chaiml-anthropic-grpo-4_77013

developer_uid: rirv938

submission_id: chaiml-anthropic-grpo-4_77013_v1

model_name: chaiml-anthropic-grpo-4_77013_v1

model_group: ChaiML/anthropic_grpo_40

status: torndown

timestamp: 2025-05-01T18:38:02+00:00

num_battles: 11349

num_wins: 6386

celo_rating: 1345.38

family_friendly_score: 0.5246

family_friendly_standard_error: 0.007062504371680062

submission_type: basic

model_repo: ChaiML/anthropic_grpo_40k_cp888_0ff

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': 0.638147801712168, 'latency_mean': 1.5669642329216003, 'latency_p50': 1.5502057075500488, 'latency_p90': 1.7316989183425904}, {'batch_size': 3, 'throughput': 1.2221489128476688, 'latency_mean': 2.4503401172161103, 'latency_p50': 2.447347402572632, 'latency_p90': 2.712162733078003}, {'batch_size': 5, 'throughput': 1.4914477944609603, 'latency_mean': 3.325359100103378, 'latency_p50': 3.3248119354248047, 'latency_p90': 3.717560148239136}, {'batch_size': 6, 'throughput': 1.6071615661106455, 'latency_mean': 3.7147930896282197, 'latency_p50': 3.6949355602264404, 'latency_p90': 4.179821395874024}, {'batch_size': 8, 'throughput': 1.6871667441075315, 'latency_mean': 4.722142757177353, 'latency_p50': 4.7457427978515625, 'latency_p90': 5.289408493041992}, {'batch_size': 10, 'throughput': 1.6989699580651774, 'latency_mean': 5.840958256721496, 'latency_p50': 5.84070885181427, 'latency_p90': 6.653552007675171}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-anthropic-grpo-4_77013_v1

is_internal_developer: True

language_model: ChaiML/anthropic_grpo_40k_cp888_0ff

model_size: 13B

ranking_group: single

throughput_3p7s: 1.61

us_pacific_date: 2025-05-01

win_ratio: 0.5626927482597586

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 chaiml-anthropic-grpo-4-77013-v1-mkmlizer
Waiting for job on chaiml-anthropic-grpo-4-77013-v1-mkmlizer to finish
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║       /___/                                                         ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: Downloaded to shared memory in 65.455s
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7ric8ceh, device:0
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: quantized model in 41.562s
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: Processed model ChaiML/anthropic_grpo_40k_cp888_0ff in 107.017s
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-77013-v1
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-77013-v1/config.json
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-77013-v1/special_tokens_map.json
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-77013-v1/tokenizer_config.json
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-77013-v1/tokenizer.json
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-77013-v1/flywheel_model.0.safetensors
chaiml-anthropic-grpo-4-77013-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.60it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.56it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.13it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 32.65it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:15, 22.52it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.91it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.85it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.12it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.18it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:10, 30.07it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:11, 26.15it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:09, 31.02it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 32.24it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.06it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.08it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 26.98it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 26.55it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 28.85it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 27.57it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.71it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 24.82it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.71it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.30it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.75it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:09, 25.88it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.22it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.27it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.70it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.04it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 28.98it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.01it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.84it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.15it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.71it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 27.99it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 29.80it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.70it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.97it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.68it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.00it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.55it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 28.29it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 27.92it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.30it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.23it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.43it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.74it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.74it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.71it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.43it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.41it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.10it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.23it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 31.26it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.96it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.83it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.21it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.15it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.46it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 26.71it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 24.56it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.63it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.15it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.66it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.25it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 28.95it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.46it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.43it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.09it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 28.71it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.33it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.68it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.62it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.21it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 28.98it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.64it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.84it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.98it/s]
                                                            
Job chaiml-anthropic-grpo-4-77013-v1-mkmlizer completed after 135.29s with status: succeeded
Stopping job with name chaiml-anthropic-grpo-4-77013-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.75s
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 chaiml-anthropic-grpo-4-77013-v1
Waiting for inference service chaiml-anthropic-grpo-4-77013-v1 to be ready
Failed to get response for submission chaiml-anthropic-grpo-4_66492_v1: HTTPConnectionPool(host='chaiml-anthropic-grpo-4-66492-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-anthropic-grpo-4-77013-v1 ready after 150.47418975830078s
Pipeline stage MKMLDeployer completed in 150.89s
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 2.1898200511932373s
Received healthy response to inference request in 1.6164250373840332s
Received healthy response to inference request in 1.5088744163513184s
Received healthy response to inference request in 1.6659305095672607s
5 requests
1 failed requests
5th percentile: 1.5303845405578613
10th percentile: 1.5518946647644043
20th percentile: 1.5949149131774902
30th percentile: 1.6263261318206788
40th percentile: 1.6461283206939696
50th percentile: 1.6659305095672607
60th percentile: 1.8754863262176513
70th percentile: 2.085042142868042
80th percentile: 5.77937517166138
90th percentile: 12.958485412597657
95th percentile: 16.548040533065794
99th percentile: 19.419684629440308
mean time: 5.423729133605957
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6900594234466553s
Received healthy response to inference request in 1.6230456829071045s
Received healthy response to inference request in 1.803335189819336s
Received healthy response to inference request in 1.678476333618164s
Received healthy response to inference request in 1.6475000381469727s
5 requests
0 failed requests
5th percentile: 1.627936553955078
10th percentile: 1.6328274250030517
20th percentile: 1.642609167098999
30th percentile: 1.653695297241211
40th percentile: 1.6660858154296876
50th percentile: 1.678476333618164
60th percentile: 1.6831095695495606
70th percentile: 1.6877428054809571
80th percentile: 1.7127145767211913
90th percentile: 1.7580248832702636
95th percentile: 1.7806800365448
99th percentile: 1.7988041591644288
mean time: 1.6884833335876466
Pipeline stage StressChecker completed in 38.27s
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 0.69s
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 0.70s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_77013_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4582.72s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_77013_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-grpo-4_77013_v1 status is now torndown due to DeploymentManager action