developer_uid: huohuo12
submission_id: mistralai-ministral-8b-_47735_v3
model_name: mistralai-ministral-8b-_47735_v3
model_group: mistralai/Ministral-8B-I
status: torndown
timestamp: 2025-02-20T07:16:10+00:00
num_battles: 5647
num_wins: 2621
celo_rating: 1219.41
family_friendly_score: 0.6244000000000001
family_friendly_standard_error: 0.006848717252157516
submission_type: basic
model_repo: mistralai/Ministral-8B-Instruct-2410
model_architecture: MistralForCausalLM
model_num_parameters: 8019808256.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.8239709535575844, 'latency_mean': 1.213567430973053, 'latency_p50': 1.2182488441467285, 'latency_p90': 1.3352568387985229}, {'batch_size': 4, 'throughput': 1.6955529230080846, 'latency_mean': 2.3492778837680817, 'latency_p50': 2.3457523584365845, 'latency_p90': 2.6142645597457883}, {'batch_size': 5, 'throughput': 1.8207593868222354, 'latency_mean': 2.7299702548980713, 'latency_p50': 2.728443741798401, 'latency_p90': 3.021314096450806}, {'batch_size': 8, 'throughput': 1.9999954509838576, 'latency_mean': 3.9636757051944733, 'latency_p50': 3.980626702308655, 'latency_p90': 4.4445028543472285}, {'batch_size': 10, 'throughput': 2.0457825285690396, 'latency_mean': 4.848912167549133, 'latency_p50': 4.867877721786499, 'latency_p90': 5.516361808776855}, {'batch_size': 12, 'throughput': 2.0906139550334704, 'latency_mean': 5.676399005651474, 'latency_p50': 5.686601042747498, 'latency_p90': 6.485167932510376}, {'batch_size': 15, 'throughput': 2.076092013619018, 'latency_mean': 7.122446502447128, 'latency_p50': 7.0843905210494995, 'latency_p90': 8.087872385978699}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: mistralai-ministral-8b-_47735_v3
is_internal_developer: False
language_model: mistralai/Ministral-8B-Instruct-2410
model_size: 8B
ranking_group: single
throughput_3p7s: 1.99
us_pacific_date: 2025-02-19
win_ratio: 0.4641402514609527
generation_params: {'temperature': 1.08, 'top_p': 0.86, 'min_p': 0.027, 'top_k': 44, 'presence_penalty': 0.62, 'frequency_penalty': 0.3, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', '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': '<|im_start|>assistant\n{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 mistralai-ministral-8b-47735-v3-mkmlizer
Waiting for job on mistralai-ministral-8b-47735-v3-mkmlizer to finish
mistralai-ministral-8b-47735-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-ministral-8b-47735-v3-mkmlizer: ║     _____            __           __                                ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║       /___/                                                         ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  belonging to:                                                      ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
mistralai-ministral-8b-47735-v3-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
mistralai-ministral-8b-47735-v3-mkmlizer: Downloaded to shared memory in 40.658s
mistralai-ministral-8b-47735-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqmgs41ou, device:0
mistralai-ministral-8b-47735-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-ministral-8b-47735-v3-mkmlizer: 
Loading 0:   0%|          | 0/327 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/327 [00:00<00:10, 30.62it/s]
Loading 0:   4%|▎         | 12/327 [00:00<00:07, 41.87it/s]
Loading 0:   5%|▌         | 17/327 [00:00<00:07, 41.20it/s]
Loading 0:   7%|▋         | 22/327 [00:00<00:08, 34.64it/s]
Loading 0:   8%|▊         | 26/327 [00:00<00:09, 32.84it/s]
Loading 0:  10%|█         | 33/327 [00:00<00:07, 40.76it/s]
Loading 0:  12%|█▏        | 38/327 [00:00<00:07, 40.82it/s]
Loading 0:  13%|█▎        | 43/327 [00:01<00:06, 41.09it/s]
