developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_51376_v1
model_name: rirv938-anthropic-grpo-_51376_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-04-29T18:30:24+00:00
num_battles: 5508
num_wins: 2943
celo_rating: 1331.81
family_friendly_score: 0.5664
family_friendly_standard_error: 0.007008438342455472
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp592_95ff_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6093703055513504, 'latency_mean': 1.6409789276123048, 'latency_p50': 1.6427804231643677, 'latency_p90': 1.8136968612670898}, {'batch_size': 3, 'throughput': 1.1058878527904918, 'latency_mean': 2.701084604263306, 'latency_p50': 2.6911158561706543, 'latency_p90': 3.028922629356384}, {'batch_size': 5, 'throughput': 1.348402194913645, 'latency_mean': 3.685804146528244, 'latency_p50': 3.6798206567764282, 'latency_p90': 4.148008513450622}, {'batch_size': 6, 'throughput': 1.4056687698983312, 'latency_mean': 4.235087773799896, 'latency_p50': 4.237600088119507, 'latency_p90': 4.803975200653076}, {'batch_size': 8, 'throughput': 1.4654391795323312, 'latency_mean': 5.4248136615753175, 'latency_p50': 5.376963257789612, 'latency_p90': 6.075176048278808}, {'batch_size': 10, 'throughput': 1.4970204501282396, 'latency_mean': 6.621156940460205, 'latency_p50': 6.659783720970154, 'latency_p90': 7.444522953033447}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_51376_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp592_95ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.36
us_pacific_date: 2025-04-29
win_ratio: 0.5343137254901961
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': 1024, '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-51376-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-51376-v1-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
rirv938-anthropic-grpo-51376-v1-mkmlizer: Downloaded to shared memory in 79.983s
rirv938-anthropic-grpo-51376-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphsdj5b7q, device:0
rirv938-anthropic-grpo-51376-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-51376-v1-mkmlizer: quantized model in 43.065s
rirv938-anthropic-grpo-51376-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp592_95ff_merged in 123.048s
rirv938-anthropic-grpo-51376-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-51376-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-51376-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v1
rirv938-anthropic-grpo-51376-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v1/config.json
rirv938-anthropic-grpo-51376-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v1/special_tokens_map.json
rirv938-anthropic-grpo-51376-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v1/tokenizer_config.json
rirv938-anthropic-grpo-51376-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v1/tokenizer.json
rirv938-anthropic-grpo-51376-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-51376-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.82it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:13, 26.54it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 23.74it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:11, 29.73it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:16, 20.06it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:18, 18.46it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:15, 21.63it/s] Loading 0: 10%|█ | 37/363 [00:01<00:12, 26.14it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:13, 24.07it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:11, 28.56it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:12, 25.25it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:10, 29.86it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:09, 30.88it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:14, 20.31it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:11, 24.88it/s] Loading 0: 20%|██ | 73/363 [00:02<00:11, 24.62it/s] Loading 0: 21%|██ | 77/363 [00:03<00:12, 23.21it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:10, 27.57it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 24.85it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:09, 29.38it/s] Loading 0: 26%|██▌ | 95/363 [00:03<00:10, 26.15it/s] Loading 0: 28%|██▊ | 100/363 [00:03<00:08, 30.59it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 20.03it/s] Loading 0: 30%|███ | 109/363 [00:04<00:10, 24.57it/s] Loading 0: 31%|███ | 113/363 [00:04<00:10, 23.37it/s] Loading 0: 33%|███▎ | 118/363 [00:04<00:08, 28.03it/s] Loading 0: 34%|███▎ | 122/363 [00:04<00:09, 25.62it/s] Loading 0: 35%|███▍ | 127/363 [00:04<00:07, 30.03it/s] Loading 0: 36%|███▌ | 131/363 [00:05<00:08, 26.24it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:07, 30.30it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 30.54it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:10, 20.74it/s] Loading 0: 41%|████ | 149/363 [00:06<00:10, 20.37it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:08, 24.82it/s] Loading 0: 44%|████▎ | 158/363 [00:06<00:08, 23.26it/s] Loading 0: 45%|████▍ | 163/363 [00:06<00:07, 27.47it/s] Loading 0: 