developer_uid: NischayDnk
submission_id: chaiml-slerpv2-mistral3_77802_v1
model_name: chaiml-slerpv2-mistral3_77802_v1
model_group: ChaiML/slerpv2_mistral31
status: torndown
timestamp: 2025-04-16T18:46:19+00:00
num_battles: 5890
num_wins: 3505
celo_rating: 1352.14
family_friendly_score: 0.475
family_friendly_standard_error: 0.007062223445912767
submission_type: basic
model_repo: ChaiML/slerpv2_mistral31_simpo_dpo_s2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3711185982081294, 'latency_mean': 2.694475162029266, 'latency_p50': 2.6720439195632935, 'latency_p90': 3.007960867881775}, {'batch_size': 2, 'throughput': 0.57632517998022, 'latency_mean': 3.457165174484253, 'latency_p50': 3.454813599586487, 'latency_p90': 3.8241796493530273}, {'batch_size': 3, 'throughput': 0.7396473851239259, 'latency_mean': 4.04679364323616, 'latency_p50': 4.069470286369324, 'latency_p90': 4.392324423789978}, {'batch_size': 4, 'throughput': 0.8515562242663626, 'latency_mean': 4.67907387137413, 'latency_p50': 4.726930499076843, 'latency_p90': 5.214463520050049}, {'batch_size': 5, 'throughput': 0.9468821752759928, 'latency_mean': 5.253840351104737, 'latency_p50': 5.247172832489014, 'latency_p90': 5.921610856056213}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-slerpv2-mistral3_77802_v1
is_internal_developer: False
language_model: ChaiML/slerpv2_mistral31_simpo_dpo_s2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.65
us_pacific_date: 2025-04-16
win_ratio: 0.5950764006791172
generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 70, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-slerpv2-mistral3-77802-v1-mkmlizer
Waiting for job on chaiml-slerpv2-mistral3-77802-v1-mkmlizer to finish
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ _____ __ __ ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ /___/ ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ belonging to: ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ║ ║
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: Downloaded to shared memory in 81.535s
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx8hhbx63, device:0
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: quantized model in 58.576s
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: Processed model ChaiML/slerpv2_mistral31_simpo_dpo_s2 in 140.112s
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-slerpv2-mistral3-77802-v1
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-slerpv2-mistral3-77802-v1/config.json
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-slerpv2-mistral3-77802-v1/special_tokens_map.json
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-slerpv2-mistral3-77802-v1/tokenizer_config.json
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-slerpv2-mistral3-77802-v1/tokenizer.json
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-slerpv2-mistral3-77802-v1/flywheel_model.1.safetensors
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-slerpv2-mistral3-77802-v1/flywheel_model.0.safetensors
