developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_41361_v1
model_name: rirv938-mistral-24b-dpo_41361_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-02-23T06:20:47+00:00
num_battles: 7986
num_wins: 3888
celo_rating: 1267.14
family_friendly_score: 0.6134
family_friendly_standard_error: 0.006886805355170131
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_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': 0.3841892219265697, 'latency_mean': 2.6028169775009156, 'latency_p50': 2.619356155395508, 'latency_p90': 2.8701189517974854}, {'batch_size': 3, 'throughput': 0.7916569594345843, 'latency_mean': 3.7622154748439787, 'latency_p50': 3.7392178773880005, 'latency_p90': 4.152676224708557}, {'batch_size': 5, 'throughput': 1.0478032451067338, 'latency_mean': 4.755832750797271, 'latency_p50': 4.755202770233154, 'latency_p90': 5.3914727687835695}, {'batch_size': 6, 'throughput': 1.1172788969191596, 'latency_mean': 5.33796550154686, 'latency_p50': 5.388320565223694, 'latency_p90': 5.93157434463501}, {'batch_size': 10, 'throughput': 1.2742619209507329, 'latency_mean': 7.759947316646576, 'latency_p50': 7.81901216506958, 'latency_p90': 8.778864479064941}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_41361_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.78
us_pacific_date: 2025-02-22
win_ratio: 0.4868519909842224
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-41361-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-41361-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: Downloaded to shared memory in 203.072s
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw7itesws, device:0
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: quantized model in 67.229s
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_95w_pref_1250_instruct_v2 in 270.314s
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-41361-v1
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-41361-v1/config.json
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-41361-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-41361-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-41361-v1/tokenizer.json
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-41361-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-41361-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-41361-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:14, 24.35it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:28, 12.34it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 18.86it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:28, 12.17it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:34, 10.17it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:23, 14.58it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.35it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:25, 13.31it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.23it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:16, 20.37it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:24, 13.38it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 12.54it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:24, 13.30it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:30, 10.64it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 15.95it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:16, 18.89it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:24, 12.69it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:25, 12.08it/s]
Loading 0:  16%|█▌        | 57/363 [00:04<00:23, 12.93it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:28, 10.51it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:18, 15.86it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 19.07it/s]
Loading 0:  20%|█▉        | 71/363 [00:05<00:21, 13.54it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:22, 12.83it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:20, 13.75it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:25, 11.18it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.61it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:14, 19.58it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:20, 13.62it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:21, 12.92it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 16.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.50it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 17.80it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:19, 13.35it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.19it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:21, 11.80it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 12.66it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:24, 10.33it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:15, 15.74it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 18.73it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:18, 12.85it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:19, 12.21it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:17, 13.06it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:21, 10.71it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:14, 16.00it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.40it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:16, 13.68it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:16, 13.14it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:15, 13.94it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:18, 11.36it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 17.31it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.53it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:14, 14.25it/s]
Loading 0:  45%|████▌     | 164/363 [00:11<00:13, 14.62it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:15, 12.94it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:15, 12.22it/s]
Loading 0:  47%|████▋     | 172/363 [00:12<00:11, 16.03it/s]
