developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v8
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-18T01:05:22+00:00
num_battles: 14184
num_wins: 7431
celo_rating: 1281.56
family_friendly_score: 0.565
family_friendly_standard_error: 0.00701106268692557
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V21
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6144564470355064, 'latency_mean': 1.627399662733078, 'latency_p50': 1.6231200695037842, 'latency_p90': 1.7922118663787843}, {'batch_size': 3, 'throughput': 1.1510107751209897, 'latency_mean': 2.6009430074691773, 'latency_p50': 2.589661121368408, 'latency_p90': 2.8865481853485107}, {'batch_size': 5, 'throughput': 1.368689344457689, 'latency_mean': 3.6374071419239042, 'latency_p50': 3.6177380084991455, 'latency_p90': 4.027246427536011}, {'batch_size': 6, 'throughput': 1.438800249136586, 'latency_mean': 4.15110330581665, 'latency_p50': 4.182476758956909, 'latency_p90': 4.636381888389587}, {'batch_size': 8, 'throughput': 1.5057273110551994, 'latency_mean': 5.271900700330734, 'latency_p50': 5.256896138191223, 'latency_p90': 5.892705130577087}, {'batch_size': 10, 'throughput': 1.5385482374212247, 'latency_mean': 6.4534139931201935, 'latency_p50': 6.470921754837036, 'latency_p90': 7.34217598438263}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v21_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V21
model_size: 13B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2024-12-17
win_ratio: 0.5239001692047377
generation_params: {'temperature': 1.25, '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}
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-nemo-dpo-v21-v8-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v8-mkmlizer to finish
cloudyu-nemo-dpo-v21-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v8-mkmlizer: Downloaded to shared memory in 33.120s
cloudyu-nemo-dpo-v21-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzoeogzvo, device:0
cloudyu-nemo-dpo-v21-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v8-mkmlizer: quantized model in 36.003s
cloudyu-nemo-dpo-v21-v8-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 69.123s
cloudyu-nemo-dpo-v21-v8-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v8
cloudyu-nemo-dpo-v21-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v8/special_tokens_map.json
cloudyu-nemo-dpo-v21-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v8/config.json
cloudyu-nemo-dpo-v21-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v8/tokenizer_config.json
cloudyu-nemo-dpo-v21-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v8/tokenizer.json
cloudyu-nemo-dpo-v21-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v8/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v21-v8-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.06it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.94it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.14it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.78it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 52.49it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 49.83it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 50.05it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:06, 52.19it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 49.67it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 36.31it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 36.43it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 41.02it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 42.33it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 42.16it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.69it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 44.95it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 42.50it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.00it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.48it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 42.23it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 46.97it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:05, 44.68it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 42.09it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 31.69it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 32.93it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.23it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 39.18it/s] Loading 0: 45%|████▍ | 162/363 [00:03<00:04, 41.61it/s] Loading 0: 46%|████▌ | 167/363 [00:03<00:05, 37.30it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 45.04it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 43.19it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.56it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 48.03it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.49it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.91it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 48.61it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 45.83it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 34.71it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 35.11it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 32.78it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.76it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 40.44it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 40.17it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 45.49it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 44.08it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 43.78it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 47.90it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 45.23it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 44.13it/s] Loading 0: 80%|████████ | 291/363 [00:06<00:01, 47.93it/s] Loading 0: 82%|████████▏ | 296/363 [00:06<00:01, 47.04it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 46.98it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:20, 2.63it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.34it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.40it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.32it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.34it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.25it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.72it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 19.60it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 24.72it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 28.39it/s]
Job cloudyu-nemo-dpo-v21-v8-mkmlizer completed after 94.12s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.63s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v21-v8
Waiting for inference service cloudyu-nemo-dpo-v21-v8 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v21-v8 ready after 240.90483045578003s
Pipeline stage MKMLDeployer completed in 241.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4189062118530273s
Received healthy response to inference request in 1.6389169692993164s
Received healthy response to inference request in 1.794513463973999s
Received healthy response to inference request in 2.0174930095672607s
Received healthy response to inference request in 1.7004377841949463s
5 requests
0 failed requests
5th percentile: 1.6512211322784425
10th percentile: 1.6635252952575683
20th percentile: 1.6881336212158202
30th percentile: 1.719252920150757
40th percentile: 1.756883192062378
50th percentile: 1.794513463973999
60th percentile: 1.8837052822113036
70th percentile: 1.9728971004486084
80th percentile: 2.0977756500244142
90th percentile: 2.258340930938721
95th percentile: 2.338623571395874
99th percentile: 2.4028496837615965
mean time: 1.91405348777771
Pipeline stage StressChecker completed in 10.86s
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 2.56s
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 2.33s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v8 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 3033.71s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v8 status is now inactive due to auto deactivation removed underperforming models