developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_67163_v1
model_name: rirv938-mistral-24b-dpo_67163_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-03-25T17:05:55+00:00
num_battles: 10290
num_wins: 5284
celo_rating: 1288.02
family_friendly_score: 0.44499999999999995
family_friendly_standard_error: 0.007028157653325657
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_kl_10k_beta1_1248_v3
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3890752566114591, 'latency_mean': 2.570105069875717, 'latency_p50': 2.5589462518692017, 'latency_p90': 2.8951537370681764}, {'batch_size': 3, 'throughput': 0.8024018988258566, 'latency_mean': 3.731645177602768, 'latency_p50': 3.730643391609192, 'latency_p90': 4.083799600601196}, {'batch_size': 5, 'throughput': 1.0655894394153425, 'latency_mean': 4.667874413728714, 'latency_p50': 4.6500502824783325, 'latency_p90': 5.165799951553344}, {'batch_size': 6, 'throughput': 1.13934213557393, 'latency_mean': 5.216143988370895, 'latency_p50': 5.28074038028717, 'latency_p90': 5.815014004707336}, {'batch_size': 10, 'throughput': 1.3148773669317897, 'latency_mean': 7.53673040151596, 'latency_p50': 7.579846978187561, 'latency_p90': 8.484819316864014}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_67163_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_kl_10k_beta1_1248_v3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.8
us_pacific_date: 2025-03-25
win_ratio: 0.5135082604470359
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-67163-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-67163-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: Downloaded to shared memory in 186.692s
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3vejyior, device:0
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: quantized model in 66.680s
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_kl_10k_beta1_1248_v3 in 253.374s
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-67163-v1
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-67163-v1/config.json
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-67163-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-67163-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-67163-v1/tokenizer.json
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-67163-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-67163-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-67163-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.65it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.47it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 19.30it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.51it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:31, 11.11it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 16.13it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.19it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.79it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.95it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 15.64it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 16.07it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.44it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.23it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.18it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 14.93it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.49it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:22, 13.79it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:22, 13.27it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.64it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.44it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.22it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.79it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 13.95it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.24it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.10it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.70it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 14.12it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:20, 13.23it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 16.85it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.74it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 18.20it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 13.96it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 12.95it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.45it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.41it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 10.92it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.80it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.27it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.55it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.77it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.57it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 11.68it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 17.43it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 20.72it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.75it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:15, 13.96it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:14, 14.61it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:18, 11.68it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 17.16it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 20.33it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.26it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.38it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:14, 14.08it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.35it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.96it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.20it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.34it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:13, 13.59it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:12, 14.18it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:15, 11.32it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 16.76it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.11it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.00it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.26it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:52,  1.80s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:44,  1.40s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:10,  1.19it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:31,  1.67it/s]
Loading 0:  58%|█████▊    | 212/363 [00:29<01:11,  2.11it/s]
Loading 0:  59%|█████▉    | 214/363 [00:29<00:58,  2.54it/s]
Loading 0:  60%|█████▉    | 216/363 [00:29<00:48,  3.06it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:32,  4.49it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:28,  4.98it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:15,  8.61it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:11, 11.76it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.42it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:10, 11.71it/s]
Loading 0:  66%|██████▌   | 239/363 [00:31<00:12, 10.04it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:08, 14.56it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 17.88it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.87it/s]
Loading 0:  70%|██████▉   | 254/363 [00:32<00:07, 14.62it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:09, 11.74it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:06, 16.22it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:05, 19.14it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 14.48it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:05, 15.23it/s]
Loading 0:  75%|███████▌  | 274/363 [00:33<00:06, 13.69it/s]
Loading 0:  76%|███████▌  | 276/363 [00:33<00:06, 13.21it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 17.48it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 21.31it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 15.00it/s]
Loading 0:  80%|███████▉  | 290/363 [00:34<00:04, 15.59it/s]
Loading 0:  80%|████████  | 292/363 [00:34<00:05, 13.60it/s]
Loading 0:  81%|████████  | 294/363 [00:34<00:05, 12.39it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:04, 16.13it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:03, 19.22it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:04, 13.70it/s]
Loading 0:  85%|████████▍ | 307/363 [00:35<00:04, 13.11it/s]
Loading 0:  85%|████████▌ | 309/363 [00:35<00:03, 13.80it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:04, 10.81it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 16.70it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 20.08it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 13.84it/s]
Loading 0:  90%|████████▉ | 325/363 [00:36<00:02, 13.13it/s]
Loading 0:  90%|█████████ | 327/363 [00:36<00:02, 13.64it/s]
Loading 0:  91%|█████████ | 329/363 [00:37<00:03, 11.06it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 16.64it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 19.77it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 13.68it/s]
Loading 0:  94%|█████████▍| 343/363 [00:38<00:01, 12.82it/s]
Loading 0:  95%|█████████▌| 345/363 [00:38<00:01, 13.44it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 10.85it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 16.37it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 19.67it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.43it/s]
Loading 0:  99%|█████████▉| 361/363 [00:46<00:01,  1.71it/s]
                                                            

Job rirv938-mistral-24b-dpo-67163-v1-mkmlizer completed after 287.86s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-67163-v1-mkmlizer
Pipeline stage MKMLizer completed in 288.32s
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-67163-v1
Waiting for inference service rirv938-mistral-24b-dpo-67163-v1 to be ready
Inference service rirv938-mistral-24b-dpo-67163-v1 ready after 100.31632328033447s
Pipeline stage MKMLDeployer completed in 100.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4171254634857178s
Received healthy response to inference request in 2.49153470993042s
Received healthy response to inference request in 2.491074323654175s
Received healthy response to inference request in 2.524604082107544s
Received healthy response to inference request in 2.481250524520874s
5 requests
0 failed requests
5th percentile: 2.4832152843475344
10th percentile: 2.4851800441741942
20th percentile: 2.4891095638275145
30th percentile: 2.4911664009094237
40th percentile: 2.491350555419922
50th percentile: 2.49153470993042
60th percentile: 2.5047624588012694
70th percentile: 2.5179902076721192
80th percentile: 2.703108358383179
90th percentile: 3.060116910934448
95th percentile: 3.2386211872100827
99th percentile: 3.3814246082305908
mean time: 2.681117820739746
Pipeline stage StressChecker completed in 14.85s
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 0.63s
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_67163_v1 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 5590.85s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_67163_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_67163_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1