,786.5418,974.9496,0,5,64.0,512.0,512.0,0.0,0.0,35.8212,,
+0.0,0,64,512,5,5.0,5,1.0,6609.8789,15063.7778,6458.6163,30896,1507,4388.6278,0.0176,0.01,0.0326,-0.0,0.2388,-0.0,0.0,1.0,0.0,0.0084,0.0469,0.0176,24.2419,74.2473,392.2894,54.3,857.9687,465.6793,0.0082,0.0708,5.0922,100.271,864.0489,964.7326,26.8792,1656.5634,55.4512,864.3903,631.2499,0,6,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,6,6.0,6,1.0,8829.9297,10493.4444,8800.165,30133,1968,5819.9374,0.0176,0.0053,0.0299,0.0,0.2372,0.0,0.0,1.0,0.0,0.0089,0.0625,0.0176,24.9465,74.243,378.2344,55.9,857.9687,479.7343,0.0102,0.0628,4.9535,153.7096,1055.2287,1209.3332,26.4602,5335.7441,13.3729,1055.5603,4108.0478,0,7,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,0,0.0,0,0.0,5491.8906,8468.3333,5474.3477,28999,1820,3261.2067,0.0059,0.0039,0.0123,-0.0,0.2489,-0.0,0.0,1.0,0.0,0.0049,0.0312,0.0059,25.0944,74.4175,379.316,55.8,857.9687,478.6526,0.0157,0.0607,4.8477,76.7948,721.2334,798.3999,25.7236,3630.5946,56.2277,721.544,2771.0787,1,8,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,1,1.0,1,1.0,6343.1797,10452.0,6286.2257,30891,1408,4243.3061,0.0137,0.0028,0.0313,0.0,0.2486,0.0,0.0,1.0,0.0,0.0065,0.0469,0.0137,25.2029,74.4615,377.9497,55.9,857.9687,480.019,0.0087,0.0924,5.2423,92.1507,814.3604,906.9465,26.4158,1698.7448,56.7294,814.703,729.796,1,9,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,2,2.0,2,1.0,6764.8047,10670.8333,6718.4881,29024,1341,4289.6832,0.0117,0.0006,0.025,0.0,0.2449,0.0,0.0,1.0,0.0,0.0058,0.0469,0.0117,25.5402,74.7013,373.5664,56.5,857.9687,484.4023,0.0101,0.0663,4.9066,114.4826,847.6325,962.5257,26.1216,1703.1381,53.9314,847.9765,681.7413,1,10,64.0,512.0,512.0,0.0,0.0,37.2556,,
+0.0,0,64,512,3,3.0,3,1.0,7283.125,10248.75,7187.4597,30131,1357,4847.2936,0.0312,0.0114,0.0336,0.0,0.2434,0.0,0.0,1.0,0.0,0.0066,0.0781,0.0312,25.9042,75.0397,367.0552,57.2,857.9687,490.9135,0.0128,0.0774,4.9367,114.9972,927.1765,1042.5931,27.0516,1937.0666,52.1278,927.5181,837.3695,1,11,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,4,4.0,4,1.0,6703.9492,11880.375,6621.7837,31308,1199,4584.4329,0.0156,0.012,0.0335,0.0,0.2502,0.0,0.0,1.0,0.0,0.0075,0.0781,0.0156,26.299,75.373,364.0743,57.6,857.9687,493.8943,0.0095,0.0691,5.2061,118.7788,876.2872,995.4744,26.4564,2048.6953,57.5023,876.6261,990.4704,1,12,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,5,5.0,5,1.0,7421.3887,8208.0,7402.51,31679,1613,5088.3515,0.0234,-0.0009,0.0206,0.0,0.2536,0.0,0.0,1.0,0.0,0.0088,0.0469,0.0234,26.9989,75.3574,359.4052,58.1,857.9687,498.5635,0.0156,0.1003,5.1434,122.1966,933.0476,1055.7212,26.3538,1969.937,56.1204,933.4237,852.9129,1,13,64.0,512.0,510.0,2.0,0.0,,0.03125,2.0
+0.0,0,64,512,6,6.0,6,1.0,10103.3047,13449.3889,9981.3826,31608,1,7042.3661,0.0352,0.0092,0.0285,-0.0,0.2518,-0.0,0.0,1.0,0.0,0.0077,0.0781,0.0352,27.131,75.2998,358.0001,58.3,857.9687,499.9686,0.0099,0.0765,5.3197,177.234,1311.06,1488.7417,28.7896,5674.9191,13.1373,1311.4308,4167.6812,1,14,,,,,,,,

training_logs/20260428_194732_metrics_report.md

@@ -0,0 +1,226 @@
+# SkyRL Training Metrics Analysis
+
+Generated from 1 log files
+
+## Overview
+
+| Log File | Total Steps | Metric Blocks | Final Reward (mean) | Final Reward (max) | Total Time (s) |
