developer_uid: NischayDnk
submission_id: chaiml-slerpv1-merge-dp_26736_v2
model_name: chaiml-slerpv1-merge-dp_26736_v2
model_group: ChaiML/slerpv1_merge_dpo
status: torndown
timestamp: 2025-04-02T16:41:23+00:00
num_battles: 8310
num_wins: 4310
celo_rating: 1296.38
family_friendly_score: 0.508
family_friendly_standard_error: 0.007070162657251953
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': 0.37268148314633254, 'latency_mean': 2.6831913101673126, 'latency_p50': 2.668683171272278, 'latency_p90': 2.9714450597763062}, {'batch_size': 2, 'throughput': 0.5823390493851193, 'latency_mean': 3.4251133465766905, 'latency_p50': 3.435904383659363, 'latency_p90': 3.7876238107681273}, {'batch_size': 3, 'throughput': 0.7338548611468598, 'latency_mean': 4.067597523927689, 'latency_p50': 4.070120453834534, 'latency_p90': 4.574696254730225}, {'batch_size': 4, 'throughput': 0.8501929418031577, 'latency_mean': 4.668730167150497, 'latency_p50': 4.671072840690613, 'latency_p90': 5.2047203302383425}, {'batch_size': 5, 'throughput': 0.9474083141497713, 'latency_mean': 5.249805485010147, 'latency_p50': 5.245549321174622, 'latency_p90': 5.952135848999023}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-slerpv1-merge-dp_26736_v2
is_internal_developer: False
language_model: ChaiML/slerpv1_merge_dpo_exp73_exp3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.66
us_pacific_date: 2025-04-02
win_ratio: 0.5186522262334536
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': "{bot_name}: {message}\n'", 'user_template': '{user_name}: {message}<|im_end|>\n', 'response_template': '[/INST]{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-v2-mkmlizer
Waiting for job on chaiml-slerpv1-merge-dp-26736-v2-mkmlizer to finish
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ _____ __ __ ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ /___/ ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ belonging to: ║
chaiml-slerpv1-merge-dp-26736-v2-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-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ║ ║
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: Downloaded to shared memory in 65.519s
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4d3qnd4l, device:0
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: quantized model in 54.473s
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: Processed model ChaiML/slerpv1_merge_dpo_exp73_exp3 in 119.993s
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v2
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v2/config.json
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v2/special_tokens_map.json
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v2/tokenizer_config.json
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v2/tokenizer.json
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v2/flywheel_model.1.safetensors
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-slerpv1-merge-dp-26736-v2/flywheel_model.0.safetensors
