chaiml-mistral-nemo-dpo-_1624

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_1624_v1

model_name: chaiml-mistral-nemo-dpo-_1624_v1

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-20T23:15:57+00:00

num_battles: 16638

num_wins: 7816

celo_rating: 1227.8

family_friendly_score: 0.5993999999999999

family_friendly_standard_error: 0.006929929869775018

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1173

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6259011459599916, 'latency_mean': 1.5976035106182098, 'latency_p50': 1.6040171384811401, 'latency_p90': 1.7554962635040283}, {'batch_size': 3, 'throughput': 1.265448453069336, 'latency_mean': 2.3677747881412508, 'latency_p50': 2.368301749229431, 'latency_p90': 2.603839087486267}, {'batch_size': 5, 'throughput': 1.582611426427754, 'latency_mean': 3.131751685142517, 'latency_p50': 3.1514732837677, 'latency_p90': 3.530503273010254}, {'batch_size': 6, 'throughput': 1.722058747413812, 'latency_mean': 3.468840472698212, 'latency_p50': 3.4765560626983643, 'latency_p90': 3.9060657024383545}, {'batch_size': 8, 'throughput': 1.8571238330921431, 'latency_mean': 4.278435424566269, 'latency_p50': 4.28927481174469, 'latency_p90': 4.840352177619934}, {'batch_size': 10, 'throughput': 1.9453610687207894, 'latency_mean': 5.097476208209992, 'latency_p50': 5.1406004428863525, 'latency_p90': 5.756405758857727}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_1624_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1173

model_size: 13B

ranking_group: single

throughput_3p7s: 1.78

us_pacific_date: 2024-12-20

win_ratio: 0.46976800096165405

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-mistral-nemo-dpo-1624-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-1624-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: quantized model in 36.166s
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1173 in 88.893s
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v1
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v1/config.json
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v1/tokenizer.json
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-1624-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.22it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.13it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.66it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 46.42it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.13it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.90it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.36it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 51.23it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.68it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.49it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.55it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.10it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 43.38it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 44.12it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 48.85it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 47.43it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 46.41it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 54.75it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 48.65it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 46.88it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.57it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 47.02it/s]
Loading 0:  37%|███▋      | 136/363 [00:02<00:05, 40.62it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.91it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.38it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.91it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.17it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.94it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.88it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:04, 46.42it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.86it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 40.67it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 44.90it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 43.51it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 44.23it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 44.01it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 43.13it/s]
Loading 0:  60%|██████    | 218/363 [00:04<00:03, 43.41it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 31.51it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.11it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 29.96it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 37.27it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:03, 39.73it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:03, 34.89it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.64it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.98it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.48it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 44.01it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 43.35it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 46.69it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 45.25it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 44.05it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 42.25it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:22,  2.60it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.32it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.27it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.01it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.48it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.52it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 19.97it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 22.91it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.40it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.70it/s]
                                                            
Job chaiml-mistral-nemo-dpo-1624-v1-mkmlizer completed after 114.26s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-1624-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.71s
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 chaiml-mistral-nemo-dpo-1624-v1
Waiting for inference service chaiml-mistral-nemo-dpo-1624-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-1624-v1 ready after 261.577273607254s
Pipeline stage MKMLDeployer completed in 262.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2520322799682617s
Received healthy response to inference request in 1.3591206073760986s
Received healthy response to inference request in 1.9537277221679688s
Received healthy response to inference request in 1.1592450141906738s
Received healthy response to inference request in 0.9323573112487793s
5 requests
0 failed requests
5th percentile: 0.9777348518371582
10th percentile: 1.0231123924255372
20th percentile: 1.1138674736022949
30th percentile: 1.1992201328277587
40th percentile: 1.2791703701019288
50th percentile: 1.3591206073760986
60th percentile: 1.5969634532928465
70th percentile: 1.8348062992095946
80th percentile: 2.0133886337280273
90th percentile: 2.1327104568481445
95th percentile: 2.192371368408203
99th percentile: 2.24010009765625
mean time: 1.5312965869903565
Pipeline stage StressChecker completed in 9.10s
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 0.97s
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 0.67s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1624_v1 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-1624-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-1624-v1-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 2140.72s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1624_v1 status is now inactive due to auto deactivation removed underperforming models