rirv938-mistral-24b-dpo_13694

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo_13694_v1

model_name: rirv938-mistral-24b-dpo_13694_v1

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-03-24T23:44:32+00:00

num_battles: 6023

num_wins: 2999

celo_rating: 1279.09

family_friendly_score: 0.587

family_friendly_standard_error: 0.0069632032858448125

submission_type: basic

model_repo: rirv938/mistral_24b_dpo_kl_2500_beta4_78_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': 0.385792555652657, 'latency_mean': 2.591972305774689, 'latency_p50': 2.6142666339874268, 'latency_p90': 2.883326864242554}, {'batch_size': 3, 'throughput': 0.7961932670020355, 'latency_mean': 3.7586824500560763, 'latency_p50': 3.7668488025665283, 'latency_p90': 4.104794669151306}, {'batch_size': 5, 'throughput': 1.0499044270105495, 'latency_mean': 4.75137223482132, 'latency_p50': 4.7888418436050415, 'latency_p90': 5.227863907814026}, {'batch_size': 6, 'throughput': 1.1452017491107271, 'latency_mean': 5.223269860744477, 'latency_p50': 5.25254225730896, 'latency_p90': 5.7984290599823}, {'batch_size': 10, 'throughput': 1.3005143598687952, 'latency_mean': 7.616165101528168, 'latency_p50': 7.630413889884949, 'latency_p90': 8.529397153854369}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo_13694_v1

