developer_uid: NischayDnk
submission_id: chaiml-slerpv1-merge-dp_26736_v3
model_name: chaiml-slerpv1-merge-dp_26736_v3
model_group: ChaiML/slerpv1_merge_dpo
status: torndown
timestamp: 2025-04-02T18:34:20+00:00
num_battles: 6692
num_wins: 3557
celo_rating: 1307.46
family_friendly_score: 0.5178
family_friendly_standard_error: 0.007066585597019256
submission_type: basic
model_repo: ChaiML/slerpv1_merge_dpo_exp73_exp3
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': 0.37250978295746145, 'latency_mean': 2.684401720762253, 'latency_p50': 2.690468907356262, 'latency_p90': 2.9727547407150268}, {'batch_size': 2, 'throughput': 0.5781839758069186, 'latency_mean': 3.452619322538376, 'latency_p50': 3.4524179697036743, 'latency_p90': 3.793765640258789}, {'batch_size': 3, 'throughput': 0.7408298016043504, 'latency_mean': 4.037763040065766, 'latency_p50': 4.025975346565247, 'latency_p90': 4.435186982154846}, {'batch_size': 4, 'throughput': 0.8541461745754065, 'latency_mean': 4.65649901509285, 'latency_p50': 4.6822086572647095, 'latency_p90': 5.177381920814514}, {'batch_size': 5, 'throughput': 0.9436927057248164, 'latency_mean': 5.273159811496734, 'latency_p50': 5.294769763946533, 'latency_p90': 5.911720132827758}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-slerpv1-merge-dp_26736_v3
is_internal_developer: False
language_model: ChaiML/slerpv1_merge_dpo_exp73_exp3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.65
us_pacific_date: 2025-04-02
win_ratio: 0.5315301852958757
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-slerpv1-merge-dp-26736-v3-mkmlizer
Waiting for job on chaiml-slerpv1-merge-dp-26736-v3-mkmlizer to finish
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║       /___/                                                         ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║                                                                     ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║                                                                     ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║                                                                     ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ║                                                                     ║
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v1: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: Downloaded to shared memory in 61.249s
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmiye86hi, device:0
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v3
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v3/config.json
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v3/special_tokens_map.json
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v3/tokenizer_config.json
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v3/tokenizer.json
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v3/flywheel_model.1.safetensors
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v3/flywheel_model.0.safetensors
chaiml-slerpv1-merge-dp-26736-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:32,  3.08s/it]
Loading 0:   1%|▏         | 5/363 [00:06<05:59,  1.00s/it]
Loading 0:   2%|▏         | 7/363 [00:06<03:47,  1.57it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:28,  3.96it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:06,  5.21it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:43,  7.84it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:37,  9.09it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:24, 13.62it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:22, 14.64it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:16, 19.83it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 20.91it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:12, 24.71it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:12, 24.63it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:10, 28.02it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:15, 19.87it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:12, 23.07it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:13, 21.85it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 27.34it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:10, 26.55it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 29.72it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:09, 27.88it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:08, 30.74it/s]
Loading 0:  27%|██▋       | 98/363 [00:09<00:12, 20.70it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:10, 23.82it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 22.47it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 27.74it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:09, 26.50it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:08, 29.59it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:08, 28.00it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:07, 30.31it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 28.46it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:09, 23.14it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:10, 21.52it/s]
