chaiml-mistral-24b-grpo_58640

developer_uid: rirv938

submission_id: chaiml-mistral-24b-grpo_58640_v1

model_name: chaiml-mistral-24b-grpo_58640_v1

model_group: ChaiML/mistral_24b_grpo_

status: torndown

timestamp: 2025-05-01T18:49:41+00:00

num_battles: 8374

num_wins: 4685

celo_rating: 1344.25

family_friendly_score: 0.5956

family_friendly_standard_error: 0.006940614382026997

submission_type: basic

model_repo: ChaiML/mistral_24b_grpo_cp1184_92ff

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5580245710079277, 'latency_mean': 1.7919803726673127, 'latency_p50': 1.7748208045959473, 'latency_p90': 1.9914806127548217}, {'batch_size': 4, 'throughput': 1.3825000370073774, 'latency_mean': 2.879571216106415, 'latency_p50': 2.865959882736206, 'latency_p90': 3.192550778388977}, {'batch_size': 5, 'throughput': 1.519704547804187, 'latency_mean': 3.26437330365181, 'latency_p50': 3.2555962800979614, 'latency_p90': 3.6125758409500124}, {'batch_size': 8, 'throughput': 1.8512713668911314, 'latency_mean': 4.274461488723755, 'latency_p50': 4.268509030342102, 'latency_p90': 4.7848059892654415}, {'batch_size': 10, 'throughput': 1.9892027035791917, 'latency_mean': 4.964869146347046, 'latency_p50': 4.994971752166748, 'latency_p90': 5.720163607597351}, {'batch_size': 12, 'throughput': 2.0558310650678195, 'latency_mean': 5.76304525732994, 'latency_p50': 5.810151100158691, 'latency_p90': 6.508871865272522}, {'batch_size': 15, 'throughput': 2.1045733728690483, 'latency_mean': 7.0281896090507505, 'latency_p50': 7.071494936943054, 'latency_p90': 7.883324861526489}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-mistral-24b-grpo_58640_v1