+|----------|-------------|---------------|---------------------|-------------------|----------------|
+| a2_rl_methods2test_v2_389761 | 14 | 14 | 0.0159 | 0.0352 | 35899.5 |
+
+## Async Metrics
+
+|                               |       Mean |      Std |   Min |   Max |   Count |
+|:------------------------------|-----------:|---------:|------:|------:|--------:|
+| async/discard_rate            |   0        | 0        |     0 |     0 |      14 |
+| async/discarded_count         |   0        | 0        |     0 |     0 |      14 |
+| async/effective_batch_groups  |  64        | 0        |    64 |    64 |      14 |
+| async/effective_batch_samples | 512        | 0        |   512 |   512 |      14 |
+| async/staleness_max           |   3        | 2.0755   |     0 |     6 |      14 |
+| async/staleness_mean          |   3        | 2.0755   |     0 |     6 |      14 |
+| async/staleness_min           |   3        | 2.0755   |     0 |     6 |      14 |
+| async/staleness_ratio         |   0.857143 | 0.363137 |     0 |     1 |      14 |
+
+## Generate Metrics
+
+|                                      |     Mean |      Std |      Min |      Max |   Count |
+|:-------------------------------------|---------:|---------:|---------:|---------:|--------:|
+| generate/avg_num_tokens              |  6839.3  | 1294.43  |  5106.72 | 10103.3  |      14 |
+| generate/avg_tokens_non_zero_rewards | 11118.7  | 4267.95  |     0    | 18067.5  |      14 |
+| generate/avg_tokens_zero_rewards     |  6769.82 | 1282.35  |  5106.72 |  9981.38 |      14 |
+| generate/max_num_tokens              | 29128    | 4089.32  | 15677    | 31679    |      14 |
+| generate/min_num_tokens              |  1390.43 |  456.423 |     1    |  1968    |      14 |
+| generate/std_num_tokens              |  4313    | 1187.68  |  2185.37 |  7042.37 |      14 |
+
+## Loss Metrics
+
+|                             |       Mean |        Std |     Min |    Max |   Count |
+|:----------------------------|-----------:|-----------:|--------:|-------:|--------:|
+| loss/avg_final_rewards      | 0.0159071  | 0.0095909  |  0      | 0.0352 |      14 |
+| loss/avg_raw_advantages     | 0.00658571 | 0.00505901 | -0.0009 | 0.0141 |      14 |
+| loss/avg_raw_advantages_abs | 0.0280143  | 0.0110504  |  0      | 0.0424 |      14 |
+
+## Policy Metrics
+
+|                            |       Mean |        Std |     Min |    Max |   Count |
+|:---------------------------|-----------:|-----------:|--------:|-------:|--------:|
+| policy/final_loss          | 0          | 0          | -0      | 0      |      14 |
+| policy/policy_entropy      | 0.238314   | 0.0122206  |  0.2196 | 0.2536 |      14 |
+| policy/policy_loss         | 0          | 0          | -0      | 0      |      14 |
+| policy/policy_lr           | 0          | 0          |  0      | 0      |      14 |
+| policy/policy_update_steps | 1          | 0          |  1      | 1      |      14 |
+| policy/ppo_clip_ratio      | 0          | 0          |  0      | 0      |      14 |
+| policy/raw_grad_norm       | 0.00642143 | 0.00227264 |  0      | 0.0089 |      14 |
+
+## Reward Metrics
+
+|                       |      Mean |       Std |   Min |    Max |   Count |
+|:----------------------|----------:|----------:|------:|-------:|--------:|
