developer_uid: azuruce
submission_id: chaiml-nitral-18k-1116-v2_v7
model_name: chaiml-nitral-18k-1116-v2_v7
model_group: ChaiML/nitral_18k_1116_v
status: torndown
timestamp: 2025-02-24T23:16:16+00:00
num_battles: 5314
num_wins: 2531
celo_rating: 1227.75
family_friendly_score: 0.386
family_friendly_standard_error: 0.0068848238902676365
submission_type: basic
model_repo: ChaiML/nitral_18k_1116_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 100
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.800501498260713, 'latency_mean': 1.2491530191898346, 'latency_p50': 1.2596677541732788, 'latency_p90': 1.4018386840820312}, {'batch_size': 5, 'throughput': 2.8700280833516314, 'latency_mean': 1.7347741436958313, 'latency_p50': 1.7317442893981934, 'latency_p90': 1.9433261632919312}, {'batch_size': 10, 'throughput': 4.321925578558941, 'latency_mean': 2.2816655373573305, 'latency_p50': 2.294243097305298, 'latency_p90': 2.573452019691467}, {'batch_size': 15, 'throughput': 4.948794923333898, 'latency_mean': 2.968131127357483, 'latency_p50': 2.976546883583069, 'latency_p90': 3.3573038816452025}, {'batch_size': 20, 'throughput': 5.424540258914691, 'latency_mean': 3.6069701051712038, 'latency_p50': 3.6009637117385864, 'latency_p90': 4.151438283920288}, {'batch_size': 25, 'throughput': 5.581879583003663, 'latency_mean': 4.373105497360229, 'latency_p50': 4.367150068283081, 'latency_p90': 5.002874875068664}, {'batch_size': 30, 'throughput': 5.6516316448329045, 'latency_mean': 5.1392487180233, 'latency_p50': 5.234048008918762, 'latency_p90': 5.885611367225647}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nitral-18k-1116-v2_v7
is_internal_developer: False
language_model: ChaiML/nitral_18k_1116_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 5.57
us_pacific_date: 2025-02-24
win_ratio: 0.47628904779826875
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '####', 'Bot:', '</s>', '\n', 'User:', '<|eot_id|>', '<|im_end|>'], 'max_input_tokens': 100, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-nitral-18k-1116-v2-v7-mkmlizer
Waiting for job on chaiml-nitral-18k-1116-v2-v7-mkmlizer to finish
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ _____ __ __ ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ /___/ ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ Version: 0.12.8 ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ https://mk1.ai ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ belonging to: ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ Chai Research Corp. ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ║ ║
chaiml-nitral-18k-1116-v2-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nitral-18k-1116-v2-v7-mkmlizer: Downloaded to shared memory in 95.008s
chaiml-nitral-18k-1116-v2-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplaqndmdj, device:0
chaiml-nitral-18k-1116-v2-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nitral-18k-1116-v2-v7-mkmlizer: quantized model in 42.534s
chaiml-nitral-18k-1116-v2-v7-mkmlizer: Processed model ChaiML/nitral_18k_1116_v2 in 137.543s
chaiml-nitral-18k-1116-v2-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nitral-18k-1116-v2-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nitral-18k-1116-v2-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nitral-18k-1116-v2-v7
chaiml-nitral-18k-1116-v2-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nitral-18k-1116-v2-v7/config.json
chaiml-nitral-18k-1116-v2-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nitral-18k-1116-v2-v7/special_tokens_map.json
chaiml-nitral-18k-1116-v2-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nitral-18k-1116-v2-v7/tokenizer_config.json
chaiml-nitral-18k-1116-v2-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nitral-18k-1116-v2-v7/tokenizer.json
chaiml-nitral-18k-1116-v2-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nitral-18k-1116-v2-v7/flywheel_model.0.safetensors
chaiml-nitral-18k-1116-v2-v7-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.34it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:13, 26.98it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 23.89it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:11, 30.16it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:14, 22.71it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:16, 19.93it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 25.61it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:12, 26.54it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 27.39it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:12, 26.35it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 28.90it/s] Loading 0: 14%|█▍ | 52/363 [00:02<00:11, 27.14it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:11, 27.59it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:10, 29.34it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:15, 19.01it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:12, 23.94it/s] Loading 0: 20%|██ | 73/363 [00:02<00:12, 24.05it/s] Loading 0: 21%|██ | 77/363 [00:03<00:12, 22.71it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:10, 27.84it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 24.89it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:09, 29.71it/s] Loading 0: 26%|██▌ | 95/363 [00:03<00:10, 26.07it/s] Loading 0: 28%|██▊ | 100/363 [00:03<00:08, 