chaiml-slerpv2-mistral3-77802-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<19:16, 3.20s/it] Loading 0: 1%|▏ | 5/363 [00:06<06:13, 1.04s/it] Loading 0: 2%|▏ | 7/363 [00:06<03:57, 1.50it/s] Loading 0: 3%|▎ | 11/363 [00:06<01:56, 3.02it/s] Loading 0: 4%|▍ | 14/363 [00:06<01:18, 4.44it/s] Loading 0: 5%|▍ | 17/363 [00:07<00:57, 6.01it/s] Loading 0: 6%|▌ | 20/363 [00:07<00:42, 7.99it/s] Loading 0: 6%|▋ | 23/363 [00:07<00:41, 8.29it/s] Loading 0: 7%|▋ | 25/363 [00:07<00:37, 9.10it/s] Loading 0: 8%|▊ | 29/363 [00:07<00:26, 12.62it/s] Loading 0: 9%|▉ | 32/363 [00:07<00:22, 14.82it/s] Loading 0: 10%|▉ | 35/363 [00:08<00:21, 15.54it/s] Loading 0: 10%|█ | 38/363 [00:08<00:18, 17.50it/s] Loading 0: 11%|█▏ | 41/363 [00:08<00:16, 19.27it/s] Loading 0: 12%|█▏ | 44/363 [00:08<00:16, 19.33it/s] Loading 0: 13%|█▎ | 47/363 [00:08<00:15, 20.67it/s] Loading 0: 14%|█▍ | 50/363 [00:08<00:14, 21.90it/s] Loading 0: 15%|█▍ | 53/363 [00:08<00:14, 20.78it/s] Loading 0: 15%|█▌ | 56/363 [00:09<00:14, 21.80it/s] Loading 0: 16%|█▋ | 59/363 [00:09<00:20, 15.09it/s] Loading 0: 17%|█▋ | 61/363 [00:09<00:20, 14.76it/s] Loading 0: 18%|█▊ | 65/363 [00:09<00:16, 18.21it/s] Loading 0: 19%|█▊ | 68/363 [00:09<00:14, 20.05it/s] Loading 0: 20%|█▉ | 71/363 [00:09<00:14, 20.56it/s] Loading 0: 21%|██ | 76/363 [00:10<00:11, 24.87it/s] Loading 0: 22%|██▏ | 79/363 [00:10<00:12, 23.10it/s] Loading 0: 23%|██▎ | 85/363 [00:10<00:09, 28.91it/s] Loading 0: 24%|██▍ | 88/363 [00:10<00:10, 25.87it/s] Loading 0: 26%|██▌ | 94/363 [00:10<00:08, 31.22it/s] Loading 0: 27%|██▋ | 99/363 [00:10<00:11, 22.33it/s] Loading 0: 28%|██▊ | 103/363 [00:11<00:10, 24.06it/s] Loading 0: 29%|██▉ | 106/363 [00:11<00:11, 21.78it/s] Loading 0: 30%|███ | 110/363 [00:11<00:10, 24.33it/s] Loading 0: 31%|███ | 113/363 [00:11<00:10, 24.60it/s] Loading 0: 32%|███▏ | 116/363 [00:11<00:10, 23.17it/s] Loading 0: 33%|███▎ | 119/363 [00:11<00:09, 24.58it/s] Loading 0: 34%|███▎ | 122/363 [00:11<00:09, 25.36it/s] Loading 0: 34%|███▍ | 125/363 [00:12<00:09, 24.38it/s] Loading 0: 35%|███▌ | 128/363 [00:12<00:09, 25.70it/s] Loading 0: 36%|███▌ | 131/363 [00:12<00:08, 26.01it/s] Loading 0: 37%|███▋ | 136/363 [00:12<00:12, 18.41it/s] Loading 0: 39%|███▊ | 140/363 [00:12<00:10, 20.36it/s] Loading 0: 39%|███▉ | 143/363 [00:12<00:10, 20.69it/s] Loading 0: 41%|████ | 148/363 [00:13<00:09, 23.48it/s] Loading 0: 42%|████▏ | 151/363 [00:13<00:09, 21.24it/s] Loading 0: 43%|████▎ | 155/363 [00:13<00:08, 24.64it/s] Loading 0: 44%|████▎ | 158/363 [00:13<00:08, 24.88it/s] Loading 0: 44%|████▍ | 161/363 [00:13<00:08, 23.83it/s] Loading 0: 45%|████▌ | 165/363 [00:13<00:07, 27.58it/s] Loading 0: 46%|████▋ | 168/363 [00:13<00:09, 20.33it/s] Loading 0: 48%|████▊ | 173/363 [00:14<00:07, 25.91it/s] Loading 0: 49%|████▉ | 177/363 [00:14<00:11, 16.37it/s] Loading 0: 50%|█████ | 182/363 [00:14<00:08, 21.05it/s] Loading 0: 51%|█████ | 185/363 [00:30<00:08, 21.05it/s] Loading 0: 51%|█████ | 186/363 [00:30<03:25, 1.16s/it] Loading 0: 53%|█████▎ | 191/363 [00:30<02:13, 1.29it/s] Loading 0: 54%|█████▎ | 195/363 [00:30<01:37, 1.72it/s] Loading 0: 55%|█████▌ | 200/363 [00:30<01:04, 2.52it/s] Loading 0: 56%|█████▌ | 204/363 [00:31<00:48, 3.29it/s] Loading 0: 58%|█████▊ | 209/363 [00:31<00:32, 4.75it/s] Loading 0: 59%|█████▊ | 213/363 [00:31<00:24, 6.21it/s] Loading 0: 60%|█████▉ | 217/363 [00:31<00:20, 7.19it/s] Loading 0: 61%|██████ | 220/363 [00:31<00:17, 8.31it/s] Loading 0: 61%|██████▏ | 223/363 [00:32<00:14, 9.50it/s] Loading 0: 63%|██████▎ | 229/363 [00:32<00:09, 14.00it/s] Loading 0: 64%|██████▍ | 232/363 [00:32<00:08, 14.83it/s] Loading 0: 66%|██████▌ | 238/363 [00:32<00:06, 20.11it/s] Loading 0: 67%|██████▋ | 242/363 [00:32<00:05, 21.35it/s] Loading 0: 68%|██████▊ | 247/363 [00:32<00:04, 24.56it/s] Loading 0: 69%|██████▉ | 251/363 [00:32<00:04, 24.14it/s] Loading 0: 71%|███████ | 256/363 [00:33<00:05, 21.13it/s] Loading 0: 71%|███████▏ | 259/363 [00:33<00:05, 20.02it/s] Loading 0: 73%|███████▎ | 265/363 [00:33<00:03, 24.96it/s] Loading 0: 74%|███████▍ | 268/363 [00:33<00:04, 22.86it/s] Loading 0: 75%|███████▍ | 272/363 [00:33<00:03, 25.30it/s] Loading 0: 76%|███████▌ | 275/363 [00:33<00:03, 25.50it/s] Loading 0: 77%|███████▋ | 278/363 [00:34<00:03, 24.38it/s] Loading 0: 77%|███████▋ | 281/363 [00:34<00:03, 24.90it/s] Loading 0: 78%|███████▊ | 284/363 [00:34<00:03, 25.01it/s] Loading 0: 79%|███████▉ | 287/363 [00:34<00:03, 24.14it/s] Loading 0: 80%|███████▉ | 290/363 [00:34<00:02, 25.43it/s] Loading 0: 82%|████████▏ | 296/363 [00:34<00:03, 21.68it/s] Loading 0: 82%|████████▏ | 299/363 [00:35<00:03, 18.62it/s] Loading 0: 83%|████████▎ | 302/363 [00:35<00:03, 19.89it/s] Loading 0: 84%|████████▍ | 305/363 [00:35<00:02, 20.19it/s] Loading 0: 85%|████████▍ | 308/363 [00:35<00:02, 22.07it/s] Loading 0: 86%|████████▌ | 311/363 [00:35<00:02, 22.82it/s] Loading 0: 87%|████████▋ | 314/363 [00:35<00:02, 22.38it/s] Loading 0: 87%|████████▋ | 317/363 [00:35<00:01, 23.38it/s] Loading 0: 88%|████████▊ | 320/363 [00:36<00:01, 24.22it/s] Loading 0: 89%|████████▉ | 323/363 [00:36<00:01, 23.50it/s] Loading 0: 90%|████████▉ | 326/363 [00:36<00:01, 24.81it/s] Loading 0: 91%|█████████▏| 332/363 [00:36<00:00, 31.74it/s] Loading 0: 93%|█████████▎| 336/363 [00:36<00:01, 16.86it/s] Loading 0: 93%|█████████▎| 339/363 [00:37<00:01, 16.58it/s] Loading 0: 95%|█████████▍| 344/363 [00:37<00:00, 21.72it/s] Loading 0: 96%|█████████▌| 347/363 [00:37<00:00, 22.66it/s] Loading 0: 96%|█████████▋| 350/363 [00:37<00:00, 22.10it/s] Loading 0: 97%|█████████▋| 353/363 [00:37<00:00, 23.35it/s] Loading 0: 98%|█████████▊| 356/363 [00:37<00:00, 23.62it/s] Loading 0: 99%|█████████▉| 359/363 [00:37<00:00, 22.54it/s] Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 23.62it/s]
Job chaiml-slerpv2-mistral3-77802-v1-mkmlizer completed after 177.1s with status: succeeded
Stopping job with name chaiml-slerpv2-mistral3-77802-v1-mkmlizer
Pipeline stage MKMLizer completed in 177.62s
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-slerpv2-mistral3-77802-v1
Waiting for inference service chaiml-slerpv2-mistral3-77802-v1 to be ready
Inference service chaiml-slerpv2-mistral3-77802-v1 ready after 130.46127891540527s
Pipeline stage MKMLDeployer completed in 131.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9974288940429688s
Received healthy response to inference request in 2.7623000144958496s
Received healthy response to inference request in 2.6501333713531494s
Received healthy response to inference request in 2.7269251346588135s
Received healthy response to inference request in 2.502562999725342s
5 requests
0 failed requests
5th percentile: 2.5320770740509033
10th percentile: 2.561591148376465
20th percentile: 2.620619297027588
30th percentile: 2.665491724014282
40th percentile: 2.696208429336548
50th percentile: 2.7269251346588135
60th percentile: 2.7410750865936278
70th percentile: 2.7552250385284425
80th percentile: 2.8093257904052735
90th percentile: 2.903377342224121
95th percentile: 2.950403118133545
99th percentile: 2.988023738861084
mean time: 2.7278700828552247
Pipeline stage StressChecker completed in 15.20s
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 0.77s
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 0.75s
Shutdown handler de-registered
chaiml-slerpv2-mistral3_77802_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 3088.10s
Shutdown handler de-registered
chaiml-slerpv2-mistral3_77802_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-slerpv2-mistral3_77802_v1 status is now torndown due to DeploymentManager action