+| reward/avg_pass_at_8  | 0.0558071 | 0.02351   |     0 | 0.0938 |      14 |
+| reward/avg_raw_reward | 0.0159071 | 0.0095909 |     0 | 0.0352 |      14 |
+
+## System Metrics
+
+|                         |     Mean |         Std |      Min |     Max |   Count |
+|:------------------------|---------:|------------:|---------:|--------:|--------:|
+| system/process_rss_gb   |  23.9415 | 3.60132     |  12.7415 |  27.131 |      14 |
+| system/process_vms_gb   |  74.4079 | 0.682947    |  73.1251 |  75.373 |      14 |
+| system/ram_available_gb | 370.54   | 9.71307     | 358      | 392.289 |      14 |
+| system/ram_percent      |  56.8071 | 1.12828     |  54.3    |  58.3   |      14 |
+| system/ram_total_gb     | 857.969  | 2.35957e-13 | 857.969  | 857.969 |      14 |
+| system/ram_used_gb      | 487.428  | 9.71307     | 465.679  | 499.969 |      14 |
+
+## Timing Metrics
+
+|                                       |        Mean |          Std |       Min |       Max |   Count |
+|:--------------------------------------|------------:|-------------:|----------:|----------:|--------:|
+| timing/cleanup_old_checkpoints        |    0.724336 |    2.66739   |    0.008  |    9.9919 |      14 |
+| timing/compute_advantages_and_returns |    0.09205  |    0.0328869 |    0.0607 |    0.1715 |      14 |
+| timing/convert_to_training_input      |    4.86437  |    0.596808  |    2.8801 |    5.3197 |      14 |
+| timing/fwd_logprobs_values_reward     |  105.977    |   30.8668    |   64.354  |  177.234  |      14 |
+| timing/policy_train                   |  864.852    |  164.394     |  638.575  | 1311.06   |      14 |
+| timing/run_training                   |  971.253    |  194.441     |  703.368  | 1488.74   |      14 |
+| timing/save_checkpoints               |   28.3985   |    4.90702   |   25.7236 |   43.9261 |      14 |
+| timing/step                           | 2564.25     | 1405.59      | 1428.47   | 5674.92   |      14 |
+| timing/sync_weights                   |   49.3106   |   15.388     |   13.1373 |   58.8195 |      14 |
+| timing/train_critic_and_policy        |  865.184    |  164.413     |  638.842  | 1311.43   |      14 |
+| timing/wait_for_generation_buffer     | 1538.79     | 1307.23      |  563.598  | 4167.68   |      14 |
+| timing/save_hf_model                  |   36.5384   |    1.01427   |   35.8212 |   37.2556 |       2 |
+
+## Trainer Metrics
+
+|                     |   Mean |      Std |   Min |   Max |   Count |
+|:--------------------|-------:|---------:|------:|------:|--------:|
+| trainer/epoch       |    0.5 | 0.518875 |     0 |     1 |      14 |
+| trainer/global_step |    7.5 | 4.1833   |     1 |    14 |      14 |
+
+## Batch_Errors Metrics
+
+|                                           |       Mean |      Std |       Min |        Max |   Count |
+|:------------------------------------------|-----------:|---------:|----------:|-----------:|--------:|
+| batch_errors/total_batches                |  68.9231   |  17.7504 |  64       |  128       |      13 |
+| batch_errors/total_instances              | 551.385    | 142.003  | 512       | 1024       |      13 |
+| batch_errors/total_successful             | 551.231    | 142.051  | 510       | 1024       |      13 |
+| batch_errors/total_failed                 |   0.153846 |   0.5547 |   0       |    2       |      13 |