Loading 0:  41%|████      | 148/363 [00:11<00:08, 26.36it/s]
Loading 0:  42%|████▏     | 151/363 [00:11<00:08, 23.69it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:07, 28.87it/s]
Loading 0:  44%|████▍     | 161/363 [00:12<00:07, 27.54it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 30.03it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:06, 28.33it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:06, 31.15it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:08, 21.21it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 24.67it/s]
Loading 0:  51%|█████     | 185/363 [00:27<00:07, 24.67it/s]
Loading 0:  51%|█████     | 186/363 [00:27<03:26,  1.17s/it]
Loading 0:  53%|█████▎    | 191/363 [00:27<02:09,  1.32it/s]
Loading 0:  54%|█████▎    | 195/363 [00:28<01:33,  1.79it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:53,  3.02it/s]
Loading 0:  57%|█████▋    | 206/363 [00:28<00:40,  3.90it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<00:27,  5.44it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:23,  6.33it/s]
Loading 0:  61%|██████    | 220/363 [00:28<00:16,  8.58it/s]
Loading 0:  62%|██████▏   | 224/363 [00:29<00:13, 10.32it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:09, 13.56it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:08, 15.38it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:06, 19.11it/s]
Loading 0:  67%|██████▋   | 242/363 [00:29<00:06, 20.10it/s]
Loading 0:  68%|██████▊   | 247/363 [00:29<00:04, 23.90it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:04, 24.05it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:04, 21.43it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:05, 20.03it/s]
Loading 0:  73%|███████▎  | 265/363 [00:30<00:03, 25.25it/s]
Loading 0:  74%|███████▍  | 268/363 [00:30<00:04, 23.45it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:03, 28.46it/s]
Loading 0:  77%|███████▋  | 278/363 [00:31<00:03, 27.71it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:02, 30.85it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:02, 29.23it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:02, 31.87it/s]
Loading 0:  82%|████████▏ | 296/363 [00:31<00:03, 21.55it/s]
Loading 0:  83%|████████▎ | 301/363 [00:31<00:02, 25.23it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:02, 25.37it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:01, 28.69it/s]
Loading 0:  87%|████████▋ | 314/363 [00:32<00:01, 27.34it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:01, 30.36it/s]
Loading 0:  89%|████████▉ | 323/363 [00:32<00:01, 28.80it/s]
Loading 0:  90%|█████████ | 328/363 [00:32<00:01, 30.44it/s]
Loading 0:  91%|█████████▏| 332/363 [00:33<00:01, 20.43it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 24.18it/s]
Loading 0:  94%|█████████▎| 340/363 [00:33<00:01, 22.65it/s]
Loading 0:  95%|█████████▌| 346/363 [00:33<00:00, 28.11it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:00, 27.03it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:00, 30.16it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 27.64it/s]
                                                            

Job chaiml-slerpv1-merge-dp-26736-v3-mkmlizer completed after 144.9s with status: succeeded
Stopping job with name chaiml-slerpv1-merge-dp-26736-v3-mkmlizer
Pipeline stage MKMLizer completed in 145.34s
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-slerpv1-merge-dp-26736-v3
Waiting for inference service chaiml-slerpv1-merge-dp-26736-v3 to be ready
Inference service chaiml-slerpv1-merge-dp-26736-v3 ready after 110.43776059150696s
Pipeline stage MKMLDeployer completed in 110.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1863343715667725s
Received healthy response to inference request in 2.3933961391448975s
Received healthy response to inference request in 2.596416711807251s
Received healthy response to inference request in 2.6323699951171875s
Received healthy response to inference request in 2.5649490356445312s
5 requests
0 failed requests
5th percentile: 2.427706718444824
10th percentile: 2.462017297744751
20th percentile: 2.5306384563446045
30th percentile: 2.571242570877075
40th percentile: 2.583829641342163
50th percentile: 2.596416711807251
60th percentile: 2.6107980251312255
70th percentile: 2.6251793384552
80th percentile: 2.7431628704071045
90th percentile: 2.9647486209869385
95th percentile: 3.0755414962768555
99th percentile: 3.164175796508789
mean time: 2.674693250656128
Pipeline stage StressChecker completed in 14.50s
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 0.66s
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-slerpv1-merge-dp_26736_v3 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 4478.05s
Shutdown handler de-registered
chaiml-slerpv1-merge-dp_26736_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-slerpv1-merge-dp_26736_v3 status is now torndown due to DeploymentManager action