Add files using upload-large-folder tool

.gitattributes

@@ -34,3 +34,5 @@ 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/20260427_180636_reward_vs_steps.png filter=lfs diff=lfs merge=lfs -text
+training_logs/a2-rl-stack_jest_v2_388828.out filter=lfs diff=lfs merge=lfs -text

training_logs/20260427_180636_metrics_a2-rl-stack_jest_v2_388828.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,batch_errors/avg_VerifierRuntimeError,batch_errors/total_VerifierRuntimeError,timing/save_hf_model
+0.0,0,64,512,0,0.0,0,0.0,4662.2324,4028.125,4693.418,19909,1041,2498.6082,0.0469,0.0,0.0,0.0,0.197,0.0,0.0,1.0,0.0,0.0,0.0469,0.0469,15.8079,73.3613,349.227,59.3,857.9687,508.7417,8.3123,0.0911,3.8976,78.9876,674.5257,753.8845,52.0858,3548.2087,53.7378,674.8055,2736.6885,0,1,128.0,1024.0,1024.0,0.0,0.0,,,
+0.0,0,64,512,1,1.0,1,1.0,6064.8848,3838.1212,6218.2944,24241,1179,3490.2217,0.0645,-0.0014,0.01,-0.0,0.2042,-0.0,0.0,1.0,0.0,0.0112,0.0781,0.0645,18.9903,73.5099,384.7603,55.2,857.9687,473.2084,0.0094,0.0789,4.12,87.6227,757.9733,846.0369,52.3647,2579.1726,54.0587,758.335,1674.935,0,2,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,2,2.0,2,1.0,5474.791,5108.55,5542.6134,20121,1267,3050.0682,0.1562,0.0,0.0,0.0,0.1968,0.0,0.0,1.0,0.0,0.0,0.1562,0.1562,19.3334,73.7449,368.8224,57.0,857.9687,489.1463,0.0073,0.046,3.6227,82.308,744.5498,827.2625,53.8506,1382.7589,53.8402,744.9082,498.0035,0,3,64.0,512.0,510.0,1.0,0.0,0.03125,2.0,
+0.0,0,64,512,3,3.0,3,1.0,5699.1973,3966.5185,5903.4869,23161,1,3770.7162,0.1055,0.0008,0.0051,0.0,0.1887,0.0,0.0,1.0,0.0,0.0067,0.1094,0.1055,19.666,73.957,363.7578,57.6,857.9687,494.2109,0.0071,0.083,3.9571,102.5779,806.9924,909.9862,52.7547,1728.7174,55.8091,807.3251,758.9374,0,4,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,4,4.0,4,1.0,5744.0078,6146.575,5709.8919,25696,1344,3513.2835,0.0781,0.0,0.0,0.0,0.1856,0.0,0.0,1.0,0.0,0.0,0.0781,0.0781,21.2582,74.2703,362.1384,57.8,857.9687,495.8303,0.0112,0.0602,4.4491,86.3703,782.6672,869.4493,53.9546,1540.5181,53.4133,783.0185,613.1685,0,5,64.0,512.0,512.0,0.0,0.0,,,37.877
+0.0,0,64,512,5,5.0,5,1.0,6107.5117,4430.6042,6280.9849,22958,1479,3691.5944,0.0938,0.0,0.0,0.0,0.1853,0.0,0.0,1.0,0.0,0.0,0.0938,0.0938,21.3301,74.3124,356.7458,58.4,857.9687,501.2229,0.0087,0.0515,4.6763,106.7279,820.4237,927.5826,52.5039,1456.9998,50.9701,820.8028,473.7404,0,6,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,6,6.0,6,1.0,7806.5371,4340.1667,7977.0143,30825,988,6175.2351,0.0469,0.0,0.0,0.0,0.1842,0.0,0.0,1.0,0.0,0.0,0.0469,0.0469,25.509,74.6829,381.4424,55.5,857.9687,476.5263,0.0124,0.1095,5.0382,186.7453,1098.6498,1286.0848,52.0406,6616.2683,12.4455,1099.2296,5312.6625,0,7,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,0,0.0,0,0.0,4898.9766,4360.25,4925.4713,16910,978,2678.3845,0.0469,0.0,0.0,0.0,0.1733,0.0,0.0,1.0,0.0,0.0,0.0469,0.0469,25.4579,74.6854,390.0168,54.5,857.9687,467.9518,0.0079,0.0447,3.1642,82.9256,676.4665,759.7588,52.5991,4268.5747,53.762,676