chaiml-slerpv1-merge-dp-26736-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:51, 3.14s/it] Loading 0: 1%|▏ | 5/363 [00:06<06:05, 1.02s/it] Loading 0: 2%|▏ | 7/363 [00:06<03:50, 1.55it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:29, 3.92it/s] Loading 0: 4%|▍ | 16/363 [00:06<01:06, 5.20it/s] Loading 0: 6%|▌ | 22/363 [00:07<00:42, 8.01it/s] Loading 0: 7%|▋ | 25/363 [00:07<00:36, 9.32it/s] Loading 0: 9%|▊ | 31/363 [00:07<00:23, 13.97it/s] Loading 0: 9%|▉ | 34/363 [00:07<00:22, 14.77it/s] Loading 0: 11%|█ | 40/363 [00:07<00:15, 20.21it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:14, 21.31it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:12, 24.94it/s] Loading 0: 15%|█▍ | 53/363 [00:08<00:12, 25.09it/s] Loading 0: 16%|█▌ | 58/363 [00:08<00:10, 28.61it/s] Loading 0: 17%|█▋ | 62/363 [00:08<00:14, 20.51it/s] Loading 0: 18%|█▊ | 67/363 [00:08<00:12, 24.32it/s] Loading 0: 20%|█▉ | 71/363 [00:08<00:12, 24.00it/s] Loading 0: 21%|██ | 76/363 [00:09<00:10, 27.61it/s] Loading 0: 22%|██▏ | 80/363 [00:09<00:10, 26.95it/s] Loading 0: 23%|██▎ | 85/363 [00:09<00:09, 29.92it/s] Loading 0: 25%|██▍ | 89/363 [00:09<00:09, 28.55it/s] Loading 0: 26%|██▌ | 94/363 [00:09<00:08, 31.50it/s] Loading 0: 27%|██▋ | 98/363 [00:09<00:12, 21.32it/s] Loading 0: 28%|██▊ | 103/363 [00:10<00:10, 24.78it/s] Loading 0: 29%|██▉ | 106/363 [00:10<00:11, 22.88it/s] Loading 0: 31%|███ | 112/363 [00:10<00:08, 28.38it/s] Loading 0: 32%|███▏ | 116/363 [00:10<00:08, 27.54it/s] Loading 0: 33%|███▎ | 121/363 [00:10<00:07, 30.35it/s] Loading 0: 34%|███▍ | 125/363 [00:10<00:08, 28.54it/s] Loading 0: 36%|███▌ | 130/363 [00:10<00:07, 30.24it/s] Loading 0: 37%|███▋ | 134/363 [00:11<00:08, 27.49it/s] Loading 0: 38%|███▊ | 139/363 [00:11<00:09, 22.88it/s] Loading 0: 39%|███▉ | 142/363 [00:11<00:10, 21.52it/s] Loading 0: 41%|████ | 148/363 [00:11<00:08, 26.83it/s] Loading 0: 42%|████▏ | 151/363 [00:11<00:08, 24.62it/s] Loading 0: 43%|████▎ | 157/363 [00:12<00:07, 29.40it/s] Loading 0: 44%|████▍ | 161/363 [00:12<00:07, 26.99it/s] Loading 0: 46%|████▌ | 166/363 [00:12<00:06, 30.00it/s] Loading 0: 47%|████▋ | 170/363 [00:12<00:07, 27.32it/s] Loading 0: 48%|████▊ | 175/363 [00:12<00:06, 28.89it/s] Loading 0: 49%|████▉ | 178/363 [00:13<00:09, 18.57it/s] Loading 0: 51%|█████ | 184/363 [00:13<00:07, 23.80it/s] Loading 0: 52%|█████▏ | 187/363 [00:28<03:13, 1.10s/it] Loading 0: 53%|█████▎ | 191/363 [00:28<02:15, 1.27it/s] Loading 0: 54%|█████▎ | 195/363 [00:28<01:37, 1.72it/s] Loading 0: 56%|█████▌ | 202/363 [00:28<00:55, 2.91it/s] Loading 0: 57%|█████▋ | 206/363 [00:28<00:41, 3.76it/s] Loading 0: 58%|█████▊ | 211/363 [00:28<00:28, 5.27it/s] Loading 0: 59%|█████▉ | 215/363 [00:29<00:23, 6.18it/s] Loading 0: 61%|██████ | 220/363 [00:29<00:16, 8.47it/s] Loading 0: 62%|██████▏ | 224/363 [00:29<00:13, 10.31it/s] Loading 0: 63%|██████▎ | 229/363 [00:29<00:09, 13.48it/s] Loading 0: 64%|██████▍ | 233/363 [00:29<00:08, 15.44it/s] Loading 0: 66%|██████▌ | 238/363 [00:29<00:06, 19.33it/s] Loading 0: 67%|██████▋ | 242/363 [00:30<00:06, 20.04it/s] Loading 0: 68%|██████▊ | 247/363 [00:30<00:05, 23.18it/s] Loading 0: 69%|██████▉ | 251/363 [00:30<00:04, 23.23it/s] Loading 0: 71%|███████ | 256/363 [00:30<00:05, 20.99it/s] Loading 0: 71%|███████▏ | 259/363 [00:30<00:05, 20.27it/s] Loading 0: 73%|███████▎ | 265/363 [00:31<00:03, 25.86it/s] Loading 0: 74%|███████▍ | 269/363 [00:31<00:03, 25.83it/s] Loading 0: 75%|███████▌ | 274/363 [00:31<00:03, 