developer_uid: rirv938
submission_id: rirv938-mistral-12b-dpo_13301_v2
model_name: rirv938-mistral-12b-dpo_13301_v2
model_group: rirv938/mistral_12b_dpo_
status: torndown
timestamp: 2025-02-25T02:27:30+00:00
num_battles: 5603
num_wins: 1729
celo_rating: 1122.0
family_friendly_score: 0.663
family_friendly_standard_error: 0.006684773743366338
submission_type: basic
model_repo: rirv938/mistral_12b_dpo_40k_1187_64_output_tokens_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 32
latencies: [{'batch_size': 1, 'throughput': 1.10378738570436, 'latency_mean': 0.9059071660041809, 'latency_p50': 0.897390604019165, 'latency_p90': 1.0726847171783447}, {'batch_size': 4, 'throughput': 2.0177388337615363, 'latency_mean': 1.9737957739830017, 'latency_p50': 1.964759111404419, 'latency_p90': 2.412567448616028}, {'batch_size': 5, 'throughput': 2.1329651785617347, 'latency_mean': 2.3366715908050537, 'latency_p50': 2.3488322496414185, 'latency_p90': 2.7989604234695435}, {'batch_size': 8, 'throughput': 2.3141223913961184, 'latency_mean': 3.429140479564667, 'latency_p50': 3.4344059228897095, 'latency_p90': 4.069322729110717}, {'batch_size': 10, 'throughput': 2.3849797379836453, 'latency_mean': 4.16200740814209, 'latency_p50': 4.142706274986267, 'latency_p90': 5.0721642017364506}, {'batch_size': 12, 'throughput': 2.3797656036662778, 'latency_mean': 4.980788042545319, 'latency_p50': 4.993963122367859, 'latency_p90': 5.9701231002807615}, {'batch_size': 15, 'throughput': 2.3719841963671002, 'latency_mean': 6.221659607887268, 'latency_p50': 6.260536193847656, 'latency_p90': 7.260914659500122}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-dpo_13301_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/mistral_12b_dpo_40k_1187_64_output_tokens_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 2.36
us_pacific_date: 2025-02-24
win_ratio: 0.308584686774942
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': 32}
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-13301-v2-mkmlizer
Waiting for job on rirv938-mistral-12b-dpo-13301-v2-mkmlizer to finish
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: Downloaded to shared memory in 78.824s
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpshdbttep, device:0
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: quantized model in 43.988s
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: Processed model rirv938/mistral_12b_dpo_40k_1187_64_output_tokens_v2 in 122.813s
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v2
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v2/tokenizer_config.json
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v2/tokenizer.json
rirv938-mistral-12b-dpo-13301-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.41it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:14, 24.25it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:13, 26.13it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:17, 19.81it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 26.01it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:12, 26.52it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:19, 17.13it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.30it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:18, 18.26it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:14, 23.22it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:15, 21.31it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:12, 25.99it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.22it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.27it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 28.10it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:16, 18.37it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:12, 22.86it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 22.79it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.18it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.24it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.60it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 27.02it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:11, 24.36it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 29.05it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.90it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.28it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.73it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:09, 26.19it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.67it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 29.98it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.51it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 28.47it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.53it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.72it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.15it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.48it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.26it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.33it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 23.44it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 27.16it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 23.56it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.36it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.07it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:07, 21.99it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:08, 20.56it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 24.54it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:07, 22.16it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 26.11it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:06, 23.13it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 26.77it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:05, 27.61it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 19.94it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.67it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 23.65it/s]
Loading 0:  66%|██████▌   | 239/363 [00:10<00:05, 22.45it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 27.15it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 24.29it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 30.57it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 28.85it/s]
Loading 0:  72%|███████▏  | 263/363 [00:11<00:04, 24.53it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 21.16it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 25.88it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 23.47it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:02, 27.86it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 25.25it/s]
Loading 0:  80%|████████  | 291/363 [00:12<00:02, 31.33it/s]
Loading 0:  81%|████████▏ | 295/363 [00:12<00:02, 28.59it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:02, 28.02it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 29.89it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.42it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:02, 19.98it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 24.63it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 21.92it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 25.91it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 23.53it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 27.67it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 23.80it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 27.54it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:08,  1.97it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.48it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.17it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.37it/s]
                                                            

Job rirv938-mistral-12b-dpo-13301-v2-mkmlizer completed after 165.46s with status: succeeded
Stopping job with name rirv938-mistral-12b-dpo-13301-v2-mkmlizer
Pipeline stage MKMLizer completed in 165.92s
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-13301-v2
Waiting for inference service rirv938-mistral-12b-dpo-13301-v2 to be ready
Inference service rirv938-mistral-12b-dpo-13301-v2 ready after 230.81427311897278s
Pipeline stage MKMLDeployer completed in 231.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6096758842468262s
Received healthy response to inference request in 0.8683609962463379s
Received healthy response to inference request in 0.8754003047943115s
Received healthy response to inference request in 0.848574161529541s
Received healthy response to inference request in 0.7973794937133789s
5 requests
0 failed requests
5th percentile: 0.8076184272766114
10th percentile: 0.8178573608398437
20th percentile: 0.8383352279663085
30th percentile: 0.8525315284729004
40th percentile: 0.8604462623596192
50th percentile: 0.8683609962463379
60th percentile: 0.8711767196655273
70th percentile: 0.8739924430847168
80th percentile: 1.0222554206848147
90th percentile: 1.3159656524658203
95th percentile: 1.462820768356323
99th percentile: 1.5803048610687256
mean time: 0.9998781681060791
Pipeline stage StressChecker completed in 6.17s
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 0.59s
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 0.60s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_13301_v2 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 0.11s
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-13301-v2-profiler
Waiting for inference service rirv938-mistral-12b-dpo-13301-v2-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 2291.37s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_13301_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-dpo_13301_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1