developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_6685_v2
model_name: chaiml-mistral-nemo-dpo-_6685_v2
model_group: ChaiML/mistral_nemo_dpo_
status: inactive
timestamp: 2024-12-15T23:09:00+00:00
num_battles: 11850
num_wins: 6208
celo_rating: 1247.02
family_friendly_score: 0.5798
family_friendly_standard_error: 0.006980429213164474
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_baseline_albert_20241213_v1-checkpoint-2496
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6313103315614075, 'latency_mean': 1.5839454305171967, 'latency_p50': 1.5773814916610718, 'latency_p90': 1.7498881578445435}, {'batch_size': 3, 'throughput': 1.2603957628403455, 'latency_mean': 2.3749854719638823, 'latency_p50': 2.363164186477661, 'latency_p90': 2.60212128162384}, {'batch_size': 5, 'throughput': 1.5724806586994213, 'latency_mean': 3.1568740689754486, 'latency_p50': 3.152785897254944, 'latency_p90': 3.507560467720032}, {'batch_size': 6, 'throughput': 1.6871558278351537, 'latency_mean': 3.5337970840930937, 'latency_p50': 3.533737063407898, 'latency_p90': 3.956988883018494}, {'batch_size': 8, 'throughput': 1.8182724611685641, 'latency_mean': 4.355986791849136, 'latency_p50': 4.390825867652893, 'latency_p90': 4.881343293190002}, {'batch_size': 10, 'throughput': 1.9036188825651175, 'latency_mean': 5.2058587539196015, 'latency_p50': 5.196915507316589, 'latency_p90': 5.935740947723389}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_6685_v2
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_baseline_albert_20241213_v1-checkpoint-2496
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2024-12-15
win_ratio: 0.5238818565400843
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': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, '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-mistral-nemo-dpo-6685-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-6685-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: Downloaded to shared memory in 36.374s
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd6fajtlr, device:0
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: quantized model in 36.971s
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_baseline_albert_20241213_v1-checkpoint-2496 in 73.345s
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6685-v2
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6685-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6685-v2/config.json
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6685-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6685-v2/tokenizer.json
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6685-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-6685-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 25.99it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 44.28it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:07, 46.52it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 41.90it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.03it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.22it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.81it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.92it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 44.21it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 33.04it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.14it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 38.28it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 37.96it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 37.33it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 42.41it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 41.55it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 40.30it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 44.79it/s] Loading 0: 31%|███ | 113/363 [00:02<00:06, 40.56it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:06, 40.07it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:04, 47.58it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 45.58it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 44.39it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.89it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.39it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.96it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.15it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:04, 41.30it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 41.54it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 47.05it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 45.23it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.58it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.57it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 44.44it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 42.93it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 46.98it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 46.67it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 46.88it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:05, 25.81it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:05, 25.12it/s] Loading 0: 65%|██████▍ | 235/363 [00:05<00:04, 29.19it/s] Loading 0: 66%|██████▌ | 239/363 [00:06<00:04, 29.14it/s] Loading 0: 68%|██████▊ | 246/363 [00:06<00:03, 37.14it/s] Loading 0: 69%|██████▉ | 251/363 [00:06<00:02, 38.21it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 39.88it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 40.24it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 40.53it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 45.92it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 45.22it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 44.83it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 49.41it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 47.14it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:21, 2.78it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:15, 3.49it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.46it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:05, 7.24it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.72it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.27it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 17.11it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 20.65it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.83it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 30.28it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.23it/s]
Job chaiml-mistral-nemo-dpo-6685-v2-mkmlizer completed after 94.94s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-6685-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-6685-v2
Waiting for inference service chaiml-mistral-nemo-dpo-6685-v2 to be ready
Inference service chaiml-mistral-nemo-dpo-6685-v2 ready after 210.77448964118958s
Pipeline stage MKMLDeployer completed in 211.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5616681575775146s
Received healthy response to inference request in 1.2536542415618896s
Received healthy response to inference request in 0.845630407333374s
Received healthy response to inference request in 0.9740562438964844s
Received healthy response to inference request in 0.8357384204864502s
5 requests
0 failed requests
5th percentile: 0.837716817855835
10th percentile: 0.8396952152252197
20th percentile: 0.8436520099639893
30th percentile: 0.8713155746459961
40th percentile: 0.9226859092712403
50th percentile: 0.9740562438964844
60th percentile: 1.0858954429626464
70th percentile: 1.1977346420288086
80th percentile: 1.3152570247650146
90th percentile: 1.4384625911712647
95th percentile: 1.5000653743743897
99th percentile: 1.5493476009368896
mean time: 1.0941494941711425
Pipeline stage StressChecker completed in 7.00s
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 2.25s
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 2.61s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_6685_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 2490.21s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_6685_v2 status is now inactive due to auto deactivation removed underperforming models