chaiml-slerpv4-merge-sl_50980

developer_uid: NischayDnk

submission_id: chaiml-slerpv4-merge-sl_50980_v2

model_name: chaiml-slerpv4-merge-sl_50980_v2

model_group: ChaiML/slerpv4_merge_sle

status: torndown

timestamp: 2025-04-02T20:48:10+00:00

num_battles: 6552

num_wins: 3390

celo_rating: 1306.58

family_friendly_score: 0.552

family_friendly_standard_error: 0.007032723512267492

submission_type: basic

model_repo: ChaiML/slerpv4_merge_slerpv1_dpodel57ff

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': 0.36847643163873833, 'latency_mean': 2.7138202929496766, 'latency_p50': 2.718094229698181, 'latency_p90': 2.9994169950485228}, {'batch_size': 2, 'throughput': 0.5785612599139, 'latency_mean': 3.447176023721695, 'latency_p50': 3.4051188230514526, 'latency_p90': 3.8326987266540526}, {'batch_size': 3, 'throughput': 0.7237098501053529, 'latency_mean': 4.127441645860672, 'latency_p50': 4.141074299812317, 'latency_p90': 4.550315642356872}, {'batch_size': 4, 'throughput': 0.848467574107836, 'latency_mean': 4.698049944639206, 'latency_p50': 4.701481938362122, 'latency_p90': 5.289036846160888}, {'batch_size': 5, 'throughput': 0.9351191715087923, 'latency_mean': 5.31462212562561, 'latency_p50': 5.320693135261536, 'latency_p90': 5.94437186717987}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-slerpv4-merge-sl_50980_v2

is_internal_developer: False

language_model: ChaiML/slerpv4_merge_slerpv1_dpodel57ff

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-04-02

win_ratio: 0.5173992673992674

generation_params: {'temperature': 0.5, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', '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-slerpv4-merge-sl-50980-v2-mkmlizer
Waiting for job on chaiml-slerpv4-merge-sl-50980-v2-mkmlizer to finish
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║       /___/                                                         ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║                                                                     ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║                                                                     ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║                                                                     ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ║                                                                     ║
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: Downloaded to shared memory in 65.150s
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4jrrbr_n, device:0
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v2: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: quantized model in 54.122s
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: Processed model ChaiML/slerpv4_merge_slerpv1_dpodel57ff in 119.272s
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-slerpv4-merge-sl-50980-v2
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-gemma-exp3-dpo-s_66157_v1: HTTPConnectionPool(host='chaiml-gemma-exp3-dpo-s-66157-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-slerpv4-merge-sl-50980-v2/config.json
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-slerpv4-merge-sl-50980-v2/special_tokens_map.json
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-slerpv4-merge-sl-50980-v2/tokenizer_config.json
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-slerpv4-merge-sl-50980-v2/tokenizer.json
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-slerpv4-merge-sl-50980-v2/flywheel_model.1.safetensors
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-slerpv4-merge-sl-50980-v2/flywheel_model.0.safetensors
chaiml-slerpv4-merge-sl-50980-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:25,  3.06s/it]
Loading 0:   1%|▏         | 5/363 [00:06<05:57,  1.00it/s]
Loading 0:   2%|▏         | 7/363 [00:06<03:45,  1.58it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:27,  3.98it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:06,  5.23it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:42,  7.96it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:36,  9.26it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:23, 13.86it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:22, 14.79it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:15, 20.22it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 20.65it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.74it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:13, 23.56it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 27.05it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:14, 20.07it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:12, 23.68it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:13, 21.78it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 27.21it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:10, 26.30it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 29.14it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:10, 27.16it/s]
Loading 0:  25%|██▌       | 92/363 [00:09<00:09, 27.66it/s]
Loading 0:  26%|██▌       | 95/363 [00:09<00:09, 27.87it/s]
Loading 0:  27%|██▋       | 98/363 [00:09<00:13, 19.16it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:11, 23.45it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:12, 21.29it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 27.24it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:09, 26.33it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:08, 28.92it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:08, 27.20it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:07, 30.37it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 28.17it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:09, 23.00it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:10, 21.71it/s]
Loading 0:  41%|████      | 148/363 [00:11<00:07, 27.07it/s]
Loading 0:  42%|████▏     | 151/363 [00:11<00:08, 23.71it/s]
Loading 0:  43%|████▎     | 155/363 [00:12<00:07, 26.55it/s]
Loading 0:  44%|████▎     | 158/363 [00:12<00:07, 26.78it/s]
Loading 0:  44%|████▍     | 161/363 [00:12<00:07, 25.57it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 28.21it/s]
Loading 0:  47%|████▋     | 169/363 [00:12<00:07, 24.68it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:06, 29.16it/s]
Loading 0:  49%|████▉     | 178/363 [00:13<00:09, 18.88it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 24.21it/s]
Loading 0:  52%|█████▏    | 187/363 [00:27<03:11,  1.09s/it]
Loading 0:  53%|█████▎    | 191/363 [00:27<02:13,  1.29it/s]
Loading 0:  54%|█████▎    | 195/363 [00:28<01:36,  1.75it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:54,  2.97it/s]
Loading 0:  57%|█████▋    | 206/363 [00:28<00:40,  3.85it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<00:28,  5.38it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:23,  6.21it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:16,  8.47it/s]
Loading 0:  61%|██████▏   | 223/363 [00:29<00:14,  9.48it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:09, 13.47it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:08, 15.33it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:06, 19.07it/s]
Loading 0:  67%|██████▋   | 242/363 [00:29<00:05, 20.38it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:04, 23.88it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:04, 23.55it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:05, 20.86it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:05, 20.07it/s]
Loading 0:  73%|███████▎  | 265/363 [00:30<00:03, 25.36it/s]
Loading 0:  74%|███████▍  | 268/363 [00:30<00:03, 23.80it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 29.24it/s]
Loading 0:  77%|███████▋  | 278/363 [00:31<00:03, 27.76it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:02, 30.27it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:02, 28.62it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:02, 31.37it/s]
Loading 0:  82%|████████▏ | 296/363 [00:32<00:03, 20.97it/s]
Loading 0:  83%|████████▎ | 301/363 [00:32<00:02, 24.70it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:02, 23.91it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:01, 27.51it/s]
Loading 0:  87%|████████▋ | 314/363 [00:32<00:01, 26.45it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:01, 29.45it/s]
Loading 0:  89%|████████▉ | 323/363 [00:32<00:01, 27.82it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 29.71it/s]
Loading 0:  91%|█████████▏| 332/363 [00:33<00:01, 19.72it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 22.88it/s]
Loading 0:  94%|█████████▎| 340/363 [00:33<00:01, 20.91it/s]
Loading 0:  95%|█████████▌| 346/363 [00:33<00:00, 25.46it/s]
Loading 0:  96%|█████████▌| 349/363 [00:34<00:00, 23.31it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:00, 27.87it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 26.46it/s]
                                                            
