developer_uid: rirv938
submission_id: rirv938-mistral-12b-dpo_13301_v3
model_name: rirv938-mistral-12b-dpo_13301_v3
model_group: rirv938/mistral_12b_dpo_
status: torndown
timestamp: 2025-02-25T02:28:11+00:00
num_battles: 5442
num_wins: 2866
celo_rating: 1272.63
family_friendly_score: 0.5682
family_friendly_standard_error: 0.0070049805138915275
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: 64
latencies: [{'batch_size': 1, 'throughput': 0.642419463192508, 'latency_mean': 1.5565413868427276, 'latency_p50': 1.5535149574279785, 'latency_p90': 1.739690399169922}, {'batch_size': 3, 'throughput': 1.2154801665300423, 'latency_mean': 2.464159871339798, 'latency_p50': 2.4615871906280518, 'latency_p90': 2.7314050674438475}, {'batch_size': 5, 'throughput': 1.4907899035698737, 'latency_mean': 3.3390757977962493, 'latency_p50': 3.376780867576599, 'latency_p90': 3.714699149131775}, {'batch_size': 6, 'throughput': 1.5821611039788568, 'latency_mean': 3.7740599608421324, 'latency_p50': 3.8148943185806274, 'latency_p90': 4.112711787223816}, {'batch_size': 8, 'throughput': 1.6738547578220555, 'latency_mean': 4.749673418998718, 'latency_p50': 4.738303542137146, 'latency_p90': 5.324942016601563}, {'batch_size': 10, 'throughput': 1.7253505648780763, 'latency_mean': 5.745012928247451, 'latency_p50': 5.805476784706116, 'latency_p90': 6.507329154014587}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-dpo_13301_v3
is_internal_developer: True
language_model: rirv938/mistral_12b_dpo_40k_1187_64_output_tokens_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.58
us_pacific_date: 2025-02-24
win_ratio: 0.5266446159500183
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': 64}
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-v3-mkmlizer
Waiting for job on rirv938-mistral-12b-dpo-13301-v3-mkmlizer to finish
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: Downloaded to shared memory in 66.494s
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt_fdo_am, device:0
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: quantized model in 43.575s
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: Processed model rirv938/mistral_12b_dpo_40k_1187_64_output_tokens_v2 in 110.070s
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v3
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v3/config.json
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v3/special_tokens_map.json
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v3/tokenizer_config.json
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v3/tokenizer.json
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v3/flywheel_model.0.safetensors
rirv938-mistral-12b-dpo-13301-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.51it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.28it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.71it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 28.47it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.65it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.71it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.17it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 23.75it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.56it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 23.92it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.01it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.58it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.08it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 27.83it/s]
Loading 0:  17%|█▋        | 63/363 [00:02<00:14, 20.41it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:14, 20.78it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:13, 22.23it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 20.34it/s]
Loading 0:  21%|██        | 76/363 [00:03<00:11, 24.38it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:12, 23.58it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.59it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.07it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.37it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:11, 23.67it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 27.84it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:14, 17.91it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 21.77it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.06it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:08, 27.47it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:08, 27.60it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 30.17it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 28.86it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.38it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.66it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.64it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:09, 22.45it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 28.96it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 27.72it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.90it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 23.22it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.14it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 23.79it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.55it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.13it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.56it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:08, 20.71it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 24.35it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 22.87it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:05, 28.98it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 28.02it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.30it/s]
Loading 0:  61%|██████▏   | 223/363 [00:09<00:05, 25.03it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 22.73it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 21.72it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:04, 26.07it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.91it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.36it/s]
Loading 0:  69%|██████▉   | 250/363 [00:10<00:04, 28.24it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 29.81it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 27.78it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.12it/s]
Loading 0:  73%|███████▎  | 265/363 [00:10<00:04, 21.10it/s]
Loading 0:  74%|███████▍  | 268/363 [00:10<00:04, 21.46it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:04, 22.84it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:04, 21.63it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 27.43it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.00it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 29.74it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 27.86it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:02, 28.29it/s]
Loading 0:  84%|████████▎ | 304/363 [00:12<00:02, 25.82it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 24.23it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 23.06it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 29.21it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 27.41it/s]
Loading 0:  90%|█████████ | 327/363 [00:13<00:01, 29.46it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 27.66it/s]
Loading 0:  92%|█████████▏| 335/363 [00:13<00:00, 30.21it/s]
Loading 0:  93%|█████████▎| 339/363 [00:13<00:00, 25.62it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 28.37it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.82it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.33it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.00it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.14it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.24it/s]
                                                            

Job rirv938-mistral-12b-dpo-13301-v3-mkmlizer completed after 134.5s with status: succeeded
Stopping job with name rirv938-mistral-12b-dpo-13301-v3-mkmlizer
Pipeline stage MKMLizer completed in 134.97s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-12b-dpo-13301-v3
Waiting for inference service rirv938-mistral-12b-dpo-13301-v3 to be ready
Inference service rirv938-mistral-12b-dpo-13301-v3 ready after 250.79886651039124s
Pipeline stage MKMLDeployer completed in 251.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.450324296951294s
Received healthy response to inference request in 1.2496683597564697s
Received healthy response to inference request in 1.3615880012512207s
Received healthy response to inference request in 1.1180706024169922s
Received healthy response to inference request in 1.1349194049835205s
5 requests
0 failed requests
5th percentile: 1.1214403629302978
10th percentile: 1.1248101234436034
20th percentile: 1.1315496444702149
30th percentile: 1.1578691959381104
40th percentile: 1.20376877784729
50th percentile: 1.2496683597564697
60th percentile: 1.2944362163543701
70th percentile: 1.3392040729522705
80th percentile: 1.3793352603912354
90th percentile: 1.4148297786712647
95th percentile: 1.4325770378112792
99th percentile: 1.446774845123291
mean time: 1.2629141330718994
Pipeline stage StressChecker completed in 7.58s
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 0.68s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_13301_v3 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 0.09s
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-v3-profiler
Waiting for inference service rirv938-mistral-12b-dpo-13301-v3-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 2556.99s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_13301_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-dpo_13301_v3 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1