developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v4_v1
model_name: cloudyu-chaiml-nemo-dpo-v4_v1
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-11-24T08:51:37+00:00
num_battles: 16541
num_wins: 8100
celo_rating: 1256.64
family_friendly_score: 0.5700000000000001
family_friendly_standard_error: 0.007001428425685719
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V4
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6234796181465907, 'latency_mean': 1.6038403761386872, 'latency_p50': 1.6013739109039307, 'latency_p90': 1.7719849586486816}, {'batch_size': 3, 'throughput': 1.151581699580121, 'latency_mean': 2.603059504032135, 'latency_p50': 2.6186341047286987, 'latency_p90': 2.8892526149749758}, {'batch_size': 5, 'throughput': 1.3942892350216454, 'latency_mean': 3.5709588861465456, 'latency_p50': 3.621836304664612, 'latency_p90': 3.938902974128723}, {'batch_size': 6, 'throughput': 1.4821334195316025, 'latency_mean': 4.023398352861404, 'latency_p50': 4.027257919311523, 'latency_p90': 4.552429056167602}, {'batch_size': 8, 'throughput': 1.552003933204853, 'latency_mean': 5.121212490797043, 'latency_p50': 5.186432838439941, 'latency_p90': 5.7353174686431885}, {'batch_size': 10, 'throughput': 1.5876725984052726, 'latency_mean': 6.252645950317383, 'latency_p50': 6.238181233406067, 'latency_p90': 7.065692353248596}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v4_v1
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V4
model_size: 13B
ranking_group: single
throughput_3p7s: 1.43
us_pacific_date: 2024-11-24
win_ratio: 0.48969227978961366
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 cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: Downloaded to shared memory in 47.349s
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfvrap3ay, device:0
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: quantized model in 36.303s
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V4 in 83.653s
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v1
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v1/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v1/tokenizer.json
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v1/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.95it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.17it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.88it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.35it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.88it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 49.69it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 50.24it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 52.28it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.74it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.16it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 34.95it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 38.94it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.95it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:07, 39.01it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.21it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 42.85it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 41.82it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 45.91it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 46.77it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 43.76it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 44.54it/s] Loading 0: 35%|███▍ | 127/363 [00:02<00:06, 37.42it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:04, 45.87it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:04, 45.62it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 31.42it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.19it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 37.35it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:05, 38.19it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:05, 38.80it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 44.05it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 42.55it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.84it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.80it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 44.10it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.38it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 48.31it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 45.54it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 34.51it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 34.88it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 34.08it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 40.69it/s] Loading 0: 67%|██████▋ | 243/363 [00:05<00:02, 42.05it/s] Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 35.51it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 38.38it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 35.88it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 40.43it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 39.68it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 39.03it/s] Loading 0: 77%|███████▋ | 279/363 [00:06<00:02, 40.71it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 33.86it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 41.30it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 41.81it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 45.69it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:22, 2.51it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:14, 3.41it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.45it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.34it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.32it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.19it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:01, 16.48it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 19.55it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 25.50it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.55it/s]
Job cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer completed after 104.66s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v4-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.20s
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 cloudyu-chaiml-nemo-dpo-v4-v1
Waiting for inference service cloudyu-chaiml-nemo-dpo-v4-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v4-v1 ready after 120.47073268890381s
Pipeline stage MKMLDeployer completed in 121.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1545979976654053s
Received healthy response to inference request in 1.7763562202453613s
Received healthy response to inference request in 1.9321439266204834s
Received healthy response to inference request in 2.1015853881835938s
Received healthy response to inference request in 2.142773389816284s
5 requests
0 failed requests
5th percentile: 1.8075137615203858
10th percentile: 1.8386713027954102
20th percentile: 1.900986385345459
30th percentile: 1.9660322189331054
40th percentile: 2.0338088035583497
50th percentile: 2.1015853881835938
60th percentile: 2.11806058883667
70th percentile: 2.134535789489746
80th percentile: 2.145138311386108
90th percentile: 2.1498681545257567
95th percentile: 2.1522330760955812
99th percentile: 2.1541250133514405
mean time: 2.0214913845062257
Pipeline stage StressChecker completed in 11.50s
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 2.58s
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 2.37s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v4_v1 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 2825.81s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v4_v1 status is now inactive due to auto deactivation removed underperforming models