rirv938-mistral-24b-rou_50061

developer_uid: rirv938

submission_id: rirv938-mistral-24b-rou_50061_v1

model_name: rirv938-mistral-24b-rou_50061_v1

model_group: rirv938/mistral_24b_roun

status: torndown

timestamp: 2025-03-06T02:57:07+00:00

num_battles: 7640

num_wins: 3968

celo_rating: 1301.59

family_friendly_score: 0.5136000000000001

family_friendly_standard_error: 0.007068451598476148

submission_type: basic

model_repo: rirv938/mistral_24b_round_2_dpo_40k_95w_pref_2500_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': 0.3874280711185984, 'latency_mean': 2.5810592806339265, 'latency_p50': 2.5728894472122192, 'latency_p90': 2.8840849876403807}, {'batch_size': 3, 'throughput': 0.7949391985857385, 'latency_mean': 3.7619763660430907, 'latency_p50': 3.744264841079712, 'latency_p90': 4.131047964096069}, {'batch_size': 5, 'throughput': 1.0488997507748248, 'latency_mean': 4.73746123790741, 'latency_p50': 4.743774056434631, 'latency_p90': 5.2970353126525875}, {'batch_size': 6, 'throughput': 1.1206880076751677, 'latency_mean': 5.335577111244202, 'latency_p50': 5.335079789161682, 'latency_p90': 5.934792971611023}, {'batch_size': 10, 'throughput': 1.295983266947921, 'latency_mean': 7.657709249258041, 'latency_p50': 7.63617205619812, 'latency_p90': 8.605147910118102}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-rou_50061_v1

is_internal_developer: True

language_model: rirv938/mistral_24b_round_2_dpo_40k_95w_pref_2500_v2

model_size: 24B

ranking_group: single

throughput_3p7s: 0.78

us_pacific_date: 2025-03-05

win_ratio: 0.5193717277486911

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-rou-50061-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-rou-50061-v1-mkmlizer to finish
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-50061-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-rou-50061-v1-mkmlizer: Downloaded to shared memory in 168.649s
rirv938-mistral-24b-rou-50061-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwbx3j2nb, device:0
rirv938-mistral-24b-rou-50061-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-rou-50061-v1-mkmlizer: quantized model in 68.090s
rirv938-mistral-24b-rou-50061-v1-mkmlizer: Processed model rirv938/mistral_24b_round_2_dpo_40k_95w_pref_2500_v2 in 236.739s
rirv938-mistral-24b-rou-50061-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-rou-50061-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-rou-50061-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-rou-50061-v1
rirv938-mistral-24b-rou-50061-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-50061-v1/config.json
rirv938-mistral-24b-rou-50061-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-50061-v1/special_tokens_map.json
rirv938-mistral-24b-rou-50061-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-50061-v1/tokenizer_config.json
rirv938-mistral-24b-rou-50061-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-50061-v1/tokenizer.json
rirv938-mistral-24b-rou-50061-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-50061-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-rou-50061-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-50061-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-rou-50061-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 26.74it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 12.99it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 19.50it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:26, 13.11it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.66it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.24it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.60it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:25, 13.41it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.46it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:16, 20.61it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 14.12it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.15it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 14.04it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:28, 11.26it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:18, 16.71it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 19.88it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.18it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 13.21it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 13.92it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:27, 11.24it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 16.77it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 19.10it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:21, 13.41it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:22, 12.75it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:21, 13.48it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:25, 11.04it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.62it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.03it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:19, 14.04it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.39it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.70it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 18.62it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:18, 13.88it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.66it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.31it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 13.19it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.64it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.45it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 19.74it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.02it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.30it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.05it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:20, 11.21it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:14, 15.81it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.06it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:16, 13.73it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:16, 13.12it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:15, 14.00it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:18, 11.32it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 17.21it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.58it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.48it/s]
Loading 0:  45%|████▌     | 164/363 [00:11<00:13, 15.12it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:14, 13.39it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:15, 12.92it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 17.08it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.64it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:12, 14.42it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:13, 13.45it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 13.98it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:16, 10.80it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 16.52it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.12it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 14.06it/s]
Loading 0:  55%|█████▌    | 200/363 [00:13<00:11, 14.54it/s]
Loading 0:  56%|█████▌    | 202/363 [00:29<04:34,  1.71s/it]
Loading 0:  56%|█████▌    | 203/363 [00:29<04:02,  1.51s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<02:16,  1.14it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:34,  1.62it/s]
Loading 0:  59%|█████▊    | 213/363 [00:30<01:08,  2.18it/s]
Loading 0:  59%|█████▉    | 215/363 [00:30<00:56,  2.62it/s]
Loading 0:  60%|█████▉    | 217/363 [00:30<00:45,  3.20it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:35,  4.03it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:31,  4.49it/s]
Loading 0:  62%|██████▏   | 226/363 [00:31<00:17,  7.85it/s]
Loading 0:  63%|██████▎   | 230/363 [00:31<00:12, 10.73it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:13,  9.65it/s]
Loading 0:  65%|██████▍   | 235/363 [00:31<00:12,  9.87it/s]
Loading 0:  65%|██████▌   | 237/363 [00:31<00:11, 10.77it/s]
Loading 0:  66%|██████▌   | 239/363 [00:32<00:14,  8.79it/s]
Loading 0:  67%|██████▋   | 244/363 [00:32<00:08, 13.78it/s]
Loading 0:  68%|██████▊   | 248/363 [00:32<00:06, 17.38it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:08, 12.79it/s]
Loading 0:  70%|██████▉   | 253/363 [00:33<00:08, 12.23it/s]
Loading 0:  70%|███████   | 255/363 [00:33<00:08, 12.98it/s]
Loading 0:  71%|███████   | 257/363 [00:33<00:10, 10.38it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:06, 15.87it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:05, 19.21it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:06, 13.63it/s]
Loading 0:  75%|███████▍  | 271/363 [00:34<00:07, 12.80it/s]
Loading 0:  75%|███████▌  | 273/363 [00:34<00:06, 13.46it/s]
Loading 0:  76%|███████▌  | 275/363 [00:34<00:08, 10.61it/s]
Loading 0:  77%|███████▋  | 280/363 [00:34<00:05, 16.13it/s]
Loading 0:  78%|███████▊  | 284/363 [00:35<00:04, 19.14it/s]
Loading 0:  79%|███████▉  | 287/363 [00:35<00:05, 13.82it/s]
Loading 0:  80%|███████▉  | 289/363 [00:35<00:05, 12.90it/s]
Loading 0:  80%|████████  | 291/363 [00:35<00:05, 13.49it/s]
Loading 0:  81%|████████  | 293/363 [00:36<00:06, 11.00it/s]
Loading 0:  82%|████████▏ | 298/363 [00:36<00:03, 16.67it/s]
Loading 0:  83%|████████▎ | 302/363 [00:36<00:03, 20.14it/s]
Loading 0:  84%|████████▍ | 305/363 [00:36<00:04, 14.31it/s]
Loading 0:  85%|████████▍ | 307/363 [00:36<00:04, 13.30it/s]
Loading 0:  85%|████████▌ | 309/363 [00:37<00:04, 13.20it/s]
Loading 0:  86%|████████▌ | 311/363 [00:37<00:04, 10.69it/s]
Loading 0:  87%|████████▋ | 316/363 [00:37<00:02, 16.25it/s]
Loading 0:  88%|████████▊ | 320/363 [00:37<00:02, 19.89it/s]
Loading 0:  89%|████████▉ | 323/363 [00:37<00:02, 13.85it/s]
Loading 0:  90%|████████▉ | 325/363 [00:38<00:02, 12.99it/s]
Loading 0:  90%|█████████ | 327/363 [00:38<00:02, 13.55it/s]
Loading 0:  91%|█████████ | 329/363 [00:38<00:03, 10.98it/s]
Loading 0:  92%|█████████▏| 334/363 [00:38<00:01, 16.32it/s]
Loading 0:  93%|█████████▎| 338/363 [00:38<00:01, 19.31it/s]
Loading 0:  94%|█████████▍| 341/363 [00:39<00:01, 13.61it/s]
Loading 0:  94%|█████████▍| 343/363 [00:39<00:01, 12.75it/s]
Loading 0:  95%|█████████▌| 345/363 [00:39<00:01, 13.57it/s]
Loading 0:  96%|█████████▌| 347/363 [00:39<00:01, 10.96it/s]
Loading 0:  97%|█████████▋| 352/363 [00:39<00:00, 17.04it/s]
Loading 0:  98%|█████████▊| 356/363 [00:40<00:00, 21.20it/s]
Loading 0:  99%|█████████▉| 359/363 [00:47<00:02,  1.45it/s]
Loading 0:  99%|█████████▉| 361/363 [00:47<00:01,  1.73it/s]
                                                            
