developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v21_v7
model_name: cloudyu-nemo-dpo-v21_v1
model_group: cloudyu/Nemo-DPO-V21
status: inactive
timestamp: 2024-12-18T00:28:10+00:00
num_battles: 16369
num_wins: 8415
celo_rating: 1273.73
family_friendly_score: 0.5628
family_friendly_standard_error: 0.007015071774401171
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': 0.6118457251417273, 'latency_mean': 1.6343428635597228, 'latency_p50': 1.6328924894332886, 'latency_p90': 1.8019661664962767}, {'batch_size': 3, 'throughput': 1.1098168478752797, 'latency_mean': 2.6882173407077787, 'latency_p50': 2.6691547632217407, 'latency_p90': 2.9942878007888796}, {'batch_size': 5, 'throughput': 1.3436465585867319, 'latency_mean': 3.7105845654010774, 'latency_p50': 3.6860668659210205, 'latency_p90': 4.195734214782715}, {'batch_size': 6, 'throughput': 1.4130425961070439, 'latency_mean': 4.222009588479995, 'latency_p50': 4.188841462135315, 'latency_p90': 4.724671149253846}, {'batch_size': 8, 'throughput': 1.4675645665730912, 'latency_mean': 5.407016884088517, 'latency_p50': 5.405066728591919, 'latency_p90': 6.124351811408997}, {'batch_size': 10, 'throughput': 1.514313228556302, 'latency_mean': 6.548203983306885, 'latency_p50': 6.497852683067322, 'latency_p90': 7.436763286590576}]
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: 1.35
us_pacific_date: 2024-12-17
win_ratio: 0.5140814955098051
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}
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-v7-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v21-v7-mkmlizer to finish
cloudyu-nemo-dpo-v21-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ║ ║
cloudyu-nemo-dpo-v21-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v21-v7-mkmlizer: Downloaded to shared memory in 32.090s
cloudyu-nemo-dpo-v21-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp86f4nd9, device:0
cloudyu-nemo-dpo-v21-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v21-v7-mkmlizer: quantized model in 36.480s
cloudyu-nemo-dpo-v21-v7-mkmlizer: Processed model cloudyu/Nemo-DPO-V21 in 68.570s
cloudyu-nemo-dpo-v21-v7-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v21-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v21-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v7
cloudyu-nemo-dpo-v21-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v7/config.json
cloudyu-nemo-dpo-v21-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v7/special_tokens_map.json
cloudyu-nemo-dpo-v21-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v7/tokenizer_config.json
cloudyu-nemo-dpo-v21-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v7/tokenizer.json
cloudyu-nemo-dpo-v21-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v21-v7/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v21-v7-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.64it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 43.42it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 42.74it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:07, 43.34it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:07, 44.79it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 36.27it/s] Loading 0: 11%|█ | 40/363 [00:00<00:07, 45.21it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:07, 43.28it/s] Loading 0: 14%|█▍ | 51/363 [00:01<00:07, 41.97it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:06, 48.59it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:09, 30.15it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 37.78it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 38.90it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 39.93it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 45.16it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 42.12it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 41.74it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 48.12it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 43.67it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 43.01it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 47.77it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 45.17it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.20it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.82it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.28it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.79it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 39.91it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:04, 40.33it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 41.16it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.90it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 46.06it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 45.20it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 50.07it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 47.23it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 45.23it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 49.81it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 45.73it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 46.75it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.31it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.13it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 38.23it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:03, 39.65it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 39.59it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 43.82it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 44.28it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 45.46it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 43.67it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 41.73it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 47.36it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 45.96it/s] Loading 0: 81%|████████ | 294/363 [00:07<00:01, 44.58it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 45.64it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:23, 2.46it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:17, 3.18it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.16it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.93it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.41it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.99it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.75it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.30it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.42it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.57it/s] Loading 0: 99%|█████████▉| 361/363 [00:15<00:00, 32.64it/s]
Job cloudyu-nemo-dpo-v21-v7-mkmlizer completed after 93.82s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v21-v7-mkmlizer
Pipeline stage MKMLizer completed in 94.32s
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-nemo-dpo-v21-v7
Waiting for inference service cloudyu-nemo-dpo-v21-v7 to be ready
Inference service cloudyu-nemo-dpo-v21-v7 ready after 241.1396520137787s
Pipeline stage MKMLDeployer completed in 241.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.946147918701172s
Received healthy response to inference request in 1.6413886547088623s
Received healthy response to inference request in 1.7108304500579834s
Received healthy response to inference request in 1.6711678504943848s
Received healthy response to inference request in 2.335177183151245s
5 requests
0 failed requests
5th percentile: 1.6473444938659667
10th percentile: 1.6533003330230713
20th percentile: 1.6652120113372804
30th percentile: 1.6791003704071046
40th percentile: 1.694965410232544
50th percentile: 1.7108304500579834
60th percentile: 1.960569143295288
70th percentile: 2.2103078365325928
80th percentile: 2.4573713302612306
90th percentile: 2.701759624481201
95th percentile: 2.8239537715911864
99th percentile: 2.9217090892791746
mean time: 2.0609424114227295
Pipeline stage StressChecker completed in 11.56s
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 2.21s
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 2.03s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v7 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 3080.75s
Shutdown handler de-registered
cloudyu-nemo-dpo-v21_v7 status is now inactive due to auto deactivation removed underperforming models