30.55it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 20.80it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 26.74it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 26.07it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 28.51it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 27.45it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 29.74it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:08, 28.44it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:08, 27.76it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:09, 24.13it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 22.59it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 21.71it/s] Loading 0: 43%|████▎ | 156/363 [00:06<00:07, 28.48it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:07, 27.50it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 29.13it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 27.75it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 29.66it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 27.10it/s] Loading 0: 50%|█████ | 182/363 [00:07<00:08, 22.46it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:09, 19.77it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:06, 24.73it/s] Loading 0: 53%|█████▎ | 194/363 [00:07<00:07, 22.91it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 29.35it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 27.51it/s] Loading 0: 58%|█████▊ | 210/363 [00:08<00:05, 29.42it/s] Loading 0: 59%|█████▉ | 214/363 [00:08<00:05, 27.68it/s] Loading 0: 60%|██████ | 218/363 [00:08<00:05, 27.78it/s] Loading 0: 61%|██████ | 222/363 [00:08<00:04, 29.82it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:06, 20.93it/s] Loading 0: 63%|██████▎ | 230/363 [00:09<00:06, 20.56it/s] Loading 0: 65%|██████▌ | 237/363 [00:09<00:04, 27.17it/s] Loading 0: 66%|██████▋ | 241/363 [00:09<00:04, 26.55it/s] Loading 0: 68%|██████▊ | 246/363 [00:09<00:04, 28.59it/s] Loading 0: 69%|██████▉ | 250/363 [00:09<00:04, 27.27it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 29.51it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 27.68it/s] Loading 0: 72%|███████▏ | 263/363 [00:10<00:04, 23.33it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 20.51it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 24.90it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:03, 23.14it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 29.37it/s] Loading 0: 79%|███████▉ | 286/363 [00:11<00:02, 27.62it/s] Loading 0: 80%|████████ | 291/363 [00:11<00:02, 29.64it/s] Loading 0: 81%|████████▏ | 295/363 [00:11<00:02, 28.05it/s] Loading 0: 82%|████████▏ | 299/363 [00:11<00:02, 28.44it/s] Loading 0: 83%|████████▎ | 303/363 [00:11<00:01, 30.75it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 21.61it/s] Loading 0: 86%|████████▌ | 311/363 [00:12<00:02, 21.06it/s] Loading 0: 88%|████████▊ | 318/363 [00:12<00:01, 27.26it/s] Loading 0: 89%|████████▊ | 322/363 [00:12<00:01, 26.09it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 28.40it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 26.79it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 29.09it/s] Loading 0: 94%|█████████▎| 340/363 [00:13<00:00, 27.64it/s] Loading 0: 95%|█████████▍| 344/363 [00:20<00:09, 1.93it/s] Loading 0: 96%|█████████▌| 348/363 [00:20<00:05, 2.59it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.76it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 4.87it/s]
Job chaiml-nitral-18k-1116-v2-v7-mkmlizer completed after 166.04s with status: succeeded
Stopping job with name chaiml-nitral-18k-1116-v2-v7-mkmlizer
Pipeline stage MKMLizer completed in 166.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nitral-18k-1116-v2-v7
Waiting for inference service chaiml-nitral-18k-1116-v2-v7 to be ready
Inference service chaiml-nitral-18k-1116-v2-v7 ready after 290.9659523963928s
Pipeline stage MKMLDeployer completed in 291.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8559389114379883s
Received healthy response to inference request in 1.435539960861206s
Received healthy response to inference request in 1.6436355113983154s
Received healthy response to inference request in 1.3760666847229004s
Received healthy response to inference request in 1.4935657978057861s
5 requests
0 failed requests
5th percentile: 1.3879613399505615
10th percentile: 1.3998559951782226
20th percentile: 1.423645305633545
30th percentile: 1.447145128250122
40th percentile: 1.470355463027954
50th percentile: 1.4935657978057861
60th percentile: 1.553593683242798
70th percentile: 1.6136215686798094
80th percentile: 1.68609619140625
90th percentile: 1.7710175514221191
95th percentile: 1.8134782314300537
99th percentile: 1.8474467754364015
mean time: 1.5609493732452393
Pipeline stage StressChecker completed in 9.08s
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 0.64s
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 0.61s
Shutdown handler de-registered
chaiml-nitral-18k-1116-v2_v7 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nitral-18k-1116-v2-v7-profiler
Waiting for inference service chaiml-nitral-18k-1116-v2-v7-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 1901.40s
Shutdown handler de-registered
chaiml-nitral-18k-1116-v2_v7 status is now inactive due to auto deactivation removed underperforming models
chaiml-nitral-18k-1116-v2_v7 status is now torndown due to DeploymentManager action