dans-discountmodels-mist_2208

developer_uid: PocketDoc

submission_id: dans-discountmodels-mist_2208_v1

model_name: Dans-Instruct-7b

model_group: Dans-DiscountModels/mist

status: inactive

timestamp: 2024-12-01T07:56:41+00:00

num_battles: 19868

num_wins: 8781

celo_rating: 1219.66

family_friendly_score: 0.5684

family_friendly_standard_error: 0.007004590494811242

submission_type: basic

model_repo: Dans-DiscountModels/mistral-7b-test-merged

model_architecture: MistralForCausalLM

model_num_parameters: 7248023552.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.9096538770732382, 'latency_mean': 1.099247750043869, 'latency_p50': 1.0910412073135376, 'latency_p90': 1.2232389450073242}, {'batch_size': 4, 'throughput': 1.9651784421484555, 'latency_mean': 2.027653616666794, 'latency_p50': 2.0286020040512085, 'latency_p90': 2.2578856468200685}, {'batch_size': 5, 'throughput': 2.0914081514244076, 'latency_mean': 2.381462345123291, 'latency_p50': 2.383885383605957, 'latency_p90': 2.6655688762664793}, {'batch_size': 8, 'throughput': 2.3137410702080703, 'latency_mean': 3.4393686389923097, 'latency_p50': 3.468088984489441, 'latency_p90': 3.880978775024414}, {'batch_size': 10, 'throughput': 2.3541816925590435, 'latency_mean': 4.2122205328941345, 'latency_p50': 4.232537269592285, 'latency_p90': 4.726288866996765}, {'batch_size': 12, 'throughput': 2.406266146745849, 'latency_mean': 4.936864730119705, 'latency_p50': 4.932483792304993, 'latency_p90': 5.62862536907196}, {'batch_size': 15, 'throughput': 2.452247519571218, 'latency_mean': 6.043495850563049, 'latency_p50': 6.050272464752197, 'latency_p90': 6.718840265274048}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: Dans-Instruct-7b

is_internal_developer: False

language_model: Dans-DiscountModels/mistral-7b-test-merged

model_size: 7B

ranking_group: single

throughput_3p7s: 2.34

us_pacific_date: 2024-11-30

win_ratio: 0.44196698208173946

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.02, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\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': True}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage MKMLizer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Starting job with name dans-discountmodels-mist-2208-v1-mkmlizer
Waiting for job on dans-discountmodels-mist-2208-v1-mkmlizer to finish
dans-discountmodels-mist-2208-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dans-discountmodels-mist-2208-v1-mkmlizer: ║     _____            __           __                                ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║       /___/                                                         ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║                                                                     ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  https://mk1.ai                                                     ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║                                                                     ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  belonging to:                                                      ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║                                                                     ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  Chai Research Corp.                                                ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
dans-discountmodels-mist-2208-v1-mkmlizer: ║                                                                     ║
dans-discountmodels-mist-2208-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dans-discountmodels-mist-2208-v1-mkmlizer: Downloaded to shared memory in 29.382s
dans-discountmodels-mist-2208-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt5e6w6km, device:0
dans-discountmodels-mist-2208-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dans-discountmodels-mist-2208-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
dans-discountmodels-mist-2208-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
dans-discountmodels-mist-2208-v1-mkmlizer: quantized model in 17.493s
dans-discountmodels-mist-2208-v1-mkmlizer: Processed model Dans-DiscountModels/mistral-7b-test-merged in 46.875s
dans-discountmodels-mist-2208-v1-mkmlizer: creating bucket guanaco-mkml-models
dans-discountmodels-mist-2208-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dans-discountmodels-mist-2208-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v1
dans-discountmodels-mist-2208-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v1/special_tokens_map.json
dans-discountmodels-mist-2208-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v1/config.json
dans-discountmodels-mist-2208-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v1/tokenizer_config.json
dans-discountmodels-mist-2208-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v1/tokenizer.json
dans-discountmodels-mist-2208-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v1/flywheel_model.0.safetensors
dans-discountmodels-mist-2208-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 48.98it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 63.30it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 73.63it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:03, 83.02it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 88.46it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 82.98it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 80.67it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 81.94it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:02, 75.52it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 77.04it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:08, 21.45it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:07, 24.46it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:05, 29.71it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 37.47it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 43.43it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 51.31it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 58.67it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 65.39it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 67.62it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 71.70it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 75.75it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 75.37it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:03, 22.60it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:03, 25.42it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 31.74it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 39.48it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 45.01it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 52.01it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 56.85it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 62.23it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 67.66it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 71.48it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.29it/s]
                                                            
Job dans-discountmodels-mist-2208-v1-mkmlizer completed after 73.51s with status: succeeded
Stopping job with name dans-discountmodels-mist-2208-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.22s
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 dans-discountmodels-mist-2208-v1
Waiting for inference service dans-discountmodels-mist-2208-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service dans-discountmodels-mist-2208-v1 ready after 140.59032559394836s
Pipeline stage MKMLDeployer completed in 141.11s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.7858107089996338s
Received healthy response to inference request in 1.1797676086425781s
Received healthy response to inference request in 1.2951970100402832s
Received healthy response to inference request in 1.9079606533050537s
Received healthy response to inference request in 1.4333748817443848s
5 requests
0 failed requests
5th percentile: 1.2028534889221192
10th percentile: 1.2259393692016602
20th percentile: 1.2721111297607421
30th percentile: 1.3228325843811035
40th percentile: 1.3781037330627441
50th percentile: 1.4333748817443848
60th percentile: 1.5743492126464844
70th percentile: 1.7153235435485839
80th percentile: 1.8102406978607177
90th percentile: 1.8591006755828858
95th percentile: 1.8835306644439698
99th percentile: 1.9030746555328368
mean time: 1.5204221725463867
Pipeline stage StressChecker completed in 8.90s
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 2.20s
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 2.00s
Shutdown handler de-registered
dans-discountmodels-mist_2208_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2717.98s
Shutdown handler de-registered
dans-discountmodels-mist_2208_v1 status is now inactive due to auto deactivation removed underperforming models