submission_id: cloudyu-chaiml-nemo-dpo-v5_v3
developer_uid: cloudyu
best_of: 8
celo_rating: 1259.75
display_name: cloudyu-chaiml-nemo-dpo-v5_v3
family_friendly_score: 0.5631999999999999
family_friendly_standard_error: 0.007014353284515972
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': 100, '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-V5
latencies: [{'batch_size': 1, 'throughput': 0.6135601353389811, 'latency_mean': 1.6297677946090698, 'latency_p50': 1.6277129650115967, 'latency_p90': 1.7920804262161254}, {'batch_size': 3, 'throughput': 1.1419183329499105, 'latency_mean': 2.6204865431785582, 'latency_p50': 2.5996891260147095, 'latency_p90': 2.906089210510254}, {'batch_size': 5, 'throughput': 1.3759454108522888, 'latency_mean': 3.6154551661014556, 'latency_p50': 3.6111884117126465, 'latency_p90': 4.008893656730652}, {'batch_size': 6, 'throughput': 1.4537299350527717, 'latency_mean': 4.100827219486237, 'latency_p50': 4.1012104749679565, 'latency_p90': 4.585330533981323}, {'batch_size': 8, 'throughput': 1.5143779940229118, 'latency_mean': 5.251574184894562, 'latency_p50': 5.260497450828552, 'latency_p90': 5.863106298446655}, {'batch_size': 10, 'throughput': 1.5677914235872887, 'latency_mean': 6.339163123369217, 'latency_p50': 6.372945189476013, 'latency_p90': 7.091270852088928}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cloudyu/ChaiML-Nemo-DPO-
model_name: cloudyu-chaiml-nemo-dpo-v5_v3
model_num_parameters: 12772070400.0
model_repo: cloudyu/ChaiML-Nemo-DPO-V5
model_size: 13B
num_battles: 25600
num_wins: 12767
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.4
timestamp: 2024-11-24T11:04:12+00:00
us_pacific_date: 2024-11-24
win_ratio: 0.4987109375
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-v5-v3-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: Downloaded to shared memory in 33.307s
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp4sbqx2y, device:0
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: quantized model in 36.035s
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V5 in 69.343s
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v3
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v3/config.json
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v3/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v3/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v3/tokenizer.json
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v3/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.04it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.84it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.62it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.59it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 52.36it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 49.31it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 49.22it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.76it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.32it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 33.93it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 33.08it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.53it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 40.54it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.02it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.46it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 44.82it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 42.82it/s] Loading 0: 30%|███ | 109/363 [00:02<00:04, 51.27it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 48.05it/s] Loading 0: 33%|███▎ | 121/363 [00:02<00:05, 46.75it/s] Loading 0: 35%|███▍ | 127/363 [00:02<00:05, 42.45it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:04, 49.15it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:04, 47.49it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 32.63it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.88it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 38.08it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:05, 39.20it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 39.44it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 44.80it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 43.11it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.05it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.25it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.32it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.80it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 48.39it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 45.96it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 35.32it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 35.24it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 33.78it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.99it/s] Loading 0: 67%|██████▋ | 243/363 [00:05<00:02, 42.12it/s] Loading 0: 68%|██████▊ | 248/363 [00:05<00:03, 38.02it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 45.33it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 43.28it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 42.46it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 42.74it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 35.17it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 43.37it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 42.87it/s] Loading 0: 81%|████████ | 294/363 [00:06<00:01, 41.99it/s] Loading 0: 83%|████████▎ | 300/363 [00:07<00:01, 46.18it/s] Loading 0: 84%|████████▍ | 305/363 [00:13<00:22, 2.60it/s] Loading 0: 85%|████████▌ | 309/363 [00:14<00:16, 3.32it/s] Loading 0: 86%|████████▌ | 313/363 [00:14<00:11, 4.30it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.74it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.25it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.85it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.74it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.43it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 23.64it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 30.08it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.78it/s]
Job cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer completed after 93.95s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v5-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.47s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v5-v3
Waiting for inference service cloudyu-chaiml-nemo-dpo-v5-v3 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
Inference service cloudyu-chaiml-nemo-dpo-v5-v3 ready after 120.42274165153503s
Pipeline stage MKMLDeployer completed in 121.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1082212924957275s
Received healthy response to inference request in 1.7368204593658447s
Received healthy response to inference request in 1.7377216815948486s
Received healthy response to inference request in 1.773510456085205s
Received healthy response to inference request in 1.7031059265136719s
5 requests
0 failed requests
5th percentile: 1.7098488330841064
10th percentile: 1.716591739654541
20th percentile: 1.7300775527954102
30th percentile: 1.7370007038116455
40th percentile: 1.737361192703247
50th percentile: 1.7377216815948486
60th percentile: 1.7520371913909911
70th percentile: 1.7663527011871338
80th percentile: 1.8404526233673095
90th percentile: 1.9743369579315186
95th percentile: 2.041279125213623
99th percentile: 2.0948328590393066
mean time: 1.8118759632110595
Pipeline stage StressChecker completed in 10.39s
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 2.17s
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 2.04s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v5_v3 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v5-v3-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v5-v3-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 2976.45s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v5_v3 status is now inactive due to auto deactivation removed underperforming models