rirv938-mistral-24b-dpo_86582

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo_86582_v1

model_name: rirv938-mistral-24b-dpo_86582_v1

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-02-23T00:32:59+00:00

num_battles: 6706

num_wins: 3359

celo_rating: 1270.13

family_friendly_score: 0.6355999999999999

family_friendly_standard_error: 0.006806065530098869

submission_type: basic

model_repo: rirv938/mistral_24b_dpo_20k_1250_without_instruct_format_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': 0.3876764661398047, 'latency_mean': 2.579385198354721, 'latency_p50': 2.586603879928589, 'latency_p90': 2.894533133506775}, {'batch_size': 3, 'throughput': 0.7952056668914735, 'latency_mean': 3.758543554544449, 'latency_p50': 3.7347060441970825, 'latency_p90': 4.202111864089966}, {'batch_size': 5, 'throughput': 1.048078896179542, 'latency_mean': 4.753010070323944, 'latency_p50': 4.735093951225281, 'latency_p90': 5.337436032295227}, {'batch_size': 6, 'throughput': 1.1491670491431958, 'latency_mean': 5.194623489379882, 'latency_p50': 5.163632392883301, 'latency_p90': 5.849819970130921}, {'batch_size': 10, 'throughput': 1.3089399786586782, 'latency_mean': 7.573104184865952, 'latency_p50': 7.560441493988037, 'latency_p90': 8.534175252914428}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo_86582_v1

