chaiml-snugstable-grpo-4_7330

developer_uid: rirv938

submission_id: chaiml-snugstable-grpo-4_7330_v1

model_name: chaiml-snugstable-grpo-4_7330_v1

model_group: ChaiML/snugstable_grpo_4

status: torndown

timestamp: 2025-05-01T18:52:04+00:00

num_battles: 8935

num_wins: 4259

celo_rating: 1288.33

family_friendly_score: 0.5262

family_friendly_standard_error: 0.007061353411351113

submission_type: basic

model_repo: ChaiML/snugstable_grpo_40k_cp1184_93ff

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': 0.6100124023956363, 'latency_mean': 1.639230945110321, 'latency_p50': 1.6367450952529907, 'latency_p90': 1.8164325475692749}, {'batch_size': 3, 'throughput': 1.1097170628462338, 'latency_mean': 2.691905297040939, 'latency_p50': 2.7003469467163086, 'latency_p90': 2.9397407293319704}, {'batch_size': 5, 'throughput': 1.3506517314261204, 'latency_mean': 3.6854861330986024, 'latency_p50': 3.7310413122177124, 'latency_p90': 4.104258012771607}, {'batch_size': 6, 'throughput': 1.4250854353074296, 'latency_mean': 4.196343961954117, 'latency_p50': 4.197868704795837, 'latency_p90': 4.717831635475159}, {'batch_size': 8, 'throughput': 1.4820314284317315, 'latency_mean': 5.365839570760727, 'latency_p50': 5.353554725646973, 'latency_p90': 6.009740710258484}, {'batch_size': 10, 'throughput': 1.5129437002201533, 'latency_mean': 6.558851101398468, 'latency_p50': 6.574720501899719, 'latency_p90': 7.40768346786499}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-snugstable-grpo-4_7330_v1

is_internal_developer: True

language_model: ChaiML/snugstable_grpo_40k_cp1184_93ff

model_size: 13B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-05-01

win_ratio: 0.476664801343033

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '\n', '####', 'User:', 'You:', 'Bot:', '</s>', '<|eot_id|>'], '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': True}

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-snugstable-grpo-4-7330-v1-mkmlizer
Waiting for job on chaiml-snugstable-grpo-4-7330-v1-mkmlizer to finish
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)
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║       /___/                                                         ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: Downloaded to shared memory in 68.162s
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprv57oprw, device:0
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: quantized model in 41.944s
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: Processed model ChaiML/snugstable_grpo_40k_cp1184_93ff in 110.107s
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable-grpo-4-7330-v1
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable-grpo-4-7330-v1/config.json
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable-grpo-4-7330-v1/special_tokens_map.json
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable-grpo-4-7330-v1/tokenizer_config.json
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable-grpo-4-7330-v1/tokenizer.json
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable-grpo-4-7330-v1/flywheel_model.0.safetensors
chaiml-snugstable-grpo-4-7330-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.18it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.73it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.95it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 35.16it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 24.38it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 24.07it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.79it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 29.79it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.92it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.57it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.24it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 30.14it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.88it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.51it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.49it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.14it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.43it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:09, 30.81it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.25it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.70it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.30it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.72it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 21.64it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 29.06it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.51it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.93it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 29.88it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.49it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.36it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.69it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.82it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.01it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.18it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.28it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.21it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.87it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.74it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.44it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.51it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.60it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.60it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 28.98it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 27.99it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.18it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.22it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.28it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.56it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.81it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 25.41it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.76it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.53it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 29.23it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.35it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.75it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:04, 28.16it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.67it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.07it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.84it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 20.87it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:03, 25.40it/s]
Loading 0:  75%|███████▌  | 274/363 [00:09<00:03, 26.05it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 25.41it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 28.34it/s]
Loading 0:  79%|███████▊  | 285/363 [00:10<00:03, 25.61it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.39it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 28.49it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 28.06it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 22.93it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 21.61it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 21.26it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 28.02it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 26.87it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 29.34it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.27it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.79it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.22it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.91it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.56it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.72it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.80it/s]
                                                            
Job chaiml-snugstable-grpo-4-7330-v1-mkmlizer completed after 135.28s with status: succeeded
Stopping job with name chaiml-snugstable-grpo-4-7330-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.73s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable-grpo-4-7330-v1
Waiting for inference service chaiml-snugstable-grpo-4-7330-v1 to be ready
Failed to get response for submission chaiml-anthropic-grpo-4_66492_v2: HTTPConnectionPool(host='chaiml-anthropic-grpo-4-66492-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-anthropic-grpo-4_66492_v2: HTTPConnectionPool(host='chaiml-anthropic-grpo-4-66492-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-snugstable-grpo-4-7330-v1 ready after 160.53070259094238s
Pipeline stage MKMLDeployer completed in 161.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.282313108444214s
Received healthy response to inference request in 1.7393264770507812s
Received healthy response to inference request in 2.0822513103485107s
Received healthy response to inference request in 1.7405500411987305s
Received healthy response to inference request in 1.765214204788208s
5 requests
0 failed requests
5th percentile: 1.7395711898803712
10th percentile: 1.739815902709961
20th percentile: 1.7403053283691405
30th percentile: 1.745482873916626
40th percentile: 1.755348539352417
50th percentile: 1.765214204788208
60th percentile: 1.892029047012329
70th percentile: 2.01884388923645
80th percentile: 2.1222636699676514
90th percentile: 2.2022883892059326
95th percentile: 2.2423007488250732
99th percentile: 2.2743106365203856
mean time: 1.9219310283660889
Pipeline stage StressChecker completed in 11.25s
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 0.67s
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
chaiml-snugstable-grpo-4_7330_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-snugstable-grpo-4-7330-v1-profiler
Waiting for inference service chaiml-snugstable-grpo-4-7330-v1-profiler to be ready
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 5244.76s
Shutdown handler de-registered
chaiml-snugstable-grpo-4_7330_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable-grpo-4_7330_v1 status is now torndown due to DeploymentManager action