Job rirv938-mistral-24b-rou-50061-v1-mkmlizer completed after 277.35s with status: succeeded
Stopping job with name rirv938-mistral-24b-rou-50061-v1-mkmlizer
Pipeline stage MKMLizer completed in 277.85s
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-rou-50061-v1
Waiting for inference service rirv938-mistral-24b-rou-50061-v1 to be ready
Inference service rirv938-mistral-24b-rou-50061-v1 ready after 110.41830801963806s
Pipeline stage MKMLDeployer completed in 110.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9615073204040527s
Received healthy response to inference request in 2.452211856842041s
Received healthy response to inference request in 2.555858850479126s
Received healthy response to inference request in 2.4351279735565186s
Received healthy response to inference request in 2.4691336154937744s
5 requests
0 failed requests
5th percentile: 2.438544750213623
10th percentile: 2.4419615268707275
20th percentile: 2.4487950801849365
30th percentile: 2.4555962085723877
40th percentile: 2.462364912033081
50th percentile: 2.4691336154937744
60th percentile: 2.503823709487915
70th percentile: 2.5385138034820556
80th percentile: 2.6369885444641112
90th percentile: 2.799247932434082
95th percentile: 2.8803776264190675
99th percentile: 2.9452813816070558
mean time: 2.5747679233551026
Pipeline stage StressChecker completed in 14.17s
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 0.75s
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 0.82s
Shutdown handler de-registered
rirv938-mistral-24b-rou_50061_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-rou-50061-v1-profiler
Waiting for inference service rirv938-mistral-24b-rou-50061-v1-profiler to be ready
Inference service rirv938-mistral-24b-rou-50061-v1-profiler ready after 110.56395649909973s
Pipeline stage MKMLProfilerDeployer completed in 111.06s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-mistral-24b-d35a773b8597c3dfd86c8c579fef3fdd-deploxmnnc:/code/chaiverse_profiler_1741231027 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-mistral-24b-d35a773b8597c3dfd86c8c579fef3fdd-deploxmnnc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741231027 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 768 --output_tokens 64 --summary /code/chaiverse_profiler_1741231027/summary.json'
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 2633.13s
Shutdown handler de-registered
rirv938-mistral-24b-rou_50061_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-rou_50061_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message