developer_uid: rirv938
submission_id: rirv938-mistral-12b-dpo_13301_v1
model_name: rirv938-mistral-12b-dpo_13301_v1
model_group: rirv938/mistral_12b_dpo_
status: torndown
timestamp: 2025-02-25T02:26:45+00:00
num_battles: 5584
num_wins: 3145
celo_rating: 1298.36
family_friendly_score: 0.5549999999999999
family_friendly_standard_error: 0.007028157653325657
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: 96
latencies: [{'batch_size': 1, 'throughput': 0.4509996236426085, 'latency_mean': 2.2172347509860995, 'latency_p50': 2.223495364189148, 'latency_p90': 2.396781396865845}, {'batch_size': 3, 'throughput': 0.9119789771423319, 'latency_mean': 3.273548197746277, 'latency_p50': 3.2752716541290283, 'latency_p90': 3.528090071678162}, {'batch_size': 5, 'throughput': 1.153330156809072, 'latency_mean': 4.312702122926712, 'latency_p50': 4.310640215873718, 'latency_p90': 4.696704435348511}, {'batch_size': 6, 'throughput': 1.229128511601944, 'latency_mean': 4.839028078317642, 'latency_p50': 4.816086292266846, 'latency_p90': 5.3067700386047365}, {'batch_size': 8, 'throughput': 1.3141962091408406, 'latency_mean': 6.045466656684876, 'latency_p50': 6.075103044509888, 'latency_p90': 6.6104895830154415}, {'batch_size': 10, 'throughput': 1.3546801388637706, 'latency_mean': 7.296190686225891, 'latency_p50': 7.262423992156982, 'latency_p90': 8.020221161842347}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-dpo_13301_v1
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: 1.03
us_pacific_date: 2025-02-24
win_ratio: 0.5632163323782235
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-13301-v1-mkmlizer
Waiting for job on rirv938-mistral-12b-dpo-13301-v1-mkmlizer to finish
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ║ ║
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: Downloaded to shared memory in 117.190s
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvwxzgs45, device:0
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: quantized model in 45.690s
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: Processed model rirv938/mistral_12b_dpo_40k_1187_64_output_tokens_v2 in 162.881s
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v1
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v1/config.json
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v1/special_tokens_map.json
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v1/tokenizer.json
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-13301-v1/flywheel_model.0.safetensors
rirv938-mistral-12b-dpo-13301-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:18, 18.93it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:14, 24.05it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:16, 21.35it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:12, 27.50it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:17, 19.84it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:19, 17.52it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:14, 22.17it/s] Loading 0: 9%|▉ | 34/363 [00:01<00:14, 22.12it/s] Loading 0: 10%|█ | 37/363 [00:01<00:13, 23.52it/s] Loading 0: 11%|█ | 40/363 [00:01<00:13, 24.61it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:13, 23.33it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:12, 24.72it/s] Loading 0: 13%|█▎ | 49/363 [00:02<00:12, 25.74it/s] Loading 0: 14%|█▍ | 52/363 [00:02<00:12, 24.27it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:12, 24.92it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:11, 26.72it/s] Loading 0: 17%|█▋ | 63/363 [00:02<00:16, 18.52it/s] Loading 0: 18%|█▊ | 66/363 [00:03<00:15, 19.14it/s] Loading 0: 19%|█▉ | 69/363 [00:03<00:13, 21.02it/s] Loading 0: 20%|█▉ | 72/363 [00:03<00:15, 19.23it/s] Loading 0: 21%|██ | 77/363 [00:03<00:14, 20.39it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 25.37it/s] Loading 0: 23%|██▎ | 85/363 [00:03<00:10, 26.23it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:10, 25.13it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:10, 25.60it/s] Loading 0: 26%|██▌ | 94/363 [00:04<00:10, 26.54it/s] Loading 0: 27%|██▋ | 97/363 [00:04<00:10, 25.62it/s] Loading 0: 28%|██▊ | 101/363 [00:04<00:12, 20.27it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:14, 18.36it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 25.84it/s] Loading 0: 31%|███▏ | 114/363 [00:05<00:10, 23.72it/s] Loading 0: 33%|███▎ | 120/363 [00:05<00:08, 29.01it/s] Loading 0: 34%|███▍ | 124/363 [00:05<00:08, 27.87it/s] Loading 0: 36%|███▌ | 129/363 [00:05<00:07, 30.23it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:08, 28.67it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:07, 28.65it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 31.10it/s] Loading 0: 40%|███▉ | 145/363 [00:06<00:10, 19.83it/s] Loading 0: 41%|████ | 148/363 [00:06<00:10, 20.98it/s] Loading 0: 42%|████▏ | 151/363 [00:06<00:09, 21.35it/s] Loading 0: 43%|████▎ | 156/363 [00:06<00:08, 24.72it/s] Loading 0: 44%|████▍ | 159/363 [00:06<00:09, 22.40it/s] Loading 0: 45%|████▍ | 163/363 [00:06<00:08, 24.12it/s] Loading 0: 46%|████▌ | 166/363 [00:07<00:07, 24.76it/s] Loading 0: 47%|████▋ | 169/363 [00:07<00:08, 23.01it/s] Loading 0: 47%|████▋ | 172/363 [00:07<00:07, 24.13it/s] Loading 0: 48%|████▊ | 176/363 [00:07<00:08, 21.56it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:06, 26.25it/s] Loading 0: 51%|█████ | 184/363 [00:07<00:09, 18.61it/s] Loading 0: 52%|█████▏ | 187/363 [00:08<00:09, 18.74it/s] Loading 0: 52%|█████▏ | 190/363 [00:08<00:08, 20.07it/s] Loading 0: 53%|█████▎ | 193/363 [00:08<00:07, 21.87it/s] Loading 0: 54%|█████▍ | 196/363 [00:08<00:07, 21.84it/s] Loading 0: 55%|█████▍ | 199/363 [00:08<00:07, 23.32it/s] Loading 0: 56%|█████▌ | 203/363 [00:08<00:07, 21.12it/s] Loading 0: 57%|█████▋ | 208/363 [00:08<00:06, 25.56it/s] Loading 0: 58%|█████▊ | 211/363 [00:09<00:05, 25.84it/s] Loading 0: 59%|█████▉ | 214/363 [00:09<00:06, 24.47it/s] Loading 0: 60%|█████▉ | 217/363 [00:09<00:05, 25.01it/s] Loading 0: 61%|██████ | 222/363 [00:09<00:05, 26.42it/s] Loading 0: 62%|██████▏ | 225/363 [00:09<00:08, 16.44it/s] Loading 0: 63%|██████▎ | 229/363 [00:09<00:06, 20.10it/s] Loading 0: 64%|██████▍ | 232/363 [00:10<00:06, 20.55it/s] Loading 0: 65%|██████▍ | 235/363 [00:10<00:05, 22.35it/s] Loading 0: 66%|██████▌ | 239/363 [00:10<00:06, 20.55it/s] Loading 0: 67%|██████▋ | 244/363 [00:10<00:04, 25.66it/s] Loading 0: 68%|██████▊ | 248/363 [00:10<00:05, 22.93it/s] Loading 0: 70%|██████▉ | 253/363 [00:10<00:03, 27.75it/s] Loading 0: 71%|███████ | 257/363 [00:11<00:04, 24.16it/s] Loading 0: 72%|███████▏ | 262/363 [00:11<00:03, 28.19it/s] Loading 0: 73%|███████▎ | 266/363 [00:11<00:05, 18.71it/s] Loading 0: 75%|███████▍ | 271/363 [00:11<00:03, 23.02it/s] Loading 0: 76%|███████▌ | 275/363 [00:11<00:04, 21.16it/s] Loading 0: 77%|███████▋ | 280/363 [00:12<00:03, 25.32it/s] Loading 0: 78%|███████▊ | 284/363 [00:12<00:03, 22.19it/s] Loading 0: 80%|███████▉ | 289/363 [00:12<00:02, 26.44it/s] Loading 0: 81%|████████ | 293/363 [00:12<00:03, 22.90it/s] Loading 0: 82%|████████▏ | 298/363 [00:12<00:02, 26.53it/s] Loading 0: 83%|████████▎ | 303/363 [00:13<00:02, 25.71it/s] Loading 0: 84%|████████▍ | 306/363 [00:13<00:03, 17.12it/s] Loading 0: 85%|████████▌ | 310/363 [00:13<00:02, 20.38it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:02, 20.27it/s] Loading 0: 87%|████████▋ | 316/363 [00:13<00:02, 21.23it/s] Loading 0: 88%|████████▊ | 319/363 [00:13<00:01, 22.14it/s] Loading 0: 89%|████████▊ | 322/363 [00:14<00:01, 21.09it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:01, 21.86it/s] Loading 0: 90%|█████████ | 328/363 [00:14<00:01, 23.04it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:01, 22.21it/s] Loading 0: 92%|█████████▏| 334/363 [00:14<00:01, 22.92it/s] Loading 0: 93%|█████████▎| 337/363 [00:14<00:01, 24.20it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:01, 22.37it/s] Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 22.82it/s] Loading 0: 95%|█████████▌| 346/363 [00:22<00:12, 1.33it/s] Loading 0: 96%|█████████▌| 348/363 [00:22<00:09, 1.65it/s] Loading 0: 97%|█████████▋| 353/363 [00:22<00:03, 2.83it/s] Loading 0: 98%|█████████▊| 357/363 [00:22<00:01, 3.95it/s] Loading 0: 100%|█████████▉| 362/363 [00:22<00:00, 6.00it/s]
Job rirv938-mistral-12b-dpo-13301-v1-mkmlizer completed after 208.55s with status: succeeded
Stopping job with name rirv938-mistral-12b-dpo-13301-v1-mkmlizer
Pipeline stage MKMLizer completed in 209.46s
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-v1
Waiting for inference service rirv938-mistral-12b-dpo-13301-v1 to be ready
Inference service rirv938-mistral-12b-dpo-13301-v1 ready after 231.06977653503418s
Pipeline stage MKMLDeployer completed in 231.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3393423557281494s
Received healthy response to inference request in 0.9059154987335205s
Received healthy response to inference request in 1.1796631813049316s
Received healthy response to inference request in 1.4468796253204346s
Received healthy response to inference request in 1.2139124870300293s
5 requests
0 failed requests
5th percentile: 0.9606650352478028
10th percentile: 1.015414571762085
20th percentile: 1.1249136447906494
30th percentile: 1.1865130424499513
40th percentile: 1.2002127647399903
50th percentile: 1.2139124870300293
60th percentile: 1.2640844345092774
70th percentile: 1.3142563819885253
80th percentile: 1.3608498096466064
90th percentile: 1.4038647174835206
95th percentile: 1.4253721714019776
99th percentile: 1.4425781345367432
mean time: 1.2171426296234131
Pipeline stage StressChecker completed in 7.61s
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 0.71s
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 0.70s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_13301_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-12b-dpo-13301-v1-profiler
Waiting for inference service rirv938-mistral-12b-dpo-13301-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 2626.89s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_13301_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-dpo_13301_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1