developer_uid: NischayDnk
submission_id: chaiml-mistral24b-dpoex_42812_v1
model_name: chaiml-mistral24b-dpoex_42812_v1
model_group: ChaiML/mistral24b-dpoexp
status: torndown
timestamp: 2025-04-09T04:43:54+00:00
num_battles: 8225
num_wins: 3995
celo_rating: 1272.39
family_friendly_score: 0.5448
family_friendly_standard_error: 0.007042626782671363
submission_type: basic
model_repo: ChaiML/mistral24b-dpoexp3-sftdel12kexp4-oldformat
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.37002558695424786, 'latency_mean': 2.702446517944336, 'latency_p50': 2.6908910274505615, 'latency_p90': 3.0045374393463136}, {'batch_size': 2, 'throughput': 0.578633725399098, 'latency_mean': 3.453759270906448, 'latency_p50': 3.4250065088272095, 'latency_p90': 3.8015101194381713}, {'batch_size': 3, 'throughput': 0.7279600551622171, 'latency_mean': 4.113541110754013, 'latency_p50': 4.107159376144409, 'latency_p90': 4.532622647285462}, {'batch_size': 4, 'throughput': 0.8441174774378157, 'latency_mean': 4.715980442762375, 'latency_p50': 4.6794737577438354, 'latency_p90': 5.257158327102661}, {'batch_size': 5, 'throughput': 0.931226112057049, 'latency_mean': 5.3356174492836, 'latency_p50': 5.335668206214905, 'latency_p90': 5.978008794784546}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-mistral24b-dpoex_42812_v1
is_internal_developer: False
language_model: ChaiML/mistral24b-dpoexp3-sftdel12kexp4-oldformat
model_size: 24B
ranking_group: single
throughput_3p7s: 0.64
us_pacific_date: 2025-04-08
win_ratio: 0.4857142857142857
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '\n', 'You:', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '[/INST]{bot_name}:', 'truncate_by_message': True}
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 chaiml-mistral24b-dpoex-42812-v1-mkmlizer
Waiting for job on chaiml-mistral24b-dpoex-42812-v1-mkmlizer to finish
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║                                                                     ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║                                                                     ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║                                                                     ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ║                                                                     ║
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: Downloaded to shared memory in 76.928s
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp07k5ixbz, device:0
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: quantized model in 53.457s
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: Processed model ChaiML/mistral24b-dpoexp3-sftdel12kexp4-oldformat in 130.386s
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral24b-dpoex-42812-v1
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral24b-dpoex-42812-v1/config.json
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral24b-dpoex-42812-v1/special_tokens_map.json
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral24b-dpoex-42812-v1/tokenizer_config.json
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral24b-dpoex-42812-v1/tokenizer.json
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral24b-dpoex-42812-v1/flywheel_model.1.safetensors
chaiml-mistral24b-dpoex-42812-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.46it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.44it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.07it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 26.84it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.67it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.82it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 34.58it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 20.43it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.96it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.84it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.51it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.74it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 30.05it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.93it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.56it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.89it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.21it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.66it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.93it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.90it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 28.14it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.23it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.35it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.60it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.68it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.62it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.32it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 26.93it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.86it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.70it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.02it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.71it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.42it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:09, 23.21it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:09, 22.89it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:09, 21.80it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.48it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.98it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.41it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.00it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.64it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.35it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.61it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.45it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.53it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.53it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.91it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.17it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.34it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.39it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.38it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.12it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.07it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.02it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.50it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.04it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.57it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.60it/s]
Loading 0:  72%|███████▏  | 263/363 [00:24<00:03, 28.42it/s]
Loading 0:  74%|███████▎  | 267/363 [00:24<00:04, 23.66it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 20.12it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.21it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.45it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 27.02it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.75it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 30.22it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.39it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.79it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.22it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.06it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.64it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.11it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.59it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.94it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 29.26it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.54it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 27.24it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.66it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:05,  2.77it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.48it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.16it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.70it/s]
                                                            

Job chaiml-mistral24b-dpoex-42812-v1-mkmlizer completed after 166.14s with status: succeeded
Stopping job with name chaiml-mistral24b-dpoex-42812-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.64s
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 chaiml-mistral24b-dpoex-42812-v1
Waiting for inference service chaiml-mistral24b-dpoex-42812-v1 to be ready
Inference service chaiml-mistral24b-dpoex-42812-v1 ready after 110.51071262359619s
Pipeline stage MKMLDeployer completed in 111.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.41403865814209s
Received healthy response to inference request in 2.4577014446258545s
Received healthy response to inference request in 2.1662089824676514s
Received healthy response to inference request in 2.211092948913574s
Received healthy response to inference request in 2.5859642028808594s
5 requests
0 failed requests
5th percentile: 2.175185775756836
10th percentile: 2.1841625690460207
20th percentile: 2.2021161556243896
30th percentile: 2.26041464805603
40th percentile: 2.3590580463409423
50th percentile: 2.4577014446258545
60th percentile: 2.5090065479278563
70th percentile: 2.5603116512298585
80th percentile: 2.7515790939331057
90th percentile: 3.0828088760375976
95th percentile: 3.2484237670898435
99th percentile: 3.3809156799316407
mean time: 2.5670012474060058
Pipeline stage StressChecker completed in 14.40s
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 0.71s
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 0.67s
Shutdown handler de-registered
chaiml-mistral24b-dpoex_42812_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5355.23s
Shutdown handler de-registered
chaiml-mistral24b-dpoex_42812_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral24b-dpoex_42812_v1 status is now torndown due to DeploymentManager action