28.18it/s] Loading 0: 77%|███████▋ | 278/363 [00:31<00:03, 26.02it/s] Loading 0: 78%|███████▊ | 283/363 [00:31<00:02, 29.07it/s] Loading 0: 79%|███████▉ | 287/363 [00:31<00:02, 27.72it/s] Loading 0: 80%|████████ | 292/363 [00:31<00:02, 30.75it/s] Loading 0: 82%|████████▏ | 296/363 [00:32<00:03, 21.69it/s] Loading 0: 83%|████████▎ | 301/363 [00:32<00:02, 25.42it/s] Loading 0: 84%|████████▍ | 305/363 [00:32<00:02, 25.26it/s] Loading 0: 85%|████████▌ | 310/363 [00:32<00:01, 27.97it/s] Loading 0: 87%|████████▋ | 314/363 [00:32<00:01, 26.15it/s] Loading 0: 88%|████████▊ | 319/363 [00:33<00:01, 29.41it/s] Loading 0: 89%|████████▉ | 323/363 [00:33<00:01, 27.76it/s] Loading 0: 90%|█████████ | 328/363 [00:33<00:01, 30.68it/s] Loading 0: 91%|█████████▏| 332/363 [00:33<00:01, 21.16it/s] Loading 0: 93%|█████████▎| 337/363 [00:33<00:01, 24.82it/s] Loading 0: 94%|█████████▎| 340/363 [00:33<00:01, 22.85it/s] Loading 0: 95%|█████████▌| 346/363 [00:34<00:00, 27.47it/s] Loading 0: 96%|█████████▋| 350/363 [00:34<00:00, 26.05it/s] Loading 0: 98%|█████████▊| 355/363 [00:34<00:00, 28.79it/s] Loading 0: 99%|█████████▉| 359/363 [00:34<00:00, 26.77it/s]
Job chaiml-slerpv1-merge-dp-26736-v2-mkmlizer completed after 145.18s with status: succeeded
Stopping job with name chaiml-slerpv1-merge-dp-26736-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.62s
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-slerpv1-merge-dp-26736-v2
Waiting for inference service chaiml-slerpv1-merge-dp-26736-v2 to be ready
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)
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)
Inference service chaiml-slerpv1-merge-dp-26736-v2 ready after 110.4160008430481s
Pipeline stage MKMLDeployer completed in 110.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2253706455230713s
Received healthy response to inference request in 2.5827648639678955s
Received healthy response to inference request in 2.7161054611206055s
Received healthy response to inference request in 2.473700761795044s
Received healthy response to inference request in 2.7073161602020264s
5 requests
0 failed requests
5th percentile: 2.495513582229614
10th percentile: 2.5173264026641844
20th percentile: 2.5609520435333253
30th percentile: 2.6076751232147215
40th percentile: 2.657495641708374
50th percentile: 2.7073161602020264
60th percentile: 2.710831880569458
70th percentile: 2.7143476009368896
80th percentile: 2.8179584980010985
90th percentile: 3.021664571762085
95th percentile: 3.123517608642578
99th percentile: 3.2050000381469728
mean time: 2.7410515785217284
Pipeline stage StressChecker completed in 14.84s
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 0.71s
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 0.72s
Shutdown handler de-registered
chaiml-slerpv1-merge-dp_26736_v2 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-slerpv1-merge-dp-26736-v2-profiler
Waiting for inference service chaiml-slerpv1-merge-dp-26736-v2-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2881.46s
Shutdown handler de-registered
chaiml-slerpv1-merge-dp_26736_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-slerpv1-merge-dp_26736_v2 status is now torndown due to DeploymentManager action