rirv938-anthropic-grpo-4_3092

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-4_3092_v3

model_name: rirv938-anthropic-grpo-4_3092_v3

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-04-29T19:58:05+00:00

num_battles: 9621

num_wins: 5174

celo_rating: 1323.23

family_friendly_score: 0.5626

family_friendly_standard_error: 0.0070154292812343285

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp888_95ff_merged

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6422579454394947, 'latency_mean': 1.5569312930107118, 'latency_p50': 1.5642329454421997, 'latency_p90': 1.7209858417510986}, {'batch_size': 3, 'throughput': 1.210176258961488, 'latency_mean': 2.470249184370041, 'latency_p50': 2.473474860191345, 'latency_p90': 2.7446171045303345}, {'batch_size': 5, 'throughput': 1.504345520065071, 'latency_mean': 3.3026544678211214, 'latency_p50': 3.300721526145935, 'latency_p90': 3.6747738122940063}, {'batch_size': 6, 'throughput': 1.5838159875757019, 'latency_mean': 3.7541436648368833, 'latency_p50': 3.7602022886276245, 'latency_p90': 4.242688155174255}, {'batch_size': 8, 'throughput': 1.6617413381295356, 'latency_mean': 4.773371133804321, 'latency_p50': 4.830794930458069, 'latency_p90': 5.301456904411316}, {'batch_size': 10, 'throughput': 1.7062082516367536, 'latency_mean': 5.820464843511582, 'latency_p50': 5.865260124206543, 'latency_p90': 6.506855440139771}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-4_3092_v3

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp888_95ff_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.59

us_pacific_date: 2025-04-29

win_ratio: 0.5377819353497557

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:', '###', '</s>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rirv938-anthropic-grpo-4-3092-v3-mkmlizer
Waiting for job on rirv938-anthropic-grpo-4-3092-v3-mkmlizer to finish
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: Downloaded to shared memory in 68.910s
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa_r9cjrf, device:0
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: quantized model in 42.763s
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp888_95ff_merged in 111.673s
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v3
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v3/special_tokens_map.json
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v3/config.json
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v3/tokenizer_config.json
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v3/tokenizer.json
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v3/flywheel_model.0.safetensors
rirv938-anthropic-grpo-4-3092-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.89it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.79it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.63it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 34.70it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 22.73it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 22.07it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.33it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 27.55it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.29it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.79it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.94it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.31it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 30.31it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.32it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 26.71it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 26.85it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 26.56it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.91it/s]
Loading 0:  23%|██▎       | 85/363 [00:03<00:10, 26.53it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:10, 26.27it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.31it/s]
Loading 0:  26%|██▋       | 96/363 [00:03<00:09, 26.76it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.32it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.04it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 26.52it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 24.27it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.70it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.31it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.73it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.54it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 28.98it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.07it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.76it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.72it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 29.10it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.47it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.90it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.56it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.87it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.64it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:08, 22.22it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.37it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 26.97it/s]
Loading 0:  54%|█████▎    | 195/363 [00:07<00:06, 25.26it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.24it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 27.61it/s]
Loading 0:  57%|█████▋    | 208/363 [00:07<00:05, 27.59it/s]
Loading 0:  58%|█████▊    | 211/363 [00:07<00:05, 27.12it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 25.99it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 26.33it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 28.62it/s]
Loading 0:  62%|██████▏   | 225/363 [00:08<00:07, 18.07it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 20.22it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:05, 25.06it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.13it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 28.08it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 24.99it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 29.54it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:04, 25.74it/s]
Loading 0:  72%|███████▏  | 262/363 [00:09<00:03, 30.05it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 19.50it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 24.07it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 22.48it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:03, 27.00it/s]
Loading 0:  78%|███████▊  | 284/363 [00:10<00:03, 23.53it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.91it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 24.37it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 28.73it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:02, 29.46it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 20.39it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 20.11it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 24.72it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 22.63it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 26.79it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 24.09it/s]
Loading 0:  92%|█████████▏| 334/363 [00:12<00:01, 28.53it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 24.21it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 28.31it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.98it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.49it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:03,  3.18it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.34it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  6.46it/s]
                                                            
Job rirv938-anthropic-grpo-4-3092-v3-mkmlizer completed after 176.37s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-4-3092-v3-mkmlizer
Pipeline stage MKMLizer completed in 176.80s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-4-3092-v3
Waiting for inference service rirv938-anthropic-grpo-4-3092-v3 to be ready
Inference service rirv938-anthropic-grpo-4-3092-v3 ready after 161.03484439849854s
Pipeline stage MKMLDeployer completed in 161.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.343806028366089s
Received healthy response to inference request in 1.5704882144927979s
Received healthy response to inference request in 1.7688796520233154s
Received healthy response to inference request in 1.632232666015625s
Received healthy response to inference request in 2.0864906311035156s
5 requests
0 failed requests
5th percentile: 1.5828371047973633
10th percentile: 1.5951859951019287
20th percentile: 1.6198837757110596
30th percentile: 1.659562063217163
40th percentile: 1.7142208576202393
50th percentile: 1.7688796520233154
60th percentile: 1.8959240436553955
70th percentile: 2.0229684352874755
80th percentile: 2.3379537105560306
90th percentile: 2.8408798694610597
95th percentile: 3.092342948913574
99th percentile: 3.293513412475586
mean time: 2.0803794384002687
Pipeline stage StressChecker completed in 11.46s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.62s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.62s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_3092_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5122.27s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_3092_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-4_3092_v3 status is now torndown due to DeploymentManager action