developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_29487_v3
model_name: rirv938-mistral-24b-dpo_29487_v3
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-03-06T18:35:48+00:00
num_battles: 9074
num_wins: 4585
celo_rating: 1282.91
family_friendly_score: 0.5906
family_friendly_standard_error: 0.006954015243008891
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3873681975088802, 'latency_mean': 2.5814571630954743, 'latency_p50': 2.5788042545318604, 'latency_p90': 2.8669109582901}, {'batch_size': 3, 'throughput': 0.7926301645274278, 'latency_mean': 3.7622555112838745, 'latency_p50': 3.714016318321228, 'latency_p90': 4.19151496887207}, {'batch_size': 5, 'throughput': 1.051355816319022, 'latency_mean': 4.717943377494812, 'latency_p50': 4.663488268852234, 'latency_p90': 5.276727461814881}, {'batch_size': 6, 'throughput': 1.1334931190563604, 'latency_mean': 5.247313274145126, 'latency_p50': 5.276708245277405, 'latency_p90': 5.921423363685608}, {'batch_size': 10, 'throughput': 1.3079134180790446, 'latency_mean': 7.594624093770981, 'latency_p50': 7.600588321685791, 'latency_p90': 8.639315533638001}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_29487_v3
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.78
us_pacific_date: 2025-03-06
win_ratio: 0.5052898391007273
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': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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-24b-dpo-29487-v3-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-29487-v3-mkmlizer to finish
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: Downloaded to shared memory in 106.926s
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphxwk9yfl, device:0
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: quantized model in 61.703s
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2 in 168.630s
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v3
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v3/config.json
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v3/special_tokens_map.json
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v3/tokenizer_config.json
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v3/tokenizer.json
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v3/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v3/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-29487-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:17, 20.65it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:20, 17.55it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:15, 22.46it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:24, 13.97it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:25, 13.56it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:19, 17.20it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:24, 13.78it/s] Loading 0: 8%|▊ | 29/363 [00:01<00:15, 21.38it/s] Loading 0: 9%|▉ | 33/363 [00:01<00:16, 19.63it/s] Loading 0: 10%|▉ | 36/363 [00:02<00:22, 14.82it/s] Loading 0: 11%|█ | 39/363 [00:02<00:19, 16.90it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:21, 15.18it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:16, 18.74it/s] Loading 0: 14%|█▍ | 51/363 [00:02<00:16, 19.19it/s] Loading 0: 15%|█▍ | 54/363 [00:03<00:21, 14.68it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:18, 16.74it/s] Loading 0: 17%|█▋ | 60/363 [00:03<00:20, 15.13it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:15, 19.14it/s] Loading 0: 19%|█▉ | 69/363 [00:03<00:15, 19.46it/s] Loading 0: 20%|█▉ | 72/363 [00:04<00:19, 14.80it/s] Loading 0: 21%|██ | 75/363 [00:04<00:17, 16.85it/s] Loading 0: 21%|██▏ | 78/363 [00:04<00:18, 15.35it/s] Loading 0: 23%|██▎ | 83/363 [00:04<00:13, 20.87it/s] Loading 0: 24%|██▍ | 87/363 [00:05<00:14, 19.53it/s] Loading 0: 25%|██▍ | 90/363 [00:05<00:18, 14.65it/s] Loading 0: 26%|██▋ | 96/363 [00:05<00:12, 21.19it/s] Loading 0: 28%|██▊ | 101/363 [00:05<00:11, 22.83it/s] Loading 0: 29%|██▊ | 104/363 [00:05<00:13, 18.85it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:17, 14.61it/s] Loading 0: 30%|███ | 109/363 [00:06<00:18, 14.04it/s] Loading 0: 31%|███ | 111/363 [00:06<00:17, 14.60it/s] Loading 0: 31%|███ | 113/363 [00:06<00:20, 11.95it/s] Loading 0: 33%|███▎ | 118/363 [00:06<00:13, 17.69it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 21.53it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 15.56it/s] Loading 0: 35%|███▌ | 128/363 [00:07<00:14, 16.35it/s] Loading 0: 36%|███▌ | 131/363 [00:07<00:18, 12.85it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:12, 18.31it/s] Loading 0: 39%|███▊ | 140/363 [00:08<00:10, 21.73it/s] Loading 0: 39%|███▉ | 143/363 [00:08<00:13, 15.81it/s] Loading 0: 40%|████ | 146/363 [00:08<00:13, 16.51it/s] Loading 0: 41%|████ | 149/363 [00:09<00:16, 12.78it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:11, 18.03it/s] Loading 0: 44%|████▍ | 159/363 [00:09<00:10, 18.65it/s] Loading 0: 45%|████▍ | 162/363 [00:09<00:13, 14.49it/s] Loading 0: 45%|████▌ | 165/363 [00:09<00:12, 16.38it/s] Loading 0: 46%|████▋ | 