chaiml-mistral32-sft-to_61184

developer_uid: NischayDnk

submission_id: chaiml-mistral32-sft-to_61184_v1

model_name: chaiml-mistral32-sft-to_61184_v1

model_group: ChaiML/mistral32-sft-top

status: torndown

timestamp: 2025-07-06T20:56:40+00:00

num_battles: 6404

num_wins: 3309

celo_rating: 1298.25

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/mistral32-sft-top10klex-cpos1-try1-lorav2-2e-deepseeksftv3

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': 0.5243079502451993, 'latency_mean': 1.9071776342391968, 'latency_p50': 1.9122189283370972, 'latency_p90': 2.1104583501815797}, {'batch_size': 3, 'throughput': 1.0567322664745733, 'latency_mean': 2.8335390651226042, 'latency_p50': 2.8323402404785156, 'latency_p90': 3.108728456497192}, {'batch_size': 5, 'throughput': 1.3459851516764136, 'latency_mean': 3.6989564549922944, 'latency_p50': 3.703885316848755, 'latency_p90': 4.147581744194031}, {'batch_size': 6, 'throughput': 1.4441826925827344, 'latency_mean': 4.134983135461807, 'latency_p50': 4.156850337982178, 'latency_p90': 4.614638352394104}, {'batch_size': 8, 'throughput': 1.5721287576310163, 'latency_mean': 5.05503970503807, 'latency_p50': 5.097672462463379, 'latency_p90': 5.647074246406555}, {'batch_size': 10, 'throughput': 1.6500698353044376, 'latency_mean': 5.980159720182419, 'latency_p50': 5.95585310459137, 'latency_p90': 6.793205094337464}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-mistral32-sft-to_61184_v1

is_internal_developer: False

language_model: ChaiML/mistral32-sft-top10klex-cpos1-try1-lorav2-2e-deepseeksftv3

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-07-06

win_ratio: 0.5167083073079325

generation_params: {'temperature': 0.55, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], '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': 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-mistral32-sft-to-61184-v1-mkmlizer
Waiting for job on chaiml-mistral32-sft-to-61184-v1-mkmlizer to finish
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ║                                                                     ║
chaiml-mistral32-sft-to-61184-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-20250611-retune-_50947_v5: HTTPConnectionPool(host='chaiml-20250611-retune-50947-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-mistral32-sft-to-61184-v1-mkmlizer: Downloaded to shared memory in 84.784s
chaiml-mistral32-sft-to-61184-v1-mkmlizer: Checking if ChaiML/mistral32-sft-top10klex-cpos1-try1-lorav2-2e-deepseeksftv3 already exists in ChaiML
chaiml-mistral32-sft-to-61184-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg05bgqln, device:0
chaiml-mistral32-sft-to-61184-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral32-sft-to-61184-v1-mkmlizer: quantized model in 47.753s
chaiml-mistral32-sft-to-61184-v1-mkmlizer: Processed model ChaiML/mistral32-sft-top10klex-cpos1-try1-lorav2-2e-deepseeksftv3 in 132.537s
chaiml-mistral32-sft-to-61184-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral32-sft-to-61184-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral32-sft-to-61184-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral32-sft-to-61184-v1/nvidia
chaiml-mistral32-sft-to-61184-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-to-61184-v1/nvidia/config.json
chaiml-mistral32-sft-to-61184-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral32-sft-to-61184-v1/nvidia/special_tokens_map.json
chaiml-mistral32-sft-to-61184-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral32-sft-to-61184-v1/nvidia/tokenizer_config.json
chaiml-mistral32-sft-to-61184-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral32-sft-to-61184-v1/nvidia/tokenizer.json
chaiml-mistral32-sft-to-61184-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-to-61184-v1/nvidia/flywheel_model.0.safetensors
chaiml-mistral32-sft-to-61184-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral32-sft-to-61184-v1/nvidia/flywheel_model.1.safetensors
chaiml-mistral32-sft-to-61184-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.82it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.12it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.65it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.87it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.98it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.21it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.52it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.35it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.21it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.04it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.20it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.12it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.04it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.80it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.71it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.02it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.10it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.34it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.73it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.87it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.53it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 27.21it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.52it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:09, 27.94it/s]
Loading 0:  30%|███       | 110/363 [00:04<00:10, 23.73it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:12, 20.66it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.46it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 26.42it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.70it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.40it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.20it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 27.84it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.09it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 22.64it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 21.14it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.33it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.99it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 23.85it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:07, 25.08it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 24.65it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 27.49it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 24.70it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 28.18it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:05, 30.06it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.07it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.25it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.74it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:07, 22.74it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:58,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:27,  1.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:28,  1.75it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.22it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.92it/s]
Loading 0:  60%|█████▉    | 217/363 [00:22<00:37,  3.88it/s]
Loading 0:  61%|██████    | 220/363 [00:22<00:28,  4.96it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.56it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.52it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.26it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.09it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.87it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.87it/s]
Loading 0:  69%|██████▊   | 249/363 [00:23<00:05, 20.34it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.38it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.56it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 28.88it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 21.91it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 21.02it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 22.49it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.25it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.96it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.97it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.87it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.16it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.69it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.14it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.99it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.20it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.66it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.07it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.43it/s]
Loading 0:  90%|████████▉ | 326/363 [00:26<00:01, 30.10it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 24.94it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 27.20it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 25.66it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.40it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 20.80it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.52it/s]
Loading 0:  97%|█████████▋| 353/363 [00:28<00:00, 22.69it/s]
Loading 0:  98%|█████████▊| 357/363 [00:28<00:00, 21.46it/s]
                                                            
Job chaiml-mistral32-sft-to-61184-v1-mkmlizer completed after 166.53s with status: succeeded
Stopping job with name chaiml-mistral32-sft-to-61184-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.03s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral32-sft-to-61184-v1
Waiting for inference service chaiml-mistral32-sft-to-61184-v1 to be ready
Inference service chaiml-mistral32-sft-to-61184-v1 ready after 212.1157250404358s
Pipeline stage MKMLDeployer completed in 212.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.13073468208313s
Received healthy response to inference request in 2.0150232315063477s
Received healthy response to inference request in 2.2974278926849365s
Received healthy response to inference request in 2.194396495819092s
Received healthy response to inference request in 2.324937105178833s
5 requests
0 failed requests
5th percentile: 2.0508978843688963
10th percentile: 2.0867725372314454
20th percentile: 2.158521842956543
30th percentile: 2.2150027751922607
40th percentile: 2.2562153339385986
50th percentile: 2.2974278926849365
60th percentile: 2.3084315776824953
70th percentile: 2.3194352626800536
80th percentile: 2.4860966205596924
90th percentile: 2.808415651321411
95th percentile: 2.9695751667022705
99th percentile: 3.098502779006958
mean time: 2.3925038814544677
Pipeline stage StressChecker completed in 13.62s
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 0.74s
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 0.69s
Shutdown handler de-registered
chaiml-mistral32-sft-to_61184_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
chaiml-mistral32-sft-to_61184_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral32-sft-to_61184_v1 status is now torndown due to DeploymentManager action