is_internal_developer: True

language_model: rirv938/mistral_24b_dpo_kl_2500_beta4_78_v3

model_size: 24B

ranking_group: single

throughput_3p7s: 0.78

us_pacific_date: 2025-03-24

win_ratio: 0.49792462228125517

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-13694-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-13694-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: Downloaded to shared memory in 226.620s
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpog13mbrt, device:0
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: quantized model in 68.901s
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_kl_2500_beta4_78_v3 in 295.536s
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-13694-v1
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-13694-v1/config.json
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-13694-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-13694-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-13694-v1/tokenizer.json
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-13694-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-13694-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-13694-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.54it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.12it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.33it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.38it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 12.93it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 15.96it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 16.13it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:27, 12.20it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.35it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.37it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 14.23it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 12.95it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.83it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:28, 11.20it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 16.87it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.24it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.67it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.64it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.41it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:26, 11.62it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.59it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.09it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.74it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:19, 14.96it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:21, 13.15it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:22, 12.59it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:17, 16.53it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 19.91it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 14.06it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.21it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 16.76it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.70it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 18.05it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:19, 13.33it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.45it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:21, 12.02it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 12.89it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.56it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:15, 16.06it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:12, 19.10it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.32it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:18, 12.53it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:17, 13.32it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:21, 10.92it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.43it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.57it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:16, 13.63it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:16, 12.87it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:15, 13.53it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:19, 11.04it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.40it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 19.46it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 13.53it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:15, 12.85it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:14, 13.62it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 10.96it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.64it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.05it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:13, 13.71it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:13, 13.09it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:13, 13.62it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:16, 10.77it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 16.30it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 19.58it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:12, 13.51it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 12.63it/s]
Loading 0:  55%|█████▌    | 201/363 [00:29<05:00,  1.86s/it]
Loading 0:  56%|█████▌    | 202/363 [00:29<04:19,  1.61s/it]
Loading 0:  56%|█████▌    | 204/363 [00:29<03:07,  1.18s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<01:56,  1.34it/s]
Loading 0:  58%|█████▊    | 209/363 [00:29<01:26,  1.77it/s]
Loading 0:  58%|█████▊    | 212/363 [00:30<00:57,  2.62it/s]
Loading 0:  59%|█████▉    | 214/363 [00:30<00:47,  3.12it/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 [00:31<00:25,  5.66it/s]
Loading 0:  62%|██████▏   | 226/363 [00:31<00:14,  9.64it/s]
Loading 0:  63%|██████▎   | 230/363 [00:31<00:10, 12.75it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:12, 10.78it/s]
Loading 0:  65%|██████▍   | 235/363 [00:31<00:11, 10.96it/s]
Loading 0:  65%|██████▌   | 237/363 [00:32<00:10, 12.16it/s]
Loading 0:  66%|██████▌   | 239/363 [00:32<00:11, 10.77it/s]
Loading 0:  67%|██████▋   | 244/363 [00:32<00:07, 16.80it/s]
Loading 0:  68%|██████▊   | 248/363 [00:32<00:05, 20.72it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:07, 15.16it/s]
Loading 0:  70%|██████▉   | 254/363 [00:33<00:06, 15.97it/s]
Loading 0:  71%|███████   | 257/363 [00:33<00:09, 11.76it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:06, 16.30it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:05, 19.00it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:06, 13.91it/s]
Loading 0:  75%|███████▍  | 271/363 [00:34<00:07, 13.09it/s]
Loading 0:  75%|███████▌  | 273/363 [00:34<00:06, 13.92it/s]
Loading 0:  76%|███████▌  | 275/363 [00:34<00:07, 11.40it/s]
Loading 0:  77%|███████▋  | 280/363 [00:34<00:04, 16.98it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 20.33it/s]
Loading 0:  79%|███████▉  | 287/363 [00:35<00:05, 14.53it/s]
Loading 0:  80%|███████▉  | 290/363 [00:35<00:04, 15.05it/s]
Loading 0:  80%|████████  | 292/363 [00:35<00:05, 13.44it/s]
Loading 0:  81%|████████  | 294/363 [00:35<00:05, 12.74it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 16.81it/s]
Loading 0:  83%|████████▎ | 302/363 [00:36<00:02, 20.37it/s]
Loading 0:  84%|████████▍ | 305/363 [00:36<00:04, 14.30it/s]
Loading 0:  85%|████████▍ | 307/363 [00:36<00:04, 13.49it/s]
Loading 0:  85%|████████▌ | 309/363 [00:36<00:03, 14.36it/s]
Loading 0:  86%|████████▌ | 311/363 [00:37<00:04, 11.74it/s]
Loading 0:  87%|████████▋ | 316/363 [00:37<00:02, 17.45it/s]
Loading 0:  88%|████████▊ | 320/363 [00:37<00:02, 20.63it/s]
Loading 0:  89%|████████▉ | 323/363 [00:37<00:02, 14.42it/s]
Loading 0:  90%|████████▉ | 325/363 [00:37<00:02, 13.40it/s]
Loading 0:  90%|█████████ | 327/363 [00:37<00:02, 13.92it/s]
Loading 0:  91%|█████████ | 329/363 [00:38<00:03, 10.79it/s]
Loading 0:  92%|█████████▏| 334/363 [00:38<00:01, 16.15it/s]
Loading 0:  93%|█████████▎| 338/363 [00:38<00:01, 19.25it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 13.51it/s]
Loading 0:  94%|█████████▍| 343/363 [00:39<00:01, 12.97it/s]
Loading 0:  95%|█████████▌| 345/363 [00:39<00:01, 13.83it/s]
Loading 0:  96%|█████████▌| 347/363 [00:39<00:01, 11.06it/s]
Loading 0:  97%|█████████▋| 352/363 [00:39<00:00, 16.37it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 19.45it/s]
Loading 0:  99%|█████████▉| 359/363 [00:47<00:02,  1.44it/s]
Loading 0:  99%|█████████▉| 361/363 [00:47<00:01,  1.71it/s]
                                                            
Job rirv938-mistral-24b-dpo-13694-v1-mkmlizer completed after 329.02s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-13694-v1-mkmlizer
Pipeline stage MKMLizer completed in 329.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-13694-v1
Waiting for inference service rirv938-mistral-24b-dpo-13694-v1 to be ready
Inference service rirv938-mistral-24b-dpo-13694-v1 ready after 100.46611833572388s
Pipeline stage MKMLDeployer completed in 100.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3324027061462402s
Received healthy response to inference request in 2.4590179920196533s
Received healthy response to inference request in 2.5870847702026367s
Received healthy response to inference request in 2.6180410385131836s
Received healthy response to inference request in 2.6977531909942627s
5 requests
0 failed requests
5th percentile: 2.48463134765625
10th percentile: 2.5102447032928468
20th percentile: 2.56147141456604
30th percentile: 2.593276023864746
40th percentile: 2.605658531188965
50th percentile: 2.6180410385131836
60th percentile: 2.6499258995056154
70th percentile: 2.681810760498047
80th percentile: 2.824683094024658
90th percentile: 3.0785429000854494
95th percentile: 3.205472803115845
99th percentile: 3.3070167255401612
mean time: 2.738859939575195
Pipeline stage StressChecker completed in 15.27s
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 0.64s
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 0.65s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_13694_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 0.12s
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-13694-v1-profiler
Waiting for inference service rirv938-mistral-24b-dpo-13694-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 2938.39s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_13694_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_13694_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message