+| batch_errors/total_masked                 |   0        |   0      |   0       |    0       |      13 |
+| batch_errors/avg_AgentSetupTimeoutError   |   0.03125  | nan      |   0.03125 |    0.03125 |       1 |
+| batch_errors/total_AgentSetupTimeoutError |   2        | nan      |   2       |    2       |       1 |
+
+## Training Progression by Log
+
+### a2_rl_methods2test_v2_389761
+
+| Step | Reward | Pass@8 | KL | Loss | Step Time (s) | Gen Wait (s) |
+|------|--------|--------|-----|------|---------------|-------------|
+| 1 | 0.0000 | 0.0000 | 0.000000 | 0.0000 | 3428.0 | 2662.9 |
+| 2 | 0.0078 | 0.0625 | 0.000000 | 0.0000 | 1605.7 | 641.6 |
+| 3 | 0.0098 | 0.0469 | 0.000000 | 0.0000 | 1867.1 | 929.6 |
+| 4 | 0.0215 | 0.0625 | 0.000000 | -0.0000 | 1428.5 | 563.6 |
+| 5 | 0.0117 | 0.0938 | 0.000000 | 0.0000 | 1914.9 | 974.9 |
+| 6 | 0.0176 | 0.0469 | 0.000000 | -0.0000 | 1656.6 | 631.2 |
+| 7 | 0.0176 | 0.0625 | 0.000000 | 0.0000 | 5335.7 | 4108.0 |
+| 8 | 0.0059 | 0.0312 | 0.000000 | -0.0000 | 3630.6 | 2771.1 |
+| 9 | 0.0137 | 0.0469 | 0.000000 | 0.0000 | 1698.7 | 729.8 |
+| 10 | 0.0117 | 0.0469 | 0.000000 | 0.0000 | 1703.1 | 681.7 |
+| 11 | 0.0312 | 0.0781 | 0.000000 | 0.0000 | 1937.1 | 837.4 |
+| 12 | 0.0156 | 0.0781 | 0.000000 | 0.0000 | 2048.7 | 990.5 |
+| 13 | 0.0234 | 0.0469 | 0.000000 | 0.0000 | 1969.9 | 852.9 |
+| 14 | 0.0352 | 0.0781 | 0.000000 | -0.0000 | 5674.9 | 4167.7 |
+
+## Timing Analysis
+
+### Average Time Breakdown (% of step time)
+
+| Component | Avg % of Step Time |
+|-----------|-------------------|
+| wait_for_generation_buffer | 52.9% |
+| run_training | 44.4% |
+| train_critic_and_policy | 39.6% |
+| policy_train | 39.6% |
+| fwd_logprobs_values_reward | 4.8% |
+| sync_weights | 2.5% |
+| save_hf_model | 2.0% |
+| save_checkpoints | 1.3% |
+| convert_to_training_input | 0.2% |
+| cleanup_old_checkpoints | 0.0% |
+| compute_advantages_and_returns | 0.0% |
+
+## vLLM Inference Engine Analysis
+
+Metrics from vLLM stat loggers (V1LoggingStatLoggerFixed).
+
+> **Note**: Ray deduplicates similar log messages with `[repeated Nx across cluster]`,
+> so we typically capture stats from one engine per timestamp. The stats shown are
+> **per-engine** values. Multiply by num_inference_engines for cluster-wide estimates.
+
+### Summary by Log (Per-Engine Stats)
+
+| Log | Avg Running/Engine | Avg Waiting/Engine | Avg Gen Throughput/Engine | Avg KV Cache % | Avg Prefix Hit % |
+|-----|-------------------|-------------------|--------------------------|----------------|------------------|
+| a2_rl_methods2test_v2_389761 | 3.5 | 0.0 | 67.8 tok/s | 6.8% | 87.8% |
+
+### Utilization Analysis (Per-Engine)
+
+Key indicators of inference engine utilization:
+
+- **Running requests/engine**: Concurrent requests being processed by each engine
+- **Waiting requests**: Requests queued (0 = engine not saturated, has spare capacity)
+- **Generation throughput**: Decode tokens/sec per engine
+  - 8B model on H100 can do **1000+ tok/s** when saturated
+  - If seeing <300 tok/s with 0 waiting, engine is **starved for requests**
+
+#### a2_rl_methods2test_v2_389761
+
+- **Running requests/engine**: avg=3.5, max=16
+- **Waiting requests**: avg=0.0, max=0