.7881,3451.851,1,8,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,1,1.0,1,1.0,5547.7832,4123.2174,5769.6682,20143,1399,3225.9525,0.1348,0.0003,0.0054,-0.0,0.178,-0.0,0.0,1.0,0.0,0.01,0.1406,0.1348,25.6384,74.7434,390.2228,54.5,857.9687,467.7458,0.0088,0.0466,3.8325,85.8132,723.6436,809.8543,52.6413,1858.802,53.523,723.9942,991.5653,1,9,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,2,2.0,2,1.0,5534.4395,4362.7857,5678.3268,18891,1200,3017.3224,0.1094,0.0,0.0,0.0,0.179,0.0,0.0,1.0,0.0,0.0,0.1094,0.1094,25.8958,74.9708,411.3132,52.1,857.9687,446.6555,0.0087,0.0435,3.3808,81.611,702.3105,784.3806,52.7175,1563.2701,51.7063,702.7258,723.772,1,10,64.0,512.0,512.0,0.0,0.0,,,36.9492
+0.0,0,64,512,3,3.0,3,1.0,6088.8008,4722.359,6201.4672,19902,1146,3677.7865,0.0762,0.0003,0.0028,-0.0,0.1789,-0.0,0.0,1.0,0.0,0.0043,0.0781,0.0762,25.9409,74.9533,400.013,53.4,857.9687,457.9557,0.0078,0.0472,3.8067,98.8787,806.3553,905.6134,53.8827,1793.5863,52.8772,806.6871,831.2583,1,11,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,4,4.0,4,1.0,5448.5254,5549.35,5439.9809,21237,1272,3397.5694,0.0781,0.0,0.0,0.0,0.1734,0.0,0.0,1.0,0.0,0.0,0.0781,0.0781,26.3522,75.2733,393.5605,54.1,857.9687,464.4082,0.0076,0.0491,3.8599,82.5733,764.0154,847.0158,53.3604,1808.5047,52.2366,764.393,905.3587,1,12,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,5,5.0,5,1.0,6116.7676,4422.8214,6324.7961,22128,1347,3878.4717,0.1094,0.0,0.0,0.0,0.1796,0.0,0.0,1.0,0.0,0.0,0.1094,0.1094,26.7385,75.5441,390.6353,54.5,857.9687,467.3334,0.0078,0.0509,3.931,90.8837,796.749,888.0035,52.3352,1472.4338,52.5954,797.0685,527.8742,1,13,64.0,512.0,512.0,0.0,0.0,,,
+0.0,0,64,512,6,6.0,6,1.0,8099.6328,6103.6087,8193.5153,30165,1466,6102.5258,0.0449,0.0005,0.0028,-0.0,0.1791,-0.0,0.0,1.0,0.0,0.0035,0.0469,0.0449,27.2599,75.8359,386.1821,55.0,857.9687,471.7866,0.0095,0.08,5.3075,198.1348,1094.446,1292.9979,52.0547,6381.7149,12.5196,1094.7827,5070.8578,1,14,,,,,,,,

training_logs/20260427_180636_metrics_report.md

@@ -0,0 +1,227 @@
+# 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-stack_jest_v2_388828 | 14 | 14 | 0.0851 | 0.1562 | 37999.5 |
+
+## 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              |  5949.58 |  954.053 |  4662.23 |  8099.63 |      14 |
+| generate/avg_tokens_non_zero_rewards |  4678.79 |  760.473 |  3838.12 |  6146.57 |      14 |
+| generate/avg_tokens_zero_rewards     |  6061.35 |  983.506 |  4693.42 |  8193.52 |      14 |
+| generate/max_num_tokens              | 22591.9  | 4043.19  | 16910    | 30825    |      14 |
+| generate/min_num_tokens              |  1150.5  |  368.613 |     1    |  1479    |      14 |
+| generate/std_num_tokens              |  3726.27 | 1098.85  |  2498.61 |  6175.24 |      14 |
+
+## Loss Metrics
+
+|                             |        Mean |         Std |     Min |    Max |   Count |
+|:----------------------------|------------:|------------:|--------:|-------:|--------:|
