rirv938-ties-40k-2500-b_21634

developer_uid: rirv938

submission_id: rirv938-ties-40k-2500-b_21634_v1

model_name: rirv938-ties-40k-2500-b_21634_v1

model_group: rirv938/ties_40k_2500_bo

status: inactive

timestamp: 2025-01-03T21:22:32+00:00

num_battles: 12537

num_wins: 6464

celo_rating: 1278.67

family_friendly_score: 0.61

family_friendly_standard_error: 0.006897825744392214

submission_type: basic

model_repo: rirv938/ties_40k_2500_bo8_80w_dpo4_v2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6447912200595991, 'latency_mean': 1.5508313274383545, 'latency_p50': 1.5681580305099487, 'latency_p90': 1.710043239593506}, {'batch_size': 3, 'throughput': 1.2374491617923657, 'latency_mean': 2.418419395685196, 'latency_p50': 2.3967891931533813, 'latency_p90': 2.6964609146118166}, {'batch_size': 5, 'throughput': 1.5144360172786286, 'latency_mean': 3.283038946390152, 'latency_p50': 3.2983384132385254, 'latency_p90': 3.6739663600921633}, {'batch_size': 6, 'throughput': 1.6033335759120222, 'latency_mean': 3.718472853899002, 'latency_p50': 3.7007189989089966, 'latency_p90': 4.183429861068725}, {'batch_size': 8, 'throughput': 1.6976923565003053, 'latency_mean': 4.682840301990509, 'latency_p50': 4.712486147880554, 'latency_p90': 5.276710748672485}, {'batch_size': 10, 'throughput': 1.7232711796442897, 'latency_mean': 5.758219723701477, 'latency_p50': 5.779220700263977, 'latency_p90': 6.603130793571472}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-ties-40k-2500-b_21634_v1

is_internal_developer: True

language_model: rirv938/ties_40k_2500_bo8_80w_dpo4_v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.61

us_pacific_date: 2025-01-03

win_ratio: 0.5155938422270081

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', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{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 rirv938-ties-40k-2500-b-21634-v1-mkmlizer
Waiting for job on rirv938-ties-40k-2500-b-21634-v1-mkmlizer to finish
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║       /___/                                                         ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║                                                                     ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║                                                                     ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║                                                                     ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ║                                                                     ║
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: Downloaded to shared memory in 93.566s
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9mbpoytd, device:0
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: quantized model in 43.034s
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: Processed model rirv938/ties_40k_2500_bo8_80w_dpo4_v2 in 136.600s
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-ties-40k-2500-b-21634-v1
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-ties-40k-2500-b-21634-v1/tokenizer_config.json
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-ties-40k-2500-b-21634-v1/tokenizer.json
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-ties-40k-2500-b-21634-v1/flywheel_model.0.safetensors
rirv938-ties-40k-2500-b-21634-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.77it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.46it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.27it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 32.83it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.16it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.95it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.41it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:12, 25.61it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.78it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.09it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.71it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:13, 23.92it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 29.47it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 30.51it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.65it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.46it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 25.33it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.96it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.81it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 25.06it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.79it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.78it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.08it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:11, 21.62it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.82it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 24.50it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.29it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.34it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.39it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.43it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 28.98it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.71it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.19it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.86it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.57it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.60it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.90it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.33it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.59it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.86it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.83it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.24it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 27.84it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.39it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.13it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.38it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:05, 30.34it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 27.92it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 27.70it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 30.26it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 21.53it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 20.90it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 25.94it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.11it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 27.58it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 24.36it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 28.86it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:04, 25.06it/s]
Loading 0:  72%|███████▏  | 262/363 [00:09<00:03, 29.56it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 19.63it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 24.09it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 22.51it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:03, 26.81it/s]
Loading 0:  78%|███████▊  | 284/363 [00:10<00:03, 23.85it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.78it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 24.09it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 28.43it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:02, 29.39it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 21.15it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 20.34it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 24.80it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 22.72it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 27.03it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 24.17it/s]
Loading 0:  92%|█████████▏| 334/363 [00:12<00:01, 28.12it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 25.02it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 29.48it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.95it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.45it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:03,  3.12it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.25it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  6.32it/s]
                                                            
Job rirv938-ties-40k-2500-b-21634-v1-mkmlizer completed after 180.68s with status: succeeded
Stopping job with name rirv938-ties-40k-2500-b-21634-v1-mkmlizer
Pipeline stage MKMLizer completed in 181.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-ties-40k-2500-b-21634-v1
Waiting for inference service rirv938-ties-40k-2500-b-21634-v1 to be ready
Inference service rirv938-ties-40k-2500-b-21634-v1 ready after 331.17924427986145s
Pipeline stage MKMLDeployer completed in 331.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3523833751678467s
Received healthy response to inference request in 1.725053310394287s
Received healthy response to inference request in 1.7247216701507568s
Received healthy response to inference request in 1.395914077758789s
Received healthy response to inference request in 1.7641339302062988s
5 requests
0 failed requests
5th percentile: 1.4616755962371826
10th percentile: 1.527437114715576
20th percentile: 1.6589601516723633
30th percentile: 1.724787998199463
40th percentile: 1.724920654296875
50th percentile: 1.725053310394287
60th percentile: 1.7406855583190919
70th percentile: 1.7563178062438964
80th percentile: 1.8817838191986085
90th percentile: 2.1170835971832274
95th percentile: 2.234733486175537
99th percentile: 2.3288533973693846
mean time: 1.7924412727355956
Pipeline stage StressChecker completed in 10.41s
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 0.99s
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 0.74s
Shutdown handler de-registered
rirv938-ties-40k-2500-b_21634_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-ties-40k-2500-b-21634-v1-profiler
Waiting for inference service rirv938-ties-40k-2500-b-21634-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 2499.56s
Shutdown handler de-registered
rirv938-ties-40k-2500-b_21634_v1 status is now inactive due to auto deactivation removed underperforming models

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message