developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_36894_v1
model_name: rirv938-mistral-24b-dpo_36894_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-03-25T17:05:56+00:00
num_battles: 9116
num_wins: 4777
celo_rating: 1295.57
family_friendly_score: 0.4448
family_friendly_standard_error: 0.007027844050631744
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_kl_10k_beta1_1560_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': 0.38784849833370716, 'latency_mean': 2.578235626220703, 'latency_p50': 2.5655592679977417, 'latency_p90': 2.880241370201111}, {'batch_size': 3, 'throughput': 0.7942000836759988, 'latency_mean': 3.767872393131256, 'latency_p50': 3.7596102952957153, 'latency_p90': 4.13102343082428}, {'batch_size': 5, 'throughput': 1.0538831460643046, 'latency_mean': 4.729632340669632, 'latency_p50': 4.743993878364563, 'latency_p90': 5.322673892974853}, {'batch_size': 6, 'throughput': 1.1278265699582366, 'latency_mean': 5.276993716955185, 'latency_p50': 5.283164978027344, 'latency_p90': 5.871898794174194}, {'batch_size': 10, 'throughput': 1.2951218479134026, 'latency_mean': 7.641192872524261, 'latency_p50': 7.7160316705703735, 'latency_p90': 8.524524235725403}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_36894_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_kl_10k_beta1_1560_v3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.78
us_pacific_date: 2025-03-25
win_ratio: 0.524023694602896
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-36894-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-36894-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: Downloaded to shared memory in 190.374s
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpptq2rtou, device:0
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: quantized model in 67.671s
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_kl_10k_beta1_1560_v3 in 258.046s
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-36894-v1
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-36894-v1/config.json
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-36894-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-36894-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-36894-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-36894-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-36894-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.35it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 13.13it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 19.24it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.53it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:31, 10.93it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 15.74it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 14.97it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.99it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.20it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.67it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.83it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.38it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.57it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 12.96it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 16.94it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.49it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.53it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.56it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.44it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:26, 11.52it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 17.35it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.53it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 14.52it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:21, 13.74it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:19, 14.55it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:24, 11.61it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.43it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.79it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.92it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.16it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.59it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.94it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.91it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 14.20it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.12it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.58it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.47it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 10.96it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.98it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.59it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.64it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:16, 13.93it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.61it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 11.76it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.57it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.17it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.64it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.27it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.70it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 12.99it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 17.02it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 20.50it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.34it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.43it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:14, 14.13it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.10it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.70it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 19.91it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:13, 13.85it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:13, 13.13it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 13.95it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:16, 11.11it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 16.78it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.03it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.24it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.50it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:57,  1.84s/it]
Loading 0:  56%|█████▌    | 202/363 [00:28<04:16,  1.60s/it]
Loading 0:  56%|█████▌    | 204/363 [00:29<03:05,  1.17s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<01:55,  1.35it/s]
Loading 0:  58%|█████▊    | 209/363 [00:29<01:25,  1.80it/s]
Loading 0:  58%|█████▊    | 212/363 [00:29<00:56,  2.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:29<00:47,  3.16it/s]
Loading 0:  60%|█████▉    | 216/363 [00:30<00:39,  3.70it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:26,  5.36it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:24,  5.68it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:14,  9.59it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:10, 12.77it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:11, 11.05it/s]
Loading 0:  65%|██████▍   | 235/363 [00:31<00:11, 11.02it/s]
Loading 0:  65%|██████▌   | 237/363 [00:31<00:10, 12.00it/s]
Loading 0:  66%|██████▌   | 239/363 [00:31<00:12, 10.25it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:07, 15.65it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 19.09it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:07, 14.09it/s]
Loading 0:  70%|██████▉   | 253/363 [00:32<00:08, 13.39it/s]
Loading 0:  70%|███████   | 255/363 [00:32<00:07, 14.13it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:09, 11.44it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:05, 17.09it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:04, 20.20it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 14.26it/s]
Loading 0:  75%|███████▍  | 271/363 [00:33<00:06, 13.47it/s]
Loading 0:  75%|███████▌  | 273/363 [00:33<00:06, 14.08it/s]
Loading 0:  76%|███████▌  | 275/363 [00:34<00:07, 11.49it/s]
Loading 0:  77%|███████▋  | 280/363 [00:34<00:04, 17.26it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 20.89it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 14.06it/s]
Loading 0:  80%|███████▉  | 290/363 [00:34<00:04, 14.91it/s]
Loading 0:  80%|████████  | 292/363 [00:35<00:05, 13.22it/s]
Loading 0:  81%|████████  | 294/363 [00:35<00:05, 12.61it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 16.75it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:02, 20.71it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:04, 14.44it/s]
Loading 0:  85%|████████▍ | 307/363 [00:36<00:04, 13.75it/s]
Loading 0:  85%|████████▌ | 309/363 [00:36<00:03, 14.59it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:04, 11.40it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 17.30it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 20.89it/s]
Loading 0:  89%|████████▉ | 323/363 [00:37<00:02, 14.64it/s]
Loading 0:  90%|████████▉ | 326/363 [00:37<00:02, 15.09it/s]
Loading 0:  90%|█████████ | 328/363 [00:37<00:02, 12.97it/s]
Loading 0:  91%|█████████ | 330/363 [00:37<00:02, 12.32it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 16.34it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 20.13it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 14.31it/s]
Loading 0:  94%|█████████▍| 343/363 [00:38<00:01, 13.61it/s]
Loading 0:  95%|█████████▌| 345/363 [00:38<00:01, 14.45it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 11.46it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 17.44it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 20.63it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.39it/s]
Loading 0:  99%|█████████▉| 361/363 [00:46<00:01,  1.67it/s]
                                                            

Job rirv938-mistral-24b-dpo-36894-v1-mkmlizer completed after 297.75s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-36894-v1-mkmlizer
Pipeline stage MKMLizer completed in 298.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-36894-v1
Waiting for inference service rirv938-mistral-24b-dpo-36894-v1 to be ready
Inference service rirv938-mistral-24b-dpo-36894-v1 ready after 100.72168278694153s
Pipeline stage MKMLDeployer completed in 101.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.003117084503174s
Received healthy response to inference request in 2.6758954524993896s
Received healthy response to inference request in 2.7637453079223633s
Received healthy response to inference request in 2.415769577026367s
Received healthy response to inference request in 2.6748435497283936s
5 requests
0 failed requests
5th percentile: 2.4675843715667725
10th percentile: 2.5193991661071777
20th percentile: 2.6230287551879883
30th percentile: 2.675053930282593
40th percentile: 2.675474691390991
50th percentile: 2.6758954524993896
60th percentile: 2.711035394668579
70th percentile: 2.7461753368377684
80th percentile: 2.8116196632385253
90th percentile: 2.90736837387085
95th percentile: 2.955242729187012
99th percentile: 2.9935422134399414
mean time: 2.7066741943359376
Pipeline stage StressChecker completed in 14.81s
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 0.66s
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 0.63s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_36894_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-dpo-36894-v1-profiler
Waiting for inference service rirv938-mistral-24b-dpo-36894-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 3008.04s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_36894_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_36894_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1