rinen0721-llama1018

submission_id: rinen0721-llama1018_v1

developer_uid: rinen0721

best_of: 8

celo_rating: 1214.58

display_name: rinen0721-llama1018_v1

family_friendly_score: 0.5547449131302833

family_friendly_standard_error: 0.005581168218997172

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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}

is_internal_developer: False

language_model: rinen0721/llama1018

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: rinen0721/llama1018

model_name: rinen0721-llama1018_v1

model_num_parameters: 8030261248.0

model_repo: rinen0721/llama1018

model_size: 8B

num_battles: 8321

num_wins: 3639

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-10-18T02:55:48+00:00

us_pacific_date: 2024-10-17

win_ratio: 0.437327244321596

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 rinen0721-llama1018-v1-mkmlizer
Waiting for job on rinen0721-llama1018-v1-mkmlizer to finish
rinen0721-llama1018-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-llama1018-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-llama1018-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-llama1018-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-llama1018-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-llama1018-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-llama1018-v1-mkmlizer: ║                                                                     ║
rinen0721-llama1018-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rinen0721-llama1018-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-llama1018-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-llama1018-v1-mkmlizer: ║                                                                     ║
rinen0721-llama1018-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-llama1018-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-llama1018-v1-mkmlizer: ║                                                                     ║
rinen0721-llama1018-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-llama1018-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-llama1018-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rinen0721-llama1018-v1-mkmlizer: ║                                                                     ║
rinen0721-llama1018-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-llama1018-v1-mkmlizer: Downloaded to shared memory in 66.328s
rinen0721-llama1018-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsl6sxzlk, device:0
rinen0721-llama1018-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-llama1018-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.
rinen0721-llama1018-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rinen0721-llama1018-v1-mkmlizer: quantized model in 25.876s
rinen0721-llama1018-v1-mkmlizer: Processed model rinen0721/llama1018 in 92.205s
rinen0721-llama1018-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-llama1018-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-llama1018-v1/config.json
rinen0721-llama1018-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-llama1018-v1/special_tokens_map.json
rinen0721-llama1018-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-llama1018-v1/tokenizer_config.json
rinen0721-llama1018-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-llama1018-v1/tokenizer.json
rinen0721-llama1018-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-llama1018-v1/flywheel_model.0.safetensors
rinen0721-llama1018-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 6/291 [00:00<00:04, 59.61it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 63.08it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 70.21it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 77.25it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 81.05it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 80.44it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 80.10it/s]
Loading 0:  24%|██▎       | 69/291 [00:00<00:02, 88.93it/s]
Loading 0:  27%|██▋       | 78/291 [00:00<00:02, 88.07it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:09, 21.51it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 25.85it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 33.29it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 42.91it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 49.66it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 56.29it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 62.79it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 75.72it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:01, 83.47it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 77.48it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 23.41it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 33.55it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 39.76it/s]
Loading 0:  76%|███████▌  | 221/291 [00:04<00:01, 47.78it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 54.03it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 59.98it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 65.12it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 66.44it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 77.95it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 75.41it/s]
                                                            
Job rinen0721-llama1018-v1-mkmlizer completed after 114.47s with status: succeeded
Stopping job with name rinen0721-llama1018-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-llama1018-v1
Waiting for inference service rinen0721-llama1018-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
Inference service rinen0721-llama1018-v1 ready after 180.89362049102783s
Pipeline stage MKMLDeployer completed in 181.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6192741394042969s
Received healthy response to inference request in 1.6060702800750732s
Received healthy response to inference request in 1.4055368900299072s
Received healthy response to inference request in 1.1927478313446045s
Received healthy response to inference request in 1.313072919845581s
5 requests
0 failed requests
5th percentile: 1.2168128490447998
10th percentile: 1.2408778667449951
20th percentile: 1.2890079021453857
30th percentile: 1.3315657138824464
40th percentile: 1.3685513019561768
50th percentile: 1.4055368900299072
60th percentile: 1.4857502460479737
70th percentile: 1.56596360206604
80th percentile: 1.608711051940918
90th percentile: 1.6139925956726073
95th percentile: 1.616633367538452
99th percentile: 1.6187459850311279
mean time: 1.4273404121398925
Pipeline stage StressChecker completed in 9.00s
Shutdown handler de-registered
rinen0721-llama1018_v1 status is now deployed due to DeploymentManager action
rinen0721-llama1018_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-llama1018_v1 status is now torndown due to DeploymentManager action