168/363 [00:10<00:13, 14.77it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:09, 20.06it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:09, 18.95it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:12, 14.55it/s] Loading 0: 50%|█████ | 183/363 [00:10<00:10, 16.50it/s] Loading 0: 51%|█████ | 186/363 [00:11<00:11, 15.05it/s] Loading 0: 53%|█████▎ | 191/363 [00:11<00:08, 20.43it/s] Loading 0: 54%|█████▎ | 195/363 [00:11<00:08, 19.14it/s] Loading 0: 55%|█████▍ | 198/363 [00:11<00:11, 14.69it/s] Loading 0: 55%|█████▌ | 201/363 [00:26<03:31, 1.30s/it] Loading 0: 56%|█████▌ | 203/363 [00:26<02:51, 1.07s/it] Loading 0: 57%|█████▋ | 207/363 [00:26<01:47, 1.45it/s] Loading 0: 58%|█████▊ | 210/363 [00:26<01:17, 1.97it/s] Loading 0: 59%|█████▊ | 213/363 [00:26<00:58, 2.58it/s] Loading 0: 59%|█████▉ | 215/363 [00:27<00:48, 3.06it/s] Loading 0: 60%|█████▉ | 217/363 [00:27<00:39, 3.72it/s] Loading 0: 60%|██████ | 219/363 [00:27<00:30, 4.66it/s] Loading 0: 61%|██████ | 221/363 [00:27<00:27, 5.20it/s] Loading 0: 63%|██████▎ | 227/363 [00:27<00:13, 9.99it/s] Loading 0: 64%|██████▎ | 231/363 [00:28<00:11, 11.55it/s] Loading 0: 64%|██████▍ | 234/363 [00:28<00:12, 10.50it/s] Loading 0: 65%|██████▌ | 237/363 [00:28<00:09, 12.65it/s] Loading 0: 66%|██████▌ | 240/363 [00:28<00:09, 12.51it/s] Loading 0: 67%|██████▋ | 244/363 [00:28<00:07, 16.45it/s] Loading 0: 68%|██████▊ | 248/363 [00:28<00:05, 20.45it/s] Loading 0: 69%|██████▉ | 251/363 [00:29<00:07, 15.21it/s] Loading 0: 70%|██████▉ | 254/363 [00:29<00:06, 15.66it/s] Loading 0: 71%|███████ | 257/363 [00:29<00:08, 12.55it/s] Loading 0: 72%|███████▏ | 263/363 [00:29<00:05, 19.03it/s] Loading 0: 74%|███████▎ | 267/363 [00:30<00:05, 18.08it/s] Loading 0: 74%|███████▍ | 270/363 [00:30<00:06, 14.22it/s] Loading 0: 75%|███████▌ | 273/363 [00:30<00:05, 16.28it/s] Loading 0: 76%|███████▌ | 276/363 [00:30<00:05, 14.87it/s] Loading 0: 77%|███████▋ | 281/363 [00:30<00:04, 20.16it/s] Loading 0: 79%|███████▊ | 285/363 [00:31<00:04, 19.11it/s] Loading 0: 79%|███████▉ | 288/363 [00:31<00:05, 14.68it/s] Loading 0: 80%|████████ | 291/363 [00:31<00:04, 16.79it/s] Loading 0: 81%|████████ | 294/363 [00:31<00:04, 14.99it/s] Loading 0: 82%|████████▏ | 298/363 [00:32<00:03, 19.00it/s] Loading 0: 83%|████████▎ | 303/363 [00:32<00:03, 19.51it/s] Loading 0: 84%|████████▍ | 306/363 [00:32<00:03, 14.79it/s] Loading 0: 85%|████████▌ | 309/363 [00:32<00:03, 16.87it/s] Loading 0: 86%|████████▌ | 312/363 [00:32<00:03, 15.17it/s] Loading 0: 87%|████████▋ | 317/363 [00:33<00:02, 20.63it/s] Loading 0: 88%|████████▊ | 321/363 [00:33<00:02, 19.36it/s] Loading 0: 89%|████████▉ | 324/363 [00:33<00:02, 14.62it/s] Loading 0: 90%|█████████ | 327/363 [00:33<00:02, 16.59it/s] Loading 0: 91%|█████████ | 330/363 [00:34<00:02, 15.01it/s] Loading 0: 92%|█████████▏| 335/363 [00:34<00:01, 20.46it/s] Loading 0: 93%|█████████▎| 339/363 [00:34<00:01, 19.43it/s] Loading 0: 94%|█████████▍| 342/363 [00:34<00:01, 14.83it/s] Loading 0: 95%|█████████▌| 345/363 [00:34<00:01, 16.95it/s] Loading 0: 96%|█████████▌| 348/363 [00:35<00:00, 15.43it/s] Loading 0: 97%|█████████▋| 353/363 [00:35<00:00, 20.82it/s] Loading 0: 98%|█████████▊| 357/363 [00:42<00:03, 1.73it/s] Loading 0: 99%|█████████▉| 360/363 [00:42<00:01, 2.22it/s] Loading 0: 100%|█████████▉| 362/363 [00:42<00:00, 2.62it/s]
Job rirv938-mistral-24b-dpo-29487-v3-mkmlizer completed after 195.74s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-29487-v3-mkmlizer
Pipeline stage MKMLizer completed in 196.52s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-29487-v3
Waiting for inference service rirv938-mistral-24b-dpo-29487-v3 to be ready
Inference service rirv938-mistral-24b-dpo-29487-v3 ready after 100.51472878456116s
Pipeline stage MKMLDeployer completed in 101.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.665710687637329s
Received healthy response to inference request in 2.4168362617492676s
Received healthy response to inference request in 2.192267894744873s
Received healthy response to inference request in 2.458895683288574s
Received healthy response to inference request in 2.394085168838501s
5 requests
0 failed requests
5th percentile: 2.2326313495635985
10th percentile: 2.272994804382324
20th percentile: 2.3537217140197755
30th percentile: 2.3986353874206543
40th percentile: 2.407735824584961
50th percentile: 2.4168362617492676
60th percentile: 2.4336600303649902
70th percentile: 2.450483798980713
80th percentile: 2.500258684158325
90th percentile: 2.582984685897827
95th percentile: 2.624347686767578
99th percentile: 2.6574380874633787
mean time: 2.425559139251709
Pipeline stage StressChecker completed in 13.34s
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 0.64s
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 0.66s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_29487_v3 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5533.94s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_29487_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_29487_v3 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1