developer_uid: NischayDnk
submission_id: nischaydnk-mistralnemo-d_4010_v1
model_name: nischaydnk-mistralnemo-d_4010_v1
model_group: NischayDnk/Mistralnemo-d
status: torndown
timestamp: 2025-01-04T08:07:21+00:00
num_battles: 18619
num_wins: 8861
celo_rating: 1245.01
family_friendly_score: 0.5944
family_friendly_standard_error: 0.006943898616771417
submission_type: basic
model_repo: NischayDnk/Mistralnemo-dpo-v3-rp-ch110
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6131850803520951, 'latency_mean': 1.630769612789154, 'latency_p50': 1.6346455812454224, 'latency_p90': 1.7901139020919798}, {'batch_size': 3, 'throughput': 1.1450625002174648, 'latency_mean': 2.6110089802742005, 'latency_p50': 2.6093286275863647, 'latency_p90': 2.8953783750534057}, {'batch_size': 5, 'throughput': 1.372529637578533, 'latency_mean': 3.615337944030762, 'latency_p50': 3.6246219873428345, 'latency_p90': 4.055535364151001}, {'batch_size': 6, 'throughput': 1.4437765396587368, 'latency_mean': 4.137303513288498, 'latency_p50': 4.1382914781570435, 'latency_p90': 4.642025423049927}, {'batch_size': 8, 'throughput': 1.5118025519338265, 'latency_mean': 5.258448858261108, 'latency_p50': 5.238648772239685, 'latency_p90': 5.840920400619507}, {'batch_size': 10, 'throughput': 1.542301980126798, 'latency_mean': 6.431190088987351, 'latency_p50': 6.451595067977905, 'latency_p90': 7.215210103988647}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nischaydnk-mistralnemo-d_4010_v1
is_internal_developer: False
language_model: NischayDnk/Mistralnemo-dpo-v3-rp-ch110
model_size: 13B
ranking_group: single
throughput_3p7s: 1.4
us_pacific_date: 2025-01-04
win_ratio: 0.4759117030989849
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 nischaydnk-mistralnemo-d-4010-v1-mkmlizer
Waiting for job on nischaydnk-mistralnemo-d-4010-v1-mkmlizer to finish
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ _____ __ __ ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ /___/ ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ Version: 0.11.12 ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ https://mk1.ai ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ belonging to: ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ Chai Research Corp. ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ║ ║
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: Downloaded to shared memory in 45.230s
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp62kowrp8, device:0
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: quantized model in 35.721s
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: Processed model NischayDnk/Mistralnemo-dpo-v3-rp-ch110 in 80.951s
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: creating bucket guanaco-mkml-models
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nischaydnk-mistralnemo-d-4010-v1
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nischaydnk-mistralnemo-d-4010-v1/config.json
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nischaydnk-mistralnemo-d-4010-v1/special_tokens_map.json
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nischaydnk-mistralnemo-d-4010-v1/tokenizer_config.json
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nischaydnk-mistralnemo-d-4010-v1/tokenizer.json
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nischaydnk-mistralnemo-d-4010-v1/flywheel_model.0.safetensors
nischaydnk-mistralnemo-d-4010-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.40it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 51.40it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 48.36it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 49.69it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 52.53it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 50.32it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 50.93it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 52.72it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 50.56it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 36.67it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 36.91it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 41.34it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.17it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.31it/s] Loading 0: 25%|██▍ | 90/363 [00:01<00:05, 46.67it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 45.04it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:05, 43.98it/s] Loading 0: 30%|███ | 109/363 [00:02<00:04, 52.24it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 46.19it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 42.97it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 45.10it/s] Loading 0: 36%|███▌ | 131/363 [00:02<00:05, 46.00it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 39.54it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 33.36it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.09it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.79it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 39.01it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:04, 40.47it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 42.28it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 40.96it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 39.52it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 44.39it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:03, 43.86it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 44.05it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 42.45it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 41.46it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 45.74it/s] Loading 0: 59%|█████▉ | 215/363 [00:04<00:03, 44.77it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:02, 48.16it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 29.18it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 29.68it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 37.74it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 38.67it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 40.57it/s] Loading 0: 69%|██████▉ | 252/363 [00:05<00:02, 42.82it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 38.15it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 46.18it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 43.90it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 43.00it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 47.47it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 44.99it/s] Loading 0: 81%|████████ | 294/363 [00:06<00:01, 43.93it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 49.77it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:19, 2.83it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:13, 3.74it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.80it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.71it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.72it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.62it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.94it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 19.96it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 26.02it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.56it/s]
Job nischaydnk-mistralnemo-d-4010-v1-mkmlizer completed after 104.56s with status: succeeded
Stopping job with name nischaydnk-mistralnemo-d-4010-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.03s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nischaydnk-mistralnemo-d-4010-v1
Waiting for inference service nischaydnk-mistralnemo-d-4010-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service nischaydnk-mistralnemo-d-4010-v1 ready after 332.74007987976074s
Pipeline stage MKMLDeployer completed in 333.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.438873767852783s
Received healthy response to inference request in 1.6904444694519043s
Received healthy response to inference request in 1.66754150390625s
Received healthy response to inference request in 1.67728590965271s
Received healthy response to inference request in 2.053555488586426s
5 requests
0 failed requests
5th percentile: 1.669490385055542
10th percentile: 1.671439266204834
20th percentile: 1.675337028503418
30th percentile: 1.6799176216125489
40th percentile: 1.6851810455322265
50th percentile: 1.6904444694519043
60th percentile: 1.835688877105713
70th percentile: 1.9809332847595214
80th percentile: 2.1306191444396974
90th percentile: 2.28474645614624
95th percentile: 2.3618101119995116
99th percentile: 2.423461036682129
mean time: 1.9055402278900146
Pipeline stage StressChecker completed in 11.31s
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 1.35s
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
nischaydnk-mistralnemo-d_4010_v1 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 nischaydnk-mistralnemo-d-4010-v1-profiler
Waiting for inference service nischaydnk-mistralnemo-d-4010-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 9111.42s
Shutdown handler de-registered
nischaydnk-mistralnemo-d_4010_v1 status is now inactive due to auto deactivation removed underperforming models
nischaydnk-mistralnemo-d_4010_v1 status is now torndown due to DeploymentManager action
nischaydnk-mistralnemo-d_4010_v1 status is now torndown due to DeploymentManager action
nischaydnk-mistralnemo-d_4010_v1 status is now torndown due to DeploymentManager action