rirv938-mistral-24b-dpo_97036

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo_97036_v1

model_name: rirv938-mistral-24b-dpo_97036_v1

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-02-24T01:21:31+00:00

num_battles: 10368

num_wins: 5146

celo_rating: 1277.63

family_friendly_score: 0.6182000000000001

family_friendly_standard_error: 0.006870644220158689

submission_type: basic

model_repo: rirv938/mistral_24b_dpo_40k_95w_pref_2500_instruct_lr_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': 0.38549639659050594, 'latency_mean': 2.593993899822235, 'latency_p50': 2.5893795490264893, 'latency_p90': 2.881579303741455}, {'batch_size': 3, 'throughput': 0.7846795415856839, 'latency_mean': 3.8101404130458834, 'latency_p50': 3.7932519912719727, 'latency_p90': 4.237749743461609}, {'batch_size': 5, 'throughput': 1.0337403261047486, 'latency_mean': 4.818204464912415, 'latency_p50': 4.80415141582489, 'latency_p90': 5.396188378334045}, {'batch_size': 6, 'throughput': 1.1115386231801625, 'latency_mean': 5.3770859897136685, 'latency_p50': 5.371838450431824, 'latency_p90': 6.008534550666809}, {'batch_size': 10, 'throughput': 1.2842375626446607, 'latency_mean': 7.7336084842681885, 'latency_p50': 7.663878560066223, 'latency_p90': 8.672402143478394}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo_97036_v1

is_internal_developer: True

language_model: rirv938/mistral_24b_dpo_40k_95w_pref_2500_instruct_lr_v2

model_size: 24B

ranking_group: single

throughput_3p7s: 0.76

us_pacific_date: 2025-02-23

win_ratio: 0.4963348765432099

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-97036-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-97036-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission rirv938-mistral-24b-dpo_35049_v1: ('http://rirv938-mistral-24b-dpo-35049-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission rirv938-mistral-24b-dpo_77960_v1: ('http://rirv938-mistral-24b-dpo-77960-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: Downloaded to shared memory in 213.036s
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf1s44wr_, device:0
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: quantized model in 63.342s
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_95w_pref_2500_instruct_lr_v2 in 276.388s
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-97036-v1
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-97036-v1/config.json
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-97036-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-97036-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-97036-v1/tokenizer.json
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-97036-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-97036-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.83it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.62it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.59it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.21it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.06it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.81it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.62it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.64it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.22it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 16.26it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 17.01it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 13.39it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 18.76it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 22.30it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:21, 14.06it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:19, 16.07it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:20, 14.76it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.48it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 22.04it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.83it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.34it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:23, 12.40it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:16, 17.14it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.05it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.48it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.76it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 17.74it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.11it/s]
Loading 0:  28%|██▊       | 102/363 [00:05<00:13, 19.49it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.95it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.80it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.44it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.45it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.74it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.73it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.02it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:16, 14.86it/s]
Loading 0:  35%|███▍      | 127/363 [00:07<00:16, 14.22it/s]
Loading 0:  36%|███▌      | 129/363 [00:07<00:15, 15.13it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 12.07it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.95it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.39it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.04it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:14, 15.49it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.50it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 12.96it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 16.84it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:10, 20.14it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:14, 14.19it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.76it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.61it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 11.74it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.51it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:09, 20.67it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.70it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:13, 13.94it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:12, 14.79it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 11.98it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.81it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.89it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.80it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 14.03it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:34,  1.69s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:30,  1.31s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:02,  1.28it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:25,  1.79it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:02,  2.40it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:50,  2.90it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:41,  3.56it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:31,  4.50it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:28,  5.04it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  8.84it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:11, 11.74it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:12, 10.62it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:11, 10.96it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:10, 12.21it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:11, 10.72it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 16.35it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:05, 19.89it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.76it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:06, 15.72it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.74it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.72it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 20.78it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.35it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.19it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 12.93it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.67it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.73it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 15.48it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.14it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.75it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.41it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:03, 20.24it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.11it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 15.73it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:03, 14.14it/s]
Loading 0:  86%|████████▌ | 312/363 [00:34<00:03, 13.59it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.14it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.53it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 14.87it/s]
Loading 0:  90%|████████▉ | 325/363 [00:34<00:02, 14.11it/s]
Loading 0:  90%|█████████ | 327/363 [00:34<00:02, 14.96it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.11it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.96it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.08it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.11it/s]
Loading 0:  94%|█████████▍| 343/363 [00:35<00:01, 14.62it/s]
Loading 0:  95%|█████████▌| 345/363 [00:36<00:01, 15.40it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.46it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.23it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.50it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.49it/s]
Loading 0:  99%|█████████▉| 361/363 [00:43<00:01,  1.78it/s]
                                                            
Job rirv938-mistral-24b-dpo-97036-v1-mkmlizer completed after 338.85s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-97036-v1-mkmlizer
Pipeline stage MKMLizer completed in 339.33s
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-97036-v1
Waiting for inference service rirv938-mistral-24b-dpo-97036-v1 to be ready
Inference service rirv938-mistral-24b-dpo-97036-v1 ready after 240.84128713607788s
Pipeline stage MKMLDeployer completed in 241.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.73687744140625s
Received healthy response to inference request in 2.62106990814209s
Received healthy response to inference request in 2.3778223991394043s
Received healthy response to inference request in 2.5840723514556885s
Received healthy response to inference request in 2.4083092212677s
5 requests
0 failed requests
5th percentile: 2.3839197635650633
10th percentile: 2.3900171279907227
20th percentile: 2.402211856842041
30th percentile: 2.443461847305298
40th percentile: 2.5137670993804933
50th percentile: 2.5840723514556885
60th percentile: 2.598871374130249
70th percentile: 2.6136703968048094
80th percentile: 2.644231414794922
90th percentile: 2.6905544281005858
95th percentile: 2.713715934753418
99th percentile: 2.7322451400756838
mean time: 2.5456302642822264
Pipeline stage StressChecker completed in 14.15s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
Retrying (%r) after connection broken by '%r': %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 1.08s
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 0.70s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_97036_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-dpo-97036-v1-profiler
Waiting for inference service rirv938-mistral-24b-dpo-97036-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4864.45s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_97036_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_97036_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message