is_internal_developer: True

language_model: ChaiML/mistral_24b_grpo_cp1184_92ff

model_size: 24B

ranking_group: single

throughput_3p7s: 1.7

us_pacific_date: 2025-05-01

win_ratio: 0.5594697874373059

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.2, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['</s>', '\n', '###', '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-mistral-24b-grpo-58640-v1-mkmlizer
Waiting for job on chaiml-mistral-24b-grpo-58640-v1-mkmlizer to finish
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-mistral-24b-grpo-58640-v1-mkmlizer: Downloaded to shared memory in 140.657s
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphrckhql8, device:0
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: quantized model in 62.136s
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: Processed model ChaiML/mistral_24b_grpo_cp1184_92ff in 202.794s
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-24b-grpo-58640-v1
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-24b-grpo-58640-v1/special_tokens_map.json
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-24b-grpo-58640-v1/config.json
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-24b-grpo-58640-v1/tokenizer_config.json
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-24b-grpo-58640-v1/tokenizer.json
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-grpo-58640-v1/flywheel_model.1.safetensors
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-grpo-58640-v1/flywheel_model.0.safetensors
chaiml-mistral-24b-grpo-58640-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.96it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 17.92it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.65it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:24, 14.14it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.70it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.29it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.56it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.22it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.19it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.38it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.96it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:22, 14.06it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:23, 13.49it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.21it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:16, 19.01it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:21, 14.39it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:18, 16.60it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:20, 14.94it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:15, 18.89it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:15, 19.59it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:19, 14.79it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:17, 16.94it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:18, 15.48it/s]
Loading 0:  23%|██▎       | 83/363 [00:04<00:13, 21.00it/s]
Loading 0:  24%|██▍       | 87/363 [00:05<00:13, 19.90it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:18, 14.92it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:13, 20.16it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 23.61it/s]
Loading 0:  29%|██▊       | 104/363 [00:05<00:13, 19.81it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:16, 15.37it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:17, 14.81it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:16, 15.48it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.43it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:13, 18.48it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.76it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:14, 15.93it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:13, 16.79it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:17, 13.11it/s]
Loading 0:  38%|███▊      | 137/363 [00:08<00:11, 19.85it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:11, 18.89it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:14, 14.71it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:12, 16.82it/s]
Loading 0:  41%|████▏     | 150/363 [00:08<00:14, 15.08it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:10, 20.38it/s]
Loading 0:  44%|████▍     | 159/363 [00:09<00:10, 19.60it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:13, 14.61it/s]
Loading 0:  45%|████▌     | 165/363 [00:09<00:11, 16.68it/s]
Loading 0:  46%|████▋     | 168/363 [00:09<00:12, 15.13it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:09, 20.57it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:09, 19.31it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:12, 14.65it/s]
Loading 0:  50%|█████     | 183/363 [00:10<00:10, 16.85it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:11, 14.99it/s]
Loading 0:  53%|█████▎    | 191/363 [00:11<00:08, 20.43it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:08, 19.53it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:11, 14.58it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<03:35,  1.33s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<02:54,  1.09s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<01:49,  1.42it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:19,  1.93it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<00:59,  2.53it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:48,  3.02it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:39,  3.67it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:31,  4.60it/s]
Loading 0:  61%|██████    | 221/363 [00:27<00:27,  5.16it/s]
Loading 0:  63%|██████▎   | 227/363 [00:27<00:13,  9.94it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:11, 11.57it/s]
Loading 0:  64%|██████▍   | 234/363 [00:28<00:12, 10.58it/s]
Loading 0:  65%|██████▌   | 237/363 [00:28<00:09, 12.73it/s]
Loading 0:  66%|██████▌   | 240/363 [00:28<00:09, 12.60it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 16.55it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:05, 20.36it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:07, 15.20it/s]
Loading 0:  70%|██████▉   | 254/363 [00:29<00:06, 15.99it/s]
Loading 0:  71%|███████   | 257/363 [00:29<00:08, 12.89it/s]
Loading 0:  72%|███████▏  | 263/363 [00:30<00:05, 19.52it/s]
Loading 0:  74%|███████▎  | 267/363 [00:30<00:05, 18.65it/s]
Loading 0:  74%|███████▍  | 270/363 [00:30<00:06, 14.42it/s]
Loading 0:  75%|███████▌  | 273/363 [00:30<00:05, 16.42it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:05, 14.78it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 18.79it/s]
Loading 0:  79%|███████▊  | 285/363 [00:31<00:04, 19.21it/s]
Loading 0:  79%|███████▉  | 288/363 [00:31<00:05, 14.80it/s]
Loading 0:  80%|████████  | 291/363 [00:31<00:04, 16.73it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:04, 15.11it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 19.12it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 22.98it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 16.44it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 17.04it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:04, 12.98it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 17.84it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:02, 20.73it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:02, 14.93it/s]
Loading 0:  90%|████████▉ | 326/363 [00:33<00:02, 15.55it/s]
Loading 0:  91%|█████████ | 329/363 [00:34<00:02, 12.52it/s]
Loading 0:  92%|█████████▏| 335/363 [00:34<00:01, 18.90it/s]
Loading 0:  93%|█████████▎| 339/363 [00:34<00:01, 18.42it/s]
Loading 0:  94%|█████████▍| 342/363 [00:35<00:01, 14.25it/s]
Loading 0:  95%|█████████▌| 345/363 [00:35<00:01, 16.24it/s]
Loading 0:  96%|█████████▌| 348/363 [00:35<00:01, 14.71it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.62it/s]
Loading 0:  98%|█████████▊| 357/363 [00:42<00:03,  1.77it/s]
Loading 0:  99%|█████████▉| 360/363 [00:42<00:01,  2.26it/s]
Loading 0: 100%|█████████▉| 362/363 [00:42<00:00,  2.67it/s]
                                                            
Job chaiml-mistral-24b-grpo-58640-v1-mkmlizer completed after 227.51s with status: succeeded
Stopping job with name chaiml-mistral-24b-grpo-58640-v1-mkmlizer
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)
Pipeline stage MKMLizer completed in 228.09s
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 chaiml-mistral-24b-grpo-58640-v1
Waiting for inference service chaiml-mistral-24b-grpo-58640-v1 to be ready
Inference service chaiml-mistral-24b-grpo-58640-v1 ready after 140.44867944717407s
Pipeline stage MKMLDeployer completed in 140.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.60247540473938s
Received healthy response to inference request in 2.237691640853882s
Received healthy response to inference request in 1.847947359085083s
Received healthy response to inference request in 2.0340912342071533s
Received healthy response to inference request in 2.198286533355713s
5 requests
0 failed requests
5th percentile: 1.885176134109497
10th percentile: 1.922404909133911
20th percentile: 1.9968624591827393
30th percentile: 2.0669302940368652
40th percentile: 2.132608413696289
50th percentile: 2.198286533355713
60th percentile: 2.2140485763549806
70th percentile: 2.229810619354248
80th percentile: 2.3106483936309816
90th percentile: 2.4565618991851808
95th percentile: 2.52951865196228
99th percentile: 2.58788405418396
mean time: 2.1840984344482424
Pipeline stage StressChecker completed in 12.28s
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 0.59s
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 0.59s
Shutdown handler de-registered
chaiml-mistral-24b-grpo_58640_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 3176.90s
Shutdown handler de-registered
chaiml-mistral-24b-grpo_58640_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-24b-grpo_58640_v1 status is now torndown due to DeploymentManager action