rirv938-mistral-24b-dpo_29487

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo_29487_v6

model_name: rirv938-mistral-24b-dpo_29487_v6

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-03-26T17:53:57+00:00

num_battles: 6961

num_wins: 3551

celo_rating: 1290.78

family_friendly_score: 0.4988

family_friendly_standard_error: 0.007071047447160852

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': 0.39268037311101, 'latency_mean': 2.5465366423130034, 'latency_p50': 2.55047607421875, 'latency_p90': 2.795258116722107}, {'batch_size': 3, 'throughput': 0.805773515517931, 'latency_mean': 3.7188318073749542, 'latency_p50': 3.680646300315857, 'latency_p90': 4.134307193756103}, {'batch_size': 5, 'throughput': 1.0668444388024996, 'latency_mean': 4.665375930070877, 'latency_p50': 4.651244521141052, 'latency_p90': 5.1623071193695065}, {'batch_size': 6, 'throughput': 1.1359942292425718, 'latency_mean': 5.255466693639756, 'latency_p50': 5.303646683692932, 'latency_p90': 5.8566572904586796}, {'batch_size': 10, 'throughput': 1.3130041635900513, 'latency_mean': 7.546963762044907, 'latency_p50': 7.568423628807068, 'latency_p90': 8.477447199821473}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo_29487_v6

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: 0.8

us_pacific_date: 2025-03-26

win_ratio: 0.5101278551932193

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-v6-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-29487-v6-mkmlizer to finish
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: Downloaded to shared memory in 130.044s
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpliu_1d4s, device:0
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: quantized model in 65.984s
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2 in 196.028s
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v6
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v6/tokenizer_config.json
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v6/tokenizer.json
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v6/special_tokens_map.json
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v6/config.json
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v6/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v6/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-29487-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.38it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.24it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 19.52it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.70it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.58it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:23, 14.95it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.60it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.64it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.66it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 20.73it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 13.79it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.09it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.99it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:28, 11.32it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:18, 17.37it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.24it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.38it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.49it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.30it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:26, 11.64it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.61it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.81it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 14.53it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:19, 14.81it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:21, 13.24it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:22, 12.69it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.54it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 19.96it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 13.95it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.11it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 15.99it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.18it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 18.04it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:19, 13.57it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.66it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.13it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 13.12it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.75it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.71it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:11, 20.22it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.24it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.55it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.44it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 11.84it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:12, 17.78it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:10, 21.01it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.47it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.02it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.45it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:16, 13.14it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 17.15it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 20.42it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.17it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.37it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:13, 14.21it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.32it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.89it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 19.96it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:13, 13.96it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:13, 13.39it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 14.11it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:15, 11.53it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 17.11it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.18it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 14.23it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:11, 13.70it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:43,  1.75s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:37,  1.36s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:06,  1.23it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:28,  1.73it/s]
Loading 0:  59%|█████▊    | 213/363 [00:29<01:04,  2.31it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:52,  2.80it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:42,  3.43it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:33,  4.34it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:29,  4.87it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:15,  8.56it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:11, 11.64it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.49it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:11, 10.71it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:10, 11.82it/s]
Loading 0:  66%|██████▌   | 239/363 [00:31<00:12, 10.13it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:07, 15.54it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 18.94it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:07, 14.11it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:08, 13.53it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:07, 14.40it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:09, 11.50it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:05, 17.26it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 20.64it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.72it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:05, 15.32it/s]
Loading 0:  75%|███████▌  | 274/363 [00:33<00:06, 13.58it/s]
Loading 0:  76%|███████▌  | 276/363 [00:33<00:06, 13.01it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 16.97it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 20.48it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 14.41it/s]
Loading 0:  80%|███████▉  | 289/363 [00:34<00:05, 13.50it/s]
Loading 0:  80%|████████  | 291/363 [00:34<00:05, 14.34it/s]
Loading 0:  81%|████████  | 293/363 [00:34<00:06, 11.58it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.25it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 20.35it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:03, 14.52it/s]
Loading 0:  85%|████████▍ | 307/363 [00:35<00:04, 13.58it/s]
Loading 0:  85%|████████▌ | 309/363 [00:35<00:03, 14.49it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 11.55it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.30it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 20.37it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 14.39it/s]
Loading 0:  90%|████████▉ | 325/363 [00:36<00:02, 13.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:36<00:02, 14.27it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 11.64it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 17.38it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 20.57it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 14.73it/s]
Loading 0:  94%|█████████▍| 343/363 [00:37<00:01, 13.92it/s]
Loading 0:  95%|█████████▌| 345/363 [00:37<00:01, 14.77it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 11.93it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 18.17it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 21.87it/s]
Loading 0:  99%|█████████▉| 359/363 [00:45<00:02,  1.47it/s]
Loading 0:  99%|█████████▉| 361/363 [00:45<00:01,  1.75it/s]
                                                            
Job rirv938-mistral-24b-dpo-29487-v6-mkmlizer completed after 237.31s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-29487-v6-mkmlizer
Pipeline stage MKMLizer completed in 237.97s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-29487-v6
Waiting for inference service rirv938-mistral-24b-dpo-29487-v6 to be ready
Inference service rirv938-mistral-24b-dpo-29487-v6 ready after 110.60283398628235s
Pipeline stage MKMLDeployer completed in 111.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9003424644470215s
Received healthy response to inference request in 2.4632043838500977s
Received healthy response to inference request in 7.9019293785095215s
Received healthy response to inference request in 2.4790713787078857s
Received healthy response to inference request in 2.3974225521087646s
5 requests
0 failed requests
5th percentile: 2.4105789184570314
10th percentile: 2.4237352848052978
20th percentile: 2.450048017501831
30th percentile: 2.466377782821655
40th percentile: 2.4727245807647704
50th percentile: 2.4790713787078857
60th percentile: 2.64757981300354
70th percentile: 2.816088247299194
80th percentile: 3.900659847259522
90th percentile: 5.901294612884522
95th percentile: 6.901611995697021
99th percentile: 7.701865901947022
mean time: 3.628394031524658
Pipeline stage StressChecker completed in 19.46s
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 0.70s
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 0.67s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_29487_v6 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 0.10s
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-v6-profiler
Waiting for inference service rirv938-mistral-24b-dpo-29487-v6-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 5319.21s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_29487_v6 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_29487_v6 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message