+| loss/avg_final_rewards      | 0.0851143   | 0.0348551   |  0.0449 | 0.1562 |      14 |
+| loss/avg_raw_advantages     | 3.57143e-05 | 0.000481356 | -0.0014 | 0.0008 |      14 |
+| loss/avg_raw_advantages_abs | 0.00186429  | 0.00306584  |  0      | 0.01   |      14 |
+
+## Policy Metrics
+
+|                            |     Mean |        Std |     Min |    Max |   Count |
+|:---------------------------|---------:|-----------:|--------:|-------:|--------:|
+| policy/final_loss          | 0        | 0          | -0      | 0      |      14 |
+| policy/policy_entropy      | 0.184507 | 0.00928559 |  0.1733 | 0.2042 |      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       | 0.00255  | 0.00401952 |  0      | 0.0112 |      14 |
+
+## Reward Metrics
+
+|                       |      Mean |       Std |    Min |    Max |   Count |
+|:----------------------|----------:|----------:|-------:|-------:|--------:|
+| reward/avg_pass_at_8  | 0.0870571 | 0.0350406 | 0.0469 | 0.1562 |      14 |
+| reward/avg_raw_reward | 0.0851143 | 0.0348551 | 0.0449 | 0.1562 |      14 |
+
+## System Metrics
+
+|                         |     Mean |          Std |      Min |      Max |   Count |
+|:------------------------|---------:|-------------:|---------:|---------:|--------:|
+| system/process_rss_gb   |  23.227  |  3.69154     |  15.8079 |  27.2599 |      14 |
+| system/process_vms_gb   |  74.5603 |  0.744513    |  73.3613 |  75.8359 |      14 |
+| system/ram_available_gb | 380.631  | 17.8364      | 349.227  | 411.313  |      14 |
+| system/ram_percent      |  55.6357 |  2.07201     |  52.1    |  59.3    |      14 |
+| system/ram_total_gb     | 857.969  |  2.35957e-13 | 857.969  | 857.969  |      14 |
+| system/ram_used_gb      | 477.337  | 17.8364      | 446.656  | 508.742  |      14 |
+
+## Timing Metrics
+
+|                                       |         Mean |          Std |       Min |       Max |   Count |
+|:--------------------------------------|-------------:|-------------:|----------:|----------:|--------:|
+| timing/cleanup_old_checkpoints        |    0.601893  |    2.21921   |    0.0071 |    8.3123 |      14 |
+| timing/compute_advantages_and_returns |    0.0630143 |    0.0212967 |    0.0435 |    0.1095 |      14 |
+| timing/convert_to_training_input      |    4.07454   |    0.601892  |    3.1642 |    5.3075 |      14 |
+| timing/fwd_logprobs_values_reward     |  103.726     |   38.5559    |   78.9876 |  198.135  |      14 |
+| timing/policy_train                   |  803.555     |  132.736     |  674.526  | 1098.65   |      14 |
+| timing/run_training                   |  907.708     |  170.557     |  753.885  | 1293      |      14 |
+| timing/save_checkpoints               |   52.7961    |    0.686843  |   52.0406 |   53.9546 |      14 |
+| timing/step                           | 2714.25      | 1813.94      | 1382.76   | 6616.27   |      14 |
+| timing/sync_weights                   |   47.3925    |   14.8349    |   12.4455 |   55.8091 |      14 |
