developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_44019_v3
model_name: rirv938-anthropic-grpo-_44019_v3
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-04-29T19:57:51+00:00
num_battles: 9248
num_wins: 4885
celo_rating: 1316.41
family_friendly_score: 0.5696
family_friendly_standard_error: 0.007002225931801972
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp148_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': 0.6420097242744442, 'latency_mean': 1.5575371015071868, 'latency_p50': 1.555978775024414, 'latency_p90': 1.7426307201385498}, {'batch_size': 3, 'throughput': 1.2282914453590037, 'latency_mean': 2.4358926391601563, 'latency_p50': 2.4269806146621704, 'latency_p90': 2.7316693544387816}, {'batch_size': 5, 'throughput': 1.5122558761038638, 'latency_mean': 3.2840693485736847, 'latency_p50': 3.300063371658325, 'latency_p90': 3.6335411787033083}, {'batch_size': 6, 'throughput': 1.5994369688271908, 'latency_mean': 3.7240067183971406, 'latency_p50': 3.7352914810180664, 'latency_p90': 4.23154296875}, {'batch_size': 8, 'throughput': 1.69842427090228, 'latency_mean': 4.676796964406967, 'latency_p50': 4.6588486433029175, 'latency_p90': 5.276412582397461}, {'batch_size': 10, 'throughput': 1.7448321289886108, 'latency_mean': 5.691593617200851, 'latency_p50': 5.713082909584045, 'latency_p90': 6.441911244392395}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_44019_v3
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp148_95ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.61
us_pacific_date: 2025-04-29
win_ratio: 0.5282223183391004
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', '</s>', 'You:', '###'], '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-44019-v3-mkmlizer
Waiting for job on rirv938-anthropic-grpo-44019-v3-mkmlizer to finish
rirv938-anthropic-grpo-44019-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-44019-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-44019-v3-mkmlizer: Downloaded to shared memory in 63.353s
rirv938-anthropic-grpo-44019-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9ff13x_l, device:0
rirv938-anthropic-grpo-44019-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-44019-v3-mkmlizer: quantized model in 43.702s
rirv938-anthropic-grpo-44019-v3-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp148_95ff_merged in 107.057s
rirv938-anthropic-grpo-44019-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-44019-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-44019-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v3
rirv938-anthropic-grpo-44019-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v3/special_tokens_map.json
rirv938-anthropic-grpo-44019-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v3/config.json
rirv938-anthropic-grpo-44019-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v3/tokenizer_config.json
rirv938-anthropic-grpo-44019-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v3/tokenizer.json
rirv938-anthropic-grpo-44019-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v3/flywheel_model.0.safetensors
rirv938-anthropic-grpo-44019-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.28it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:15, 22.50it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 23.99it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:18, 18.87it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:14, 24.39it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:13, 24.82it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:21, 16.04it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.03it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:19, 17.16it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 21.64it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:16, 20.08it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:12, 24.78it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 22.16it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 26.38it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:11, 26.83it/s]
Loading 0:  17%|█▋        | 63/363 [00:02<00:15, 19.30it/s]
Loading 0:  18%|█▊        | 66/363 [00:03<00:14, 20.20it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:13, 21.95it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 20.71it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.68it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.63it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.47it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:09, 28.63it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:10, 25.46it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 22.39it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.42it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 25.44it/s]
Loading 0:  31%|███       | 113/363 [00:05<00:10, 23.70it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:08, 28.03it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:09, 25.62it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:07, 30.39it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:08, 26.83it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 30.73it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:08, 25.37it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:09, 24.12it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:09, 22.95it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 29.45it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.37it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.22it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.46it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 29.93it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:06, 28.15it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:08, 22.30it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.33it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 26.65it/s]
Loading 0:  54%|█████▎    | 195/363 [00:08<00:07, 23.81it/s]
Loading 0:  55%|█████▌    | 201/363 [00:08<00:05, 28.40it/s]
Loading 0:  56%|█████▋    | 205/363 [00:08<00:05, 27.95it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:05, 30.00it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 28.05it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 27.26it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.73it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 19.65it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.34it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.06it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 22.35it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 26.72it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 24.02it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 28.63it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 25.76it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 30.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 19.44it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 23.80it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 22.45it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.80it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.49it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 29.01it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 25.83it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 29.65it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 30.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.89it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 19.59it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 23.89it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.11it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 26.19it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 23.44it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 27.74it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 24.60it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 28.74it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.98it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.49it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.16it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.31it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.39it/s]
                                                            

Job rirv938-anthropic-grpo-44019-v3-mkmlizer completed after 177.27s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-44019-v3-mkmlizer
Pipeline stage MKMLizer completed in 177.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-44019-v3
Waiting for inference service rirv938-anthropic-grpo-44019-v3 to be ready
Inference service rirv938-anthropic-grpo-44019-v3 ready after 170.56006717681885s
Pipeline stage MKMLDeployer completed in 170.97s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.0444958209991455s
Received healthy response to inference request in 1.7021052837371826s
Received healthy response to inference request in 1.8509650230407715s
Received healthy response to inference request in 1.9310176372528076s
5 requests
1 failed requests
5th percentile: 1.7318772315979003
10th percentile: 1.7616491794586182
20th percentile: 1.8211930751800538
30th percentile: 1.8669755458831787
40th percentile: 1.8989965915679932
50th percentile: 1.9310176372528076
60th percentile: 1.9764089107513427
70th percentile: 2.021800184249878
80th percentile: 5.6926191806793245
90th percentile: 12.988865900039674
95th percentile: 16.636989259719847
99th percentile: 19.555487947463988
mean time: 5.562739276885987
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6124398708343506s
Received healthy response to inference request in 1.609663724899292s
Received healthy response to inference request in 1.8850584030151367s
Received healthy response to inference request in 1.6063258647918701s
Received healthy response to inference request in 1.8966405391693115s
5 requests
0 failed requests
5th percentile: 1.6069934368133545
10th percentile: 1.6076610088348389
20th percentile: 1.6089961528778076
30th percentile: 1.6102189540863037
40th percentile: 1.6113294124603272
50th percentile: 1.6124398708343506
60th percentile: 1.721487283706665
70th percentile: 1.8305346965789795
80th percentile: 1.8873748302459716
90th percentile: 1.8920076847076417
95th percentile: 1.8943241119384766
99th percentile: 1.8961772537231445
mean time: 1.7220256805419922
Pipeline stage StressChecker completed in 38.92s
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 0.73s
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 0.68s
Shutdown handler de-registered
rirv938-anthropic-grpo-_44019_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
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 5165.42s
Shutdown handler de-registered
rirv938-anthropic-grpo-_44019_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_44019_v3 status is now torndown due to DeploymentManager action