submission_id: cloudyu-chaiml-nemo-dpo-v3_v2
developer_uid: cloudyu
best_of: 8
celo_rating: 1243.26
display_name: cloudyu-chaiml-nemo-dpo-v3_v2
family_friendly_score: 0.5771999999999999
family_friendly_standard_error: 0.0069862745437035325
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}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V3
latencies: [{'batch_size': 1, 'throughput': 0.609092804720863, 'latency_mean': 1.6417196047306062, 'latency_p50': 1.6568372249603271, 'latency_p90': 1.796048927307129}, {'batch_size': 3, 'throughput': 1.1334890725601434, 'latency_mean': 2.6404061985015868, 'latency_p50': 2.6474153995513916, 'latency_p90': 2.9123090028762815}, {'batch_size': 5, 'throughput': 1.348891544132338, 'latency_mean': 3.687710648775101, 'latency_p50': 3.730376362800598, 'latency_p90': 4.12139675617218}, {'batch_size': 6, 'throughput': 1.4429993018250828, 'latency_mean': 4.139958589076996, 'latency_p50': 4.165493011474609, 'latency_p90': 4.594270873069763}, {'batch_size': 8, 'throughput': 1.5006739188722815, 'latency_mean': 5.2990265512466435, 'latency_p50': 5.294904589653015, 'latency_p90': 5.945349812507629}, {'batch_size': 10, 'throughput': 1.535087563590529, 'latency_mean': 6.476097556352616, 'latency_p50': 6.478458046913147, 'latency_p90': 7.297338080406189}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cloudyu/ChaiML-Nemo-DPO-
model_name: cloudyu-chaiml-nemo-dpo-v3_v2
model_num_parameters: 12772070400.0
model_repo: cloudyu/ChaiML-Nemo-DPO-V3
model_size: 13B
num_battles: 18159
num_wins: 8674
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.36
timestamp: 2024-11-24T07:55:42+00:00
us_pacific_date: 2024-11-23
win_ratio: 0.47766947519136516
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 cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: Downloaded to shared memory in 47.067s
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp48d_6arl, device:0
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: quantized model in 36.232s
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V3 in 83.298s
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v2/config.json
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v2/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v2/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v2/tokenizer.json
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v3-v2/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.27it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.56it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.95it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.44it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.72it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 49.78it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 50.44it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:05, 52.42it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.97it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.64it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.72it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.75it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 40.22it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 40.67it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 45.96it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 44.32it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 42.86it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.09it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.90it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 42.29it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 46.76it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:05, 44.63it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.63it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.83it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.60it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.78it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 39.81it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 40.14it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 40.78it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.36it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 44.69it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 43.14it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 48.14it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.83it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 44.06it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 49.16it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 45.91it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 35.64it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 36.07it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 35.04it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:02, 41.69it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 42.31it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 41.30it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 44.66it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 43.45it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 43.82it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 45.34it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 37.24it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 45.61it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 44.56it/s] Loading 0: 81%|████████ | 294/363 [00:06<00:01, 43.39it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 43.13it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:23, 2.52it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:16, 3.24it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.22it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 7.04it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.54it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.03it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.74it/s] Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 20.18it/s] Loading 0: 96%|█████████▌| 348/363 [00:14<00:00, 21.26it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 28.74it/s] Loading 0: 99%|█████████▉| 361/363 [00:15<00:00, 31.13it/s]
Job cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer completed after 104.02s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v3-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.51s
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 cloudyu-chaiml-nemo-dpo-v3-v2
Waiting for inference service cloudyu-chaiml-nemo-dpo-v3-v2 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 cloudyu-chaiml-nemo-dpo-v3-v2 ready after 120.44778227806091s
Pipeline stage MKMLDeployer completed in 120.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2580087184906006s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.0207438468933105s
Received healthy response to inference request in 1.6913073062896729s
Received healthy response to inference request in 1.6847612857818604s
5 requests
1 failed requests
5th percentile: 1.686070489883423
10th percentile: 1.6873796939849854
20th percentile: 1.6899981021881103
30th percentile: 1.7571946144104005
40th percentile: 1.8889692306518555
50th percentile: 2.0207438468933105
60th percentile: 2.1156497955322267
70th percentile: 2.2105557441711428
80th percentile: 5.8324725627899205
90th percentile: 12.981400251388552
95th percentile: 16.555864095687863
99th percentile: 19.415435171127317
mean time: 5.557029819488525
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6415462493896484s
Received healthy response to inference request in 2.131929874420166s
Received healthy response to inference request in 1.709423542022705s
Received healthy response to inference request in 1.956589937210083s
Received healthy response to inference request in 1.8158307075500488s
5 requests
0 failed requests
5th percentile: 1.6551217079162597
10th percentile: 1.6686971664428711
20th percentile: 1.6958480834960938
30th percentile: 1.7307049751281738
40th percentile: 1.7732678413391114
50th percentile: 1.8158307075500488
60th percentile: 1.8721343994140625
70th percentile: 1.928438091278076
80th percentile: 1.9916579246520996
90th percentile: 2.061793899536133
95th percentile: 2.0968618869781492
99th percentile: 2.1249162769317627
mean time: 1.8510640621185304
Pipeline stage StressChecker completed in 39.72s
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 2.15s
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 2.10s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v3_v2 status is now deployed due to DeploymentManager action
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 2796.43s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v3_v2 status is now inactive due to auto deactivation removed underperforming models