rirv938-mistral-24b-dpo_29487

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo_29487_v4

model_name: rirv938-mistral-24b-dpo_29487_v4

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-03-06T20:59:02+00:00

num_battles: 13175

num_wins: 6636

celo_rating: 1285.12

family_friendly_score: 0.5912

family_friendly_standard_error: 0.006952446475881709

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': 0.387880052482027, 'latency_mean': 2.578049820661545, 'latency_p50': 2.590411901473999, 'latency_p90': 2.86316773891449}, {'batch_size': 3, 'throughput': 0.7881152439775004, 'latency_mean': 3.7841043162345884, 'latency_p50': 3.802312731742859, 'latency_p90': 4.230611205101013}, {'batch_size': 5, 'throughput': 1.0431917911601518, 'latency_mean': 4.783815295696258, 'latency_p50': 4.797714352607727, 'latency_p90': 5.3661150455474855}, {'batch_size': 6, 'throughput': 1.1222083305124084, 'latency_mean': 5.302212258577347, 'latency_p50': 5.314496994018555, 'latency_p90': 5.944004106521606}, {'batch_size': 10, 'throughput': 1.2933143730866294, 'latency_mean': 7.659066667556763, 'latency_p50': 7.623149156570435, 'latency_p90': 8.611184191703796}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo_29487_v4

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: 0.5036812144212524

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-v4-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-29487-v4-mkmlizer to finish
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: Downloaded to shared memory in 106.192s
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5qoggqqo, device:0
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: quantized model in 64.371s
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2 in 170.563s
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v4
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v4/config.json
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v4/special_tokens_map.json
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v4/tokenizer_config.json
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v4/tokenizer.json
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v4/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-29487-v4/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-29487-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 27.79it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.47it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.13it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.89it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:33, 10.38it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 14.96it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.32it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:25, 13.30it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.14it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:16, 20.38it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 13.99it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 13.01it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.82it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:28, 11.24it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:18, 17.57it/s]
Loading 0:  14%|█▍        | 51/363 [00:03<00:17, 18.16it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:22, 13.46it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:19, 15.53it/s]
Loading 0:  17%|█▋        | 60/363 [00:04<00:21, 14.14it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.66it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.14it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.12it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.65it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:21, 13.14it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:22, 12.59it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.93it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.63it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:20, 13.60it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 12.99it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.27it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.00it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.72it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:19, 13.36it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.41it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:21, 11.63it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:20, 12.35it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:24, 10.04it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:16, 15.19it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 18.61it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.42it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.11it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.02it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.59it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:12, 17.76it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:10, 21.29it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.88it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.23it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:16, 13.15it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:17, 12.36it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.44it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 19.90it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 13.59it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:15, 12.67it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:14, 13.34it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.10it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 17.02it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.56it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:13, 13.77it/s]
Loading 0:  50%|█████     | 182/363 [00:12<00:12, 14.16it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:14, 12.44it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:14, 11.94it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 15.90it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 19.17it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:12, 13.82it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.32it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:41,  1.74s/it]
Loading 0:  56%|█████▌    | 202/363 [00:28<04:02,  1.51s/it]
Loading 0:  56%|█████▌    | 204/363 [00:28<02:54,  1.10s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<01:48,  1.44it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:10,  2.16it/s]
Loading 0:  58%|█████▊    | 212/363 [00:28<00:54,  2.77it/s]
Loading 0:  59%|█████▉    | 214/363 [00:28<00:44,  3.35it/s]
Loading 0:  60%|█████▉    | 216/363 [00:29<00:37,  3.94it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:25,  5.76it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:23,  6.07it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:13, 10.33it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:09, 13.83it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:11, 11.79it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:09, 12.81it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:10, 11.87it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:10, 11.85it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.90it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:05, 19.71it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:07, 14.31it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:07, 13.83it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:07, 14.66it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:08, 11.92it/s]
Loading 0:  72%|███████▏  | 263/363 [00:31<00:05, 19.98it/s]
Loading 0:  74%|███████▎  | 267/363 [00:32<00:05, 18.89it/s]
Loading 0:  74%|███████▍  | 270/363 [00:32<00:06, 14.09it/s]
Loading 0:  75%|███████▌  | 273/363 [00:32<00:05, 16.11it/s]
Loading 0:  76%|███████▌  | 276/363 [00:32<00:06, 14.30it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 18.10it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 21.90it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:04, 15.54it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 16.30it/s]
Loading 0:  81%|████████  | 293/363 [00:34<00:05, 12.48it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.55it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 20.84it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 15.00it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 14.91it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 11.86it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 16.83it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 19.90it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 15.12it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 15.68it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 12.48it/s]
Loading 0:  92%|█████████▏| 335/363 [00:36<00:01, 18.91it/s]
Loading 0:  93%|█████████▎| 339/363 [00:36<00:01, 18.21it/s]
Loading 0:  94%|█████████▍| 342/363 [00:37<00:01, 14.01it/s]
Loading 0:  95%|█████████▌| 345/363 [00:37<00:01, 15.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:37<00:01, 14.41it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 18.21it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 21.72it/s]
Loading 0:  99%|█████████▉| 359/363 [00:44<00:02,  1.54it/s]
Loading 0:  99%|█████████▉| 361/363 [00:45<00:01,  1.82it/s]
                                                            
Job rirv938-mistral-24b-dpo-29487-v4-mkmlizer completed after 196.22s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-29487-v4-mkmlizer
Pipeline stage MKMLizer completed in 196.73s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-29487-v4
Waiting for inference service rirv938-mistral-24b-dpo-29487-v4 to be ready
Inference service rirv938-mistral-24b-dpo-29487-v4 ready after 110.55698418617249s
Pipeline stage MKMLDeployer completed in 111.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0926504135131836s
Received healthy response to inference request in 2.2657735347747803s
Received healthy response to inference request in 1.9397919178009033s
Received healthy response to inference request in 2.391707181930542s
Received healthy response to inference request in 2.3739562034606934s
5 requests
0 failed requests
5th percentile: 2.0049882411956785
10th percentile: 2.070184564590454
20th percentile: 2.200577211380005
30th percentile: 2.2874100685119627
40th percentile: 2.330683135986328
50th percentile: 2.3739562034606934
60th percentile: 2.3810565948486326
70th percentile: 2.3881569862365724
80th percentile: 2.5318958282470705
90th percentile: 2.812273120880127
95th percentile: 2.952461767196655
99th percentile: 3.064612684249878
mean time: 2.4127758502960206
Pipeline stage StressChecker completed in 13.49s
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 0.66s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_29487_v4 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2718.88s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_29487_v4 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_29487_v4 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message