pocketdoc-mistral-12b-te_5489

developer_uid: PocketDoc

submission_id: pocketdoc-mistral-12b-te_5489_v6

model_name: Dans-Instruct-12b

model_group: PocketDoc/Mistral-12b-Te

status: inactive

timestamp: 2024-12-19T00:06:06+00:00

num_battles: 11675

num_wins: 5781

celo_rating: 1260.89

family_friendly_score: 0.5796

family_friendly_standard_error: 0.006980885903665809

submission_type: basic

model_repo: PocketDoc/Mistral-12b-Test-V0.0.3

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6254156507660745, 'latency_mean': 1.5988688743114472, 'latency_p50': 1.5911494493484497, 'latency_p90': 1.7601276874542235}, {'batch_size': 3, 'throughput': 1.1524259117241797, 'latency_mean': 2.597790571451187, 'latency_p50': 2.592514157295227, 'latency_p90': 2.8390465259552}, {'batch_size': 5, 'throughput': 1.4009315068378765, 'latency_mean': 3.548251179456711, 'latency_p50': 3.5514988899230957, 'latency_p90': 3.9407949209213258}, {'batch_size': 6, 'throughput': 1.4739445193446135, 'latency_mean': 4.046637885570526, 'latency_p50': 4.088898539543152, 'latency_p90': 4.529201817512512}, {'batch_size': 8, 'throughput': 1.545449367365177, 'latency_mean': 5.13645304441452, 'latency_p50': 5.148763418197632, 'latency_p90': 5.772393226623535}, {'batch_size': 10, 'throughput': 1.5983955253717734, 'latency_mean': 6.217507736682892, 'latency_p50': 6.155287146568298, 'latency_p90': 7.091588306427002}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: Dans-Instruct-12b

is_internal_developer: False

language_model: PocketDoc/Mistral-12b-Test-V0.0.3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.43

us_pacific_date: 2024-12-18

win_ratio: 0.49516059957173447

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], '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
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name pocketdoc-mistral-12b-te-5489-v6-mkmlizer
Waiting for job on pocketdoc-mistral-12b-te-5489-v6-mkmlizer to finish
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║     _____            __           __                                ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║       /___/                                                         ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║                                                                     ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  Version: 0.11.12                                                   ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  https://mk1.ai                                                     ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║                                                                     ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  belonging to:                                                      ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║                                                                     ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  Chai Research Corp.                                                ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ║                                                                     ║
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: Downloaded to shared memory in 50.042s
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpasj35tg3, device:0
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pocketdoc-mistral-12b-te-5489-v6-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.
pocketdoc-mistral-12b-te-5489-v6-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: quantized model in 36.399s
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: Processed model PocketDoc/Mistral-12b-Test-V0.0.3 in 86.442s
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: creating bucket guanaco-mkml-models
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pocketdoc-mistral-12b-te-5489-v6
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pocketdoc-mistral-12b-te-5489-v6/config.json
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pocketdoc-mistral-12b-te-5489-v6/special_tokens_map.json
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pocketdoc-mistral-12b-te-5489-v6/tokenizer_config.json
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pocketdoc-mistral-12b-te-5489-v6/tokenizer.json
pocketdoc-mistral-12b-te-5489-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.77it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:04, 70.16it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 85.75it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:03, 83.65it/s]
Loading 0:  14%|█▍        | 51/363 [00:00<00:03, 91.69it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:14, 20.72it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:11, 26.46it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 33.12it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.12it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:05, 49.33it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:04, 55.43it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:03, 66.72it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:03, 70.89it/s]
Loading 0:  38%|███▊      | 139/363 [00:02<00:03, 73.63it/s]
Loading 0:  41%|████      | 148/363 [00:03<00:09, 21.60it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 29.17it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 36.45it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 42.07it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 49.25it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:02, 62.72it/s]
Loading 0:  58%|█████▊    | 212/363 [00:04<00:02, 69.30it/s]
Loading 0:  61%|██████    | 221/363 [00:04<00:02, 70.95it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:05, 22.17it/s]
Loading 0:  66%|██████▌   | 240/363 [00:06<00:04, 28.98it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 34.29it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 40.46it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 49.87it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 56.72it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 60.02it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:01, 64.02it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 21.18it/s]
Loading 0:  86%|████████▌ | 313/363 [00:07<00:01, 26.69it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 33.35it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 40.16it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 47.41it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 52.31it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 57.71it/s]
                                                            
Job pocketdoc-mistral-12b-te-5489-v6-mkmlizer completed after 114.84s with status: succeeded
Stopping job with name pocketdoc-mistral-12b-te-5489-v6-mkmlizer
Pipeline stage MKMLizer completed in 115.77s
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 pocketdoc-mistral-12b-te-5489-v6
Waiting for inference service pocketdoc-mistral-12b-te-5489-v6 to be ready
Inference service pocketdoc-mistral-12b-te-5489-v6 ready after 241.34432101249695s
Pipeline stage MKMLDeployer completed in 242.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2486038208007812s
Received healthy response to inference request in 1.6547722816467285s
Received healthy response to inference request in 1.647517442703247s
Received healthy response to inference request in 1.8760294914245605s
Received healthy response to inference request in 1.8501763343811035s
5 requests
0 failed requests
5th percentile: 1.6489684104919433
10th percentile: 1.6504193782806396
20th percentile: 1.6533213138580323
30th percentile: 1.6938530921936035
40th percentile: 1.7720147132873536
50th percentile: 1.8501763343811035
60th percentile: 1.8605175971984864
70th percentile: 1.870858860015869
80th percentile: 1.9505443572998047
90th percentile: 2.099574089050293
95th percentile: 2.174088954925537
99th percentile: 2.2337008476257325
mean time: 1.8554198741912842
Pipeline stage StressChecker completed in 10.64s
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 2.24s
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
pocketdoc-mistral-12b-te_5489_v6 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service pocketdoc-mistral-12b-te-5489-v6-profiler
Waiting for inference service pocketdoc-mistral-12b-te-5489-v6-profiler to be ready
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 3068.52s
Shutdown handler de-registered
pocketdoc-mistral-12b-te_5489_v6 status is now inactive due to auto deactivation removed underperforming models