rirv938-mistral-12b-dpo_75616

developer_uid: chai_backend_admin

submission_id: rirv938-mistral-12b-dpo_75616_v4

model_name: rirv938-mistral-12b-dpo_75616_v4

model_group: rirv938/mistral_12b_dpo_

status: torndown

timestamp: 2025-02-27T19:01:59+00:00

num_battles: 6254

num_wins: 3605

celo_rating: 1331.65

family_friendly_score: 0.5642

family_friendly_standard_error: 0.0070125367735221185

submission_type: basic

model_repo: rirv938/mistral_12b_dpo_40k_2374_96_output_tokens_v2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 96

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.4537654525763601, 'latency_mean': 2.203716744184494, 'latency_p50': 2.1830172538757324, 'latency_p90': 2.3885236263275145}, {'batch_size': 3, 'throughput': 0.9200121951785136, 'latency_mean': 3.2460500228405, 'latency_p50': 3.244923710823059, 'latency_p90': 3.5183069944381713}, {'batch_size': 5, 'throughput': 1.1724552668614996, 'latency_mean': 4.244603261947632, 'latency_p50': 4.229761004447937, 'latency_p90': 4.6113365411758425}, {'batch_size': 6, 'throughput': 1.2483694226108524, 'latency_mean': 4.769465502500534, 'latency_p50': 4.771833181381226, 'latency_p90': 5.238121080398559}, {'batch_size': 8, 'throughput': 1.330529355546367, 'latency_mean': 5.98330511212349, 'latency_p50': 6.0037126541137695, 'latency_p90': 6.560097885131836}, {'batch_size': 10, 'throughput': 1.3667969673318956, 'latency_mean': 7.234939175844192, 'latency_p50': 7.201881647109985, 'latency_p90': 7.941810274124146}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-mistral-12b-dpo_75616_v4

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: rirv938/mistral_12b_dpo_40k_2374_96_output_tokens_v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.06

us_pacific_date: 2025-02-27

win_ratio: 0.576431084106172

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '###', '</s>', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 96}

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 rirv938-mistral-12b-dpo-75616-v4-mkmlizer
Waiting for job on rirv938-mistral-12b-dpo-75616-v4-mkmlizer to finish
Failed to get response for submission nischaydnk-exp26-mistra_55673_v2: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: Downloaded to shared memory in 63.478s
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp81h1655c, device:0
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: quantized model in 41.728s
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: Processed model rirv938/mistral_12b_dpo_40k_2374_96_output_tokens_v2 in 105.206s
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-75616-v4
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-75616-v4/special_tokens_map.json
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-75616-v4/config.json
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-75616-v4/tokenizer_config.json
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-75616-v4/tokenizer.json
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-75616-v4/flywheel_model.0.safetensors
rirv938-mistral-12b-dpo-75616-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.47it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.55it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.71it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.22it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:15, 22.58it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 22.01it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.49it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:12, 25.56it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.88it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.17it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.23it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.82it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.01it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.24it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.31it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.51it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.27it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:11, 24.95it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.03it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.04it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.75it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 27.82it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 22.73it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.29it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.17it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:09, 25.58it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.60it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.83it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.00it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.33it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.38it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 24.66it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.29it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.71it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 29.38it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.54it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.81it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.61it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.53it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.85it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.77it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.25it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 28.25it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 27.85it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.10it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.88it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.88it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.21it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.93it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.61it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.07it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.73it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.28it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 27.87it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 29.50it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 28.32it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.37it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.82it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 22.73it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 20.31it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 26.88it/s]
Loading 0:  76%|███████▌  | 276/363 [00:10<00:03, 25.52it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.13it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.52it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.25it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.08it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.00it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.49it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.56it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.75it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 28.01it/s]
Loading 0:  88%|████████▊ | 320/363 [00:11<00:01, 24.79it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.56it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.17it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.38it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.90it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.99it/s]
                                                            
Job rirv938-mistral-12b-dpo-75616-v4-mkmlizer completed after 257.75s with status: succeeded
Stopping job with name rirv938-mistral-12b-dpo-75616-v4-mkmlizer
Pipeline stage MKMLizer completed in 258.22s
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 rirv938-mistral-12b-dpo-75616-v4
Waiting for inference service rirv938-mistral-12b-dpo-75616-v4 to be ready
Failed to get response for submission nischaydnk-exp26-mistra_55673_v2: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-mistral-12b-dpo-75616-v4 ready after 321.2809064388275s
Pipeline stage MKMLDeployer completed in 321.79s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6492419242858887s
Received healthy response to inference request in 1.4004554748535156s
Received healthy response to inference request in 2.0764710903167725s
Received healthy response to inference request in 2.018146514892578s
Received healthy response to inference request in 2.1089789867401123s
5 requests
0 failed requests
5th percentile: 1.4502127647399903
10th percentile: 1.499970054626465
20th percentile: 1.599484634399414
30th percentile: 1.7230228424072265
40th percentile: 1.8705846786499023
50th percentile: 2.018146514892578
60th percentile: 2.041476345062256
70th percentile: 2.0648061752319338
80th percentile: 2.0829726696014403
90th percentile: 2.0959758281707765
95th percentile: 2.1024774074554444
99th percentile: 2.1076786708831787
mean time: 1.8506587982177733
Pipeline stage StressChecker completed in 10.53s
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 0.65s
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 0.68s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_75616_v4 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-12b-dpo-75616-v4-profiler
Waiting for inference service rirv938-mistral-12b-dpo-75616-v4-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 2803.02s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_75616_v4 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-dpo_75616_v4 status is now torndown due to DeploymentManager action