Loading 0:  15%|█▍        | 48/327 [00:01<00:06, 42.09it/s]
Loading 0:  16%|█▌        | 53/327 [00:01<00:08, 34.06it/s]
Loading 0:  18%|█▊        | 58/327 [00:01<00:07, 37.44it/s]
Loading 0:  19%|█▉        | 63/327 [00:01<00:07, 37.32it/s]
Loading 0:  20%|██        | 67/327 [00:01<00:06, 37.95it/s]
Loading 0:  22%|██▏       | 71/327 [00:01<00:07, 34.89it/s]
Loading 0:  23%|██▎       | 76/327 [00:02<00:06, 38.16it/s]
Loading 0:  24%|██▍       | 80/327 [00:02<00:07, 35.22it/s]
Loading 0:  26%|██▌       | 85/327 [00:02<00:06, 37.29it/s]
Loading 0:  27%|██▋       | 89/327 [00:02<00:06, 34.36it/s]
Loading 0:  29%|██▉       | 95/327 [00:02<00:08, 27.17it/s]
Loading 0:  30%|███       | 99/327 [00:02<00:08, 27.73it/s]
Loading 0:  32%|███▏      | 104/327 [00:02<00:07, 29.91it/s]
Loading 0:  34%|███▍      | 111/327 [00:03<00:05, 37.07it/s]
Loading 0:  35%|███▌      | 116/327 [00:03<00:05, 37.72it/s]
Loading 0:  37%|███▋      | 121/327 [00:03<00:05, 38.08it/s]
Loading 0:  38%|███▊      | 125/327 [00:03<00:05, 37.87it/s]
Loading 0:  39%|███▉      | 129/327 [00:03<00:05, 37.36it/s]
Loading 0:  41%|████      | 133/327 [00:03<00:05, 35.24it/s]
Loading 0:  42%|████▏     | 137/327 [00:03<00:05, 36.03it/s]
Loading 0:  43%|████▎     | 141/327 [00:03<00:05, 34.20it/s]
Loading 0:  44%|████▍     | 145/327 [00:04<00:05, 35.51it/s]
Loading 0:  46%|████▌     | 149/327 [00:04<00:05, 33.51it/s]
Loading 0:  47%|████▋     | 155/327 [00:04<00:04, 40.36it/s]
Loading 0:  49%|████▉     | 160/327 [00:04<00:04, 38.76it/s]
Loading 0:  50%|█████     | 165/327 [00:04<00:04, 39.67it/s]
Loading 0:  52%|█████▏    | 170/327 [00:04<00:03, 40.04it/s]
Loading 0:  54%|█████▎    | 175/327 [00:04<00:03, 40.78it/s]
Loading 0:  55%|█████▌    | 180/327 [00:04<00:03, 42.37it/s]
Loading 0:  57%|█████▋    | 185/327 [00:05<00:04, 34.18it/s]
Loading 0:  59%|█████▊    | 192/327 [00:05<00:03, 40.99it/s]
Loading 0:  60%|██████    | 197/327 [00:05<00:03, 41.25it/s]
Loading 0:  62%|██████▏   | 202/327 [00:05<00:03, 40.88it/s]
Loading 0:  63%|██████▎   | 207/327 [00:05<00:02, 41.47it/s]
Loading 0:  65%|██████▍   | 212/327 [00:05<00:04, 27.93it/s]
Loading 0:  66%|██████▌   | 216/327 [00:06<00:03, 29.57it/s]
Loading 0:  67%|██████▋   | 220/327 [00:06<00:03, 30.44it/s]
Loading 0:  69%|██████▊   | 224/327 [00:06<00:03, 31.83it/s]
Loading 0:  70%|██████▉   | 228/327 [00:06<00:03, 32.37it/s]
Loading 0:  71%|███████   | 232/327 [00:06<00:02, 32.55it/s]
Loading 0:  72%|███████▏  | 236/327 [00:06<00:02, 33.58it/s]
Loading 0:  73%|███████▎  | 240/327 [00:06<00:02, 32.49it/s]
Loading 0:  75%|███████▍  | 244/327 [00:06<00:02, 34.03it/s]
Loading 0:  76%|███████▌  | 248/327 [00:06<00:02, 32.87it/s]
Loading 0:  77%|███████▋  | 253/327 [00:07<00:02, 36.64it/s]
Loading 0:  79%|███████▊  | 257/327 [00:07<00:02, 34.43it/s]
Loading 0:  80%|████████  | 262/327 [00:07<00:01, 37.72it/s]
Loading 0:  81%|████████▏ | 266/327 [00:07<00:01, 35.22it/s]
Loading 0:  83%|████████▎ | 271/327 [00:07<00:01, 38.89it/s]
Loading 0:  84%|████████▍ | 275/327 [00:07<00:01, 35.81it/s]
Loading 0:  86%|████████▌ | 280/327 [00:07<00:01, 39.39it/s]
Loading 0:  87%|████████▋ | 285/327 [00:07<00:01, 38.63it/s]
Loading 0:  89%|████████▉ | 291/327 [00:08<00:00, 42.37it/s]
Loading 0:  91%|█████████ | 296/327 [00:08<00:00, 42.05it/s]
Loading 0:  92%|█████████▏| 301/327 [00:08<00:00, 42.22it/s]
Loading 0:  94%|█████████▎| 306/327 [00:08<00:00, 43.58it/s]
Loading 0:  95%|█████████▌| 311/327 [00:08<00:00, 34.72it/s]
Loading 0:  97%|█████████▋| 316/327 [00:08<00:00, 37.69it/s]
Loading 0:  98%|█████████▊| 321/327 [00:08<00:00, 37.16it/s]
Loading 0:  99%|█████████▉| 325/327 [00:08<00:00, 37.54it/s]
                                                            
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message.