is_internal_developer: True

language_model: rirv938/mistral_24b_dpo_20k_1250_without_instruct_format_v2

model_size: 24B

ranking_group: single

throughput_3p7s: 0.78

us_pacific_date: 2025-02-22

win_ratio: 0.500894721145243

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-86582-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-86582-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission rirv938-mistral-24b-bon_67508_v1: ('http://rirv938-mistral-24b-bon-67508-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: Downloaded to shared memory in 204.877s
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfyv59enl, device:0
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: quantized model in 69.003s
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_20k_1250_without_instruct_format_v2 in 273.900s
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-86582-v1
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-86582-v1/config.json
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-86582-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-86582-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-86582-v1/tokenizer.json
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-86582-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-86582-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-86582-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:14, 24.69it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:29, 12.12it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:19, 18.47it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:28, 12.31it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:34, 10.07it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:23, 14.35it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:24, 13.92it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:26, 12.92it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 16.91it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:16, 20.27it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:24, 13.49it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 12.55it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:24, 13.29it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:30, 10.52it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:20, 15.66it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:16, 18.53it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:24, 12.64it/s]
Loading 0:  15%|█▌        | 55/363 [00:04<00:26, 11.76it/s]
Loading 0:  16%|█▌        | 57/363 [00:04<00:24, 12.51it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:29, 10.16it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:19, 15.32it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:16, 18.32it/s]
Loading 0:  20%|█▉        | 71/363 [00:05<00:22, 12.92it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:23, 12.20it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:22, 12.99it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:27, 10.40it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:18, 15.61it/s]
Loading 0:  24%|██▎       | 86/363 [00:06<00:14, 18.61it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:20, 13.22it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:21, 12.54it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 16.16it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.28it/s]
Loading 0:  28%|██▊       | 102/363 [00:07<00:14, 17.61it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:19, 13.27it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:21, 12.12it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:21, 11.70it/s]
Loading 0:  31%|███       | 111/363 [00:08<00:19, 12.71it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:24, 10.22it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:15, 15.85it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 18.87it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:18, 13.11it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:18, 12.46it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:17, 13.32it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:21, 10.83it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.33it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.72it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:15, 14.13it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:16, 13.34it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:15, 14.08it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:18, 11.32it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.83it/s]
Loading 0:  44%|████▎     | 158/363 [00:11<00:10, 20.04it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:14, 14.06it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:15, 13.11it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:14, 13.78it/s]
Loading 0:  46%|████▌     | 167/363 [00:12<00:18, 10.87it/s]
Loading 0:  47%|████▋     | 172/363 [00:12<00:11, 15.97it/s]
Loading 0:  48%|████▊     | 176/363 [00:12<00:09, 18.96it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:14, 13.03it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:14, 12.38it/s]
Loading 0:  50%|█████     | 183/363 [00:13<00:13, 13.20it/s]
Loading 0:  51%|█████     | 185/363 [00:13<00:16, 10.49it/s]
Loading 0:  52%|█████▏    | 190/363 [00:13<00:11, 15.59it/s]
Loading 0:  53%|█████▎    | 194/363 [00:13<00:09, 18.27it/s]
Loading 0:  54%|█████▍    | 197/363 [00:14<00:13, 12.70it/s]
Loading 0:  55%|█████▍    | 199/363 [00:14<00:13, 12.04it/s]
Loading 0:  55%|█████▌    | 200/363 [00:30<00:13, 12.04it/s]
Loading 0:  55%|█████▌    | 201/363 [00:30<05:02,  1.87s/it]
Loading 0:  56%|█████▌    | 203/363 [00:30<03:52,  1.45s/it]
Loading 0:  57%|█████▋    | 207/363 [00:30<02:14,  1.16it/s]
Loading 0:  58%|█████▊    | 210/363 [00:30<01:34,  1.62it/s]
Loading 0:  59%|█████▊    | 213/363 [00:31<01:09,  2.17it/s]
Loading 0:  59%|█████▉    | 215/363 [00:31<00:56,  2.62it/s]
Loading 0:  60%|█████▉    | 217/363 [00:31<00:45,  3.21it/s]
Loading 0:  60%|██████    | 219/363 [00:31<00:35,  4.07it/s]
Loading 0:  61%|██████    | 221/363 [00:31<00:31,  4.57it/s]
Loading 0:  62%|██████▏   | 226/363 [00:32<00:17,  8.00it/s]
Loading 0:  63%|██████▎   | 230/363 [00:32<00:12, 10.94it/s]
Loading 0:  64%|██████▍   | 233/363 [00:32<00:12, 10.03it/s]
Loading 0:  65%|██████▍   | 235/363 [00:32<00:12, 10.24it/s]
Loading 0:  65%|██████▌   | 237/363 [00:32<00:11, 11.32it/s]
Loading 0:  66%|██████▌   | 239/363 [00:33<00:12,  9.90it/s]
Loading 0:  67%|██████▋   | 244/363 [00:33<00:07, 15.18it/s]
Loading 0:  68%|██████▊   | 248/363 [00:33<00:06, 18.71it/s]
Loading 0:  69%|██████▉   | 251/363 [00:33<00:08, 13.82it/s]
Loading 0:  70%|██████▉   | 253/363 [00:33<00:08, 13.31it/s]
Loading 0:  70%|███████   | 255/363 [00:34<00:07, 14.16it/s]
Loading 0:  71%|███████   | 257/363 [00:34<00:09, 11.56it/s]
Loading 0:  72%|███████▏  | 262/363 [00:34<00:05, 17.50it/s]
Loading 0:  73%|███████▎  | 266/363 [00:34<00:04, 20.37it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:06, 14.26it/s]
Loading 0:  75%|███████▍  | 271/363 [00:35<00:06, 13.59it/s]
Loading 0:  75%|███████▌  | 273/363 [00:35<00:06, 14.37it/s]
Loading 0:  76%|███████▌  | 275/363 [00:35<00:07, 11.65it/s]
Loading 0:  77%|███████▋  | 280/363 [00:35<00:04, 17.65it/s]
Loading 0:  78%|███████▊  | 284/363 [00:35<00:03, 21.45it/s]
Loading 0:  79%|███████▉  | 287/363 [00:36<00:05, 14.83it/s]
Loading 0:  80%|███████▉  | 290/363 [00:36<00:04, 15.38it/s]
Loading 0:  80%|████████  | 292/363 [00:36<00:05, 13.54it/s]
Loading 0:  81%|████████  | 294/363 [00:36<00:05, 12.97it/s]
Loading 0:  82%|████████▏ | 298/363 [00:36<00:03, 17.11it/s]
Loading 0:  83%|████████▎ | 302/363 [00:36<00:02, 20.78it/s]
Loading 0:  84%|████████▍ | 305/363 [00:37<00:04, 14.34it/s]
Loading 0:  85%|████████▍ | 307/363 [00:37<00:04, 13.58it/s]
Loading 0:  85%|████████▌ | 309/363 [00:37<00:03, 14.41it/s]
Loading 0:  86%|████████▌ | 311/363 [00:37<00:04, 11.61it/s]
Loading 0:  87%|████████▋ | 316/363 [00:37<00:02, 17.57it/s]
Loading 0:  88%|████████▊ | 320/363 [00:38<00:02, 21.13it/s]
Loading 0:  89%|████████▉ | 323/363 [00:38<00:02, 14.68it/s]
Loading 0:  90%|████████▉ | 326/363 [00:38<00:02, 15.36it/s]
Loading 0:  90%|█████████ | 328/363 [00:38<00:02, 13.62it/s]
Loading 0:  91%|█████████ | 330/363 [00:39<00:02, 12.86it/s]
Loading 0:  92%|█████████▏| 334/363 [00:39<00:01, 17.06it/s]
Loading 0:  93%|█████████▎| 338/363 [00:39<00:01, 20.69it/s]
Loading 0:  94%|█████████▍| 341/363 [00:39<00:01, 13.88it/s]
Loading 0:  94%|█████████▍| 343/363 [00:39<00:01, 13.25it/s]
Loading 0:  95%|█████████▌| 345/363 [00:39<00:01, 14.09it/s]
Loading 0:  96%|█████████▌| 347/363 [00:40<00:01, 11.63it/s]
Loading 0:  97%|█████████▋| 352/363 [00:40<00:00, 17.81it/s]
Loading 0:  98%|█████████▊| 356/363 [00:40<00:00, 21.37it/s]
Loading 0:  99%|█████████▉| 359/363 [00:47<00:02,  1.43it/s]
Loading 0:  99%|█████████▉| 361/363 [00:48<00:01,  1.71it/s]
                                                            