Job chaiml-slerpv4-merge-sl-50980-v2-mkmlizer completed after 145.56s with status: succeeded
Stopping job with name chaiml-slerpv4-merge-sl-50980-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.03s
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-slerpv4-merge-sl-50980-v2
Waiting for inference service chaiml-slerpv4-merge-sl-50980-v2 to be ready
Failed to get response for submission chaiml-gemma-exp3-dpo-s_66157_v1: HTTPConnectionPool(host='chaiml-gemma-exp3-dpo-s-66157-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-slerpv4-merge-sl_50980_v1: HTTPConnectionPool(host='chaiml-slerpv4-merge-sl-50980-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)
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-slerpv4-merge-sl-50980-v2 ready after 110.45592308044434s
Pipeline stage MKMLDeployer completed in 110.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.43538761138916s
Received healthy response to inference request in 2.56250262260437s
Received healthy response to inference request in 2.8216869831085205s
Received healthy response to inference request in 2.919856548309326s
Received healthy response to inference request in 2.479098081588745s
5 requests
0 failed requests
5th percentile: 2.4957789897918703
10th percentile: 2.512459897994995
20th percentile: 2.545821714401245
30th percentile: 2.6143394947052
40th percentile: 2.7180132389068605
50th percentile: 2.8216869831085205
60th percentile: 2.8609548091888426
70th percentile: 2.900222635269165
80th percentile: 3.022962760925293
90th percentile: 3.2291751861572267
95th percentile: 3.332281398773193
99th percentile: 3.414766368865967
mean time: 2.8437063694000244
Pipeline stage StressChecker completed in 15.36s
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 0.69s
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 0.71s
Shutdown handler de-registered
chaiml-slerpv4-merge-sl_50980_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 0.12s
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-slerpv4-merge-sl-50980-v2-profiler
Waiting for inference service chaiml-slerpv4-merge-sl-50980-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5436.06s
Shutdown handler de-registered
chaiml-slerpv4-merge-sl_50980_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-slerpv4-merge-sl_50980_v2 status is now torndown due to DeploymentManager action