rirv938-mistral-24b-dpo_29487

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo_29487_v5

model_name: rirv938-mistral-24b-dpo_29487_v5

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-03-06T20:59:04+00:00

num_battles: 7549

num_wins: 3740

celo_rating: 1281.11

family_friendly_score: 0.5880000000000001

family_friendly_standard_error: 0.00696068962100739

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': 0.38740988890300265, 'latency_mean': 2.5811605978012087, 'latency_p50': 2.5955746173858643, 'latency_p90': 2.858634281158447}, {'batch_size': 3, 'throughput': 0.7901097961657315, 'latency_mean': 3.7799910259246827, 'latency_p50': 3.7665659189224243, 'latency_p90': 4.209070324897766}, {'batch_size': 5, 'throughput': 1.0509141815899048, 'latency_mean': 4.750415259599686, 'latency_p50': 4.747751593589783, 'latency_p90': 5.365240621566772}, {'batch_size': 6, 'throughput': 1.1289986859558523, 'latency_mean': 5.269727271795273, 'latency_p50': 5.235273122787476, 'latency_p90': 5.921584486961365}, {'batch_size': 10, 'throughput': 1.284859525919391, 'latency_mean': 7.709101217985153, 'latency_p50': 7.709479928016663, 'latency_p90': 8.67042088508606}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo_29487_v5

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: 0.77

us_pacific_date: 2025-03-06

win_ratio: 0.4954298582593721

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-v5-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-29487-v5-mkmlizer to finish
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: Downloaded to shared memory in 101.103s
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeab6h9oq, device:0
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: quantized model in 64.880s
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2 in 165.983s
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v5
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v5/special_tokens_map.json
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v5/config.json
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v5/tokenizer_config.json
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v5/tokenizer.json
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v5/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v5/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-29487-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 27.28it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 12.99it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 19.60it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:26, 12.99it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.56it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 14.96it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.44it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:25, 13.54it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.72it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 20.95it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 14.18it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.29it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:22, 14.10it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:28, 11.12it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 16.63it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 19.77it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 14.02it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 13.28it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.02it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:26, 11.65it/s]
Loading 0:  18%|█▊        | 65/363 [00:04<00:15, 19.50it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:16, 18.35it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:21, 13.74it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:18, 15.90it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:20, 14.12it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.40it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.31it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 13.78it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.14it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 16.75it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.20it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 17.65it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:19, 13.34it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.44it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:21, 12.01it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 13.02it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.65it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:15, 16.18it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 19.43it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.70it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:18, 13.08it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 13.84it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.45it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:12, 17.47it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:10, 20.64it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.82it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 15.57it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.71it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:16, 13.19it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:11, 17.67it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 21.38it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.48it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:13, 15.03it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:14, 13.17it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:15, 12.43it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.14it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 19.54it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:13, 13.92it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:13, 13.29it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 14.14it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:15, 11.27it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 16.83it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 19.68it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 13.83it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.04it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:40,  1.73s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:35,  1.35s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:05,  1.25it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:27,  1.75it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:04,  2.34it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:52,  2.82it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:42,  3.47it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:32,  4.38it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:29,  4.87it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:15,  8.58it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.67it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.43it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:12, 10.56it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:10, 11.67it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:12, 10.05it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:07, 15.71it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 19.05it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.94it/s]
Loading 0:  70%|██████▉   | 254/363 [00:31<00:07, 14.76it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:08, 13.13it/s]
Loading 0:  71%|███████   | 258/363 [00:32<00:08, 12.76it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:05, 17.16it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 20.51it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.56it/s]
Loading 0:  75%|███████▍  | 271/363 [00:32<00:06, 13.65it/s]
Loading 0:  75%|███████▌  | 273/363 [00:32<00:06, 14.51it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:07, 11.66it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 17.87it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 21.80it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:04, 15.29it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.96it/s]
Loading 0:  81%|████████  | 293/363 [00:34<00:05, 12.34it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.07it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:03, 20.16it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:04, 14.42it/s]
Loading 0:  85%|████████▍ | 308/363 [00:35<00:03, 15.07it/s]
Loading 0:  85%|████████▌ | 310/363 [00:35<00:04, 12.89it/s]
Loading 0:  86%|████████▌ | 312/363 [00:35<00:04, 12.70it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.07it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 19.96it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 14.29it/s]
Loading 0:  90%|████████▉ | 325/363 [00:36<00:02, 13.79it/s]
Loading 0:  90%|█████████ | 327/363 [00:36<00:02, 14.50it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 11.77it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.91it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 21.63it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 15.14it/s]
Loading 0:  95%|█████████▍| 344/363 [00:37<00:01, 15.89it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 12.48it/s]
Loading 0:  97%|█████████▋| 353/363 [00:37<00:00, 19.12it/s]
Loading 0:  98%|█████████▊| 357/363 [00:45<00:03,  1.76it/s]
Loading 0:  99%|█████████▉| 360/363 [00:45<00:01,  2.24it/s]
Loading 0: 100%|█████████▉| 362/363 [00:45<00:00,  2.63it/s]
                                                            
Job rirv938-mistral-24b-dpo-29487-v5-mkmlizer completed after 195.78s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-29487-v5-mkmlizer
Pipeline stage MKMLizer completed in 196.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-29487-v5
Waiting for inference service rirv938-mistral-24b-dpo-29487-v5 to be ready
Inference service rirv938-mistral-24b-dpo-29487-v5 ready after 110.41464281082153s
Pipeline stage MKMLDeployer completed in 111.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.983938694000244s
Received healthy response to inference request in 2.4253358840942383s
Received healthy response to inference request in 2.475477695465088s
Received healthy response to inference request in 1.9012737274169922s
Received healthy response to inference request in 2.1104073524475098s
5 requests
0 failed requests
5th percentile: 1.9431004524230957
10th percentile: 1.9849271774291992
20th percentile: 2.0685806274414062
30th percentile: 2.1733930587768553
40th percentile: 2.299364471435547
50th percentile: 2.4253358840942383
60th percentile: 2.445392608642578
70th percentile: 2.465449333190918
80th percentile: 2.577169895172119
90th percentile: 2.7805542945861816
95th percentile: 2.882246494293213
99th percentile: 2.963600254058838
mean time: 2.3792866706848144
Pipeline stage StressChecker completed in 13.27s
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 0.73s
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 0.71s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_29487_v5 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-dpo-29487-v5-profiler
Waiting for inference service rirv938-mistral-24b-dpo-29487-v5-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5099.82s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_29487_v5 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_29487_v5 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message