Job rirv938-mistral-24b-dpo-86582-v1-mkmlizer completed after 328.98s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-86582-v1-mkmlizer
Pipeline stage MKMLizer completed in 329.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Failed to get response for submission rirv938-mistral-24b-bon_67508_v1: ('http://rirv938-mistral-24b-bon-67508-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-86582-v1
Waiting for inference service rirv938-mistral-24b-dpo-86582-v1 to be ready
Failed to get response for submission rirv938-mistral-24b-bon_67508_v1: ('http://rirv938-mistral-24b-bon-67508-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service rirv938-mistral-24b-dpo-86582-v1 ready after 220.76981806755066s
Pipeline stage MKMLDeployer completed in 221.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7897660732269287s
Received healthy response to inference request in 1.8562185764312744s
Received healthy response to inference request in 1.9429526329040527s
Received healthy response to inference request in 2.1341824531555176s
Received healthy response to inference request in 1.797393560409546s
5 requests
0 failed requests
5th percentile: 1.8091585636138916
10th percentile: 1.8209235668182373
20th percentile: 1.8444535732269287
30th percentile: 1.87356538772583
40th percentile: 1.9082590103149415
50th percentile: 1.9429526329040527
60th percentile: 2.0194445610046388
70th percentile: 2.095936489105225
80th percentile: 2.2652991771698
90th percentile: 2.527532625198364
95th percentile: 2.6586493492126464
99th percentile: 2.7635427284240723
mean time: 2.1041026592254637
Pipeline stage StressChecker completed in 11.99s
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 0.65s
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 0.74s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_86582_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2990.58s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_86582_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_86582_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message