mistralai-ministral-8b-47735-v3-mkmlizer: quantized model in 30.072s
mistralai-ministral-8b-47735-v3-mkmlizer: Processed model mistralai/Ministral-8B-Instruct-2410 in 70.731s
mistralai-ministral-8b-47735-v3-mkmlizer: creating bucket guanaco-mkml-models
mistralai-ministral-8b-47735-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-ministral-8b-47735-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v3
mistralai-ministral-8b-47735-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v3/config.json
mistralai-ministral-8b-47735-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v3/special_tokens_map.json
mistralai-ministral-8b-47735-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v3/tokenizer_config.json
mistralai-ministral-8b-47735-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v3/flywheel_model.0.safetensors
Job mistralai-ministral-8b-47735-v3-mkmlizer completed after 93.85s with status: succeeded
Stopping job with name mistralai-ministral-8b-47735-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.30s
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 mistralai-ministral-8b-47735-v3
Waiting for inference service mistralai-ministral-8b-47735-v3 to be ready
2 validation errors for MultiheadRewardSubmission
platform
  unexpected value; permitted: 'multihead_reward' (type=value_error.const; given=coreweave/mkml; permitted=('multihead_reward',))
weights
  field required (type=value_error.missing)
2 validation errors for MultiheadRewardSubmission
platform
  unexpected value; permitted: 'multihead_reward' (type=value_error.const; given=coreweave/mkml; permitted=('multihead_reward',))
weights
  field required (type=value_error.missing)
2 validation errors for MultiheadRewardSubmission
platform
  unexpected value; permitted: 'multihead_reward' (type=value_error.const; given=coreweave/mkml; permitted=('multihead_reward',))
weights
  field required (type=value_error.missing)
1 validation error for RewardSubmission
platform
  unexpected value; permitted: 'reward' (type=value_error.const; given=coreweave/mkml; permitted=('reward',))
1 validation error for RewardSubmission
platform
  unexpected value; permitted: 'reward' (type=value_error.const; given=coreweave/mkml; permitted=('reward',))
1 validation error for RewardSubmission
platform
  unexpected value; permitted: 'reward' (type=value_error.const; given=coreweave/mkml; permitted=('reward',))
1 validation error for GuardSubmission
platform
  unexpected value; permitted: 'guard' (type=value_error.const; given=coreweave/mkml; permitted=('guard',))
1 validation error for GuardSubmission
platform
  unexpected value; permitted: 'guard' (type=value_error.const; given=coreweave/mkml; permitted=('guard',))
1 validation error for GuardSubmission
platform
  unexpected value; permitted: 'guard' (type=value_error.const; given=coreweave/mkml; permitted=('guard',))
1 validation error for NemoGuardSubmission
platform
  unexpected value; permitted: 'nemo_guard' (type=value_error.const; given=coreweave/mkml; permitted=('nemo_guard',))
1 validation error for NemoGuardSubmission
platform
  unexpected value; permitted: 'nemo_guard' (type=value_error.const; given=coreweave/mkml; permitted=('nemo_guard',))
1 validation error for NemoGuardSubmission
platform
  unexpected value; permitted: 'nemo_guard' (type=value_error.const; given=coreweave/mkml; permitted=('nemo_guard',))
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 mistralai-ministral-8b-47735-v4-mkmlizer
Waiting for job on mistralai-ministral-8b-47735-v4-mkmlizer to finish
mistralai-ministral-8b-47735-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-ministral-8b-47735-v4-mkmlizer: ║     _____            __           __                                ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║       /___/                                                         ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  belonging to:                                                      ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
