developer_uid: NischayDnk
submission_id: chaiml-mistral31-exp1-d_76128_v1
model_name: chaiml-mistral31-exp1-d_76128_v1
model_group: ChaiML/mistral31_exp1_dp
status: torndown
timestamp: 2025-04-11T22:40:18+00:00
num_battles: 8118
num_wins: 4509
celo_rating: 1320.01
family_friendly_score: 0.5036
family_friendly_standard_error: 0.0070708845274123945
submission_type: basic
model_repo: ChaiML/mistral31_exp1_dpo3e_simpo_mergeties_stage1_v1
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': 0.3651422343758414, 'latency_mean': 2.7385942792892455, 'latency_p50': 2.760228753089905, 'latency_p90': 3.0099798440933228}, {'batch_size': 2, 'throughput': 0.5646464148192544, 'latency_mean': 3.5298458635807037, 'latency_p50': 3.56181538105011, 'latency_p90': 3.897547388076782}, {'batch_size': 3, 'throughput': 0.713084968590123, 'latency_mean': 4.185815047025681, 'latency_p50': 4.175535082817078, 'latency_p90': 4.554739570617675}, {'batch_size': 4, 'throughput': 0.8346414545821216, 'latency_mean': 4.7799269437789915, 'latency_p50': 4.765438795089722, 'latency_p90': 5.376242232322693}, {'batch_size': 5, 'throughput': 0.9104563960331117, 'latency_mean': 5.459685783386231, 'latency_p50': 5.518842458724976, 'latency_p90': 6.048120212554932}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-mistral31-exp1-d_76128_v1
is_internal_developer: False
language_model: ChaiML/mistral31_exp1_dpo3e_simpo_mergeties_stage1_v1
model_size: 24B
ranking_group: single
throughput_3p7s: 0.61
us_pacific_date: 2025-04-11
win_ratio: 0.5554323725055432
generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 chaiml-mistral31-exp1-d-76128-v1-mkmlizer
Waiting for job on chaiml-mistral31-exp1-d-76128-v1-mkmlizer to finish
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ _____ __ __ ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ /___/ ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ belonging to: ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ║ ║
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: Downloaded to shared memory in 78.387s
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr_3o6i9e, device:0
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: quantized model in 52.796s
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: Processed model ChaiML/mistral31_exp1_dpo3e_simpo_mergeties_stage1_v1 in 131.184s
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-exp1-d-76128-v1
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-exp1-d-76128-v1/config.json
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-exp1-d-76128-v1/special_tokens_map.json
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-exp1-d-76128-v1/tokenizer_config.json
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-exp1-d-76128-v1/tokenizer.json
Failed to get response for submission jellywibble-tyler-james_92283_v1: HTTPConnectionPool(host='jellywibble-tyler-james-92283-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-exp1-d-76128-v1/flywheel_model.1.safetensors
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-exp1-d-76128-v1/flywheel_model.0.safetensors