Loading 0:  48%|████▊     | 176/363 [00:12<00:09, 19.29it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:13, 13.16it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:14, 12.55it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:13, 13.40it/s]
Loading 0:  51%|█████     | 185/363 [00:13<00:16, 10.51it/s]
Loading 0:  52%|█████▏    | 190/363 [00:13<00:10, 15.76it/s]
Loading 0:  53%|█████▎    | 194/363 [00:13<00:08, 18.79it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:12, 13.22it/s]
Loading 0:  55%|█████▍    | 199/363 [00:14<00:12, 12.63it/s]
Loading 0:  55%|█████▌    | 201/363 [00:29<04:51,  1.80s/it]
Loading 0:  56%|█████▌    | 202/363 [00:29<04:11,  1.56s/it]
Loading 0:  56%|█████▌    | 204/363 [00:29<03:01,  1.14s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<01:52,  1.38it/s]
Loading 0:  58%|█████▊    | 209/363 [00:29<01:23,  1.84it/s]
Loading 0:  58%|█████▊    | 212/363 [00:30<00:55,  2.71it/s]
Loading 0:  59%|█████▉    | 214/363 [00:30<00:46,  3.24it/s]
Loading 0:  60%|█████▉    | 216/363 [00:30<00:38,  3.79it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:26,  5.52it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:24,  5.89it/s]
Loading 0:  62%|██████▏   | 226/363 [00:31<00:13,  9.94it/s]
Loading 0:  63%|██████▎   | 230/363 [00:31<00:10, 13.06it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:11, 11.19it/s]
Loading 0:  65%|██████▍   | 235/363 [00:31<00:11, 11.07it/s]
Loading 0:  65%|██████▌   | 237/363 [00:31<00:10, 12.04it/s]
Loading 0:  66%|██████▌   | 239/363 [00:32<00:12, 10.16it/s]
Loading 0:  67%|██████▋   | 244/363 [00:32<00:07, 15.40it/s]
Loading 0:  68%|██████▊   | 248/363 [00:32<00:06, 18.37it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:08, 12.83it/s]
Loading 0:  70%|██████▉   | 253/363 [00:33<00:08, 12.34it/s]
Loading 0:  70%|███████   | 255/363 [00:33<00:08, 13.01it/s]
Loading 0:  71%|███████   | 257/363 [00:33<00:09, 10.66it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:06, 15.87it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:05, 18.88it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:07, 13.29it/s]
Loading 0:  75%|███████▍  | 271/363 [00:34<00:07, 12.54it/s]
Loading 0:  75%|███████▌  | 273/363 [00:34<00:06, 13.18it/s]
Loading 0:  76%|███████▌  | 275/363 [00:34<00:08, 10.64it/s]
Loading 0:  77%|███████▋  | 280/363 [00:34<00:05, 15.76it/s]
Loading 0:  78%|███████▊  | 284/363 [00:35<00:04, 18.69it/s]
Loading 0:  79%|███████▉  | 287/363 [00:35<00:05, 13.36it/s]
Loading 0:  80%|███████▉  | 289/363 [00:35<00:05, 12.75it/s]
Loading 0:  80%|████████  | 291/363 [00:35<00:05, 13.41it/s]
Loading 0:  81%|████████  | 293/363 [00:36<00:06, 10.75it/s]
Loading 0:  82%|████████▏ | 298/363 [00:36<00:04, 15.97it/s]
Loading 0:  83%|████████▎ | 302/363 [00:36<00:03, 18.97it/s]
Loading 0:  84%|████████▍ | 305/363 [00:36<00:04, 13.44it/s]
Loading 0:  85%|████████▍ | 307/363 [00:36<00:04, 12.56it/s]
Loading 0:  85%|████████▌ | 309/363 [00:37<00:04, 13.36it/s]
Loading 0:  86%|████████▌ | 311/363 [00:37<00:04, 11.30it/s]
Loading 0:  87%|████████▋ | 317/363 [00:37<00:02, 18.99it/s]
Loading 0:  88%|████████▊ | 321/363 [00:37<00:02, 18.35it/s]
Loading 0:  89%|████████▉ | 324/363 [00:38<00:02, 13.90it/s]
Loading 0:  90%|█████████ | 327/363 [00:38<00:02, 16.05it/s]
Loading 0:  91%|█████████ | 330/363 [00:38<00:02, 14.52it/s]
Loading 0:  92%|█████████▏| 334/363 [00:38<00:01, 18.15it/s]
Loading 0:  93%|█████████▎| 338/363 [00:38<00:01, 21.01it/s]
Loading 0:  94%|█████████▍| 341/363 [00:39<00:01, 14.66it/s]
Loading 0:  95%|█████████▍| 344/363 [00:39<00:01, 15.29it/s]
Loading 0:  95%|█████████▌| 346/363 [00:39<00:01, 13.55it/s]
Loading 0:  96%|█████████▌| 348/363 [00:39<00:01, 12.94it/s]
Loading 0:  97%|█████████▋| 352/363 [00:39<00:00, 16.92it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 20.40it/s]
Loading 0:  99%|█████████▉| 359/363 [00:47<00:02,  1.43it/s]
Loading 0:  99%|█████████▉| 361/363 [00:47<00:01,  1.73it/s]
                                                            

Job rirv938-mistral-24b-dpo-41361-v1-mkmlizer completed after 329.23s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-41361-v1-mkmlizer
Pipeline stage MKMLizer completed in 329.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-41361-v1
Waiting for inference service rirv938-mistral-24b-dpo-41361-v1 to be ready
Inference service rirv938-mistral-24b-dpo-41361-v1 ready after 230.77210116386414s
Pipeline stage MKMLDeployer completed in 231.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.330868721008301s
Received healthy response to inference request in 2.143411636352539s
Received healthy response to inference request in 2.212008237838745s
Received healthy response to inference request in 2.403440475463867s
Received healthy response to inference request in 1.8330528736114502s
5 requests
0 failed requests
5th percentile: 1.895124626159668
10th percentile: 1.9571963787078857
20th percentile: 2.081339883804321
30th percentile: 2.1571309566497803
40th percentile: 2.1845695972442627
50th percentile: 2.212008237838745
60th percentile: 2.2595524311065676
70th percentile: 2.3070966243743896
80th percentile: 2.345383071899414
90th percentile: 2.374411773681641
95th percentile: 2.388926124572754
99th percentile: 2.4005376052856446
mean time: 2.1845563888549804
Pipeline stage StressChecker completed in 12.21s
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 0.63s
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 0.65s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_41361_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-dpo-41361-v1-profiler
Waiting for inference service rirv938-mistral-24b-dpo-41361-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 4915.86s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_41361_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_41361_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1