mistralai-ministral-8b-47735-v4-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-ministral-8b-47735-v4-mkmlizer: Downloaded to shared memory in 39.049s
mistralai-ministral-8b-47735-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpif6d0zde, device:0
mistralai-ministral-8b-47735-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-ministral-8b-47735-v4-mkmlizer: 
Loading 0:   0%|          | 0/327 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/327 [00:00<00:09, 33.29it/s]
Loading 0:   4%|▎         | 12/327 [00:00<00:06, 45.52it/s]
Loading 0:   5%|▌         | 17/327 [00:00<00:06, 45.18it/s]
Loading 0:   7%|▋         | 22/327 [00:00<00:08, 37.71it/s]
Loading 0:   8%|▊         | 26/327 [00:00<00:08, 35.92it/s]
Loading 0:  10%|█         | 33/327 [00:00<00:06, 43.10it/s]
Loading 0:  12%|█▏        | 38/327 [00:00<00:06, 42.66it/s]
Loading 0:  13%|█▎        | 43/327 [00:01<00:06, 42.87it/s]
Loading 0:  15%|█▍        | 48/327 [00:01<00:06, 44.01it/s]
Loading 0:  16%|█▌        | 53/327 [00:01<00:07, 34.87it/s]
Loading 0:  18%|█▊        | 60/327 [00:01<00:06, 41.60it/s]
Loading 0:  20%|█▉        | 65/327 [00:01<00:06, 42.50it/s]
Loading 0:  21%|██▏       | 70/327 [00:01<00:06, 42.43it/s]
Loading 0:  23%|██▎       | 75/327 [00:01<00:05, 43.78it/s]
Loading 0:  24%|██▍       | 80/327 [00:02<00:06, 36.17it/s]
Loading 0:  27%|██▋       | 87/327 [00:02<00:05, 42.47it/s]
Loading 0:  28%|██▊       | 92/327 [00:02<00:05, 42.80it/s]
Loading 0:  30%|██▉       | 97/327 [00:02<00:07, 30.21it/s]
Loading 0:  31%|███       | 101/327 [00:02<00:07, 31.99it/s]
Loading 0:  32%|███▏      | 105/327 [00:02<00:06, 32.50it/s]
Loading 0:  34%|███▍      | 111/327 [00:02<00:05, 37.59it/s]
Loading 0:  35%|███▌      | 116/327 [00:02<00:05, 38.74it/s]
Loading 0:  37%|███▋      | 121/327 [00:03<00:05, 39.25it/s]
Loading 0:  39%|███▊      | 126/327 [00:03<00:04, 40.78it/s]
Loading 0:  40%|████      | 131/327 [00:03<00:05, 34.00it/s]
Loading 0:  42%|████▏     | 136/327 [00:03<00:05, 37.49it/s]
Loading 0:  43%|████▎     | 141/327 [00:03<00:04, 38.11it/s]
Loading 0:  45%|████▍     | 147/327 [00:03<00:04, 41.96it/s]
Loading 0:  46%|████▋     | 152/327 [00:03<00:04, 40.57it/s]
Loading 0:  48%|████▊     | 157/327 [00:04<00:04, 40.86it/s]
Loading 0:  50%|████▉     | 162/327 [00:04<00:03, 42.19it/s]
Loading 0:  51%|█████     | 167/327 [00:04<00:04, 34.35it/s]
Loading 0:  53%|█████▎    | 172/327 [00:04<00:04, 37.74it/s]
Loading 0:  54%|█████▍    | 177/327 [00:04<00:03, 38.23it/s]
Loading 0:  56%|█████▌    | 183/327 [00:04<00:03, 41.91it/s]
Loading 0:  57%|█████▋    | 188/327 [00:04<00:03, 41.94it/s]
Loading 0:  59%|█████▉    | 193/327 [00:04<00:03, 42.03it/s]
Loading 0:  61%|██████    | 198/327 [00:05<00:02, 43.37it/s]
Loading 0:  62%|██████▏   | 203/327 [00:05<00:03, 35.11it/s]
Loading 0:  64%|██████▎   | 208/327 [00:05<00:03, 37.97it/s]
Loading 0:  65%|██████▌   | 213/327 [00:05<00:04, 27.11it/s]
Loading 0:  67%|██████▋   | 219/327 [00:05<00:03, 31.96it/s]
Loading 0:  68%|██████▊   | 223/327 [00:05<00:03, 32.66it/s]
Loading 0:  70%|██████▉   | 228/327 [00:05<00:02, 35.18it/s]
Loading 0:  71%|███████   | 232/327 [00:06<00:02, 35.48it/s]
Loading 0:  72%|███████▏  | 237/327 [00:06<00:02, 37.98it/s]
Loading 0:  74%|███████▍  | 242/327 [00:06<00:02, 39.57it/s]
Loading 0:  76%|███████▌  | 247/327 [00:06<00:01, 40.88it/s]
Loading 0:  77%|███████▋  | 252/327 [00:06<00:01, 42.78it/s]
Loading 0:  79%|███████▊  | 257/327 [00:06<00:02, 34.36it/s]
Loading 0:  81%|████████  | 264/327 [00:06<00:01, 41.45it/s]
Loading 0:  82%|████████▏ | 269/327 [00:06<00:01, 42.03it/s]
Loading 0:  84%|████████▍ | 274/327 [00:07<00:01, 41.83it/s]
Loading 0:  85%|████████▌ | 279/327 [00:07<00:01, 41.63it/s]
Loading 0:  87%|████████▋ | 284/327 [00:07<00:01, 35.04it/s]
Loading 0:  89%|████████▉ | 291/327 [00:07<00:00, 41.23it/s]