chaiml-mistral31-exp1-d-76128-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:53, 3.14s/it] Loading 0: 1%|▏ | 5/363 [00:06<06:06, 1.02s/it] Loading 0: 2%|▏ | 7/363 [00:06<03:51, 1.54it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:30, 3.89it/s] Loading 0: 4%|▍ | 16/363 [00:06<01:06, 5.18it/s] Loading 0: 6%|▌ | 22/363 [00:07<00:42, 7.96it/s] Loading 0: 7%|▋ | 25/363 [00:07<00:36, 9.26it/s] Loading 0: 9%|▊ | 31/363 [00:07<00:24, 13.82it/s] Loading 0: 9%|▉ | 34/363 [00:07<00:22, 14.93it/s] Loading 0: 11%|█ | 40/363 [00:07<00:15, 20.23it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:15, 20.97it/s] Loading 0: 13%|█▎ | 49/363 [00:08<00:12, 25.01it/s] Loading 0: 15%|█▍ | 53/363 [00:08<00:12, 24.40it/s] Loading 0: 16%|█▌ | 58/363 [00:08<00:10, 27.86it/s] Loading 0: 17%|█▋ | 62/363 [00:08<00:14, 20.39it/s] Loading 0: 18%|█▊ | 67/363 [00:08<00:12, 24.30it/s] Loading 0: 20%|█▉ | 71/363 [00:08<00:12, 23.97it/s] Loading 0: 21%|██ | 76/363 [00:09<00:10, 27.47it/s] Loading 0: 22%|██▏ | 80/363 [00:09<00:10, 26.67it/s] Loading 0: 23%|██▎ | 85/363 [00:09<00:09, 29.81it/s] Loading 0: 25%|██▍ | 89/363 [00:09<00:09, 28.78it/s] Loading 0: 26%|██▌ | 94/363 [00:09<00:08, 31.50it/s] Loading 0: 27%|██▋ | 98/363 [00:09<00:12, 21.72it/s] Loading 0: 28%|██▊ | 103/363 [00:10<00:10, 25.56it/s] Loading 0: 29%|██▉ | 107/363 [00:10<00:09, 25.78it/s] Loading 0: 31%|███ | 112/363 [00:10<00:08, 29.08it/s] Loading 0: 32%|███▏ | 116/363 [00:10<00:08, 28.15it/s] Loading 0: 33%|███▎ | 121/363 [00:10<00:07, 31.41it/s] Loading 0: 34%|███▍ | 125/363 [00:10<00:07, 30.00it/s] Loading 0: 36%|███▌ | 130/363 [00:10<00:07, 32.48it/s] Loading 0: 37%|███▋ | 134/363 [00:11<00:07, 30.52it/s] Loading 0: 38%|███▊ | 139/363 [00:11<00:09, 24.65it/s] Loading 0: 39%|███▉ | 142/363 [00:11<00:09, 23.00it/s] Loading 0: 41%|████ | 148/363 [00:11<00:07, 28.27it/s] Loading 0: 42%|████▏ | 152/363 [00:11<00:07, 27.64it/s] Loading 0: 43%|████▎ | 157/363 [00:11<00:06, 30.51it/s] Loading 0: 44%|████▍ | 161/363 [00:12<00:06, 29.34it/s] Loading 0: 46%|████▌ | 166/363 [00:12<00:06, 32.48it/s] Loading 0: 47%|████▋ | 170/363 [00:12<00:06, 30.64it/s] Loading 0: 48%|████▊ | 175/363 [00:12<00:05, 32.88it/s] Loading 0: 49%|████▉ | 179/363 [00:12<00:08, 22.62it/s] Loading 0: 51%|█████ | 184/363 [00:12<00:06, 26.18it/s] Loading 0: 52%|█████▏ | 188/363 [00:27<02:55, 1.00s/it] Loading 0: 53%|█████▎ | 191/363 [00:27<02:15, 1.27it/s] Loading 0: 53%|█████▎ | 194/363 [00:27<01:42, 1.65it/s] Loading 0: 54%|█████▍ | 197/363 [00:27<01:16, 2.17it/s] Loading 0: 56%|█████▌ | 202/363 [00:27<00:47, 3.40it/s] Loading 0: 57%|█████▋ | 206/363 [00:27<00:33, 4.63it/s] Loading 0: 58%|█████▊ | 211/363 [00:28<00:22, 6.73it/s] Loading 0: 59%|█████▉ | 215/363 [00:28<00:19, 7.76it/s] Loading 0: 61%|██████ | 220/363 [00:28<00:13, 10.57it/s] Loading 0: 61%|██████▏ | 223/363 [00:28<00:11, 11.72it/s] Loading 0: 63%|██████▎ | 229/363 [00:28<00:08, 16.48it/s] Loading 0: 64%|██████▍ | 233/363 [00:28<00:07, 18.41it/s] Loading 0: 66%|██████▌ | 238/363 [00:29<00:05, 22.48it/s] Loading 0: 67%|██████▋ | 242/363 [00:29<00:05, 23.36it/s] Loading 0: 68%|██████▊ | 247/363 [00:29<00:04, 27.23it/s] Loading 0: 69%|██████▉ | 251/363 [00:29<00:04, 27.07it/s] Loading 0: 71%|███████ | 256/363 [00:29<00:04, 23.18it/s] Loading 0: 71%|███████▏ | 259/363 [00:29<00:04, 21.96it/s] Loading 0: 73%|███████▎ | 265/363 [00:30<00:03, 27.67it/s] Loading 0: 74%|███████▍ | 269/363 [00:30<00:03, 27.42it/s] Loading 0: 75%|███████▌ | 274/363 [00:30<00:02, 30.35it/s] Loading 0: 77%|███████▋ | 278/363 [00:30<00:02, 29.36it/s] Loading 0: 78%|███████▊ | 283/363 [00:30<00:02, 32.40it/s] Loading 0: 79%|███████▉ | 287/363 [00:30<00:02, 30.53it/s] Loading 0: 80%|████████ | 292/363 [00:30<00:02, 32.91it/s] Loading 