+| timing/train_critic_and_policy        |  803.919     |  132.775     |  674.806  | 1099.23   |      14 |
+| timing/wait_for_generation_buffer     | 1755.05      | 1703.98      |  473.74   | 5312.66   |      14 |
+| timing/save_hf_model                  |   37.4131    |    0.656054  |   36.9492 |   37.877  |       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               |   0.0769231 |   0.27735 |   0       |    1       |      13 |
+| batch_errors/total_masked               |   0         |   0       |   0       |    0       |      13 |
+| batch_errors/avg_VerifierRuntimeError   |   0.03125   | nan       |   0.03125 |    0.03125 |       1 |
+| batch_errors/total_VerifierRuntimeError |   2         | nan       |   2       |    2       |       1 |
+
+## Training Progression by Log
+
+### a2-rl-stack_jest_v2_388828
+
+| Step | Reward | Pass@8 | KL | Loss | Step Time (s) | Gen Wait (s) |
+|------|--------|--------|-----|------|---------------|-------------|
+| 1 | 0.0469 | 0.0469 | 0.000000 | 0.0000 | 3548.2 | 2736.7 |
+| 2 | 0.0645 | 0.0781 | 0.000000 | -0.0000 | 2579.2 | 1674.9 |
+| 3 | 0.1562 | 0.1562 | 0.000000 | 0.0000 | 1382.8 | 498.0 |
+| 4 | 0.1055 | 0.1094 | 0.000000 | 0.0000 | 1728.7 | 758.9 |
+| 5 | 0.0781 | 0.0781 | 0.000000 | 0.0000 | 1540.5 | 613.2 |
+| 6 | 0.0938 | 0.0938 | 0.000000 | 0.0000 | 1457.0 | 473.7 |
+| 7 | 0.0469 | 0.0469 | 0.000000 | 0.0000 | 6616.3 | 5312.7 |
+| 8 | 0.0469 | 0.0469 | 0.000000 | 0.0000 | 4268.6 | 3451.9 |
+| 9 | 0.1348 | 0.1406 | 0.000000 | -0.0000 | 1858.8 | 991.6 |
+| 10 | 0.1094 | 0.1094 | 0.000000 | 0.0000 | 1563.3 | 723.8 |
+| 11 | 0.0762 | 0.0781 | 0.000000 | -0.0000 | 1793.6 | 831.3 |
+| 12 | 0.0781 | 0.0781 | 0.000000 | 0.0000 | 1808.5 | 905.4 |
+| 13 | 0.1094 | 0.1094 | 0.000000 | 0.0000 | 1472.4 | 527.9 |
+| 14 | 0.0449 | 0.0469 | 0.000000 | -0.0000 | 6381.7 | 5070.9 |
+
+## Timing Analysis
+
+### Average Time Breakdown (% of step time)
+
+| Component | Avg % of Step Time |
+|-----------|-------------------|
+| wait_for_generation_buffer | 54.8% |
+| run_training | 42.5% |
+| train_critic_and_policy | 37.9% |
+| policy_train | 37.9% |
+| fwd_logprobs_values_reward | 4.6% |
+| save_checkpoints | 2.6% |
+| sync_weights | 2.5% |
+| save_hf_model | 2.4% |
+| 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-stack_jest_v2_388828 | 3.5 | 0.0 | 71.1 tok/s | 7.5% | 88.4% |
+
+### 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-stack_jest_v2_388828
+
+- **Running requests/engine**: avg=3.5, max=15
+- **Waiting requests**: avg=0.0, max=0
+- **Generation throughput/engine**: avg=71.1 tok/s, max=327.9 tok/s
+- **KV cache usage**: avg=7.5%
+- **Prefix cache hit rate**: avg=88.4%
+- ⚠️ **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 | 3.2 |
+| Median | 2.0 |
+| Std | 2.4 |
+| Min | 2 |
+| Max | 34 |
+| Count | 7168 |
+
+### Exception Distribution
+
+| Exception Type | Count | % |
+|---------------|-------|---|
+| No exception | 7098 | 99.0% |
+| ContextLengthExceededError | 38 | 0.5% |
