developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_39021_v1
model_name: rirv938-mistral-24b-dpo_39021_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-03-25T18:22:05+00:00
num_battles: 7552
num_wins: 3876
celo_rating: 1288.05
family_friendly_score: 0.47740000000000005
family_friendly_standard_error: 0.007063840881560117
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_kl_10k_beta2_936_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': 0.3895319912113613, 'latency_mean': 2.567095800638199, 'latency_p50': 2.564176082611084, 'latency_p90': 2.8545956373214723}, {'batch_size': 3, 'throughput': 0.7978022335534813, 'latency_mean': 3.7431054735183715, 'latency_p50': 3.784648895263672, 'latency_p90': 4.12861065864563}, {'batch_size': 5, 'throughput': 1.0535338221799622, 'latency_mean': 4.719520328044891, 'latency_p50': 4.695702433586121, 'latency_p90': 5.293870282173157}, {'batch_size': 6, 'throughput': 1.1442811446465568, 'latency_mean': 5.213332259654999, 'latency_p50': 5.230786442756653, 'latency_p90': 5.83596134185791}, {'batch_size': 10, 'throughput': 1.311574423108599, 'latency_mean': 7.551805933713913, 'latency_p50': 7.617508172988892, 'latency_p90': 8.42671821117401}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_39021_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_kl_10k_beta2_936_v3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.79
us_pacific_date: 2025-03-25
win_ratio: 0.5132415254237288
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-39021-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-39021-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: Downloaded to shared memory in 194.006s
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1aizl70f, device:0
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: quantized model in 66.226s
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_kl_10k_beta2_936_v3 in 260.233s
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-39021-v1
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-39021-v1/config.json
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-39021-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-39021-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-39021-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-39021-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-39021-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.22it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.35it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.06it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:26, 13.12it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.87it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.51it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.68it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.75it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.94it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.64it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.60it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.22it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:24, 13.24it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:25, 12.68it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 16.77it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.47it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.34it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.77it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.54it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:26, 11.65it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.61it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.10it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.00it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.37it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:21, 13.47it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:22, 12.85it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.06it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.79it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.49it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:19, 13.76it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.54it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.10it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.71it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 13.92it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 12.92it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.46it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 13.21it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 10.90it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.85it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.53it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.40it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.62it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.30it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.57it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.58it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.15it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.53it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.00it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:16, 12.91it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 12.63it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.90it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.76it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 13.83it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:15, 13.07it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:14, 13.75it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:18, 10.83it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.57it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 19.93it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:13, 13.68it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:14, 12.88it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:13, 13.54it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:16, 11.06it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 16.80it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.06it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 14.19it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.21it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:45,  1.76s/it]
Loading 0:  56%|█████▌    | 202/363 [00:28<04:06,  1.53s/it]
Loading 0:  56%|█████▌    | 204/363 [00:28<02:59,  1.13s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<01:51,  1.40it/s]
Loading 0:  58%|█████▊    | 209/363 [00:28<01:23,  1.85it/s]
Loading 0:  58%|█████▊    | 212/363 [00:28<00:54,  2.76it/s]
Loading 0:  59%|█████▉    | 214/363 [00:29<00:45,  3.27it/s]
Loading 0:  60%|█████▉    | 216/363 [00:29<00:38,  3.81it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:26,  5.53it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:25,  5.68it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:14,  9.63it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:10, 12.85it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.83it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:11, 10.80it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:10, 11.64it/s]
Loading 0:  66%|██████▌   | 239/363 [00:31<00:12,  9.94it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:07, 15.29it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 18.77it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.21it/s]
Loading 0:  70%|██████▉   | 253/363 [00:32<00:08, 12.34it/s]
Loading 0:  70%|███████   | 255/363 [00:32<00:08, 12.87it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:10, 10.44it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:06, 15.94it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:05, 19.13it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:07, 13.30it/s]
Loading 0:  75%|███████▍  | 271/363 [00:33<00:07, 12.84it/s]
Loading 0:  75%|███████▌  | 273/363 [00:33<00:06, 13.52it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:08, 10.97it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 16.70it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 19.96it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 13.52it/s]
Loading 0:  80%|███████▉  | 289/363 [00:34<00:05, 12.45it/s]
Loading 0:  80%|████████  | 291/363 [00:34<00:05, 13.22it/s]
Loading 0:  81%|████████  | 293/363 [00:35<00:06, 10.92it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 16.63it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:03, 19.92it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:04, 13.22it/s]
Loading 0:  85%|████████▍ | 307/363 [00:35<00:04, 12.83it/s]
Loading 0:  85%|████████▌ | 309/363 [00:36<00:03, 13.64it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:04, 10.79it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 16.68it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 20.45it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 14.46it/s]
Loading 0:  90%|████████▉ | 326/363 [00:37<00:02, 15.18it/s]
Loading 0:  91%|█████████ | 329/363 [00:37<00:02, 11.67it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 16.57it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 19.85it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 14.46it/s]
Loading 0:  95%|█████████▍| 344/363 [00:38<00:01, 15.14it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 12.09it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 16.89it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 20.23it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.58it/s]
Loading 0:  99%|█████████▉| 361/363 [00:46<00:01,  1.86it/s]
                                                            

Job rirv938-mistral-24b-dpo-39021-v1-mkmlizer completed after 298.33s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-39021-v1-mkmlizer
Pipeline stage MKMLizer completed in 298.81s
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-39021-v1
Waiting for inference service rirv938-mistral-24b-dpo-39021-v1 to be ready
Failed to get response for submission nitral-ai-captain-eris_45741_v27: HTTPConnectionPool(host='nitral-ai-captain-eris-45741-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-mistral-24b-dpo-39021-v1 ready after 100.34444761276245s
Pipeline stage MKMLDeployer completed in 100.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1951780319213867s
Received healthy response to inference request in 2.666800022125244s
Received healthy response to inference request in 2.6797728538513184s
Received healthy response to inference request in 2.780022621154785s
Received healthy response to inference request in 2.6162302494049072s
5 requests
0 failed requests
5th percentile: 2.6263442039489746
10th percentile: 2.636458158493042
20th percentile: 2.6566860675811768
30th percentile: 2.669394588470459
40th percentile: 2.6745837211608885
50th percentile: 2.6797728538513184
60th percentile: 2.719872760772705
70th percentile: 2.759972667694092
80th percentile: 2.8630537033081054
90th percentile: 3.0291158676147463
95th percentile: 3.1121469497680665
99th percentile: 3.1785718154907228
mean time: 2.7876007556915283
Pipeline stage StressChecker completed in 15.33s
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 0.67s
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-dpo_39021_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-dpo-39021-v1-profiler
Waiting for inference service rirv938-mistral-24b-dpo-39021-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 2889.52s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_39021_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_39021_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1