+- **Generation throughput/engine**: avg=67.8 tok/s, max=282.6 tok/s
+- **KV cache usage**: avg=6.8%
+- **Prefix cache hit rate**: avg=87.8%
+- ⚠️ **Underutilized**: Engines starved for requests (0 waiting, avg 3.5 running)
+  - Bottleneck is likely upstream (environment execution, not inference)
+
+## Trial-Level Analysis (from result.json)
+
+Total trials parsed: 7168
+
+### Turn Count Statistics
+
+| Metric | Value |
+|--------|-------|
+| Mean | 4.9 |
+| Median | 4.0 |
+| Std | 3.4 |
+| Min | 2 |
+| Max | 46 |
+| Count | 7166 |
+
+### Exception Distribution
+
+| Exception Type | Count | % |
+|---------------|-------|---|
+| No exception | 7139 | 99.6% |
+| ContextLengthExceededError | 18 | 0.3% |
+| AgentTimeoutError | 9 | 0.1% |
+| AgentSetupTimeoutError | 2 | 0.0% |
+
+### Turn Count by Exception Type
+
+| Exception Type | Mean Turns | Median Turns | Count |
+|---------------|-----------|-------------|-------|
+| ContextLengthExceededError | 22.7 | 19.0 | 18 |
+| AgentTimeoutError | 16.7 | 15.0 | 9 |
+| No exception | 4.8 | 4.0 | 7139 |
+
+### Turn Count by Outcome
+
+| Outcome | Mean Turns | Median Turns | Count |
+|---------|-----------|-------------|-------|
+| Success | 6.2 | 6.0 | 114 |
+| Failure | 4.9 | 4.0 | 7052 |
+
+### Reward Summary
+
+- Mean reward: 0.0159
+- Success rate: 1.6%
+- Trials with reward data: 7166
+

training_logs/20260428_194732_metrics_table.csv

@@ -0,0 +1,15 @@
+log_file,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/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/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,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,timing/save_hf_model,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError,global_step
+a2_rl_methods2test_v2_389761,0.0,0,64,512,0,0.0,0,0.0,5106.7188,0.0,5106.7188,15677,1619,2185.3688,0.0,0.0,0.0,0.0,0.2223,0.0,0.0,1.0,0.0,0.0,0.0,0.0,12.7415,73.1251,378.4116,55.9,857.9687,479.5571,9.9919,0.1715,2.8801,64.354,638.5748,703.3682,43.9261,3427.9835,58.8195,638.8424,2662.9154,0,1,128.0,1024.0,1024.0,0.0,0.0,,,,1
+a2_rl_methods2test_v2_389761,0.0,0,64,512,1,1.0,1,1.0,6248.166,18067.5,6155.1004,29410,1270,3915.2344,0.0078,0.013,0.0322,0.0,0.2196,0.0,0.0,1.0,0.0,0.0051,0.0625,0.0078,21.6705,73.6664,367.7108,57.1,857.9687,490.2579,0.0081,0.109,4.6803,86.3502,816.2377,902.993,33.7455,1605.6566,56.3303,816.5334,641.6262,0,2,64.0,512.0,512.0,0.0,0.0,,,,2
+a2_rl_methods2test_v2_389761,0.0,0,64,512,2,2.0,2,1.0,6357.0273,13508.0,6286.5049,30895,1388,3634.7855,0.0098,0.0066,0.0293,0.0,0.2251,0.0,0.0,1.0,0.0,0.0052,0.0469,0.0098,22.7518,73.9107,365.9809,57.3,857.9687,491.9878,0.0166,0.0903,5.0536,93.4424,785.2264,879.1039,27.3005,1867.0723,53.3037,785.5707,929.575,0,3,64.0,512.0,512.0,0.0,0.0,,,,3
+a2_rl_methods2test_v2_389761,0.0,0,64,512,3,3.0,3,1.0,5928.8125,9741.0,5845.1118,26706,1675,3223.1948,0.0215,0.0042,0.0424,-0.0,0.2236,-0.0,0.0,1.0,0.0,0.0074,0.0625,0.0215,22.9205,73.9024,364.6489,57.5,857.9687,493.3198,0.0154,0.1508,4.868,75.1605,731.5847,807.2278,26.1899,1428.4654,52.7378,731.9162,563.5984,0,4,64.0,512.0,512.0,0.0,0.0,,,,4
+a2_rl_methods2test_v2_389761,0.0,0,64,512,4,4.0,4,1.0,6558.0508,15410.1667,6453.085,30435,1300,3858.2506,0.0117,0.0141,0.041,0.0,0.2284,0.0,0.0,1.0,0.0,0.0071,0.0938,0.0117,23.7376,73.9656,360.9219,57.9,857.9687,497.0468,0.008,0.0908,4.971,93.7531,786.2253,880.3861,26.1649,1914.8962,54.5565,786.5418,974.9496,0,5,64.0,512.0,512.0,0.0,0.0,35.8212,,,5
