cloudyu-chaiml-nemo-dpo-v8

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v8_v1

model_name: cloudyu-chaiml-nemo-dpo-v8_v1

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-11-24T13:39:43+00:00

num_battles: 29765

num_wins: 14931

celo_rating: 1262.74

family_friendly_score: 0.5568

family_friendly_standard_error: 0.007025293730514049

submission_type: basic

model_repo: cloudyu/ChaiML-Nemo-DPO-V8

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6119989791884856, 'latency_mean': 1.6338913702964784, 'latency_p50': 1.642406940460205, 'latency_p90': 1.784209394454956}, {'batch_size': 3, 'throughput': 1.1316638139082285, 'latency_mean': 2.6425990974903106, 'latency_p50': 2.648085117340088, 'latency_p90': 2.902845788002014}, {'batch_size': 5, 'throughput': 1.3799637862091128, 'latency_mean': 3.605164510011673, 'latency_p50': 3.6116198301315308, 'latency_p90': 4.101019048690796}, {'batch_size': 6, 'throughput': 1.4382821051196397, 'latency_mean': 4.153738138675689, 'latency_p50': 4.1252511739730835, 'latency_p90': 4.691023993492126}, {'batch_size': 8, 'throughput': 1.5135822750926395, 'latency_mean': 5.24114213347435, 'latency_p50': 5.272455334663391, 'latency_p90': 5.880850005149841}, {'batch_size': 10, 'throughput': 1.5392393453613198, 'latency_mean': 6.438842010498047, 'latency_p50': 6.424763202667236, 'latency_p90': 7.268917846679687}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-chaiml-nemo-dpo-v8_v1

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V8

model_size: 13B

ranking_group: single

throughput_3p7s: 1.4

us_pacific_date: 2024-11-24

win_ratio: 0.5016294305392239

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-v8-v1-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: Downloaded to shared memory in 48.854s
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp27lwij4z, device:0
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: quantized model in 35.510s
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V8 in 84.364s
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v1
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v1/config.json
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v1/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v1/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v1/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:08,  3.02s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:50,  1.23it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:43,  3.37it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.93it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  8.07it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.61it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 14.99it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.89it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.42it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.05it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 29.03it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 31.57it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:07, 37.83it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:07, 39.17it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:07, 39.85it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 44.82it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 43.91it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 43.49it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 48.70it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 46.10it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:05, 44.78it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:06, 34.77it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:06, 34.14it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:05, 38.92it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 40.29it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 40.62it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 47.01it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:04, 46.32it/s]
Loading 0:  44%|████▍     | 160/363 [00:09<00:04, 44.51it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:03, 50.04it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:03, 48.05it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 45.93it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:03, 50.27it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:03, 46.34it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:03, 44.78it/s]
Loading 0:  56%|█████▌    | 202/363 [00:10<00:04, 35.49it/s]
Loading 0:  57%|█████▋    | 206/363 [00:10<00:04, 35.40it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 39.76it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 40.37it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 40.66it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:02, 46.46it/s]
Loading 0:  65%|██████▌   | 236/363 [00:11<00:02, 45.54it/s]
Loading 0:  66%|██████▋   | 241/363 [00:11<00:02, 44.66it/s]
Loading 0:  68%|██████▊   | 247/363 [00:11<00:02, 47.56it/s]
Loading 0:  69%|██████▉   | 252/363 [00:11<00:02, 47.63it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 43.03it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:01, 50.14it/s]
Loading 0:  75%|███████▍  | 272/363 [00:12<00:01, 48.17it/s]
Loading 0:  76%|███████▋  | 277/363 [00:12<00:01, 47.29it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:02, 37.67it/s]
Loading 0:  79%|███████▉  | 288/363 [00:12<00:01, 39.12it/s]
Loading 0:  81%|████████  | 294/363 [00:12<00:01, 37.38it/s]
Loading 0:  83%|████████▎ | 301/363 [00:13<00:01, 43.69it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:01, 43.17it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 42.55it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 43.84it/s]
Loading 0:  88%|████████▊ | 321/363 [00:13<00:01, 37.84it/s]
Loading 0:  90%|█████████ | 328/363 [00:13<00:00, 45.25it/s]
Loading 0:  92%|█████████▏| 333/363 [00:13<00:00, 45.48it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 45.97it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 46.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 39.06it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 47.33it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 42.88it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer completed after 104.52s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v8-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.06s
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-v8-v1
Waiting for inference service cloudyu-chaiml-nemo-dpo-v8-v1 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
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
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-v8-v1 ready after 120.49629187583923s
Pipeline stage MKMLDeployer completed in 121.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6294450759887695s
Received healthy response to inference request in 1.8283274173736572s
Received healthy response to inference request in 1.9996154308319092s
Received healthy response to inference request in 1.7948765754699707s
Received healthy response to inference request in 2.0409717559814453s
5 requests
0 failed requests
5th percentile: 1.801566743850708
10th percentile: 1.8082569122314454
20th percentile: 1.82163724899292
30th percentile: 1.8625850200653076
40th percentile: 1.9311002254486085
50th percentile: 1.9996154308319092
60th percentile: 2.0161579608917237
70th percentile: 2.0327004909515383
80th percentile: 2.1586664199829104
90th percentile: 2.3940557479858398
95th percentile: 2.5117504119873044
99th percentile: 2.6059061431884767
mean time: 2.0586472511291505
Pipeline stage StressChecker completed in 11.71s
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 2.55s
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 2.29s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v8_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 2996.92s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v8_v1 status is now inactive due to auto deactivation removed underperforming models