Loading 0:  91%|█████████ | 296/327 [00:07<00:00, 41.80it/s]
Loading 0:  92%|█████████▏| 301/327 [00:07<00:00, 42.29it/s]
Loading 0:  94%|█████████▎| 306/327 [00:07<00:00, 43.52it/s]
Loading 0:  95%|█████████▌| 311/327 [00:08<00:00, 34.93it/s]
Loading 0:  97%|█████████▋| 318/327 [00:08<00:00, 41.71it/s]
Loading 0:  99%|█████████▉| 323/327 [00:08<00:00, 42.16it/s]
                                                            
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message.
mistralai-ministral-8b-47735-v4-mkmlizer: quantized model in 28.794s
mistralai-ministral-8b-47735-v4-mkmlizer: Processed model mistralai/Ministral-8B-Instruct-2410 in 67.844s
mistralai-ministral-8b-47735-v4-mkmlizer: creating bucket guanaco-mkml-models
mistralai-ministral-8b-47735-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-ministral-8b-47735-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v4
mistralai-ministral-8b-47735-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v4/config.json
mistralai-ministral-8b-47735-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v4/special_tokens_map.json
mistralai-ministral-8b-47735-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v4/tokenizer_config.json
mistralai-ministral-8b-47735-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v4/tokenizer.json
Job mistralai-ministral-8b-47735-v4-mkmlizer completed after 95.98s with status: succeeded
Stopping job with name mistralai-ministral-8b-47735-v4-mkmlizer
Pipeline stage MKMLizer completed in 96.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-ministral-8b-47735-v4
Waiting for inference service mistralai-ministral-8b-47735-v4 to be ready
Inference service mistralai-ministral-8b-47735-v3 ready after 200.77076935768127s
Pipeline stage MKMLDeployer completed in 201.29s
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 1.997208595275879s
Received healthy response to inference request in 2.5282528400421143s
Received healthy response to inference request in 1.2919142246246338s
Received healthy response to inference request in 1.2611005306243896s
5 requests
1 failed requests
5th percentile: 1.2672632694244386
10th percentile: 1.2734260082244873
20th percentile: 1.2857514858245849
30th percentile: 1.4329730987548828
40th percentile: 1.715090847015381
50th percentile: 1.997208595275879
60th percentile: 2.209626293182373
70th percentile: 2.422043991088867
80th percentile: 6.0732502460479765
90th percentile: 13.163245058059694
95th percentile: 16.70824246406555
99th percentile: 19.54424038887024
mean time: 5.466343212127685
%s, retrying in %s seconds...
Received healthy response to inference request in 1.1576111316680908s
Received healthy response to inference request in 1.3471429347991943s
Received healthy response to inference request in 1.5022993087768555s
Received healthy response to inference request in 1.172363042831421s
Received healthy response to inference request in 1.155292272567749s
5 requests
0 failed requests
5th percentile: 1.1557560443878174
10th percentile: 1.1562198162078858
20th percentile: 1.1571473598480224
30th percentile: 1.1605615139007568
40th percentile: 1.166462278366089
50th percentile: 1.172363042831421
60th percentile: 1.2422749996185303
70th percentile: 1.3121869564056396
80th percentile: 1.3781742095947267
90th percentile: 1.440236759185791
95th percentile: 1.471268033981323
99th percentile: 1.496093053817749
mean time: 1.266941738128662
Pipeline stage StressChecker completed in 39.09s
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 1.00s
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 0.96s
Shutdown handler de-registered
mistralai-ministral-8b-_47735_v3 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2179.33s
Shutdown handler de-registered
mistralai-ministral-8b-_47735_v3 status is now inactive due to auto deactivation removed underperforming models
mistralai-ministral-8b-_47735_v3 status is now torndown due to DeploymentManager action