developer_uid: rirv938
submission_id: rirv938-mistral-12b-dpo_40235_v1
model_name: rirv938-mistral-12b-dpo_40235_v1
model_group: rirv938/mistral_12b_dpo_
status: torndown
timestamp: 2025-02-25T02:26:46+00:00
num_battles: 5489
num_wins: 3209
celo_rating: 1313.15
family_friendly_score: 0.5631999999999999
family_friendly_standard_error: 0.007014353284515972
submission_type: basic
model_repo: rirv938/mistral_12b_dpo_40k_1187_96_output_tokens_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 96
latencies: [{'batch_size': 1, 'throughput': 0.45372349655658617, 'latency_mean': 2.2039172613620757, 'latency_p50': 2.1983591318130493, 'latency_p90': 2.381718325614929}, {'batch_size': 3, 'throughput': 0.9157247202552943, 'latency_mean': 3.2612193036079407, 'latency_p50': 3.246858239173889, 'latency_p90': 3.4944097280502318}, {'batch_size': 5, 'throughput': 1.1483617030692959, 'latency_mean': 4.345477851629258, 'latency_p50': 4.322136998176575, 'latency_p90': 4.733943605422974}, {'batch_size': 6, 'throughput': 1.2255788711350848, 'latency_mean': 4.863806734085083, 'latency_p50': 4.890612840652466, 'latency_p90': 5.324469757080078}, {'batch_size': 8, 'throughput': 1.2941344956509317, 'latency_mean': 6.121262085437775, 'latency_p50': 6.135868430137634, 'latency_p90': 6.659621524810791}, {'batch_size': 10, 'throughput': 1.33880077090375, 'latency_mean': 7.4130283081531525, 'latency_p50': 7.405318737030029, 'latency_p90': 8.118780469894409}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-dpo_40235_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/mistral_12b_dpo_40k_1187_96_output_tokens_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.03
us_pacific_date: 2025-02-24
win_ratio: 0.5846237930406267
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-40235-v1-mkmlizer
Waiting for job on rirv938-mistral-12b-dpo-40235-v1-mkmlizer to finish
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: Downloaded to shared memory in 121.938s
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn7izljvu, device:0
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: quantized model in 44.549s
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: Processed model rirv938/mistral_12b_dpo_40k_1187_96_output_tokens_v2 in 166.487s
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-40235-v1
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-40235-v1/config.json
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-40235-v1/special_tokens_map.json
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-40235-v1/tokenizer_config.json
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-40235-v1/tokenizer.json
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-40235-v1/flywheel_model.0.safetensors
rirv938-mistral-12b-dpo-40235-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.43it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.06it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 21.96it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 26.16it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:13, 25.86it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:18, 17.98it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.60it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:17, 18.47it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:14, 22.42it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.18it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.02it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:13, 23.95it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.71it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.26it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 28.75it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:16, 17.76it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:13, 21.85it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 20.52it/s]
Loading 0:  21%|██        | 76/363 [00:03<00:12, 23.81it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:12, 22.59it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.42it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 21.49it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.36it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:09, 27.10it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 25.96it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 26.92it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:13, 18.90it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:12, 20.00it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 23.68it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:11, 22.15it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:09, 24.68it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.38it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.38it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.17it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.72it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.49it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.38it/s]
Loading 0:  41%|████      | 148/363 [00:06<00:09, 21.92it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:10, 21.07it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 22.11it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 20.57it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:07, 25.35it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 22.24it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 26.61it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:08, 22.41it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.48it/s]
Loading 0:  51%|█████     | 185/363 [00:08<00:09, 17.96it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:07, 22.00it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:07, 23.13it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 22.34it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 23.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:07, 21.22it/s]
Loading 0:  57%|█████▋    | 208/363 [00:09<00:05, 26.27it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:06, 22.79it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 27.38it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 28.83it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.69it/s]
Loading 0:  63%|██████▎   | 230/363 [00:10<00:06, 19.43it/s]
Loading 0:  65%|██████▍   | 235/363 [00:10<00:05, 22.77it/s]
Loading 0:  66%|██████▌   | 239/363 [00:10<00:05, 21.52it/s]
Loading 0:  67%|██████▋   | 245/363 [00:10<00:04, 28.27it/s]
Loading 0:  69%|██████▊   | 249/363 [00:10<00:04, 25.39it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 29.53it/s]
Loading 0:  71%|███████▏  | 259/363 [00:11<00:03, 28.29it/s]
Loading 0:  72%|███████▏  | 263/363 [00:11<00:04, 23.67it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 20.75it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 25.99it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 23.74it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 29.86it/s]
Loading 0:  79%|███████▉  | 286/363 [00:12<00:02, 28.61it/s]
Loading 0:  80%|████████  | 291/363 [00:12<00:02, 30.80it/s]
Loading 0:  81%|████████▏ | 295/363 [00:12<00:02, 28.46it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:02, 28.49it/s]
Loading 0:  84%|████████▎ | 304/363 [00:12<00:02, 24.28it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 22.66it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:02, 23.69it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:02, 22.41it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 23.84it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.33it/s]
Loading 0:  90%|█████████ | 327/363 [00:13<00:01, 29.09it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 27.09it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:01, 27.02it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:00, 27.59it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 26.28it/s]
Loading 0:  95%|█████████▍| 344/363 [00:21<00:11,  1.62it/s]
Loading 0:  96%|█████████▌| 348/363 [00:21<00:06,  2.29it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:02,  3.47it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.59it/s]
                                                            

Job rirv938-mistral-12b-dpo-40235-v1-mkmlizer completed after 205.68s with status: succeeded
Stopping job with name rirv938-mistral-12b-dpo-40235-v1-mkmlizer
Pipeline stage MKMLizer completed in 206.15s
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-40235-v1
Waiting for inference service rirv938-mistral-12b-dpo-40235-v1 to be ready
Failed to get response for submission blend_gesub_2025-01-22: HTTPConnectionPool(host='chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission blend_gesub_2025-01-22: HTTPConnectionPool(host='chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-mistral-12b-dpo-40235-v1 ready after 230.8065094947815s
Pipeline stage MKMLDeployer completed in 231.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8185195922851562s
Received healthy response to inference request in 2.041755199432373s
Received healthy response to inference request in 1.704949140548706s
Received healthy response to inference request in 2.0752642154693604s
Received healthy response to inference request in 1.8748538494110107s
5 requests
0 failed requests
5th percentile: 1.727663230895996
10th percentile: 1.750377321243286
20th percentile: 1.7958055019378663
30th percentile: 1.829786443710327
40th percentile: 1.852320146560669
50th percentile: 1.8748538494110107
60th percentile: 1.9416143894195557
70th percentile: 2.0083749294281006
80th percentile: 2.0484570026397706
90th percentile: 2.0618606090545653
95th percentile: 2.068562412261963
99th percentile: 2.0739238548278807
mean time: 1.9030683994293214
Pipeline stage StressChecker completed in 10.96s
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 0.67s
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 0.64s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_40235_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 2728.63s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_40235_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-dpo_40235_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1