+| AgentTimeoutError | 30 | 0.4% |
+| VerifierRuntimeError | 2 | 0.0% |
+
+### Turn Count by Exception Type
+
+| Exception Type | Mean Turns | Median Turns | Count |
+|---------------|-----------|-------------|-------|
+| ContextLengthExceededError | 19.6 | 19.0 | 38 |
+| AgentTimeoutError | 13.7 | 12.0 | 30 |
+| No exception | 3.1 | 2.0 | 7098 |
+| VerifierRuntimeError | 2.0 | 2.0 | 2 |
+
+### Turn Count by Outcome
+
+| Outcome | Mean Turns | Median Turns | Count |
+|---------|-----------|-------------|-------|
+| Success | 2.6 | 2.0 | 610 |
+| Failure | 3.3 | 2.0 | 6556 |
+
+### Reward Summary
+
+- Mean reward: 0.0851
+- Success rate: 8.5%
+- Trials with reward data: 7166
+

training_logs/20260427_180636_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,batch_errors/avg_VerifierRuntimeError,batch_errors/total_VerifierRuntimeError,timing/save_hf_model,global_step
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,0,0.0,0,0.0,4662.2324,4028.125,4693.418,19909,1041,2498.6082,0.0469,0.0,0.0,0.0,0.197,0.0,0.0,1.0,0.0,0.0,0.0469,0.0469,15.8079,73.3613,349.227,59.3,857.9687,508.7417,8.3123,0.0911,3.8976,78.9876,674.5257,753.8845,52.0858,3548.2087,53.7378,674.8055,2736.6885,0,1,128.0,1024.0,1024.0,0.0,0.0,,,,1
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,1,1.0,1,1.0,6064.8848,3838.1212,6218.2944,24241,1179,3490.2217,0.0645,-0.0014,0.01,-0.0,0.2042,-0.0,0.0,1.0,0.0,0.0112,0.0781,0.0645,18.9903,73.5099,384.7603,55.2,857.9687,473.2084,0.0094,0.0789,4.12,87.6227,757.9733,846.0369,52.3647,2579.1726,54.0587,758.335,1674.935,0,2,64.0,512.0,512.0,0.0,0.0,,,,2
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,2,2.0,2,1.0,5474.791,5108.55,5542.6134,20121,1267,3050.0682,0.1562,0.0,0.0,0.0,0.1968,0.0,0.0,1.0,0.0,0.0,0.1562,0.1562,19.3334,73.7449,368.8224,57.0,857.9687,489.1463,0.0073,0.046,3.6227,82.308,744.5498,827.2625,53.8506,1382.7589,53.8402,744.9082,498.0035,0,3,64.0,512.0,510.0,1.0,0.0,0.03125,2.0,,3
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,3,3.0,3,1.0,5699.1973,3966.5185,5903.4869,23161,1,3770.7162,0.1055,0.0008,0.0051,0.0,0.1887,0.0,0.0,1.0,0.0,0.0067,0.1094,0.1055,19.666,73.957,363.7578,57.6,857.9687,494.2109,0.0071,0.083,3.9571,102.5779,806.9924,909.9862,52.7547,1728.7174,55.8091,807.3251,758.9374,0,4,64.0,512.0,512.0,0.0,0.0,,,,4
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,4,4.0,4,1.0,5744.0078,6146.575,5709.8919,25696,1344,3513.2835,0.0781,0.0,0.0,0.0,0.1856,0.0,0.0,1.0,0.0,0.0,0.0781,0.0781,21.2582,74.2703,362.1384,57.8,857.9687,495.8303,0.0112,0.0602,4.4491,86.3703,782.6672,869.4493,53.9546,1540.5181,53.4133,783.0185,613.1685,0,5,64.0,512.0,512.0,0.0,0.0,,,37.877,5
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,5,5.0,5,1.0,6107.5117,4430.6042,6280.9849,22958,1479,3691.5944,0.0938,0.0,0.0,0.0,0.1853,0.0,0.0,1.0,0.0,0.0,0.0938,0.0938,21.3301,74.3124,356.7458,58.4,857.9687,501.2229,0.0087,0.0515,4.6763,106.7279,820.4237,927.5826,52.5039,1456.9998,50.9701,820.8028,473.7404,0,6,64.0,512.0,512.0,0.0,0.0,,,,6
