chaiml-arli-24b-sft-exp2

developer_uid: NischayDnk

submission_id: chaiml-arli-24b-sft-exp2_v2

model_name: chaiml-arli-24b-sft-exp2_v2

model_group: ChaiML/arli-24b-sft-exp2

status: torndown

timestamp: 2025-04-24T16:31:01+00:00

num_battles: 8110

num_wins: 4240

celo_rating: 1305.85

family_friendly_score: 0.5416000000000001

family_friendly_standard_error: 0.007046551497009016

submission_type: basic

model_repo: ChaiML/arli-24b-sft-exp2

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': 0.525117239216507, 'latency_mean': 1.9042826211452484, 'latency_p50': 1.9187192916870117, 'latency_p90': 2.08079354763031}, {'batch_size': 3, 'throughput': 1.0812849578287216, 'latency_mean': 2.762526860237122, 'latency_p50': 2.7610726356506348, 'latency_p90': 3.034720778465271}, {'batch_size': 5, 'throughput': 1.3849749218917469, 'latency_mean': 3.5954116773605347, 'latency_p50': 3.5965158939361572, 'latency_p90': 3.9731918573379517}, {'batch_size': 6, 'throughput': 1.4974883096644207, 'latency_mean': 3.98750107049942, 'latency_p50': 3.968872547149658, 'latency_p90': 4.4958205938339235}, {'batch_size': 8, 'throughput': 1.6353069669880114, 'latency_mean': 4.86034234046936, 'latency_p50': 4.838713765144348, 'latency_p90': 5.422111582756043}, {'batch_size': 10, 'throughput': 1.7195487110351122, 'latency_mean': 5.788303484916687, 'latency_p50': 5.816846609115601, 'latency_p90': 6.5087809562683105}]

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

display_name: chaiml-arli-24b-sft-exp2_v2

is_internal_developer: False

language_model: ChaiML/arli-24b-sft-exp2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.42

us_pacific_date: 2025-04-24

win_ratio: 0.5228113440197287

generation_params: {'temperature': 0.45, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|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-arli-24b-sft-exp2-v2-mkmlizer
Waiting for job on chaiml-arli-24b-sft-exp2-v2-mkmlizer to finish
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║       /___/                                                         ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║                                                                     ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║                                                                     ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║                                                                     ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ║                                                                     ║
chaiml-arli-24b-sft-exp2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-arli-24b-sft-exp2-v2-mkmlizer: Downloaded to shared memory in 61.714s
chaiml-arli-24b-sft-exp2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpafs2doz2, device:0
chaiml-arli-24b-sft-exp2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission chaiml-ghost-girl-letha_81645_v3: HTTPConnectionPool(host='chaiml-ghost-girl-letha-81645-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-arli-24b-sft-exp2-v2-mkmlizer: quantized model in 54.309s
chaiml-arli-24b-sft-exp2-v2-mkmlizer: Processed model ChaiML/arli-24b-sft-exp2 in 116.023s
chaiml-arli-24b-sft-exp2-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-arli-24b-sft-exp2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-arli-24b-sft-exp2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp2-v2
chaiml-arli-24b-sft-exp2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp2-v2/special_tokens_map.json
chaiml-arli-24b-sft-exp2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp2-v2/tokenizer_config.json
chaiml-arli-24b-sft-exp2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp2-v2/tokenizer.json
chaiml-arli-24b-sft-exp2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp2-v2/flywheel_model.1.safetensors
chaiml-arli-24b-sft-exp2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp2-v2/flywheel_model.0.safetensors
chaiml-arli-24b-sft-exp2-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.06it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.32it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.91it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.57it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.87it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.26it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.05it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.21it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.80it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.82it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.91it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.19it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.77it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.62it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.52it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.98it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.06it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:10, 26.24it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.72it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.57it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.86it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.49it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.66it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.53it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 24.38it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.42it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.19it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.85it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 26.41it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 27.90it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:09, 24.26it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 27.14it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 26.87it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.72it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 33.84it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:09, 23.00it/s]
Loading 0:  43%|████▎     | 155/363 [00:05<00:08, 23.34it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:10, 19.26it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.17it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 25.32it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 27.97it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:07, 26.30it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 26.89it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.47it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.21it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.13it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 23.88it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:02,  1.13s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:30,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.17it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:52,  2.86it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.09it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.23it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.29it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.26it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.00it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.92it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.51it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.63it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.88it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.64it/s]
Loading 0:  71%|███████   | 258/363 [00:24<00:04, 23.09it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 30.13it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 23.53it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.63it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.58it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.84it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.36it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.11it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.37it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.64it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.04it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 23.24it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 21.35it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 22.52it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 22.46it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 25.82it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.43it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.44it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.22it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.09it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.07it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:13,  1.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:05,  2.77it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.48it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.17it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00,  6.71it/s]
                                                            
Job chaiml-arli-24b-sft-exp2-v2-mkmlizer completed after 145.67s with status: succeeded
Stopping job with name chaiml-arli-24b-sft-exp2-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.13s
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-arli-24b-sft-exp2-v2
Waiting for inference service chaiml-arli-24b-sft-exp2-v2 to be ready
Inference service chaiml-arli-24b-sft-exp2-v2 ready after 140.52620363235474s
Pipeline stage MKMLDeployer completed in 141.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.57454514503479s
Received healthy response to inference request in 2.30430006980896s
Received healthy response to inference request in 2.1447360515594482s
Received healthy response to inference request in 1.8888282775878906s
Received healthy response to inference request in 2.080669641494751s
5 requests
0 failed requests
5th percentile: 1.9271965503692627
10th percentile: 1.9655648231506349
20th percentile: 2.042301368713379
30th percentile: 2.0934829235076906
40th percentile: 2.1191094875335694
50th percentile: 2.1447360515594482
60th percentile: 2.208561658859253
70th percentile: 2.2723872661590576
80th percentile: 2.358349084854126
90th percentile: 2.466447114944458
95th percentile: 2.520496129989624
99th percentile: 2.563735342025757
mean time: 2.198615837097168
Pipeline stage StressChecker completed in 12.48s
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 0.78s
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-arli-24b-sft-exp2_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-arli-24b-sft-exp2-v2-profiler
Waiting for inference service chaiml-arli-24b-sft-exp2-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 4641.13s
Shutdown handler de-registered
chaiml-arli-24b-sft-exp2_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-arli-24b-sft-exp2_v2 status is now torndown due to DeploymentManager action