46%|████▌ | 167/363 [00:06<00:07, 24.64it/s] Loading 0: 47%|████▋ | 172/363 [00:06<00:06, 28.37it/s] Loading 0: 48%|████▊ | 176/363 [00:07<00:07, 25.17it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:06, 29.36it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:09, 19.64it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 24.04it/s] Loading 0: 53%|█████▎ | 194/363 [00:07<00:07, 22.57it/s] Loading 0: 55%|█████▍ | 199/363 [00:07<00:06, 27.00it/s] Loading 0: 56%|█████▌ | 203/363 [00:08<00:06, 24.61it/s] Loading 0: 57%|█████▋ | 208/363 [00:08<00:05, 28.87it/s] Loading 0: 58%|█████▊ | 212/363 [00:08<00:05, 25.48it/s] Loading 0: 60%|█████▉ | 217/363 [00:08<00:04, 29.87it/s] Loading 0: 61%|██████ | 222/363 [00:08<00:04, 30.22it/s] Loading 0: 62%|██████▏ | 226/363 [00:09<00:06, 21.00it/s] Loading 0: 63%|██████▎ | 230/363 [00:09<00:06, 20.73it/s] Loading 0: 65%|██████▍ | 235/363 [00:09<00:05, 25.16it/s] Loading 0: 66%|██████▌ | 239/363 [00:09<00:05, 23.42it/s] Loading 0: 67%|██████▋ | 244/363 [00:09<00:04, 27.90it/s] Loading 0: 68%|██████▊ | 248/363 [00:09<00:04, 25.09it/s] Loading 0: 70%|██████▉ | 253/363 [00:10<00:03, 29.51it/s] Loading 0: 71%|███████ | 257/363 [00:10<00:04, 26.07it/s] Loading 0: 72%|███████▏ | 262/363 [00:10<00:03, 30.27it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 19.80it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 24.28it/s] Loading 0: 76%|███████▌ | 275/363 [00:11<00:03, 22.74it/s] Loading 0: 77%|███████▋ | 280/363 [00:11<00:03, 27.02it/s] Loading 0: 78%|███████▊ | 284/363 [00:11<00:03, 24.56it/s] Loading 0: 80%|███████▉ | 289/363 [00:11<00:02, 28.84it/s] Loading 0: 81%|████████ | 293/363 [00:11<00:02, 25.23it/s] Loading 0: 82%|████████▏ | 298/363 [00:11<00:02, 29.85it/s] Loading 0: 83%|████████▎ | 303/363 [00:11<00:01, 30.60it/s] Loading 0: 85%|████████▍ | 307/363 [00:12<00:02, 21.35it/s] Loading 0: 86%|████████▌ | 311/363 [00:12<00:02, 21.12it/s] Loading 0: 87%|████████▋ | 316/363 [00:12<00:01, 26.02it/s] Loading 0: 88%|████████▊ | 320/363 [00:12<00:01, 24.18it/s] Loading 0: 90%|████████▉ | 325/363 [00:12<00:01, 29.05it/s] Loading 0: 91%|█████████ | 329/363 [00:13<00:01, 23.94it/s] Loading 0: 93%|█████████▎| 336/363 [00:13<00:00, 29.83it/s] Loading 0: 94%|█████████▎| 340/363 [00:13<00:00, 28.60it/s] Loading 0: 95%|█████████▍| 344/363 [00:20<00:09, 2.07it/s] Loading 0: 96%|█████████▌| 348/363 [00:20<00:05, 2.74it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.92it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 5.02it/s] Loading 0: 100%|█████████▉| 362/363 [00:21<00:00, 7.10it/s]
Job rirv938-anthropic-grpo-51376-v1-mkmlizer completed after 154.58s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-51376-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.06s
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-51376-v1
Waiting for inference service rirv938-anthropic-grpo-51376-v1 to be ready
Inference service rirv938-anthropic-grpo-51376-v1 ready after 140.61844873428345s
Pipeline stage MKMLDeployer completed in 141.13s
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 2.321012258529663s
Received healthy response to inference request in 1.8037786483764648s
Received healthy response to inference request in 1.875112771987915s
Received healthy response to inference request in 1.709563970565796s
5 requests
1 failed requests
5th percentile: 1.7284069061279297
10th percentile: 1.7472498416900635
20th percentile: 1.784935712814331
30th percentile: 1.818045473098755
40th percentile: 1.846579122543335
50th percentile: 1.875112771987915
60th percentile: 2.053472566604614
70th percentile: 2.2318323612213136
80th percentile: 5.888052272796634
90th percentile: 13.022132301330569
95th percentile: 16.58917231559753
99th percentile: 19.442804327011107
mean time: 5.5731359958648685
%s, retrying in %s seconds...
Received healthy response to inference request in 1.8078036308288574s
Received healthy response to inference request in 1.8393843173980713s
Received healthy response to inference request in 2.152510404586792s
Received healthy response to inference request in 1.8574814796447754s
Received healthy response to inference request in 1.499981164932251s
5 requests
0 failed requests
5th percentile: 1.5615456581115723
10th percentile: 1.6231101512908936
20th percentile: 1.746239137649536
30th percentile: 1.8141197681427002
40th percentile: 1.8267520427703858
50th percentile: 1.8393843173980713
60th percentile: 1.846623182296753
70th percentile: 1.8538620471954346
80th percentile: 1.9164872646331788
90th percentile: 2.0344988346099853
95th percentile: 2.0935046195983884
99th percentile: 2.140709247589111
mean time: 1.8314321994781495
Pipeline stage StressChecker completed in 40.66s
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 0.74s
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 0.71s
Shutdown handler de-registered
rirv938-anthropic-grpo-_51376_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3047.20s
Shutdown handler de-registered
rirv938-anthropic-grpo-_51376_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_51376_v1 status is now torndown due to DeploymentManager action