0: 82%|████████▏ | 296/363 [00:31<00:02, 22.86it/s] Loading 0: 83%|████████▎ | 301/363 [00:31<00:02, 26.35it/s] Loading 0: 84%|████████▍ | 305/363 [00:31<00:02, 26.45it/s] Loading 0: 85%|████████▌ | 310/363 [00:31<00:01, 30.00it/s] Loading 0: 87%|████████▋ | 314/363 [00:31<00:01, 28.53it/s] Loading 0: 88%|████████▊ | 319/363 [00:31<00:01, 30.71it/s] Loading 0: 89%|████████▉ | 323/363 [00:32<00:01, 29.07it/s] Loading 0: 90%|█████████ | 328/363 [00:32<00:01, 32.19it/s] Loading 0: 91%|█████████▏| 332/363 [00:32<00:01, 21.87it/s] Loading 0: 93%|█████████▎| 337/363 [00:32<00:01, 25.69it/s] Loading 0: 94%|█████████▍| 341/363 [00:32<00:00, 25.90it/s] Loading 0: 95%|█████████▌| 346/363 [00:32<00:00, 28.68it/s] Loading 0: 96%|█████████▋| 350/363 [00:33<00:00, 28.02it/s] Loading 0: 98%|█████████▊| 355/363 [00:33<00:00, 31.28it/s] Loading 0: 99%|█████████▉| 359/363 [00:33<00:00, 29.73it/s]
Job chaiml-mistral31-exp1-d-76128-v1-mkmlizer completed after 166.94s with status: succeeded
Stopping job with name chaiml-mistral31-exp1-d-76128-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral31-exp1-d-76128-v1
Waiting for inference service chaiml-mistral31-exp1-d-76128-v1 to be ready
Inference service chaiml-mistral31-exp1-d-76128-v1 ready after 110.44513368606567s
Pipeline stage MKMLDeployer completed in 111.00s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.9980766773223877s
Received healthy response to inference request in 2.5435690879821777s
Received healthy response to inference request in 2.562772512435913s
Received healthy response to inference request in 2.522165298461914s
5 requests
1 failed requests
5th percentile: 2.526446056365967
10th percentile: 2.5307268142700194
20th percentile: 2.539288330078125
30th percentile: 2.547409772872925
40th percentile: 2.555091142654419
50th percentile: 2.562772512435913
60th percentile: 2.7368941783905028
70th percentile: 2.911015844345093
80th percentile: 6.426303625106815
90th percentile: 13.282757520675661
95th percentile: 16.71098446846008
99th percentile: 19.45356602668762
mean time: 6.1531589984893795
%s, retrying in %s seconds...
Received healthy response to inference request in 2.6387441158294678s
Received healthy response to inference request in 2.4546048641204834s
Received healthy response to inference request in 2.642180919647217s
Received healthy response to inference request in 2.5504090785980225s
Received healthy response to inference request in 2.4312283992767334s
5 requests
0 failed requests
5th percentile: 2.4359036922454833
10th percentile: 2.440578985214233
20th percentile: 2.4499295711517335
30th percentile: 2.4737657070159913
40th percentile: 2.5120873928070067
50th percentile: 2.5504090785980225
60th percentile: 2.5857430934906005
70th percentile: 2.6210771083831785
80th percentile: 2.6394314765930176
90th percentile: 2.640806198120117
95th percentile: 2.641493558883667
99th percentile: 2.642043447494507
mean time: 2.5434334754943846
Pipeline stage StressChecker completed in 46.51s
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 0.73s
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 0.71s
Shutdown handler de-registered
chaiml-mistral31-exp1-d_76128_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 4843.23s
Shutdown handler de-registered
chaiml-mistral31-exp1-d_76128_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-exp1-d_76128_v1 status is now torndown due to DeploymentManager action