rirv938-anthropic-grpo-_96183

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_96183_v1

model_name: rirv938-anthropic-grpo-_96183_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-04-30T15:01:00+00:00

num_battles: 8865

num_wins: 4939

celo_rating: 1348.91

family_friendly_score: 0.4992

family_friendly_standard_error: 0.007071058760892883

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp1184_0ff_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': 0.6443403058349904, 'latency_mean': 1.5519115626811981, 'latency_p50': 1.5498316287994385, 'latency_p90': 1.720259189605713}, {'batch_size': 3, 'throughput': 1.248273986006845, 'latency_mean': 2.39188570022583, 'latency_p50': 2.391154646873474, 'latency_p90': 2.6656292200088503}, {'batch_size': 5, 'throughput': 1.5388725294942764, 'latency_mean': 3.2298995733261107, 'latency_p50': 3.235883355140686, 'latency_p90': 3.599725675582886}, {'batch_size': 6, 'throughput': 1.6241791756605588, 'latency_mean': 3.675695104598999, 'latency_p50': 3.6999534368515015, 'latency_p90': 4.118960046768189}, {'batch_size': 8, 'throughput': 1.691310215438231, 'latency_mean': 4.6972155916690825, 'latency_p50': 4.711253881454468, 'latency_p90': 5.245153284072876}, {'batch_size': 10, 'throughput': 1.7718537246692918, 'latency_mean': 5.600369173288345, 'latency_p50': 5.631422519683838, 'latency_p90': 6.282196998596191}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_96183_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp1184_0ff_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-04-30

win_ratio: 0.5571347997743937

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': ['You:', '\n', '</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-96183-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-96183-v1-mkmlizer to finish
rirv938-anthropic-grpo-96183-v1-mkmlizer: Downloaded to shared memory in 88.462s
rirv938-anthropic-grpo-96183-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpergwe4vz, device:0
rirv938-anthropic-grpo-96183-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-96183-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-96183-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-96183-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-96183-v1
rirv938-anthropic-grpo-96183-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-96183-v1/config.json
rirv938-anthropic-grpo-96183-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-96183-v1/special_tokens_map.json
rirv938-anthropic-grpo-96183-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-96183-v1/tokenizer_config.json
rirv938-anthropic-grpo-96183-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-96183-v1/tokenizer.json
rirv938-anthropic-grpo-96183-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-96183-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-96183-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.81it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.88it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.74it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.12it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.95it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 18.87it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.38it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:13, 25.18it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.08it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 23.77it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 26.80it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.50it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.17it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.07it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 18.96it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.29it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.70it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.01it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.58it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.59it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.97it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 24.83it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 29.10it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.02it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.38it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.87it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.14it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.41it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.60it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.58it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.51it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.67it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.57it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 19.76it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.10it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.56it/s]
Loading 0:  45%|████▌     | 164/363 [00:06<00:06, 29.32it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 26.04it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 28.35it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 25.46it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.72it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.67it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.31it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 22.47it/s]
Loading 0:  55%|█████▌    | 201/363 [00:08<00:05, 28.82it/s]
Loading 0:  56%|█████▋    | 205/363 [00:08<00:05, 28.21it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:05, 30.25it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.00it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.17it/s]
Loading 0:  61%|██████▏   | 223/363 [00:09<00:05, 24.16it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:05, 23.17it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 21.92it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:04, 27.12it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:04, 24.93it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.78it/s]
Loading 0:  69%|██████▉   | 250/363 [00:10<00:03, 29.35it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 31.34it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 29.69it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 24.08it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.39it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.98it/s]
Loading 0:  76%|███████▋  | 277/363 [00:11<00:03, 27.33it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 29.61it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 28.19it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 30.20it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.80it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 28.98it/s]
Loading 0:  84%|████████▎ | 304/363 [00:12<00:02, 23.74it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 22.41it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.66it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 26.76it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 24.55it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.56it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 28.34it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 29.98it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 28.21it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 28.45it/s]
Loading 0:  95%|█████████▌| 346/363 [00:20<00:09,  1.71it/s]
Loading 0:  96%|█████████▌| 349/363 [00:20<00:06,  2.23it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:03,  3.17it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.34it/s]
                                                            
Job rirv938-anthropic-grpo-96183-v1-mkmlizer completed after 165.41s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-96183-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-96183-v1
Waiting for inference service rirv938-anthropic-grpo-96183-v1 to be ready
Inference service rirv938-anthropic-grpo-96183-v1 ready after 151.1443874835968s
Pipeline stage MKMLDeployer completed in 151.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2396128177642822s
Received healthy response to inference request in 2.0608363151550293s
Received healthy response to inference request in 1.692800521850586s
Received healthy response to inference request in 1.4829285144805908s
Received healthy response to inference request in 1.6485769748687744s
5 requests
0 failed requests
5th percentile: 1.5160582065582275
10th percentile: 1.5491878986358643
20th percentile: 1.6154472827911377
30th percentile: 1.6574216842651368
40th percentile: 1.6751111030578614
50th percentile: 1.692800521850586
60th percentile: 1.8400148391723632
70th percentile: 1.9872291564941404
80th percentile: 2.09659161567688
90th percentile: 2.1681022167205812
95th percentile: 2.2038575172424317
99th percentile: 2.232461757659912
mean time: 1.8249510288238526
Pipeline stage StressChecker completed in 10.46s
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 0.68s
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 0.74s
Shutdown handler de-registered
rirv938-anthropic-grpo-_96183_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 3287.19s
Shutdown handler de-registered
rirv938-anthropic-grpo-_96183_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_96183_v1 status is now torndown due to DeploymentManager action