developer_uid: rirv938
submission_id: rirv938-ties-40k-1250-b_43348_v1
model_name: rirv938-ties-40k-1250-b_43348_v1
model_group: rirv938/ties_40k_1250_bo
status: torndown
timestamp: 2025-01-03T21:22:34+00:00
num_battles: 12200
num_wins: 6165
celo_rating: 1268.06
family_friendly_score: 0.6092
family_friendly_standard_error: 0.006900367526443791
submission_type: basic
model_repo: rirv938/ties_40k_1250_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': 0.6675498333679875, 'latency_mean': 1.497926391363144, 'latency_p50': 1.4783982038497925, 'latency_p90': 1.6671875}, {'batch_size': 3, 'throughput': 1.2807678490145589, 'latency_mean': 2.328858677148819, 'latency_p50': 2.3317116498947144, 'latency_p90': 2.5913681268692015}, {'batch_size': 5, 'throughput': 1.610171192536936, 'latency_mean': 3.0893835365772246, 'latency_p50': 3.069961428642273, 'latency_p90': 3.4906460762023923}, {'batch_size': 6, 'throughput': 1.6948938269722758, 'latency_mean': 3.523335301876068, 'latency_p50': 3.5101513862609863, 'latency_p90': 3.9724517107009887}, {'batch_size': 8, 'throughput': 1.8034217438756035, 'latency_mean': 4.414913911819458, 'latency_p50': 4.371729016304016, 'latency_p90': 5.040891146659851}, {'batch_size': 10, 'throughput': 1.8510884382354642, 'latency_mean': 5.351812876462937, 'latency_p50': 5.381643176078796, 'latency_p90': 5.9347631454467775}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-ties-40k-1250-b_43348_v1
is_internal_developer: True
language_model: rirv938/ties_40k_1250_bo8_80w_dpo4_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2025-01-03
win_ratio: 0.5053278688524591
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-1250-b-43348-v1-mkmlizer
Waiting for job on rirv938-ties-40k-1250-b-43348-v1-mkmlizer to finish
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║       /___/                                                         ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║                                                                     ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║                                                                     ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║                                                                     ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ║                                                                     ║
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission rirv938-ties-20k-624-bo_46192_v1: ('http://rirv938-ties-20k-624-bo-46192-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:44394->127.0.0.1:8080: read: connection reset by peer\n')
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: Downloaded to shared memory in 91.115s
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1e9h045g, device:0
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: quantized model in 43.257s
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: Processed model rirv938/ties_40k_1250_bo8_80w_dpo4_v2 in 134.372s
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-ties-40k-1250-b-43348-v1
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-ties-40k-1250-b-43348-v1/config.json
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-ties-40k-1250-b-43348-v1/special_tokens_map.json
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-ties-40k-1250-b-43348-v1/tokenizer_config.json
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-ties-40k-1250-b-43348-v1/tokenizer.json
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-ties-40k-1250-b-43348-v1/flywheel_model.0.safetensors
rirv938-ties-40k-1250-b-43348-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.11it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.22it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.97it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.47it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 23.86it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.84it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.40it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:13, 25.08it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.17it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 24.27it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.80it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.54it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.71it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.79it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.44it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.46it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 28.89it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.46it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:08, 31.47it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:08, 30.78it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 33.41it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 32.18it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:09, 26.39it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.67it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 29.77it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 29.13it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.32it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.11it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.99it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.82it/s]
Loading 0:  37%|███▋      | 136/363 [00:04<00:07, 29.08it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.45it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 22.22it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 20.97it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:08, 25.70it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 23.67it/s]
Loading 0:  45%|████▍     | 163/363 [00:05<00:07, 28.23it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 24.60it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.30it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 24.51it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 27.91it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.77it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.06it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 21.49it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 26.19it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 23.48it/s]
Loading 0:  57%|█████▋    | 208/363 [00:07<00:05, 28.27it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.44it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 27.73it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:05, 28.18it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 19.80it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 19.18it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 23.30it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 21.44it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 25.47it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 23.02it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:04, 27.47it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:04, 24.04it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.04it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:05, 18.21it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:04, 22.47it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:04, 21.30it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:03, 25.76it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.13it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.01it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 23.82it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 28.00it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:02, 29.50it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 22.21it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.69it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 28.60it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 28.61it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.36it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.34it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.58it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 29.74it/s]
Loading 0:  95%|█████████▍| 344/363 [00:20<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.82it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.92it/s]
                                                            

Job rirv938-ties-40k-1250-b-43348-v1-mkmlizer completed after 187.82s with status: succeeded
Stopping job with name rirv938-ties-40k-1250-b-43348-v1-mkmlizer
Pipeline stage MKMLizer completed in 188.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-ties-40k-1250-b-43348-v1
Waiting for inference service rirv938-ties-40k-1250-b-43348-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
Inference service rirv938-ties-40k-1250-b-43348-v1 ready after 331.42682790756226s
Pipeline stage MKMLDeployer completed in 332.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.194516181945801s
Received healthy response to inference request in 1.5439064502716064s
Received healthy response to inference request in 1.9510571956634521s
Received healthy response to inference request in 1.412947177886963s
Received healthy response to inference request in 1.4334938526153564s
5 requests
0 failed requests
5th percentile: 1.4170565128326416
10th percentile: 1.4211658477783202
20th percentile: 1.4293845176696778
30th percentile: 1.4555763721466064
40th percentile: 1.4997414112091065
50th percentile: 1.5439064502716064
60th percentile: 1.7067667484283446
70th percentile: 1.8696270465850828
80th percentile: 1.999748992919922
90th percentile: 2.0971325874328612
95th percentile: 2.1458243846893312
99th percentile: 2.1847778224945067
mean time: 1.7071841716766358
Pipeline stage StressChecker completed in 9.87s
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 0.70s
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 0.99s
Shutdown handler de-registered
rirv938-ties-40k-1250-b_43348_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 0.10s
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-1250-b-43348-v1-profiler
Waiting for inference service rirv938-ties-40k-1250-b-43348-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 2501.19s
Shutdown handler de-registered
rirv938-ties-40k-1250-b_43348_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-ties-40k-1250-b_43348_v1 status is now torndown due to DeploymentManager action
rirv938-ties-40k-1250-b_43348_v1 status is now torndown due to DeploymentManager action
rirv938-ties-40k-1250-b_43348_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1