developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_4097_v1
model_name: chaiml-mistral-nemo-dpo-_4097_v1
model_group: ChaiML/mistral_nemo_dpo_
status: torndown
timestamp: 2024-12-21T19:39:20+00:00
num_battles: 18890
num_wins: 8831
celo_rating: 1234.24
family_friendly_score: 0.601
family_friendly_standard_error: 0.006925301437482704
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-345
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6418800505662592, 'latency_mean': 1.5578595042228698, 'latency_p50': 1.5459195375442505, 'latency_p90': 1.7183400869369507}, {'batch_size': 3, 'throughput': 1.2731438070531653, 'latency_mean': 2.3560813105106355, 'latency_p50': 2.350894808769226, 'latency_p90': 2.6021369457244874}, {'batch_size': 5, 'throughput': 1.59869537921541, 'latency_mean': 3.1023069286346434, 'latency_p50': 3.123727798461914, 'latency_p90': 3.532013511657715}, {'batch_size': 6, 'throughput': 1.7293734719421503, 'latency_mean': 3.4588826870918274, 'latency_p50': 3.4505916833877563, 'latency_p90': 3.953403687477112}, {'batch_size': 8, 'throughput': 1.8986612061132524, 'latency_mean': 4.177663260698319, 'latency_p50': 4.1632643938064575, 'latency_p90': 4.8145643949508665}, {'batch_size': 10, 'throughput': 1.9738436761535845, 'latency_mean': 5.020810446739197, 'latency_p50': 5.023312926292419, 'latency_p90': 5.665684008598328}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_4097_v1
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-345
model_size: 13B
ranking_group: single
throughput_3p7s: 1.8
us_pacific_date: 2024-12-21
win_ratio: 0.467496029645315
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-4097-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-4097-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: Downloaded to shared memory in 55.663s
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpolsn7_gn, device:0
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: quantized model in 37.006s
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-345 in 92.669s
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4097-v1
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4097-v1/tokenizer.json
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4097-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-4097-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 25.78it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 43.58it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.58it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:07, 44.33it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:07, 42.57it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:07, 41.84it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 48.64it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:06, 46.64it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 44.30it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 50.48it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:10, 29.71it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.46it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.43it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 38.51it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.12it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.21it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.38it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 43.03it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 41.31it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 39.16it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 46.16it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 44.07it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 44.32it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 44.96it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.82it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 27.43it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.51it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.45it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.76it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.86it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.49it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.95it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 40.58it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 40.90it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:04, 40.93it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 32.81it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 39.86it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 40.38it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.53it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 26.24it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.51it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.29it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.21it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 38.95it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.95it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.40it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.79it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.98it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 41.69it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 45.25it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 44.22it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 43.48it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 44.88it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 45.73it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.34it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.26it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:05,  7.11it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:03,  9.11it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 12.93it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 15.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 17.97it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.10it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 27.91it/s]
                                                            

Job chaiml-mistral-nemo-dpo-4097-v1-mkmlizer completed after 114.9s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-4097-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.39s
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-4097-v1
Waiting for inference service chaiml-mistral-nemo-dpo-4097-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
Inference service chaiml-mistral-nemo-dpo-4097-v1 ready after 261.0497522354126s
Pipeline stage MKMLDeployer completed in 261.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5790269374847412s
Received healthy response to inference request in 0.9692678451538086s
Received healthy response to inference request in 1.512108325958252s
Received healthy response to inference request in 2.025134325027466s
Received healthy response to inference request in 1.4075958728790283s
5 requests
0 failed requests
5th percentile: 1.0569334506988526
10th percentile: 1.1445990562438966
20th percentile: 1.3199302673339843
30th percentile: 1.4284983634948731
40th percentile: 1.4703033447265625
50th percentile: 1.512108325958252
60th percentile: 1.5388757705688476
70th percentile: 1.5656432151794433
80th percentile: 1.6682484149932861
90th percentile: 1.846691370010376
95th percentile: 1.935912847518921
99th percentile: 2.0072900295257567
mean time: 1.4986266613006591
Pipeline stage StressChecker completed in 8.76s
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 0.64s
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 0.65s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_4097_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 2514.93s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_4097_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_4097_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_4097_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_4097_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1