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,6,6.0,6,1.0,7806.5371,4340.1667,7977.0143,30825,988,6175.2351,0.0469,0.0,0.0,0.0,0.1842,0.0,0.0,1.0,0.0,0.0,0.0469,0.0469,25.509,74.6829,381.4424,55.5,857.9687,476.5263,0.0124,0.1095,5.0382,186.7453,1098.6498,1286.0848,52.0406,6616.2683,12.4455,1099.2296,5312.6625,0,7,64.0,512.0,512.0,0.0,0.0,,,,7
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,0,0.0,0,0.0,4898.9766,4360.25,4925.4713,16910,978,2678.3845,0.0469,0.0,0.0,0.0,0.1733,0.0,0.0,1.0,0.0,0.0,0.0469,0.0469,25.4579,74.6854,390.0168,54.5,857.9687,467.9518,0.0079,0.0447,3.1642,82.9256,676.4665,759.7588,52.5991,4268.5747,53.762,676.7881,3451.851,1,8,64.0,512.0,512.0,0.0,0.0,,,,8
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,1,1.0,1,1.0,5547.7832,4123.2174,5769.6682,20143,1399,3225.9525,0.1348,0.0003,0.0054,-0.0,0.178,-0.0,0.0,1.0,0.0,0.01,0.1406,0.1348,25.6384,74.7434,390.2228,54.5,857.9687,467.7458,0.0088,0.0466,3.8325,85.8132,723.6436,809.8543,52.6413,1858.802,53.523,723.9942,991.5653,1,9,64.0,512.0,512.0,0.0,0.0,,,,9
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,2,2.0,2,1.0,5534.4395,4362.7857,5678.3268,18891,1200,3017.3224,0.1094,0.0,0.0,0.0,0.179,0.0,0.0,1.0,0.0,0.0,0.1094,0.1094,25.8958,74.9708,411.3132,52.1,857.9687,446.6555,0.0087,0.0435,3.3808,81.611,702.3105,784.3806,52.7175,1563.2701,51.7063,702.7258,723.772,1,10,64.0,512.0,512.0,0.0,0.0,,,36.9492,10
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,3,3.0,3,1.0,6088.8008,4722.359,6201.4672,19902,1146,3677.7865,0.0762,0.0003,0.0028,-0.0,0.1789,-0.0,0.0,1.0,0.0,0.0043,0.0781,0.0762,25.9409,74.9533,400.013,53.4,857.9687,457.9557,0.0078,0.0472,3.8067,98.8787,806.3553,905.6134,53.8827,1793.5863,52.8772,806.6871,831.2583,1,11,64.0,512.0,512.0,0.0,0.0,,,,11
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,4,4.0,4,1.0,5448.5254,5549.35,5439.9809,21237,1272,3397.5694,0.0781,0.0,0.0,0.0,0.1734,0.0,0.0,1.0,0.0,0.0,0.0781,0.0781,26.3522,75.2733,393.5605,54.1,857.9687,464.4082,0.0076,0.0491,3.8599,82.5733,764.0154,847.0158,53.3604,1808.5047,52.2366,764.393,905.3587,1,12,64.0,512.0,512.0,0.0,0.0,,,,12
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,5,5.0,5,1.0,6116.7676,4422.8214,6324.7961,22128,1347,3878.4717,0.1094,0.0,0.0,0.0,0.1796,0.0,0.0,1.0,0.0,0.0,0.1094,0.1094,26.7385,75.5441,390.6353,54.5,857.9687,467.3334,0.0078,0.0509,3.931,90.8837,796.749,888.0035,52.3352,1472.4338,52.5954,797.0685,527.8742,1,13,64.0,512.0,512.0,0.0,0.0,,,,13
+a2-rl-stack_jest_v2_388828,0.0,0,64,512,6,6.0,6,1.0,8099.6328,6103.6087,8193.5153,30165,1466,6102.5258,0.0449,0.0005,0.0028,-0.0,0.1791,-0.0,0.0,1.0,0.0,0.0035,0.0469,0.0449,27.2599,75.8359,386.1821,55.0,857.9687,471.7866,0.0095,0.08,5.3075,198.1348,1094.446,1292.9979,52.0547,6381.7149,12.5196,1094.7827,5070.8578,1,14,,,,,,,,,14

training_logs/a2-rl-stack_jest_v2_388828.out

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b505562f5352302ac6b7da64448b7eb101f46caacd98cef211b4195ff7b21ea9
+size 20237247