+a2_rl_methods2test_v2_389761,0.0,0,64,512,5,5.0,5,1.0,6609.8789,15063.7778,6458.6163,30896,1507,4388.6278,0.0176,0.01,0.0326,-0.0,0.2388,-0.0,0.0,1.0,0.0,0.0084,0.0469,0.0176,24.2419,74.2473,392.2894,54.3,857.9687,465.6793,0.0082,0.0708,5.0922,100.271,864.0489,964.7326,26.8792,1656.5634,55.4512,864.3903,631.2499,0,6,64.0,512.0,512.0,0.0,0.0,,,,6
+a2_rl_methods2test_v2_389761,0.0,0,64,512,6,6.0,6,1.0,8829.9297,10493.4444,8800.165,30133,1968,5819.9374,0.0176,0.0053,0.0299,0.0,0.2372,0.0,0.0,1.0,0.0,0.0089,0.0625,0.0176,24.9465,74.243,378.2344,55.9,857.9687,479.7343,0.0102,0.0628,4.9535,153.7096,1055.2287,1209.3332,26.4602,5335.7441,13.3729,1055.5603,4108.0478,0,7,64.0,512.0,512.0,0.0,0.0,,,,7
+a2_rl_methods2test_v2_389761,0.0,0,64,512,0,0.0,0,0.0,5491.8906,8468.3333,5474.3477,28999,1820,3261.2067,0.0059,0.0039,0.0123,-0.0,0.2489,-0.0,0.0,1.0,0.0,0.0049,0.0312,0.0059,25.0944,74.4175,379.316,55.8,857.9687,478.6526,0.0157,0.0607,4.8477,76.7948,721.2334,798.3999,25.7236,3630.5946,56.2277,721.544,2771.0787,1,8,64.0,512.0,512.0,0.0,0.0,,,,8
+a2_rl_methods2test_v2_389761,0.0,0,64,512,1,1.0,1,1.0,6343.1797,10452.0,6286.2257,30891,1408,4243.3061,0.0137,0.0028,0.0313,0.0,0.2486,0.0,0.0,1.0,0.0,0.0065,0.0469,0.0137,25.2029,74.4615,377.9497,55.9,857.9687,480.019,0.0087,0.0924,5.2423,92.1507,814.3604,906.9465,26.4158,1698.7448,56.7294,814.703,729.796,1,9,64.0,512.0,512.0,0.0,0.0,,,,9
+a2_rl_methods2test_v2_389761,0.0,0,64,512,2,2.0,2,1.0,6764.8047,10670.8333,6718.4881,29024,1341,4289.6832,0.0117,0.0006,0.025,0.0,0.2449,0.0,0.0,1.0,0.0,0.0058,0.0469,0.0117,25.5402,74.7013,373.5664,56.5,857.9687,484.4023,0.0101,0.0663,4.9066,114.4826,847.6325,962.5257,26.1216,1703.1381,53.9314,847.9765,681.7413,1,10,64.0,512.0,512.0,0.0,0.0,37.2556,,,10
+a2_rl_methods2test_v2_389761,0.0,0,64,512,3,3.0,3,1.0,7283.125,10248.75,7187.4597,30131,1357,4847.2936,0.0312,0.0114,0.0336,0.0,0.2434,0.0,0.0,1.0,0.0,0.0066,0.0781,0.0312,25.9042,75.0397,367.0552,57.2,857.9687,490.9135,0.0128,0.0774,4.9367,114.9972,927.1765,1042.5931,27.0516,1937.0666,52.1278,927.5181,837.3695,1,11,64.0,512.0,512.0,0.0,0.0,,,,11
+a2_rl_methods2test_v2_389761,0.0,0,64,512,4,4.0,4,1.0,6703.9492,11880.375,6621.7837,31308,1199,4584.4329,0.0156,0.012,0.0335,0.0,0.2502,0.0,0.0,1.0,0.0,0.0075,0.0781,0.0156,26.299,75.373,364.0743,57.6,857.9687,493.8943,0.0095,0.0691,5.2061,118.7788,876.2872,995.4744,26.4564,2048.6953,57.5023,876.6261,990.4704,1,12,64.0,512.0,512.0,0.0,0.0,,,,12
+a2_rl_methods2test_v2_389761,0.0,0,64,512,5,5.0,5,1.0,7421.3887,8208.0,7402.51,31679,1613,5088.3515,0.0234,-0.0009,0.0206,0.0,0.2536,0.0,0.0,1.0,0.0,0.0088,0.0469,0.0234,26.9989,75.3574,359.4052,58.1,857.9687,498.5635,0.0156,0.1003,5.1434,122.1966,933.0476,1055.7212,26.3538,1969.937,56.1204,933.4237,852.9129,1,13,64.0,512.0,510.0,2.0,0.0,,0.03125,2.0,13
+a2_rl_methods2test_v2_389761,0.0,0,64,512,6,6.0,6,1.0,10103.3047,13449.3889,9981.3826,31608,1,7042.3661,0.0352,0.0092,0.0285,-0.0,0.2518,-0.0,0.0,1.0,0.0,0.0077,0.0781,0.0352,27.131,75.2998,358.0001,58.3,857.9687,499.9686,0.0099,0.0765,5.3197,177.234,1311.06,1488.7417,28.7896,5674.9191,13.1373,1311.4308,4167.6812,1,14,,,,,,,,,14