developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_9775_v1
model_name: chaiml-mistral-nemo-dpo-_9775_v1
model_group: ChaiML/mistral_nemo_dpo_
status: torndown
timestamp: 2024-12-20T17:25:31+00:00
num_battles: 8702
num_wins: 4180
celo_rating: 1236.39
family_friendly_score: 0.5952
family_friendly_standard_error: 0.006941713909403066
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-621
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6323870055216245, 'latency_mean': 1.5812323820590972, 'latency_p50': 1.592826247215271, 'latency_p90': 1.7487723112106324}, {'batch_size': 3, 'throughput': 1.2473262604394109, 'latency_mean': 2.3946991574764254, 'latency_p50': 2.388627529144287, 'latency_p90': 2.6271015644073485}, {'batch_size': 5, 'throughput': 1.5673565022319262, 'latency_mean': 3.1758898448944093, 'latency_p50': 3.1886051893234253, 'latency_p90': 3.517783832550049}, {'batch_size': 6, 'throughput': 1.6856318183743033, 'latency_mean': 3.540217125415802, 'latency_p50': 3.5300309658050537, 'latency_p90': 3.9929831504821776}, {'batch_size': 8, 'throughput': 1.8440377306739277, 'latency_mean': 4.310550104379654, 'latency_p50': 4.294172406196594, 'latency_p90': 4.835150170326233}, {'batch_size': 10, 'throughput': 1.924755711411023, 'latency_mean': 5.162238010168076, 'latency_p50': 5.194711804389954, 'latency_p90': 5.927279949188232}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_9775_v1
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-621
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2024-12-20
win_ratio: 0.48034934497816595
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-9775-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-9775-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_giruk_2024-11-13: ('http://chaiml-llama-8b-multihea-7878-v5-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:37550->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: Downloaded to shared memory in 48.953s
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk066hp_0, device:0
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: quantized model in 35.906s
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-621 in 84.859s
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9775-v1
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9775-v1/config.json
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9775-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9775-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9775-v1/tokenizer.json
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9775-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-9775-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.48it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.69it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.99it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.11it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.00it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 49.22it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 48.81it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.99it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 49.05it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.79it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.58it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.28it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.51it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 42.42it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 48.47it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 47.78it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:05, 46.00it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:04, 52.07it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 48.44it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:04, 48.87it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 49.90it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:04, 46.89it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:04, 45.99it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.04it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 35.57it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.28it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.84it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 40.71it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 39.73it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 44.81it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 43.03it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.25it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 45.83it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 46.74it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:04, 39.14it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 46.93it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:03, 44.90it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 46.04it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 31.86it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.37it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 36.76it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 37.21it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 39.18it/s] Loading 0: 70%|██████▉ | 253/363 [00:05<00:02, 39.35it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 39.00it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.49it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 43.92it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 37.64it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 45.38it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 43.73it/s] Loading 0: 81%|████████ | 294/363 [00:06<00:01, 38.97it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 40.99it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:23, 2.51it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:17, 3.23it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.18it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:06, 6.60it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:04, 8.73it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:02, 11.47it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:01, 14.98it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:01, 18.13it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 24.24it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 27.74it/s] Loading 0: 99%|█████████▊| 358/363 [00:15<00:00, 30.48it/s]
Job chaiml-mistral-nemo-dpo-9775-v1-mkmlizer completed after 115.15s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-9775-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.66s
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 chaiml-mistral-nemo-dpo-9775-v1
Waiting for inference service chaiml-mistral-nemo-dpo-9775-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-9775-v1 ready after 261.24671387672424s
Pipeline stage MKMLDeployer completed in 261.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5320522785186768s
Received healthy response to inference request in 2.0296363830566406s
Received healthy response to inference request in 2.0355262756347656s
Received healthy response to inference request in 1.1870977878570557s
Received healthy response to inference request in 0.8536479473114014s
5 requests
0 failed requests
5th percentile: 0.9203379154205322
10th percentile: 0.9870278835296631
20th percentile: 1.1204078197479248
30th percentile: 1.2560886859893798
40th percentile: 1.3940704822540284
50th percentile: 1.5320522785186768
60th percentile: 1.7310859203338622
70th percentile: 1.9301195621490477
80th percentile: 2.030814361572266
90th percentile: 2.0331703186035157
95th percentile: 2.0343482971191404
99th percentile: 2.0352906799316406
mean time: 1.527592134475708
Pipeline stage StressChecker completed in 8.83s
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 0.61s
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 0.95s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_9775_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 2331.73s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_9775_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_9775_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_9775_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_9775_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1